Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 is the method flow diagram according to one aspect of the invention, illustrates and evaluates and tests by computer implemented the process promoting keyword quality score based on weighted mean click-through rate.Wherein, this process completes at network equipment end usually, at this, the network equipment includes but not limited to network host, single network server, multiple webserver collection or the set of computers based on cloud computing, wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection.Those skilled in the art will be understood that the above-mentioned network equipment is only citing, and other network equipments that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
Particularly, the network equipment obtains the popularization keyword of user's input; According to described popularization keyword, obtain the individual click-through rate of the described popularization keyword corresponding with this user; According to described popularization keyword, obtain the weighted mean click-through rate of described popularization keyword; According to described individual click-through rate and described weighted mean click-through rate, determine the quality degree of the described popularization keyword corresponding with this user.
More specifically, in step sl, the network equipment obtains the popularization keyword of user's input.Particularly, in step sl, the network equipment obtains the popularization keyword of user's input in several ways, such as, mutual by with subscriber equipment of user, as carried out man-machine interaction by modes such as keyboard, mouse, telepilot, touch pad, touch-screen or handwriting equipments, and subscriber equipment is connected with the network equipment via network, send the popularization keyword of this user input to the network equipment, the network equipment obtains the popularization keyword of user's input accordingly; User is by the promoted account of this user in subscriber equipment logging in network equipment, and then in this promoted account, keyword is promoted in input, and the network equipment obtains the popularization keyword of this user input from this promoted account; User will promote keyword input keywords database, and the network equipment and this keywords database connect, and read the popularization keyword of this user input from this keywords database.Those skilled in the art will be understood that the mode of the popularization keyword of above-mentioned network equipment acquisition user input is only citing; other network equipments that are existing or that may occur from now on obtain the mode of the popularization keyword of user's input as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN, wireless self-organization network (Ad Hoc network), GSM, WCDMA, CDMA2000, TD-SCDMA, GSM, CDMA1x, WIFI, WAPI, WiMax etc.Those skilled in the art will be understood that above-mentioned network is only citing, and other networks that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
Subsequently, in step s 2, the network equipment, according to described popularization keyword, obtains the individual click-through rate of the described popularization keyword corresponding with this user.Particularly, in step s 2, the popularization keyword of user's input that the network equipment obtains in step sl according to it, obtains the individual click-through rate of this popularization keyword of this user.At this, the acquisition of the individual click-through rate of this popularization keyword source includes but not limited to, the memory storage of the network equipment itself, the management server of the extension system of popularization belonging to keyword and can with other equipment of this network device communications.The obtain manner of the individual click-through rate of this popularization keyword includes but not limited to, such as, the network equipment itself is the management server of the extension system promoted belonging to keyword, and the network equipment obtains the individual click-through rate of this popularization keyword from the historical record of this popularization keyword, and for example, the network equipment is by reading in a database, call the communication mode of specific application programming interfaces (API) or other agreements, obtain the individual click-through rate of this popularization keyword of this user, such as, the application programming interfaces (API) that the network equipment is provided by the third party device of the individual click-through rate calling this popularization keyword storing this user, the request of the individual click-through rate of this popularization keyword obtaining this user is sent to this third party device, and receive this third party device asks this popularization keyword of this user returned individual click-through rate according to this.Those skilled in the art will be understood that the acquisition source of above-mentioned individual click-through rate and obtain manner are only citing; the acquisition source of other individual click-through rates that are existing or that may occur from now on or obtain manner are as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Then, in step s3, the network equipment, according to described popularization keyword, obtains the weighted mean click-through rate of described popularization keyword.Particularly, in step s3, the popularization keyword that the network equipment obtains in step sl according to it, obtains the weighted mean click-through rate of this popularization keyword.The obtain manner of this weighted mean click-through rate includes but not limited to: obtained by network device computes, namely the click-through rate of different user or different popularization unit is corresponded to according to this popularization keyword, and give these click-through rates different weights, be weighted on average to these click-through rates again, to obtain the weighted mean click-through rate (when the weight of these click-through rates is identical, the weighted mean click-through rate of this popularization keyword is arithmetic mean click-through rate) of this popularization keyword; Directly obtained from himself memory storage or third party device by the network equipment, such as, the network equipment, by reading, calling the communication mode of specific application programming interfaces (API) or other agreements in a database, obtains the weighted mean click-through rate of this popularization keyword.Such as, the application programming interfaces (API) that the network equipment is provided by the third party device calling the weighted mean click-through rate storing this popularization keyword, send the request of the weighted mean click-through rate obtaining this popularization keyword to this third party device, and receive this third party device asks this popularization keyword returned weighted mean click-through rate according to this.Those skilled in the art will be understood that above-mentioned obtain manner is only citing, and other obtain manners that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.At this; the Consideration of weight promoting the click-through rate of keyword includes but not limited to promote the dog-eat-dog degree of keyword, the retrieval amount of netizen, or the industry etc. promoted belonging to keyword; those skilled in the art will be understood that the Consideration of the weight of the click-through rate of above-mentioned popularization keyword is only citing; the Consideration of the weight of the click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
It should be noted that, those skilled in the art will be understood that, step S2 and step S3 is not that strict order performs relation, the network equipment first can perform step S2, obtain the individual click-through rate of this popularization keyword corresponding with this user, perform step S3 again, obtain the weighted mean click-through rate of this popularization keyword; Also first can perform step S3, obtain the weighted mean click-through rate of this popularization keyword, then perform step S2, obtain the individual click-through rate of this popularization keyword corresponding with this user; Step S2 and step S3 can also be performed simultaneously, obtain the individual click-through rate of this popularization keyword corresponding with this user and the weighted mean click-through rate of this popularization keyword; Even can in same step, obtain the individual click-through rate of this popularization keyword corresponding with this user and the weighted mean click-through rate of this popularization keyword simultaneously, the such as network equipment with third party device mutual in, same request with receives in response and the corresponding individual click-through rate of this popularization keyword of this user and the weighted mean click-through rate of this popularization keyword.For simplicity's sake, we first state the network equipment and perform step S2, obtain the individual click-through rate of this popularization keyword corresponding with this user, then state network equipment execution step S3, obtain the weighted mean click-through rate of this popularization keyword.It is convenient that those skilled in the art will be understood that such statement order is only statement, should as limitation of the present invention.
Subsequently, in step s 4 which, the network equipment, according to described individual click-through rate and described weighted mean click-through rate, determines the quality degree of the described popularization keyword corresponding with this user.Particularly, in step s 4 which, the individual click-through rate of this popularization keyword of this user that the network equipment obtains in step s 2 according to it and the weighted mean click-through rate of its this popularization keyword obtained in step s3, determine the quality degree of this popularization keyword of this user by the mode of such as ratio, difference.Such as, the network equipment, according to the ratio of the individual click-through rate of this popularization keyword of this user with the weighted mean click-through rate of this popularization keyword, determines the quality degree of this popularization keyword of this user; Suppose that the individual click-through rate of this popularization keyword of this user is 0.2%, the weighted mean click-through rate of this popularization keyword is 0.15%, and so their ratio is 1.33, and this ratio is exactly the quality degree of this popularization keyword of this user.And for example, the network equipment, according to the difference of the individual click-through rate of this popularization keyword of this user with the weighted mean click-through rate of this popularization keyword, determines the quality degree of this popularization keyword of this user; Suppose that the individual click-through rate of this popularization keyword of this user is 0.2%, the weighted mean click-through rate of this popularization keyword is 0.15%, and so their difference is 0.05%, and this difference is exactly the quality degree of this popularization keyword of this user.Those skilled in the art will be understood that the determination mode of above-mentioned quality degree is only citing; the determination mode of other quality degree that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, step S1, step S2, step S3 and step S4 are constant work.Particularly, the network equipment in step sl, obtains the popularization keyword of user's input; In step s 2, according to described popularization keyword, obtain the individual click-through rate of the described popularization keyword corresponding with this user; In step s3, according to described popularization keyword, obtain the weighted mean click-through rate of described popularization keyword; In step s 4 which, according to described individual click-through rate and described weighted mean click-through rate, determine the quality degree of the described popularization keyword corresponding with this user.At this, it will be understood by those skilled in the art that " continuing " refers to that the network equipment requires to carry out promoting the acquisition of keyword, the acquisition of individual click-through rate of this popularization keyword of this user, the acquisition of the weighted mean click-through rate of this popularization keyword according to the mode of operation of setting or real-time adjustment in step S1, step S2, step S3 and step S4 respectively, and the determination of the quality degree of this popularization keyword, until this network equipment stops evaluating and testing the quality degree promoting keyword in a long time.
In a preferred embodiment, in step s3, the network equipment, according to described popularization keyword, obtains user's click-through rate of the described popularization keyword corresponding with using each user of described popularization keyword; According to described user's click-through rate, obtain the weighted mean click-through rate of described popularization keyword.Particularly, in step s3, the popularization keyword that the network equipment obtains in step sl according to it, obtain user's click-through rate that other users using this popularization keyword correspond to this popularization keyword, then according to this (a bit) user's click-through rate, the weighted mean click-through rate of this popularization keyword is obtained.Such as, the amount of representing corresponding to user's click-through rate gives user's click-through rate different weights, according to the weighted mean click-through rate of this popularization keyword of this Weight Acquisition; Suppose to promote keyword for " fresh flower ", the user using " fresh flower " under identical linguistic context is user's first and user's second, user's click-through rate that user's first corresponds to " fresh flower " is 0.2%, the amount of representing is 1000 times, user's click-through rate that user's second corresponds to " fresh flower " is 0.15%, and the amount of representing is 10000 times, and the weight of giving user's click-through rate of user's first is 0.1, the weight of giving user's click-through rate of user's second is 0.9, thus the weighted mean click-through rate obtaining " fresh flower " is 0.155%.And for example, suppose that the weight of user's click-through rate of the same popularization keyword of all users is the same, now the weighted mean click-through rate of this popularization keyword is arithmetic mean click-through rate; As promoted keyword for " fresh flower ", user's click-through rate that user's first corresponds to " fresh flower " is 0.2%, user's click-through rate that user's second corresponds to " fresh flower " is 0.15%, user's click-through rate that user third corresponds to " fresh flower " is 0.24%, and now the weighted mean click-through rate of " fresh flower " is 0.197%.Those skilled in the art will be understood that the mode of the weighted mean click-through rate of above-mentioned acquisition popularization keyword is only citing; other acquisitions that are existing or that may occur from now on promote the mode of the weighted mean click-through rate of keyword as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a further advantageous embodiment, in step s3, the network equipment, according to described popularization keyword, obtains and relevant to described popularization keyword one or morely associates keyword; Obtain the click-through rate of described one or more association keyword; The click-through rate of described one or more association keyword is averaged, obtains the weighted mean click-through rate of described popularization keyword; Wherein, described one or more association keyword includes but not limited to, below at least any one: the 1) synonymous keyword of described popularization keyword; 2) the near adopted keyword of described popularization keyword; 3) keyword of the same trade is mutually belonged to described popularization keyword; 4) keyword of identical region is belonged to described popularization keyword.Particularly, in step s3, the popularization keyword that the network equipment obtains in step sl according to it, obtain and relevant to this popularization keyword one or morely associate keyword, such as, the synonym of this popularization keyword, nearly adopted keyword, keyword etc. with this popularization keyword of the same trade or identical region mutually, obtain the click-through rate that this (a bit) associates keyword, again this (a bit) click-through rate is averaged, thus obtain the weighted mean click-through rate of this popularization keyword.Such as, suppose to promote keyword for " click-through rate ", the network equipment is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", then by calling the application programming interfaces (API) that the third party device of click-through rate that stores keyword provides, send the request of the click-through rate obtaining " CTR " and " clicking rate " to this third party device, and receive this third party device asks " CTR " and " clicking rate " returned click-through rate according to this; Then average to the click-through rate of " CTR " and " clicking rate ", obtain the weighted mean click-through rate of " click-through rate ", weighted mean click-through rate now is also arithmetic mean click-through rate.And for example, still hypothesis promotes keyword is " click-through rate ", the network equipment is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", nearly adopted keyword " click volume " and " average click-through rate ", then by reading the data of keywords database, obtain " CTR " respectively, " clicking rate ", the click-through rate of " click volume " and " average click-through rate ", the weight arranging the click-through rate of " CTR " and " clicking rate " is 0.3, the weight of the click-through rate of " click volume " and " average click-through rate " is 0.2, weighted mean value is asked to these click-through rates, the weighted mean click-through rate of " click-through rate " can be obtained.And for example, still hypothesis promotes keyword is " click-through rate ", the network equipment is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", again region cluster analysis is carried out to these " CTR " and " clicking rate ", region is " East China ", thus the click-through rate obtaining " CTR " used in " East China " area is 0.2%, the click-through rate of " clicking rate " that use in " East China " area is 0.15%, the weight arranging the click-through rate of " CTR " is 0.4, the weight of the click-through rate of " clicking rate " is 0.6, show that the weighted mean click-through rate of " click-through rate " is 0.17%.Those skilled in the art will be understood that the obtain manner of the weighted mean click-through rate of above-mentioned popularization keyword and associate keyword and be only citing; the obtain manner of the weighted mean click-through rate of other popularization keywords that are existing or that may occur from now on or association keyword are as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In another preferred embodiment, in step s3, the network equipment is according to described popularization keyword, and in conjunction with the statistics click-through rate (namely in this extension system the click volume of all keywords with the ratio of the amount of representing) of the extension system belonging to described popularization keyword, obtain the weighted mean click-through rate of described popularization keyword.Particularly, in step s3, the popularization keyword that the network equipment obtains in step sl according to it, in conjunction with the statistics click-through rate of the extension system belonging to this popularization keyword, obtains the weighted mean click-through rate of this popularization keyword.Degree of confidence such as when the weighted mean click-through rate of this popularization keyword is too low, and the network equipment selects the weighted mean click-through rate of statistics click-through rate as this popularization keyword of this extension system; Suppose that the weighted mean click-through rate promoting keyword is 0.09%, the statistics click-through rate of extension system is 0.1%, now promote the statistics click-through rate of weighted mean click-through rate lower than extension system of keyword, the network equipment obtains the statistics click-through rate of extension system, namely 0.1%, as the weighted mean click-through rate of this popularization keyword.Preferably, the network equipment gives different weights for the popularization weighted mean click-through rate of keyword and the statistics click-through rate of extension system, weighted mean value is asked to this weighted mean click-through rate and this statistics click-through rate, to obtain the new weighted mean click-through rate of this popularization keyword; Suppose that the weighted mean click-through rate promoting keyword is 0.09%, weight corresponding to this weighted mean click-through rate is 0.6, and the statistics click-through rate of extension system is 0.1%, and weight corresponding to this statistics click-through rate is 0.4, so, the new weighted mean click-through rate of this popularization keyword is 0.094%.Those skilled in the art will be understood that the obtain manner of the weighted mean click-through rate of above-mentioned popularization keyword is only citing; the obtain manner of the weighted mean click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, the acquisition source of promoting the statistics click-through rate of the extension system belonging to keyword includes but not limited to, the memory storage of the network equipment itself, the management server of extension system, can with other equipment of this network device communications, those skilled in the art will be understood that the acquisition source of the statistics click-through rate of the extension system belonging to above-mentioned popularization keyword is only citing, the acquisition source of the statistics click-through rate of other extension systems belonging to popularization keyword that is existing or that may occur from now on is as being applicable to the present invention, also within should being included in scope, and be contained in this at this with way of reference.
Preferably, in step s 2, the network equipment, according to described popularization keyword, obtains the click-through rate of other popularization keywords of this user; According to the click-through rate of other popularization keywords of this user described, the individual click-through rate of the described popularization keyword corresponding with this user is determined in weighting.Particularly, in step s 2, the popularization keyword that the network equipment obtains in step sl according to it, obtain the click-through rate of other popularization keywords of this user, such as, this user, promote the click-through rate of keyword, according to this (a bit) click-through rate with other in same popularization unit of this popularization keyword, determined the weight of this (a bit) click-through rate by the mode of such as meaning of a word cluster, thus the individual click-through rate of this popularization keyword of this user is determined in weighting.Such as, suppose this management server as extension system of the network equipment, promoting keyword is " click-through rate ", other popularization keywords that the network equipment obtains this user are accordingly " CTR ", " clicking rate ", " click volume " and " average click-through rate ", then from the record of this user, " CTR " is read, " clicking rate ", the click-through rate of " click volume " and " average click-through rate ", to " CTR ", " clicking rate ", " click volume " and " average click-through rate " carries out meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate " of " click-through rate ", the weight that their click-through rate is corresponding is 0.3, the near adopted keyword " click volume " of " click-through rate " and " average click-through rate ", the weight that their click-through rate is corresponding is 0.2, weighted mean value is asked to these click-through rates, obtain the individual click-through rate of " click-through rate ".Those skilled in the art will be understood that the obtain manner of the individual click-through rate of above-mentioned popularization keyword is only citing; the obtain manner of the individual click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, other popularization keywords of this user include but not limited to, this user, promote keyword with other in same popularization unit of this popularization keyword, or this user, with the popularization unit same class other other at this popularization keyword place promotes in unit other promote keyword, or this user, other popularization keywords in all popularization unit.Those skilled in the art will be understood that other popularization keywords of this user above-mentioned are only citing; other of other these users that are existing or that may occur from now on promote keyword as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a preferred embodiment, in step s 2, the network equipment, according to described popularization keyword, in conjunction with the user related information of this user, obtains the individual click-through rate of the described popularization keyword corresponding with this user.Particularly, in step s 2, the popularization keyword that the network equipment obtains in step sl according to it, in conjunction with the user related information of this user, such as, the historical record of the individual click-through rate of this popularization keyword of this user, for the unusual fluctuations of this individual click-through rate level and smooth, the submission record of the described popularization keyword of this user, for identifying the malicious registration behavior of this user, obtains the individual click-through rate of this popularization keyword of this user.Such as, suppose that the popularization keyword that user inputs is " fresh flower ", according to the historical record of the individual click-through rate of " fresh flower " of this user, the individual click-through rate of 3:00PM-4:00PM time period yesterday is 2%, the individual click-through rate of 3:00PM-4:00PM time period today is 0.02%, judge that the individual click-through rate of 3:00PM-4:00PM time period today may receive the impact of the malicious act of the network user, the network equipment these unusual fluctuations level and smooth, obtain the individual click-through rate of history average (mean value as the individual click-through rate of period same in January in past) as 3:00PM-4:00PM time period today " fresh flower " of the individual click-through rate of " fresh flower ".Those skilled in the art will be understood that the mode of the individual click-through rate of this popularization keyword of above-mentioned this user of acquisition is only citing; the mode of the individual click-through rate of this popularization keyword of other these users of acquisition that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, user related information includes but not limited to, below at least any one: the 1) historical record of the individual click-through rate of this popularization keyword of this user; 2) the submission record of this popularization keyword of this user.Wherein, the historical record of the individual click-through rate of this popularization keyword of this user includes but not limited to the historical record of a period of time of the individual click-through rate of the historical record of the adjacent moment of the individual click-through rate of this popularization keyword of this user and this popularization keyword of this user, may be used for the unusual fluctuations of this individual click-through rate level and smooth, such as, according to the adjacent moment of individual click-through rate or the historical record of the past period of this popularization keyword of this user, filtering is because of the malicious act of the network user, search for (represent in a large number and but do not click) as broiler chicken or click maliciously in a large number, the unusual fluctuations of the individual click-through rate caused.Such as, suppose that the popularization keyword that user inputs is " fresh flower ", according to the historical record of the individual click-through rate of " fresh flower " of this user, yesterday, the individual click-through rate of " fresh flower " of this user was 2%, netizen is had today to use broiler chicken to search for " fresh flower ", the individual click-through rate of " fresh flower " of this user today is made to be 0.02%, the difference of the individual click-through rate of " fresh flower " of this user of yesterday and today is 1.98%, exceed the relative value scope (as 0.5%-0.8%) of the individual click-through rate that the network equipment is preset, the network equipment obtains the individual click-through rate of critical value (as 1.2%) as " fresh flower " of this user of today of this individual click-through rate.The submission record of this popularization keyword of this user includes but not limited to that this user promotes at one the record submitting this popularization keyword in unit to, or this user submits the record of this popularization keyword in its all popularization unit, may be used for the malicious registration behavior identifying this user, such as this user promotes in unit at one and have registered the very large popularization keyword that still click volume is very little of the amount of representing, make the quality degree of this popularization keyword very low, this user is in order to eliminate this submission record, this popularization keyword of the renewal of registration in unit is promoted at other, wish to reach the very large object that still click volume is very little of the amount of representing equally, after the network equipment identifies the malicious registration behavior of this user, according to the former individual click-through rate submitted in record of this popularization keyword, determine the individual click-through rate of this popularization keyword of new registration, namely the individual click-through rate of this popularization keyword original is very low, the individual click-through rate of this popularization keyword of new registration is still very low, thus make the quality degree of this popularization keyword of new registration also very low.Such as, suppose to promote keyword for " fresh flower ", this user promotes registration in unit at " product " is somebody's turn to do " fresh flower ", should " fresh flower " be 100000 times in this " product " amount of representing promoted in unit, click volume is 200 times, thus to obtain individual click-through rate be 0.2%; This user promotes in unit again to register in " service " is somebody's turn to do " fresh flower ", the network equipment identifies this malicious registration behavior of this user, to promote the individual click-through rate in unit according to this " fresh flower " at " product ", determine that individual click-through rate that this " fresh flower " is promoted in unit in " service " is 0.2%.Those skilled in the art will be understood that above-mentioned user related information is only citing, and other user related informations that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
More preferably, it is not shown that this process also comprises step S5(), in step s 5, network equipment record or upgrade described user related information.Particularly, the network equipment, according to the change of the popularization operation of user and/or the popularization data of user, records or upgrades the user related information of this user.Such as, when in the network equipment also not this user related information time, once this popularization keyword of this user is clicked or be demonstrated in a network, the network equipment records this user related information in step s 5; When the network equipment has had the record of user related information, when user carries out the popularization operations such as Advertising registration, or when the click-through rate of this popularization keyword of this user changes, upgrade this user related information according to the change of this user related information in step s 5.Such as, when keyword is promoted in user's new registration one, now think historical record not about the individual click-through rate of this popularization keyword of this user in the network equipment, when netizen is in accesses network resource, this popularization keyword of this user is represented or is clicked, and the network equipment will record this user related information (i.e. the original records of the individual click-through rate of this popularization keyword of this user).Based on this, the network equipment calls this user related information, judge whether the individual click-through rate of this popularization keyword of this user occurs unusual fluctuations, the individual click-through rate judging now this popularization keyword of this user when the network equipment is unusual fluctuations, and determine the individual click-through rate of this popularization keyword of now this user according to preset critical after, the network equipment upgrades this user related information historical record of the individual click-through rate of this popularization keyword of this user (namely now) according to this preset critical.Those skilled in the art will be understood that the mode of above-mentioned record and renewal user related information is only citing; the mode of other records that are existing or that may occur from now on or renewal user related information is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a further advantageous embodiment, it is not shown that this process also comprises step S6(), in step s 6, the network equipment is according to the change of described quality degree, and the evaluation and test frequency of described popularization keyword is evaluated and tested in adjustment; According to the evaluation and test frequency after adjustment, evaluate and test the quality degree of described popularization keyword.Particularly, in step s 6, the quality degree of the popularization keyword that the network equipment obtains in step s 4 which according to it, obtains the change of this quality degree, and according to this change, the evaluation and test frequency of this popularization keyword of adjustment evaluation and test.Such as, if the change of (as continuous two days) is less in the unit interval, then the evaluation and test frequency of this popularization keyword of evaluation and test is reduced; If (as continuous two days) changes greatly in the unit interval, then improve the evaluation and test frequency of this popularization keyword of evaluation and test, then according to the evaluation and test frequency after adjustment, carry out the evaluation and test of the quality degree of this follow-up popularization keyword, the network equipment accordingly adaptive adjustment for the evaluation and test frequency of the quality degree of this popularization keyword.Those skilled in the art will be understood that the mode of above-mentioned adjustment evaluation and test frequency is only citing; the mode of other adjustment evaluation and test frequency that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, in step s 6, when the variable quantity of described quality degree in double evaluation and test is lower than frequency reducing threshold value, the network equipment reduces described evaluation and test frequency; When the variable quantity of described quality degree in double evaluation and test exceedes raising frequency threshold value, the network equipment improves described evaluation and test frequency.Particularly, in step s 6, the network equipment contrasts the variable quantity of the quality degree of double evaluation and test, when this variable quantity is lower than frequency reducing threshold value, reduces the evaluation and test frequency of the quality degree of this popularization keyword; When this variable quantity exceedes raising frequency threshold value, improve the evaluation and test frequency of the quality degree of this popularization keyword.The network equipment, according to the situation of change of quality degree, improves or reduces the evaluation and test frequency for the quality degree promoting keyword, making rationality of the present invention higher.Such as, suppose that frequency reducing threshold value is 0.2, the variable quantity promoting the double quality degree of keyword is 0.1, then reduce the evaluation and test frequency of the quality degree of this popularization keyword, as being reduced to 1 times/day from present 2 times/day.And for example, suppose that raising frequency threshold value is 0.8, the variable quantity promoting the double quality degree of keyword is 1.0, then improve the evaluation and test frequency of the quality degree of this popularization keyword, as being reduced to 3 times/day from present 2 times/day.Those skilled in the art will be understood that above-mentioned reduction and improve the mode evaluating and testing frequency and are only citing; the mode of other reductions that are existing or that may occur from now on or raising evaluation and test frequency is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Fig. 2 is equipment schematic diagram according to a further aspect of the present invention, and the network equipment promoting keyword quality score based on the evaluation and test of weighted mean click-through rate is shown.At this, the network equipment 1 includes but not limited to network host, single network server, multiple webserver collection or the set of computers based on cloud computing, wherein, cloud computing is the one of Distributed Calculation, the super virtual machine be made up of a group loosely-coupled computing machine collection.Those skilled in the art will be understood that the above-mentioned network equipment is only citing, and other network equipments that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
Particularly, the network equipment 1 comprises the first acquisition device 11, second acquisition device 12, the 3rd acquisition device 13 and determining device 14.Wherein, the first acquisition device 11 obtains the popularization keyword of user's input; Second acquisition device 12, according to described popularization keyword, obtains the individual click-through rate of the described popularization keyword corresponding with this user; 3rd acquisition device 13, according to described popularization keyword, obtains the weighted mean click-through rate of described popularization keyword; Determining device 14, according to described individual click-through rate and described weighted mean click-through rate, determines the quality degree of the described popularization keyword corresponding with this user.
More specifically, the first acquisition device 11 obtains the popularization keyword of user's input.Particularly, first acquisition device 11 obtains the popularization keyword of user's input in several ways, such as, mutual by with subscriber equipment of user, as carried out man-machine interaction by modes such as keyboard, mouse, telepilot, touch pad, touch-screen or handwriting equipments, and subscriber equipment is connected with the network equipment 1 via network, send the popularization keyword of this user input to the network equipment 1, the first acquisition device 11 obtains the popularization keyword of user's input accordingly; User is by the promoted account of this user in subscriber equipment logging in network equipment 1, and then in this promoted account, keyword is promoted in input, and the first acquisition device 11 obtains the popularization keyword of this user input from this promoted account; User will promote keyword input keywords database, and the network equipment 1 and this keywords database connect, and the first acquisition device 11 reads the popularization keyword of this user input from this keywords database.Those skilled in the art will be understood that the mode that above-mentioned first acquisition device obtains the popularization keyword that user inputs is only citing; other first acquisition device that are existing or that may occur from now on obtain the mode of the popularization keyword of user's input as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, network includes but not limited to internet, wide area network, Metropolitan Area Network (MAN), LAN (Local Area Network), VPN, wireless self-organization network (Ad Hoc network), GSM, WCDMA, CDMA2000, TD-SCDMA, GSM, CDMA1x, WIFI, WAPI, WiMax etc.Those skilled in the art will be understood that above-mentioned network is only citing, and other networks that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
Subsequently, the second acquisition device 12, according to described popularization keyword, obtains the individual click-through rate of the described popularization keyword corresponding with this user.Particularly, the popularization keyword of user's input that the second acquisition device 12 obtains according to the first acquisition device 11, obtains the individual click-through rate of this popularization keyword of this user.At this, the acquisition source of the individual click-through rate of this popularization keyword includes but not limited to, the memory storage of the network equipment 1 itself, the management server promoting the extension system belonging to keyword and other equipment that can communicate with this network equipment 1.The obtain manner of the individual click-through rate of this popularization keyword includes but not limited to, such as, the network equipment 1 itself is the management server of the extension system promoted belonging to keyword, and the second acquisition device 12 obtains the individual click-through rate of this popularization keyword from the historical record of this popularization keyword, and for example, second acquisition device 12 is by reading in a database, call the communication mode of specific application programming interfaces (API) or other agreements, obtain the individual click-through rate of this popularization keyword of this user, such as, the application programming interfaces (API) that second acquisition device 12 is provided by the third party device of the individual click-through rate calling this popularization keyword storing this user, the request of the individual click-through rate of this popularization keyword obtaining this user is sent to this third party device, and receive this third party device asks this popularization keyword of this user returned individual click-through rate according to this.Those skilled in the art will be understood that the acquisition source of above-mentioned individual click-through rate and obtain manner are only citing; the acquisition source of other individual click-through rates that are existing or that may occur from now on or obtain manner are as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Those skilled in the art will be understood that above-mentioned first acquisition device and the second acquisition device are only example, and in practice, they can be two independently modules, and also accessible site is in a module.
Then, the 3rd acquisition device 13, according to described popularization keyword, obtains the weighted mean click-through rate of described popularization keyword.Particularly, the popularization keyword that the 3rd acquisition device 13 obtains according to the first acquisition device 11, obtains the weighted mean click-through rate of this popularization keyword.The obtain manner of this weighted mean click-through rate includes but not limited to: calculate acquisition by the 3rd acquisition device 13, namely the click-through rate of different user or different popularization unit is corresponded to according to this popularization keyword, and give these click-through rates different weights, be weighted on average to these click-through rates again, to obtain the weighted mean click-through rate (when the weight of these click-through rates is identical, the weighted mean click-through rate of this popularization keyword is arithmetic mean click-through rate) of this popularization keyword; Directly obtained from the memory storage of the network equipment 1 self or third party device by the 3rd acquisition device 13, such as, 3rd acquisition device 13, by reading, calling the communication mode of specific application programming interfaces (API) or other agreements in a database, obtains the weighted mean click-through rate of this popularization keyword.Such as, the application programming interfaces (API) that 3rd acquisition device 13 is provided by the third party device calling the weighted mean click-through rate storing this popularization keyword, send the request of the weighted mean click-through rate obtaining this popularization keyword to this third party device, and receive this third party device asks this popularization keyword returned weighted mean click-through rate according to this.Those skilled in the art will be understood that above-mentioned obtain manner is only citing, and other obtain manners that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.At this; the Consideration of weight promoting the click-through rate of keyword includes but not limited to promote the dog-eat-dog degree of keyword, the retrieval amount of netizen, or the industry etc. promoted belonging to keyword; those skilled in the art will be understood that the Consideration of the weight of the click-through rate of above-mentioned popularization keyword is only citing; the Consideration of the weight of the click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
It should be noted that, those skilled in the art will be understood that, second acquisition device 12 and the 3rd acquisition device 13 are not strict sequential working relations, second acquisition device 12 first can obtain the individual click-through rate of this popularization keyword corresponding with this user, and the 3rd acquisition device 13 obtains the weighted mean click-through rate of this popularization keyword again; Also can first obtain the weighted mean click-through rate of this popularization keyword by the 3rd acquisition device 13, the second acquisition device 12 obtains the individual click-through rate of this popularization keyword corresponding with this user again; Second acquisition device 12 and the 3rd acquisition device 13 can also work simultaneously, obtain the individual click-through rate of this popularization keyword corresponding with this user and the weighted mean click-through rate of this popularization keyword respectively; At this, second acquisition device 11 and the 3rd acquisition device 12 are only example, in practice, they can be two independently modules, also accessible site is in a module, the such as network equipment 1 with third party device mutual in, this integration module same request with receives in response and the corresponding individual click-through rate of this popularization keyword of this user and the weighted mean click-through rate of this popularization keyword.For simplicity's sake, we first state the individual click-through rate that the second acquisition device 12 obtains this popularization keyword corresponding with this user, then state the weighted mean click-through rate that the 3rd acquisition device 13 obtains this popularization keyword.It is convenient that those skilled in the art will be understood that such statement order is only statement, should as limitation of the present invention.
Those skilled in the art also will be understood that, above-mentioned first acquisition device, the second acquisition device and the 3rd acquisition device are only example, and in practice, they can be three independently modules, or any two devices are integrated in a module, also can all be integrated in a module.
Subsequently, determining device 14, according to described individual click-through rate and described weighted mean click-through rate, determines the quality degree of the described popularization keyword corresponding with this user.Particularly, the weighted mean click-through rate of this popularization keyword that the individual click-through rate of this popularization keyword of this user that determining device 14 obtains according to the second acquisition device 12 and the 3rd acquisition device 13 obtain, determines the quality degree of this popularization keyword of this user by the mode of such as ratio, difference.Such as, determining device 14, according to the ratio of the individual click-through rate of this popularization keyword of this user with the weighted mean click-through rate of this popularization keyword, determines the quality degree of this popularization keyword of this user; Suppose that the individual click-through rate of this popularization keyword of this user is 0.2%, the weighted mean click-through rate of this popularization keyword is 0.15%, and so their ratio is 1.33, and this ratio is exactly the quality degree of this popularization keyword of this user.And for example, determining device 14, according to the difference of the individual click-through rate of this popularization keyword of this user with the weighted mean click-through rate of this popularization keyword, determines the quality degree of this popularization keyword of this user; Suppose that the individual click-through rate of this popularization keyword of this user is 0.2%, the weighted mean click-through rate of this popularization keyword is 0.15%, and so their difference is 0.05%, and this difference is exactly the quality degree of this popularization keyword of this user.Those skilled in the art will be understood that the determination mode of above-mentioned quality degree is only citing; the determination mode of other quality degree that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, the first acquisition device 11, second acquisition device 12, the 3rd acquisition device 13 and determining device 14 are constant work.Particularly, the first acquisition device 11 obtains the popularization keyword of user's input; Second acquisition device 12, according to described popularization keyword, obtains the individual click-through rate of the described popularization keyword corresponding with this user; 3rd acquisition device 13, according to described popularization keyword, obtains the weighted mean click-through rate of described popularization keyword; Determining device 14, according to described individual click-through rate and described weighted mean click-through rate, determines the quality degree of the described popularization keyword corresponding with this user.At this, it will be understood by those skilled in the art that " continuing " refers to that the first acquisition device 11, second acquisition device 12, the 3rd acquisition device 13 and determining device 14 require to carry out promoting the acquisition of keyword, the acquisition of individual click-through rate of this popularization keyword of this user, the acquisition of the weighted mean click-through rate of this popularization keyword according to the mode of operation of setting or real-time adjustment respectively, and the determination of the quality degree of this popularization keyword, until this network equipment stops evaluating and testing the quality degree promoting keyword in a long time.
In a preferred embodiment, the 3rd acquisition device 13, also according to described popularization keyword, obtains user's click-through rate of the described popularization keyword corresponding with using each user of described popularization keyword; According to described user's click-through rate, obtain the weighted mean click-through rate of described popularization keyword.Particularly, the popularization keyword that 3rd acquisition device 13 obtains according to the first acquisition device 11, obtain user's click-through rate that other users using this popularization keyword correspond to this popularization keyword, then according to this (a bit) user's click-through rate, obtain the weighted mean click-through rate of this popularization keyword.Such as, the represent amount of the 3rd acquisition device 13 corresponding to user's click-through rate gives user's click-through rate different weights, according to the weighted mean click-through rate of this popularization keyword of this Weight Acquisition; Suppose to promote keyword for " fresh flower ", the user using " fresh flower " under identical linguistic context is user's first and user's second, user's click-through rate that user's first corresponds to " fresh flower " is 0.2%, the amount of representing is 1000 times, user's click-through rate that user's second corresponds to " fresh flower " is 0.15%, and the amount of representing is 10000 times, and the weight of giving user's click-through rate of user's first is 0.1, the weight of giving user's click-through rate of user's second is 0.9, thus the weighted mean click-through rate obtaining " fresh flower " is 0.155%.And for example, suppose that the weight of user's click-through rate of the same popularization keyword of all users is the same, now the weighted mean click-through rate of this popularization keyword is arithmetic mean click-through rate; As promoted keyword for " fresh flower ", user's click-through rate that user's first corresponds to " fresh flower " is 0.2%, user's click-through rate that user's second corresponds to " fresh flower " is 0.15%, user's click-through rate that user third corresponds to " fresh flower " is 0.24%, and now the weighted mean click-through rate of " fresh flower " is 0.197%.Those skilled in the art will be understood that the mode of the weighted mean click-through rate of above-mentioned acquisition popularization keyword is only citing; other acquisitions that are existing or that may occur from now on promote the mode of the weighted mean click-through rate of keyword as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a further advantageous embodiment, the 3rd acquisition device 13, also according to described popularization keyword, obtains and relevant to described popularization keyword one or morely associates keyword; Obtain the click-through rate of described one or more association keyword; The click-through rate of described one or more association keyword is averaged, obtains the weighted mean click-through rate of described popularization keyword; Wherein, described one or more association keyword includes but not limited to, below at least any one: the 1) synonymous keyword of described popularization keyword; 2) the near adopted keyword of described popularization keyword; 3) keyword of the same trade is mutually belonged to described popularization keyword; 4) keyword of identical region is belonged to described popularization keyword.Particularly, the popularization keyword that 3rd acquisition device 13 obtains according to the first acquisition device 11, obtain and relevant to this popularization keyword one or morely associate keyword, such as, the synonym of this popularization keyword, nearly adopted keyword, keyword etc. with this popularization keyword of the same trade or identical region mutually, obtain the click-through rate of this (a bit) association keyword, then this (a bit) click-through rate is averaged, thus obtain the weighted mean click-through rate of this popularization keyword.Such as, suppose to promote keyword for " click-through rate ", 3rd acquisition device 13 is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", then by calling the application programming interfaces (API) that the third party device of click-through rate that stores keyword provides, send the request of the click-through rate obtaining " CTR " and " clicking rate " to this third party device, and receive this third party device asks " CTR " and " clicking rate " returned click-through rate according to this; Then average to the click-through rate of " CTR " and " clicking rate ", obtain the weighted mean click-through rate of " click-through rate ", weighted mean click-through rate now is also arithmetic mean click-through rate.And for example, still hypothesis promotes keyword is " click-through rate ", 3rd acquisition device 13 is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", nearly adopted keyword " click volume " and " average click-through rate ", then by reading the data of keywords database, obtain " CTR " respectively, " clicking rate ", the click-through rate of " click volume " and " average click-through rate ", the weight arranging the click-through rate of " CTR " and " clicking rate " is 0.3, the weight of the click-through rate of " click volume " and " average click-through rate " is 0.2, weighted mean value is asked to these click-through rates, the weighted mean click-through rate of " click-through rate " can be obtained.And for example, still hypothesis promotes keyword is " click-through rate ", 3rd acquisition device 13 is through meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate ", again region cluster analysis is carried out to these " CTR " and " clicking rate ", region is " East China ", thus the click-through rate obtaining " CTR " used in " East China " area is 0.2%, the click-through rate of " clicking rate " that use in " East China " area is 0.15%, the weight arranging the click-through rate of " CTR " is 0.4, the weight of the click-through rate of " clicking rate " is 0.6, show that the weighted mean click-through rate of " click-through rate " is 0.17%.Those skilled in the art will be understood that the obtain manner of the weighted mean click-through rate of above-mentioned popularization keyword and associate keyword and be only citing; the obtain manner of the weighted mean click-through rate of other popularization keywords that are existing or that may occur from now on or association keyword are as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In another preferred embodiment, 3rd acquisition device 13 is also according to described popularization keyword, and in conjunction with the statistics click-through rate (namely in this extension system the click volume of all keywords with the ratio of the amount of representing) of the extension system belonging to described popularization keyword, obtain the weighted mean click-through rate of described popularization keyword.Particularly, in step s3, the popularization keyword that the network equipment obtains in step sl according to it, in conjunction with the statistics click-through rate of the extension system belonging to this popularization keyword, obtains the weighted mean click-through rate of this popularization keyword.Degree of confidence such as when the weighted mean click-through rate of this popularization keyword is too low, and the network equipment selects the weighted mean click-through rate of statistics click-through rate as this popularization keyword of this extension system; Suppose that the weighted mean click-through rate promoting keyword is 0.09%, the statistics click-through rate of extension system is 0.1%, now promote the statistics click-through rate of weighted mean click-through rate lower than extension system of keyword, the network equipment obtains the statistics click-through rate of extension system, namely 0.1%, as the weighted mean click-through rate of this popularization keyword.Preferably, the network equipment gives different weights for the popularization weighted mean click-through rate of keyword and the statistics click-through rate of extension system, weighted mean value is asked to this weighted mean click-through rate and this statistics click-through rate, to obtain the new weighted mean click-through rate of this popularization keyword; Suppose that the weighted mean click-through rate promoting keyword is 0.09%, weight corresponding to this weighted mean click-through rate is 0.6, and the statistics click-through rate of extension system is 0.1%, and weight corresponding to this statistics click-through rate is 0.4, so, the new weighted mean click-through rate of this popularization keyword is 0.094%.Those skilled in the art will be understood that the obtain manner of the weighted mean click-through rate of above-mentioned popularization keyword is only citing; the obtain manner of the weighted mean click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, the acquisition source of promoting the statistics click-through rate of the extension system belonging to keyword includes but not limited to, the memory storage of the network equipment itself, the management server of extension system, can with other equipment of this network device communications, those skilled in the art will be understood that the acquisition source of the statistics click-through rate of the extension system belonging to above-mentioned popularization keyword is only citing, the acquisition source of the statistics click-through rate of other extension systems belonging to popularization keyword that is existing or that may occur from now on is as being applicable to the present invention, also within should being included in scope, and be contained in this at this with way of reference.
Preferably, the second acquisition device 12, according to described popularization keyword, obtains the click-through rate of other popularization keywords of this user; According to the click-through rate of other popularization keywords of this user described, the individual click-through rate of the described popularization keyword corresponding with this user is determined in weighting.Particularly, the popularization keyword that second acquisition device 12 obtains according to the first acquisition device 11, obtain the click-through rate of other popularization keywords of this user, such as, this user, promote the click-through rate of keyword with other in same popularization unit of this popularization keyword, according to this (a bit) click-through rate, determined the weight of this (a bit) click-through rate by the mode of such as meaning of a word cluster, thus the individual click-through rate of this popularization keyword of this user is determined in weighting.Such as, suppose the network equipment 1 management server as extension system, promoting keyword is " click-through rate ", other popularization keywords that second acquisition device 12 obtains this user are accordingly " CTR ", " clicking rate ", " click volume " and " average click-through rate ", then from the record of this user, " CTR " is read, " clicking rate ", the click-through rate of " click volume " and " average click-through rate ", to " CTR ", " clicking rate ", " click volume " and " average click-through rate " carries out meaning of a word analysis, obtain synonymous keyword " CTR " and " clicking rate " of " click-through rate ", the weight that their click-through rate is corresponding is 0.3, the near adopted keyword " click volume " of " click-through rate " and " average click-through rate ", the weight that their click-through rate is corresponding is 0.2, weighted mean value is asked to these click-through rates, obtain the individual click-through rate of " click-through rate ".Those skilled in the art will be understood that the obtain manner of the individual click-through rate of above-mentioned popularization keyword is only citing; the obtain manner of the individual click-through rate of other popularization keywords that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.At this, other popularization keywords of this user include but not limited to, this user, promote keyword with other in same popularization unit of this popularization keyword, or this user, with the popularization unit same class other other at this popularization keyword place promotes in unit other promote keyword, or this user, other popularization keywords in all popularization unit.Those skilled in the art will be understood that other popularization keywords of this user above-mentioned are only citing; other of other these users that are existing or that may occur from now on promote keyword as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a preferred embodiment, the second acquisition device 12, also according to described popularization keyword, in conjunction with the user related information of this user, obtains the individual click-through rate of the described popularization keyword corresponding with this user.Particularly, the popularization keyword that second acquisition device 12 obtains according to the first acquisition device 11, in conjunction with the user related information of this user, such as, the historical record of the individual click-through rate of this popularization keyword of this user, for the unusual fluctuations of this individual click-through rate level and smooth, the submission record of the described popularization keyword of this user, for identifying the malicious registration behavior of this user, obtain the individual click-through rate of this popularization keyword of this user.Such as, suppose that the popularization keyword that user inputs is " fresh flower ", according to the historical record of the individual click-through rate of " fresh flower " of this user, the individual click-through rate of 3:00PM-4:00PM time period yesterday is 2%, the individual click-through rate of 3:00PM-4:00PM time period today is 0.02%, judge that the individual click-through rate of 3:00PM-4:00PM time period today may receive the impact of the malicious act of the network user, these unusual fluctuations level and smooth of second acquisition device 12, obtain the individual click-through rate of history average (mean value as the individual click-through rate of period same in January in past) as 3:00PM-4:00PM time period today " fresh flower " of the individual click-through rate of " fresh flower ".Those skilled in the art will be understood that the mode of the individual click-through rate of this popularization keyword of above-mentioned this user of acquisition is only citing; the mode of the individual click-through rate of this popularization keyword of other these users of acquisition that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, user related information includes but not limited to, below at least any one: the 1) historical record of the individual click-through rate of this popularization keyword of this user; 2) the submission record of this popularization keyword of this user.Wherein, the historical record of the individual click-through rate of this popularization keyword of this user includes but not limited to the historical record of a period of time of the individual click-through rate of the historical record of the adjacent moment of the individual click-through rate of this popularization keyword of this user and this popularization keyword of this user, may be used for the unusual fluctuations of this individual click-through rate level and smooth, such as, according to the adjacent moment of individual click-through rate or the historical record of the past period of this popularization keyword of this user, filtering is because of the malicious act of the network user, search for (represent in a large number and but do not click) as broiler chicken or click maliciously in a large number, the unusual fluctuations of the individual click-through rate caused.Such as, suppose that the popularization keyword that user inputs is " fresh flower ", according to the historical record of the individual click-through rate of " fresh flower " of this user, yesterday, the individual click-through rate of " fresh flower " of this user was 2%, netizen is had today to use broiler chicken to search for " fresh flower ", the individual click-through rate of " fresh flower " of this user today is made to be 0.02%, the difference of the individual click-through rate of " fresh flower " of this user of yesterday and today is 1.98%, exceed the relative value scope (as 0.5%-0.8%) of the individual click-through rate preset, second acquisition device 12 obtains the individual click-through rate of critical value (as 1.2%) as " fresh flower " of this user of today of this individual click-through rate.The submission record of this popularization keyword of this user includes but not limited to that this user promotes at one the record submitting this popularization keyword in unit to, or this user submits the record of this popularization keyword in its all popularization unit, may be used for the malicious registration behavior identifying this user, such as this user promotes in unit at one and have registered the very large popularization keyword that still click volume is very little of the amount of representing, make the quality degree of this popularization keyword very low, this user is in order to eliminate this submission record, this popularization keyword of the renewal of registration in unit is promoted at other, wish to reach the very large object that still click volume is very little of the amount of representing equally, after the malicious registration behavior identifying this user, second acquisition device 12 is according to the former individual click-through rate submitted in record of this popularization keyword, determine the individual click-through rate of this popularization keyword of new registration, namely the individual click-through rate of this popularization keyword original is very low, the individual click-through rate of this popularization keyword of new registration is still very low, thus make the quality degree of this popularization keyword of new registration also very low.Such as, suppose to promote keyword for " fresh flower ", this user promotes registration in unit at " product " is somebody's turn to do " fresh flower ", should " fresh flower " be 100000 times in this " product " amount of representing promoted in unit, click volume is 200 times, thus to obtain individual click-through rate be 0.2%; This user promotes in unit again to register in " service " is somebody's turn to do " fresh flower ", after this malicious registration behavior identifying this user, second acquisition device 12 to promote the individual click-through rate in unit at " product " according to this " fresh flower ", determine that individual click-through rate that this " fresh flower " is promoted in unit in " service " is 0.2%.Those skilled in the art will be understood that above-mentioned user related information is only citing, and other user related informations that are existing or that may occur from now on, as being applicable to the present invention, within also should being included in scope, and are contained in this at this with way of reference.
More preferably, the network equipment 1 also comprises updating device (not shown), records or upgrades described user related information.Particularly, updating device, according to the change of the popularization operation of user and/or the popularization data of user, records or upgrades the user related information of this user.Such as, when in the network equipment 1 also not this user related information time, once this popularization keyword of this user is clicked or be demonstrated, this user related information of updating device record in a network; When the network equipment 1 has had the record of user related information, when user carries out the popularization operations such as Advertising registration, or when the click-through rate of this popularization keyword of this user changes, updating device upgrades this user related information according to the change of this user related information.Such as, when keyword is promoted in user's new registration one, now think historical record not about the individual click-through rate of this popularization keyword of this user in the network equipment 1, when netizen is in accesses network resource, this popularization keyword of this user is represented or is clicked, and updating device will record this user related information (i.e. the original records of the individual click-through rate of this popularization keyword of this user).Based on this, second acquisition device 12 calls this user related information, judge whether the individual click-through rate of this popularization keyword of this user occurs unusual fluctuations, when the second acquisition device 12 judges that the individual click-through rate of this popularization keyword of now this user is unusual fluctuations, and determine the individual click-through rate of this popularization keyword of now this user according to preset critical after, updating device upgrades this user related information historical record of the individual click-through rate of this popularization keyword of this user (namely now) according to this preset critical.Those skilled in the art will be understood that the mode of above-mentioned record and renewal user related information is only citing; the mode of other records that are existing or that may occur from now on or renewal user related information is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
In a further advantageous embodiment, the network equipment 1 also comprises adjusting gear (not shown), according to the change of described quality degree, and the evaluation and test frequency of the described popularization keyword of adjustment evaluation and test; According to the evaluation and test frequency after adjustment, evaluate and test the quality degree of described popularization keyword.Particularly, the quality degree of the popularization keyword that adjusting gear obtains according to determining device 14, obtains the change of this quality degree, and according to this change, the evaluation and test frequency of this popularization keyword of adjustment evaluation and test.Such as, if the change of (as continuous two days) is less in the unit interval, adjusting gear then reduces the evaluation and test frequency of this popularization keyword of evaluation and test; If (as continuous two days) changes greatly in the unit interval, adjusting gear then improves the evaluation and test frequency of this popularization keyword of evaluation and test, then according to the evaluation and test frequency after adjustment, carry out the evaluation and test of the quality degree of this follow-up popularization keyword, adjusting gear accordingly adaptive adjustment for the evaluation and test frequency of the quality degree of this popularization keyword.Those skilled in the art will be understood that the mode of above-mentioned adjustment evaluation and test frequency is only citing; the mode of other adjustment evaluation and test frequency that are existing or that may occur from now on is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
Preferably, when the variable quantity of described quality degree in double evaluation and test is lower than frequency reducing threshold value, adjusting gear reduces described evaluation and test frequency; When the variable quantity of described quality degree in double evaluation and test exceedes raising frequency threshold value, adjusting gear improves described evaluation and test frequency.Particularly, adjusting gear contrasts the variable quantity of the quality degree of double evaluation and test, when this variable quantity is lower than frequency reducing threshold value, reduces the evaluation and test frequency of the quality degree of this popularization keyword; When this variable quantity exceedes raising frequency threshold value, improve the evaluation and test frequency of the quality degree of this popularization keyword.Adjusting gear, according to the situation of change of quality degree, improves or reduces the evaluation and test frequency for the quality degree promoting keyword, making rationality of the present invention higher.Such as, suppose that frequency reducing threshold value is 0.2, the variable quantity promoting the double quality degree of keyword is 0.1, and adjusting gear then reduces the evaluation and test frequency of the quality degree of this popularization keyword, as being reduced to 1 times/day from present 2 times/day.And for example, suppose that raising frequency threshold value is 0.8, the variable quantity promoting the double quality degree of keyword is 1.0, and adjusting gear then improves the evaluation and test frequency of the quality degree of this popularization keyword, as being reduced to 3 times/day from present 2 times/day.Those skilled in the art will be understood that above-mentioned reduction and improve the mode evaluating and testing frequency and are only citing; the mode of other reductions that are existing or that may occur from now on or raising evaluation and test frequency is as being applicable to the present invention; also within scope should being included in, and this is contained at this with way of reference.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.In addition, obviously " comprising " one word do not get rid of other unit or step, odd number does not get rid of plural number.Multiple unit of stating in system claims or device also can be realized by software or hardware by a unit or device.First, second word such as grade is used for representing title, and does not represent any specific order.