CN105072466A - Information push method and device - Google Patents

Information push method and device Download PDF

Info

Publication number
CN105072466A
CN105072466A CN201510386575.6A CN201510386575A CN105072466A CN 105072466 A CN105072466 A CN 105072466A CN 201510386575 A CN201510386575 A CN 201510386575A CN 105072466 A CN105072466 A CN 105072466A
Authority
CN
China
Prior art keywords
information
client
pushed information
type
probability
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510386575.6A
Other languages
Chinese (zh)
Other versions
CN105072466B (en
Inventor
李勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201510386575.6A priority Critical patent/CN105072466B/en
Publication of CN105072466A publication Critical patent/CN105072466A/en
Application granted granted Critical
Publication of CN105072466B publication Critical patent/CN105072466B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26208—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The embodiment of the invention discloses an information push method and device, and relates to the technical field of the Internet. The method comprises the steps: receiving an information push request sent by a target client A; determining an alternative push information set suitable for the target client A; enabling the alternative push information set to be divided into a first alternative push information set and a second alternative push information set; calculating information loss probability of each piece of information in the second alternative push information set; carrying out the information loss processing of the information in the second alternative push information set according to the information loss probability obtained through calculation; determining the actual push information according to the first alternative push information set and the second alternative push information set after loss processing; and pushing the determined actual push information to the target client A. Through the scheme provided by the embodiment of the invention, the method can and device can push information to different types of clients in a balanced manner.

Description

A kind of information-pushing method and device
Technical field
The present invention relates to Internet technical field, particularly a kind of information-pushing method and device.
Background technology
Along with the fast development of network and hardware technology, increasing user watches video by network, Given this, increasing advertiser wishes that media platform is in the process of user's displaying video in client, by server to information such as client push advertisements, to increase the exposure rate of its product.
In addition, the hardware device used due to user is different, such as, mobile phone, panel computer, desktop computer etc., further, various hardware device may be provided with different operating system again, so, for the client of user's displaying video exists miscellaneous editions type usually, such as, Android version cell-phone customer terminal, Android version panel computer client, iOS version cell-phone customer terminal, iOS version panel computer client etc.
In prior art, server usually according to received information pushing request, is determined to treat advertisement after receiving the information pushing request sent from dissimilar client, and directly selected each is treated that advertisement is pushed to client successively.
But, in practical application, because media platform may take different migration efficiency for dissimilar client in actual operation, media platform is that dissimilar client arranges different planning advertisement information pushing amounts, advertiser only selects the reasons such as the client displaying advertising messages of several types, when server application said method is to client push advertising message, easy appearance is to the unbalanced situation of amount of dissimilar client push advertising message, such as, too much to Android version cell-phone customer terminal advertisement information, and it is very few etc. to iOS version cell-phone customer terminal advertisement information, especially, in this case, when same user switches between dissimilar client, Consumer's Experience is poor.
Summary of the invention
The embodiment of the invention discloses a kind of information-pushing method and device, with can be balanced to dissimilar client push information.
For achieving the above object, the embodiment of the invention discloses a kind of information-pushing method, for concentrating selection information to push to destination client from the information preset, in every bar information that described default information is concentrated, specify in advance have this information the client type that is suitable for, described method comprises:
The information pushing request that receiving target customer end A sends, wherein, described information pushing carries the type identification value IDC of described destination client A in asking a;
According to described IDC a, and every bar information of concentrating of described default information the client type that is suitable for, determine the alternative pushed information collection being applicable to described destination client A;
According to the client type that described alternative pushed information concentrates every bar information to be suitable for, described alternative pushed information collection is divided into the alternative pushed information subset of the first alternative pushed information subset sums second, wherein, every bar information in described first alternative pushed information subset is only applicable to the client of a type, and the every bar information in described second alternative pushed information subset is applicable to the client of at least two types;
For each information in described second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information;
According to the information dropout probability calculated, information discard processing is carried out to the information in described second alternative pushed information subset;
According to the second alternative pushed information subset of described first alternative pushed information subset sums after discard processing, determine actual pushed information;
Determined actual pushed information is pushed to described destination client A.
In a kind of specific implementation of the present invention, described for each information in described second alternative pushed information subset, be IDC according to the total amount of client actual pushed information in preset period of time of this information institute application type and type identification value athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information, comprising:
Respectively by with under type, calculate the information dropout probability of each the information M in described second alternative pushed information subset:
Obtain the total amount N of client actual pushed information in preset period of time of described M institute application type tAin described preset period of time, the total amount N of pushed information is planned with it tP;
Obtaining type identification value is IDC aclient actual pushed information amount N in described preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
According to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
According to described P twith described P s, determine the information dropout probability of described M.
In a kind of specific implementation of the present invention, described according to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s, comprising:
According to following formula, calculate the idle probability P of Global Information of polymorphic type client t,
P T = 1 - N T A N T P ;
According to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
In a kind of specific implementation of the present invention, described according to described P twith described P s, determine the information dropout probability of described M, comprising:
According to described P twith described P s, calculate segment factor f=(P t-P s) × g, wherein, described g is default threshold factor, g > 0;
According to described f, according to following formula, obtain the information dropout probability W of described M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, 0 < k < 1.
In a kind of specific implementation of the present invention, described information-pushing method also comprises:
Successful after the determined each actual pushed information of described destination client A propelling movement, updating type ident value is IDC athe actual pushed information amount of client in described preset period of time.
For achieving the above object, the embodiment of the invention discloses a kind of information push-delivery apparatus, for concentrating selection information to push to destination client from the information preset, in every bar information that described default information is concentrated, specify in advance have this information the client type that is suitable for, described device comprises:
Push request receiving module, for the information pushing request that receiving target customer end A sends, wherein, described information pushing carries the type identification value IDC of described destination client A in asking a;
Information set determination module, for according to described IDC a, and every bar information of concentrating of described default information the client type that is suitable for, determine the alternative pushed information collection being applicable to described destination client A;
Information set divides module, for the client type concentrating every bar information to be suitable for according to described alternative pushed information, described alternative pushed information collection is divided into the alternative pushed information subset of the first alternative pushed information subset sums second, wherein, every bar information in described first alternative pushed information subset is only applicable to the client of a type, and the every bar information in described second alternative pushed information subset is applicable to the client of at least two types;
Losing probability computing module, for for each information in described second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information;
Discard processing module, for according to the information dropout probability calculated, carries out information discard processing to the information in described second alternative pushed information subset;
Pushed information determination module, for according to the second alternative pushed information subset of described first alternative pushed information subset sums after discard processing, determines actual pushed information;
Info push module, for pushing determined actual pushed information to described destination client A.
In a kind of specific implementation of the present invention, described losing probability computing module, specifically for calculating the information dropout probability of each the information M in described second alternative pushed information subset respectively;
Described losing probability computing module, comprising:
First information amount obtains submodule, for obtaining the total amount N of client actual pushed information in preset period of time of described M institute application type tAin described preset period of time, the total amount N of pushed information is planned with it tP;
Second amount of information obtains submodule, is IDC for obtaining type identification value aclient actual pushed information amount N in described preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
Idle probability calculation submodule, for according to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
Losing probability determination submodule, for according to described P twith described P s, determine the information dropout probability of described M.
In a kind of specific implementation of the present invention, described idle probability calculation submodule, comprising:
First idle probability calculation unit, for according to following formula, calculates the idle probability P of Global Information of polymorphic type client t,
P T = 1 - N T A N T P ;
Second idle probability calculation unit, for according to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
In a kind of specific implementation of the present invention, described losing probability determination submodule, comprising:
Segment factor computing unit, for according to described P twith described P s, calculate segment factor f=(P t-P s) × g, wherein, described g is default threshold factor, g > 0;
Losing probability obtains unit, for according to described f, according to following formula, obtains the information dropout probability W of described M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, 0 < k < 1.
In a kind of specific implementation of the present invention, described information push-delivery apparatus also comprises:
Amount of information update module, in success to after described destination client A pushes determined each actual pushed information, updating type ident value is IDC athe actual pushed information amount of client in described preset period of time.
As seen from the above, in the scheme that the embodiment of the present invention provides, due to the information dropout probability of each information in the second alternative pushed information subset, be IDC according to client actual pushed information total amount and type identification value in preset period of time of this information institute application type athe numerical relation of client in preset period of time between actual pushed information amount calculate, so this value can reflect that type identification value is IDC aclient actual information pushed in preset period of time whether too much or very few compared to the client of other types.In addition, after carrying out discard processing according to the information drop probability calculated, again according to the second alternative pushed information subset of the first alternative pushed information subset sums after discard processing, determine the actual pushed information obtained, although, cannot directly make actual pushed information amount reach balance like this, knowledge according to statistical probability aspect can be known, along with server is IDC to ident value aclient push information increased frequency, actual pushed information amount can be made on the whole to reach balance according to this information dropout probability.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
The schematic flow sheet of a kind of information-pushing method that Fig. 1 provides for the embodiment of the present invention;
The schematic flow sheet of the another kind of information-pushing method that Fig. 2 provides for the embodiment of the present invention;
The structural representation of a kind of information push-delivery apparatus that Fig. 3 provides for the embodiment of the present invention;
The structural representation of the another kind of information push-delivery apparatus that Fig. 4 provides for the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
The schematic flow sheet of a kind of information-pushing method that Fig. 1 provides for the embodiment of the present invention, the information that the method is used for from presetting concentrates selection information to push to destination client, wherein, in every bar information that the information preset is concentrated, specify in advance have this information the client type that is suitable for.
Concrete, every bar information that the information preset is concentrated goes for the client of a type, and also go for polytype client, the application does not limit this.
The information that the information preset is concentrated can be advertising message, news information, weather forecast information etc.
The method comprises:
S101: the information pushing request that receiving target customer end A sends.
Wherein, information pushing at least carries the type identification value IDC of destination client A in asking a.
Be understandable that, client for a certain application may operate on different hardware devices, and different hardware devices may corresponding different operating system, so, in order to adapt to different situations, developer often releases polytype client for same application, such as, and Android version cell-phone customer terminal, Android version panel computer client, iOS version cell-phone customer terminal, iOS version panel computer client, win7 version computer client etc.
Given this, above-mentioned IDC ait can be the ident value that Android version cell-phone customer terminal, Android version panel computer client, iOS version cell-phone customer terminal, iOS version panel computer client, win7 version computer client etc. are corresponding.
S102: according to IDC a, and the every bar information concentrated of information preset the client type that is suitable for, determine the alternative pushed information collection being applicable to destination client A.
Due to specified in advance default information concentrate every bar information the client type that is suitable for, so, when the alternative pushed information determining to be applicable to destination client A concentrates comprised information, can concentrate from the information preset that to be applicable to client type ident value be IDC ainformation in determine.
S103: the client type concentrating every bar information to be suitable for according to alternative pushed information, is divided into the alternative pushed information subset of the first alternative pushed information subset sums second by alternative pushed information collection.
Concrete, when dividing above-mentioned alternative pushed information collection, alternative pushed information concentrated the information of the client being only applicable to a type to be divided in the first alternative pushed information subset, alternative pushed information concentrated the information of the client being applicable at least two types to be divided in the second alternative pushed information subset.
The each bar information concentrated due to alternative pushed information is the information being applicable to destination client A, so after above-mentioned division operation, the information in the first alternative pushed information subset is IDC for being only only applicable to client type ident value athe information of client.
S104: for each information in the second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information.
Wherein, the information dropout probability of an information, for representing the probability not pushing this information.
In a kind of Alternate embodiments of the present invention, respectively by with under type, the information dropout probability of each the information M in the second alternative pushed information subset can be calculated:
Obtain the total amount N of client actual pushed information in preset period of time of M institute application type tAin preset period of time, the total amount N of pushed information is planned with it tP;
Obtaining type identification value is IDC aclient actual pushed information amount N in preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
According to N tAand N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to N sAand N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
According to P tand P s, determine the information dropout probability of M.
Concrete, according to N tAand N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to N sAand N sP, compute type ident value is IDC athe idle probability P of single piece of information of client stime, according to following formula, the idle probability P of Global Information of polymorphic type client can be calculated t,
P T = 1 - N T A N T P ;
And according to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
Suppose, M the client type that is suitable for comprise: Android version type of cell phone, Android version panel computer type, iOS version type of cell phone, iOS version panel computer type, destination client A is Android version cell-phone customer terminal.
Various types of client is actual pushed information amount in Preset Time, see table 1.
Table 1
Then according to above-mentioned information, can learn:
N TA＝100+200+150+180＝630，N TP＝150+220+180+220＝770；
N SA＝100，N SP＝150。
In addition, according to P tand P s, when determining the information dropout probability of M, can first according to P tand P s, calculate segment factor f=(P t-P s) × g, then according to f, according to following formula, obtain the information dropout probability W of M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, g is default threshold factor, g > 0,0 < k < 1.
It should be noted that, those skilled in the art can obtain the piecewise function of other types according to above-mentioned thinking, the application does not limit this.
S105: according to the information dropout probability calculated, carries out information discard processing to the information in the second alternative pushed information subset.
After the information dropout probability calculating each bar information in the second alternative pushed information subset, can, by the random function preset, according to the information drop probability of each bar information, determine whether to abandon this information, if abandon this information, then in fact can not to this information of client push.
S106: according to the second alternative pushed information subset of the first alternative pushed information subset sums after discard processing, determine actual pushed information.
Concrete, actual pushed information can be made up of the information in the information in the first alternative pushed information subset and the second alternative pushed information subset after discard processing.
S107: push determined actual pushed information to destination client A.
As seen from the above, in the scheme that the present embodiment provides, due to the information dropout probability of each information in the second alternative pushed information subset, be IDC according to client actual pushed information total amount and type identification value in preset period of time of this information institute application type athe numerical relation of client in preset period of time between actual pushed information amount calculate, so this value can reflect that type identification value is IDC aclient actual information pushed in preset period of time whether too much or very few compared to the client of other types.In addition, after carrying out discard processing according to the information drop probability calculated, again according to the second alternative pushed information subset of the first alternative pushed information subset sums after discard processing, determine the actual pushed information obtained, although, cannot directly make actual pushed information amount reach balance like this, knowledge according to statistical probability aspect can be known, along with server is IDC to ident value aclient push information increased frequency, actual pushed information amount can be made on the whole to reach balance according to this information dropout probability.
In one particular embodiment of the present invention, see Fig. 2, provide the schematic flow sheet of another kind of information-pushing method, compared with previous embodiment, in the present embodiment, the method also comprises:
S108: successful after the determined each actual pushed information of destination client A propelling movement, updating type ident value is IDC athe actual pushed information amount of client in preset period of time.
Due to the determined alternative pushed information being applicable to client at every turn concentrate each actual pushed information comprising and successfully pushing to destination client A time, all needing to obtain type identification value is IDC athe actual pushed information amount of client in preset period of time, so after successfully carrying out information pushing, updating type ident value is IDC at every turn athe actual pushed information amount of client in preset period of time, contribute to improve computational efficiency.
Corresponding with above-mentioned information-pushing method, additionally provide a kind of information push-delivery apparatus in the embodiment of the present invention.
The structural representation of a kind of information push-delivery apparatus that Fig. 3 provides for the embodiment of the present invention, the information that this device is used for from presetting concentrates selection information to push to destination client, in every bar information that described default information is concentrated, specify in advance have this information the client type that is suitable for.
This device comprises:
Push request receiving module 301, for the information pushing request that receiving target customer end A sends, wherein, described information pushing carries the type identification value IDC of described destination client A in asking a;
Information set determination module 302, for according to described IDC a, and every bar information of concentrating of described default information the client type that is suitable for, determine the alternative pushed information collection being applicable to described destination client A;
Information set divides module 303, for the client type concentrating every bar information to be suitable for according to described alternative pushed information, described alternative pushed information collection is divided into the alternative pushed information subset of the first alternative pushed information subset sums second, wherein, every bar information in described first alternative pushed information subset is only applicable to the client of a type, and the every bar information in described second alternative pushed information subset is applicable to the client of at least two types;
Losing probability computing module 304, for for each information in described second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information;
Discard processing module 305, for according to the information dropout probability calculated, carries out information discard processing to the information in described second alternative pushed information subset;
Pushed information determination module 306, for according to the second alternative pushed information subset of described first alternative pushed information subset sums after discard processing, determines actual pushed information;
Info push module 307, for pushing determined actual pushed information to described destination client A.
Concrete, described losing probability computing module 304, specifically for calculating the information dropout probability of each the information M in described second alternative pushed information subset respectively;
Described losing probability computing module 304 can comprise:
First information amount obtains submodule, for obtaining the total amount N of client actual pushed information in preset period of time of described M institute application type tAin described preset period of time, the total amount N of pushed information is planned with it tP;
Second amount of information obtains submodule, is IDC for obtaining type identification value aclient actual pushed information amount N in described preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
Idle probability calculation submodule, for according to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
Losing probability determination submodule, for according to described P twith described P s, determine the information dropout probability of described M.
Concrete, described idle probability calculation submodule can comprise:
First idle probability calculation unit, for according to following formula, calculates the idle probability P of Global Information of polymorphic type client t,
P T = 1 - N T A N T P ;
Second idle probability calculation unit, for according to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
Concrete, described losing probability determination submodule can comprise:
Segment factor computing unit, for according to described P twith described P s, calculate segment factor f=(P t-P s) × g, wherein, described g is default threshold factor, g > 0;
Losing probability obtains unit, for according to described f, according to following formula, obtains the information dropout probability W of described M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, 0 < k < 1.
As seen from the above, in the scheme that the present embodiment provides, due to the information dropout probability of each information in the second alternative pushed information subset, be IDC according to client actual pushed information total amount and type identification value in preset period of time of this information institute application type athe numerical relation of client in preset period of time between actual pushed information amount calculate, so this value can reflect that type identification value is IDC aclient actual information pushed in preset period of time whether too much or very few compared to the client of other types.In addition, after carrying out discard processing according to the information drop probability calculated, again according to the second alternative pushed information subset of the first alternative pushed information subset sums after discard processing, determine the actual pushed information obtained, although, cannot directly make actual pushed information amount reach balance like this, knowledge according to statistical probability aspect can be known, along with server is IDC to ident value aclient push information increased frequency, actual pushed information amount can be made on the whole to reach balance according to this information dropout probability.
In one particular embodiment of the present invention, see Fig. 4, provide the structural representation of another kind of information push-delivery apparatus, compared with previous embodiment, in the present embodiment, said apparatus also comprises:
Amount of information update module 308, in success to after described destination client A pushes determined each actual pushed information, updating type ident value is IDC athe actual pushed information amount of client in described preset period of time.
Due to the determined alternative pushed information being applicable to client at every turn concentrate each actual pushed information comprising and successfully pushing to destination client A time, all needing to obtain type identification value is IDC athe actual pushed information amount of client in preset period of time, so after successfully carrying out information pushing, updating type ident value is IDC at every turn athe actual pushed information amount of client in preset period of time, contribute to improve computational efficiency.
For device embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, relevant part illustrates see the part of embodiment of the method.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operating space, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment comprising described key element and also there is other identical element.
One of ordinary skill in the art will appreciate that all or part of step realized in said method execution mode is that the hardware that can carry out instruction relevant by program has come, described program can be stored in computer read/write memory medium, here the alleged storage medium obtained, as: ROM/RAM, magnetic disc, CD etc.
The foregoing is only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.All any amendments done within the spirit and principles in the present invention, equivalent replacement, improvement etc., be all included in protection scope of the present invention.

Claims (10)

1. an information-pushing method, for concentrating selection information to push to destination client from the information preset, in every bar information that described default information is concentrated, specify in advance have this information the client type that is suitable for, it is characterized in that, described method comprises:
The information pushing request that receiving target customer end A sends, wherein, described information pushing carries the type identification value IDC of described destination client A in asking a;
According to described IDC a, and every bar information of concentrating of described default information the client type that is suitable for, determine the alternative pushed information collection being applicable to described destination client A;
According to the client type that described alternative pushed information concentrates every bar information to be suitable for, described alternative pushed information collection is divided into the alternative pushed information subset of the first alternative pushed information subset sums second, wherein, every bar information in described first alternative pushed information subset is only applicable to the client of a type, and the every bar information in described second alternative pushed information subset is applicable to the client of at least two types;
For each information in described second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information;
According to the information dropout probability calculated, information discard processing is carried out to the information in described second alternative pushed information subset;
According to the second alternative pushed information subset of described first alternative pushed information subset sums after discard processing, determine actual pushed information;
Determined actual pushed information is pushed to described destination client A.
2. method according to claim 1, it is characterized in that, described for each information in described second alternative pushed information subset, be IDC according to the total amount of client actual pushed information in preset period of time of this information institute application type and type identification value athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information, comprising:
Respectively by with under type, calculate the information dropout probability of each the information M in described second alternative pushed information subset:
Obtain the total amount N of client actual pushed information in preset period of time of described M institute application type tAin described preset period of time, the total amount N of pushed information is planned with it tP;
Obtaining type identification value is IDC aclient actual pushed information amount N in described preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
According to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
According to described P twith described P s, determine the information dropout probability of described M.
3. method according to claim 2, is characterized in that, described according to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s, comprising:
According to following formula, calculate the idle probability P of Global Information of polymorphic type client t,
P T = 1 - N T A N T P ;
According to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
4. method according to claim 2, is characterized in that, described according to described P twith described P s, determine the information dropout probability of described M, comprising:
According to described P twith described P s, calculate segment factor f=(P t-P s) × g, wherein, described g is default threshold factor, g > 0;
According to described f, according to following formula, obtain the information dropout probability W of described M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, 0 < k < 1.
5. method according to claim 1, is characterized in that, described method also comprises:
Successful after the determined each actual pushed information of described destination client A propelling movement, updating type ident value is IDC athe actual pushed information amount of client in described preset period of time.
6. an information push-delivery apparatus, for concentrating selection information to push to destination client from the information preset, in every bar information that described default information is concentrated, specify in advance have this information the client type that is suitable for, it is characterized in that, described device comprises:
Push request receiving module, for the information pushing request that receiving target customer end A sends, wherein, described information pushing carries the type identification value IDC of described destination client A in asking a;
Information set determination module, for according to described IDC a, and every bar information of concentrating of described default information the client type that is suitable for, determine the alternative pushed information collection being applicable to described destination client A;
Information set divides module, for the client type concentrating every bar information to be suitable for according to described alternative pushed information, described alternative pushed information collection is divided into the alternative pushed information subset of the first alternative pushed information subset sums second, wherein, every bar information in described first alternative pushed information subset is only applicable to the client of a type, and the every bar information in described second alternative pushed information subset is applicable to the client of at least two types;
Losing probability computing module, for for each information in described second alternative pushed information subset, client actual pushed information total amount and type identification value in preset period of time according to this information institute application type are IDC athe numerical relation of client in preset period of time between actual pushed information amount, calculate the information dropout probability of this information;
Discard processing module, for according to the information dropout probability calculated, carries out information discard processing to the information in described second alternative pushed information subset;
Pushed information determination module, for according to the second alternative pushed information subset of described first alternative pushed information subset sums after discard processing, determines actual pushed information;
Info push module, for pushing determined actual pushed information to described destination client A.
7. device according to claim 6, is characterized in that,
Described losing probability computing module, specifically for calculating the information dropout probability of each the information M in described second alternative pushed information subset respectively;
Described losing probability computing module, comprising:
First information amount obtains submodule, for obtaining the total amount N of client actual pushed information in preset period of time of described M institute application type tAin described preset period of time, the total amount N of pushed information is planned with it tP;
Second amount of information obtains submodule, is IDC for obtaining type identification value aclient actual pushed information amount N in described preset period of time sAin described preset period of time, pushed information amount N is planned with it sP;
Idle probability calculation submodule, for according to described N tAwith described N tP, calculate the idle probability P of Global Information of polymorphic type client t, and according to described N sAwith described N sP, compute type ident value is IDC athe idle probability P of single piece of information of client s;
Losing probability determination submodule, for according to described P twith described P s, determine the information dropout probability of described M.
8. device according to claim 7, is characterized in that, described idle probability calculation submodule, comprising:
First idle probability calculation unit, for according to following formula, calculates the idle probability P of Global Information of polymorphic type client t,
P T = 1 - N T A N T P ;
Second idle probability calculation unit, for according to following formula, compute type is designated IDC athe idle probability P of single piece of information of client s,
P S = 1 - N S A N S P .
9. device according to claim 7, is characterized in that, described losing probability determination submodule, comprising:
Segment factor computing unit, for according to described P twith described P s, calculate segment factor f=(P t-P s) × g, wherein, described g is default threshold factor, g > 0;
Losing probability obtains unit, for according to described f, according to following formula, obtains the information dropout probability W of described M,
W = 1 , f > 1 f , k < f < = 1 k , 0 < f < = k 0 , f < 0 ,
Wherein, 0 < k < 1.
10. device according to claim 6, is characterized in that, described device also comprises:
Amount of information update module, in success to after described destination client A pushes determined each actual pushed information, updating type ident value is IDC athe actual pushed information amount of client in described preset period of time.
CN201510386575.6A 2015-06-30 2015-06-30 A kind of information-pushing method and device Active CN105072466B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510386575.6A CN105072466B (en) 2015-06-30 2015-06-30 A kind of information-pushing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510386575.6A CN105072466B (en) 2015-06-30 2015-06-30 A kind of information-pushing method and device

Publications (2)

Publication Number Publication Date
CN105072466A true CN105072466A (en) 2015-11-18
CN105072466B CN105072466B (en) 2018-02-09

Family

ID=54501726

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510386575.6A Active CN105072466B (en) 2015-06-30 2015-06-30 A kind of information-pushing method and device

Country Status (1)

Country Link
CN (1) CN105072466B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103389990A (en) * 2012-05-09 2013-11-13 腾讯科技（北京）有限公司 Directional information pushing method and device
CN103442269A (en) * 2013-09-17 2013-12-11 北京奇艺世纪科技有限公司 Method and device for pushing program information
CN103685502A (en) * 2013-12-09 2014-03-26 腾讯科技（深圳）有限公司 Message pushing method, device and system
CN103679498A (en) * 2012-09-21 2014-03-26 亿赞普(北京)科技有限公司 Method and system for pushing the information on network terminal
CN104573113A (en) * 2015-02-03 2015-04-29 深圳市腾讯计算机系统有限公司 Information processing method and server

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103389990A (en) * 2012-05-09 2013-11-13 腾讯科技（北京）有限公司 Directional information pushing method and device
CN103679498A (en) * 2012-09-21 2014-03-26 亿赞普(北京)科技有限公司 Method and system for pushing the information on network terminal
CN103442269A (en) * 2013-09-17 2013-12-11 北京奇艺世纪科技有限公司 Method and device for pushing program information
CN103685502A (en) * 2013-12-09 2014-03-26 腾讯科技（深圳）有限公司 Message pushing method, device and system
CN104573113A (en) * 2015-02-03 2015-04-29 深圳市腾讯计算机系统有限公司 Information processing method and server

Also Published As

Publication number Publication date
CN105072466B (en) 2018-02-09

Similar Documents

Publication Publication Date Title
US9824156B1 (en) Targeting of digital content to geographic regions
US11038975B2 (en) Information pushing method and device
EP3001332A1 (en) Target user determination method, device and network server
CN104731917A (en) Recommendation method and device
CN103473230B (en) Service area determines that method, logistics service provider recommend method and related device
CN108521439A (en) A kind of method and apparatus of message push
US20160034968A1 (en) Method and device for determining target user, and network server
KR20200106566A (en) Wide and deep machine learning models
CN104850641A (en) Information recommendation method and device
CN105989107A (en) Application recommendation method and device
CN111401228B (en) Video target labeling method and device and electronic equipment
CN104915359A (en) Theme label recommending method and device
CN107679186A (en) The method and device of entity search is carried out based on entity storehouse
CN104822072A (en) Playing control method and playing system for push video as well as client and server
CN110427574B (en) Route similarity determination method, device, equipment and medium
CN108874835A (en) Information-pushing method and device
US20130203443A1 (en) Providing information about a location to a mobile device based on the location of the mobile device
CN106844504B (en) A kind of method and apparatus for sending song and singly identifying
CN113742564A (en) Target resource pushing method and device
CN105072466A (en) Information push method and device
CN114417137B (en) Information recommendation method and device
CN110347973A (en) Method and apparatus for generating information
CN106959991B (en) Dynamic presentation method and device for large data visualization analysis and terminal
CN114092226A (en) Method and device for recommending foreign exchange products of bank outlets
CN107798112A (en) A kind of public feelings information processing method and processing device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant