CN103716338A - Information push method and device - Google Patents
Information push method and device Download PDFInfo
- Publication number
- CN103716338A CN103716338A CN201210370622.4A CN201210370622A CN103716338A CN 103716338 A CN103716338 A CN 103716338A CN 201210370622 A CN201210370622 A CN 201210370622A CN 103716338 A CN103716338 A CN 103716338A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- pushed
- historical
- similar users
- 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
Links
Images
Abstract
The embodiment of the invention discloses an information push method and an information push device. The method includes the following steps that: user information of a current user and user information of a historical user are obtained; a similar user circle of the current user is obtained according to the user information of the current user and the user information of the historical user, wherein the similar user circle comprises one or more historical users related to the current user; and preferences of the historical users in the similar user circle to various information to be pushed are obtained, and the information to be pushed is selected and pushed to the current user according to the preferences. With the information push method and the information push device of the invention adopted, the characteristics of users are considered in an information push process, and information can be pushed to the users in a targeted way.
Description
Technical field
The present invention relates to internet arena, relate in particular to a kind of information-pushing method and device.
Background technology
Along with the development of Internet technology, there is on the internet increasing information interchange.As, service provider can issue various advertisements on the internet, and the distributor who has user resources can directly be pushed to user by these advertisements.
(Push) technology that pushes be a kind of based on client server mechanism by the server technology of client that information is mail to initiatively, the information of its transmission normally user is scheduled in advance.With traditional pull technology (PULL), compare, the former initiatively sends information by server, and the latter is by client computer active request information.The advantage of push technology is initiative and the promptness of information, can push information in face of user at any time.
It is mainly to utilize (Push) technology of propelling movement that existing internet information pushes, and has object, user may interested information initiatively be sent in user's computer on time.Similarly be broadcasting station broadcast, " propelling movement " technology is initiatively pushed to client by up-to-date news and data, and user needn't internet searching.The major advantage of Push technology is user to be required low, is generally applicable to the public, does not require special technology; The 2nd, promptness is good, the multidate information that information source is constantly updated to user's " propelling movement " in time.
But, in existing internet information push technology, the fresh demand of considering less user, only pushing to user simply.On the one hand, meaningless Internet resources have been taken; On the other hand, user may and lose interest in to these information, has also caused the waste of Internet resources.
Summary of the invention
Embodiment of the present invention technical problem to be solved is, a kind of information-pushing method and device are provided.In information pushing process, consider user's feature, targetedly user is carried out to information pushing.
In order to solve the problems of the technologies described above, the embodiment of the present invention provides a kind of information-pushing method, comprising:
Obtain active user's user profile and historical user's user profile;
According to described active user's user profile, historical user's user profile, obtain described active user's similar users circle, described similar users circle comprises the one or more historical users relevant with described active user;
Obtain historical user in the described similar users circle preference degree to each information to be pushed, and according to described preference degree, choose information to be pushed and be pushed to described active user.
On the one hand, the embodiment of the present invention also provides a kind of information push-delivery apparatus, comprising again:
Acquisition of information module, for obtaining active user's user profile and historical user's user profile;
User encloses acquisition module, for according to described active user's user profile, historical user's user profile, obtains described active user's similar users circle, and described similar users circle comprises the one or more historical users relevant with described active user;
Preference degree acquisition module, the preference degree for the historical user that obtains described similar users circle to each information to be pushed;
Pushing module, is pushed to described active user for choosing information to be pushed according to described preference degree.
Implement the embodiment of the present invention, there is following beneficial effect: when carrying out information pushing to a certain user, investigate this user's relevant historical user's information, form the similar users circle relevant with this user; According to the historical behavior of similar users circle investigate these users to the preference degree of pushed information after, then carry out information pushing according to preference degree.So, the information pushing to user, with regard to there being larger probability to meet user's demand, has improved the accuracy pushing, and has also improved the utilance of Internet resources.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, to the accompanying drawing of required use in embodiment or description of the Prior Art be briefly described below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is an idiographic flow schematic diagram of the information-pushing method in the embodiment of the present invention;
Fig. 2 is a concrete schematic diagram that forms of the information push-delivery apparatus in the embodiment of the present invention;
Fig. 3 is the concrete schematic diagram that forms that the user in the embodiment of the present invention encloses acquisition module;
Fig. 4 is a concrete schematic diagram that forms of the preference degree acquisition module in the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
In embodiments of the present invention based on basic ideas, when certain user carry out network behavior (as, searching resource, watch online multimedia data) time, investigate the behavior of the user circle similar to this user, that this user's circle comprises is historical user, these historical users once carried out diverse network behavior, according to these historical users' network behavior, predict that the information that certain user may like just has higher accuracy so, as, according to historical user's search, click preference and calculate the advertisement that hobby index comes predictive user maximum possible to like, may like the film of seeing, may like webpage of browsing etc.
Wherein, when obtaining similar users circle, can pass through the various dimensions to user, as the division of similar users circle is carried out in educational background, region, age, income, education degree etc.Certainly, according to the difference on opportunity of pushed information, pushed information etc., can also there is more dimension to select.With next, each specific embodiment of the present invention is described.
As shown in Figure 1, be an idiographic flow schematic diagram of the information-pushing method in the embodiment of the present invention.This flow process comprises the steps.
101, obtain active user's user profile and historical user's user profile.As previously mentioned, this user profile can comprise user's each side information, as, educational background, age, region, income, occupation, hobby etc.
This user can refer to, login certain application user, login network address of the user of certain Web Community, the login user of certain search engine or even certain terminal equipment etc., carry out the user of a certain network behavior.Certainly, if certain user's who once logined by this network address relevant information, while collecting user profile, can be investigated in the network address of certain terminal equipment.
For the ease of follow-up calculating, this user profile can be the array quantizing, and claims that described array is user profile array, the value that quantizes of one or more attributes of the element respective user in described user profile array.
102, according to described active user's user profile, historical user's user profile, obtain described active user's similar users circle, described similar users circle comprises the one or more historical users relevant with described active user.
Historical user described herein refers to, carried out in history the user of certain network behavior, this concrete network behavior can be consistent with aforesaid active user, as being all the user who carries out web search, also can be inconsistent, as the historical user in certain Web Community, what this history user carried out is to deliver new post, and active user may be only browsing video etc.The historical user's of statistics source, relevant with the Data Source of server, do not limit herein.
When aforesaid user profile is when quantizing array, this step specifically can be: the total amount of calculating the difference of corresponding element between described active user's user profile array and each historical user's user profile array; Determine that historical user that the total amount of described difference is less than predetermined value is as the railway carriage or compartment history user in described active user's similar users circle.
Certainly, the specific algorithm that calculates the total amount of above-mentioned difference can have multiple, as calculate the absolute value of the difference of each corresponding element between two arrays, then summation, or calculate each corresponding element difference square after sue for peace again, or calculate each corresponding element difference square after sue for peace after being multiplied by again certain coefficient, or pass through space projection, two arrays are projected to a bit in a certain space, calculate again distance of point-to-point transmission etc., in a word by the difference under the various forms of two arrays of various existing mathematical algorithms acquisition.
As, when when the nearest neighbor algorithm calculated difference, can calculate according to formula 1 or formula 2 total amount of described active users and described historical user's difference:
From D (k), the user of the D obtaining in k=1～m (k)≤υ is as the historical user in described active user's similar users circle again, and wherein, υ is predetermined threshold.As, be predefined constant.
Wherein, K (n) is the value of k historical user's n attribute, the value of n the attribute that X (n) is described active user, H (n) is the mean value of described k n attribute of historical user, D (k) is the total amount of described active user and described k historical user's difference, n is the sum of the element in described array, the sum that m is described historical user, and n and m are the integer that is more than or equal to 1.
In specific embodiment, be to take formula 1 to calculate, still take formula 2 to calculate, need to consider concrete condition.; value for each attribute of user; some can directly be weighed with numerical value; as emolument, age etc., some can not directly be weighed with numerical value, as hobby class etc.; now; for the result of X (n)-K (n), can be by hobby identical to get X (n)-K (n) value be 0, it is different that to get X (n)-K (n) value be 1.So now consider differing greatly of different dimensions attribute, as age and emolument, calculated difference can be very large, and general recommend adoption formula 2 is calculated, with the difference of the number range between balance different attribute.Certainly, if in the little situation of the difference of different dimensions attribute, for simplifying to calculate, can adopt formula 1 to calculate distance.
103, obtain historical user in the described similar users circle preference degree to each information to be pushed.When concrete calculating, can be according to the historical user in described similar users circle to the number of processes of each information to be pushed, process one or more in density, processes complete degree and calculate the preference degree of described each information to be pushed." processing " described herein is relevant with concrete pushed information, as, pushed information is video ads, processes and is specially broadcasting, does not enumerate herein.
The pushed information of take below illustrates that as Playable content as example the concrete computational process of preference degree comprises: according to the historical user in described similar users circle, play the number of times of described each information to be pushed and the density that time weighting calculates described each information to be pushed; According to the historical user in described similar users circle, click number of times and the time weighting of described each information to be pushed, and the click degree of each information to be pushed described in the density calculation of described each information to be pushed; According to number of times and the time weighting of each information to be pushed described in the complete broadcasting of historical user in described similar users circle, and the integrity degree of each information to be pushed described in the density calculation of described each information to be pushed; According to the preference degree of described click degree and described each information to be pushed of integrity degree calculating.
Wherein, take pushed information as the advertisement that can play is example, illustrate that the specific algorithm of the above-mentioned density of calculating, click degree, integrity degree and preference degree is as follows:
(1) be calculated as follows described density:
Wherein, the broadcasting number of days that d is pushed information, t is the initial calculation time, qv
ifor the historical user in similar users circle described in when the time is i plays the overall number of times of this message, Intensity (l) is historical user in the described similar users circle density to the 1st information to be pushed.Wherein, τ is constant, i.e. definition in this example, and τ can be 0.01 or 0.05.Certainly, τ also may be defined as other values, specifically can determine according to actual needs.
It should be noted that, in this example, the density of advertisement is that the advertising display number of times of historical a period of time is according to 1/e
τ * i(i for apart from the number of days of current time) accumulated value after decaying.Far away apart from current time, decay more.
(2) calculate according to the following equation described click degree:
Click(l)＝Click_num(l)/Intensity(l)，
Wherein, click
ihits during for time i, Click (l) is historical user in the described similar users circle click degree to the 1st information to be pushed.
Similarly, in this example, the hits of advertisement is not the simple cumulative of ad click number of times, but the clicked number of times of advertisement of historical a period of time is according to 1/e
τ * i(i for apart from the number of days of current time) accumulated value after decaying.Far away apart from current time, decay more.
(3) calculate according to the following equation described integrity degree:
Integrity(l)＝Integrity_num(l)/Intensity(l)，
Wherein, Integrity
icomplete broadcasting time during for time i, Integrity (l) is historical user in the described similar users circle integrity degree to the 1st information to be pushed.
In this example, what the complete broadcasting number of advertisement neither advertisement broadcasting time is simple cumulative, but the advertisement of historical a period of time by the number of times of complete broadcasting according to 1/e
τ * i(i for apart from the number of days of current time) accumulated value after decaying.Far away apart from current time, decay more.
(4) calculate according to the following equation described preference degree:
Adc(l)＝Click(l)
α*Integrity(l)
β
Wherein, α, β are constant parameter, and 0≤α≤1,0≤β≤1, alpha+beta=1, and Adc (l) is the preference degree of the historical user in described similar users circle to the 1st information to be pushed.
As can be seen from the above equation, the advertisement that Adc exponential quantity is higher, just higher in user's clicking rate of nearest a period of time of history, complete broadcasting rate, comparing traditional use single " clicking/exposure " or " complete broadcasting/exposure " calculates, this algorithm can synthetically be weighed advertisement, can embody the timeliness of historical data simultaneously.Visible by foregoing description, the computing reference of preference degree the impression of advertisement, hits, complete broadcasting number etc.Certainly, for the pushed information of other types, can content corresponding to corresponding reference.
Meanwhile, in above-mentioned algorithm, adopted e
τ * ithis variable weight mode, is conducive to catch the situation of change of nearest generation.
104, according to described preference degree, choose information to be pushed and be pushed to described active user.As, the pushed information of described preference degree maximum is pushed to described active user.Certainly, also a threshold constant can be set, when preference degree surpasses this constant by information pushing to user.
Visible, in embodiments of the present invention, after the preference degree by the similar circle of user calculates, can push corresponding certain of higher preference degree value, certain class or a plurality of pushed information.Thereby realize personalized recommendation, improved the utilance of Internet resources.
Accordingly, the embodiment of the present invention also provides an information push-delivery apparatus, and as shown in Figure 2, this device 1 comprises: acquisition of information module 10, for obtaining active user's user profile and historical user's user profile; User encloses acquisition module 12, for according to described active user's user profile, historical user's user profile, obtains described active user's similar users circle, and described similar users circle comprises the one or more historical users relevant with described active user; Preference degree acquisition module 14, the preference degree for the historical user that obtains described similar users circle to each pushed information; Pushing module 16, is pushed to described active user for choosing information to be pushed according to described preference degree.
Wherein, described user profile is the array that quantizes, and claim that described array is user profile array, the value that quantizes of one or more attributes of the element respective user in described user profile array, as shown in Figure 3, described user encloses acquisition module 12 and can comprise: difference computing unit 120, for calculating the total amount of the difference of corresponding element between described active user's user profile array and each historical user's user profile array; Similar circle determining unit 122, for determining that the total amount of described difference is less than the historical user of predetermined value as the historical user of described active user's similar users circle.
Concrete, described difference computing unit 120, can be used for calculating according to following formula the total amount of described active user and described historical user's difference:
Or,
Wherein K (n) is the value of k historical user's n attribute, the value of n the attribute that X (n) is described active user, H (n) is the mean value of described k n attribute of historical user, D (k) is the total amount of described active user and described k historical user's difference, n is the sum of the element in described array, m is described historical user's sum, and n and m are the integer that is more than or equal to 1;
Described similar circle determining unit 122 for, from D (k), the user of the D obtaining in k=1～m (k)≤υ is as the historical user in described active user's similar users circle, wherein, υ is predetermined threshold.
Wherein, described preference degree acquisition module 14 also for, according to the historical user in described similar users circle, one or more in the processing density of pushed information, number of processes, processes complete degree are calculated to the preference degree of described pushed information.
Concrete, preference degree acquisition module 14 is also for the preference degree to described each information to be pushed of one or more calculating in the number of processes of each information to be pushed, processing density, processes complete degree according to the historical user of described similar users circle.As shown in Figure 4, preference degree acquisition module 14 can comprise: density calculation submodule 140, for play the number of times of described each information to be pushed and the density that time weighting calculates described each information to be pushed according to the historical user of described similar users circle; Click degree calculating sub module 142, for click number of times and the time weighting of described each information to be pushed according to the historical user of described similar users circle, and the click degree of each information to be pushed described in the density calculation of described each information to be pushed; Integrity degree calculating sub module 144, for according to number of times and the time weighting of each information to be pushed described in the complete broadcasting of historical user of described similar users circle, and the integrity degree of each information to be pushed described in the density calculation of described each information to be pushed; Preference degree calculating sub module 146, for calculating the preference degree of described each information to be pushed according to described click degree and integrity degree.
As, concrete, density calculation submodule 140, can be calculated as follows described density:
Wherein, the broadcasting number of days that d is pushed information, t is the initial calculation time, qv
ifor the historical user in similar users circle described in when the time is i plays the overall number of times of this message, Intensity (l) is historical user in the described similar users circle density to the 1st information to be pushed;
Click degree calculating sub module 142, can calculate according to the following equation described click degree:
Click(l)＝Click_num(l)/Intensity(l)，
Wherein, click
ihits during for time i, Click (l) is historical user in the described similar users circle click degree to the 1st information to be pushed;
Integrity degree calculating sub module 144, can calculate according to the following equation described integrity degree:
Integrity(l)＝Integrity_num(l)/Intensity(l)，
Wherein, Integrity
icomplete broadcasting time during for time i, Integrity (l) is historical user in the described similar users circle integrity degree to the 1st information to be pushed;
Preference degree calculating sub module 146, can calculate according to the following equation described preference degree:
Adc(l)＝Click(l)
α*Integrity(l)
β
Wherein, α, β are constant parameter, and 0≤α≤1,0≤β≤1, alpha+beta=1, and Adc (l) is the preference degree of the historical user in described similar users circle to the 1st information to be pushed.
Concrete, described pushing module 16 also for, the pushed information of described preference degree maximum is pushed to described active user.
Be understandable that, consistent with preceding method embodiment of the ins and outs in said apparatus embodiment, does not do one by one and repeats herein.
In sum, in embodiments of the present invention, while carrying out information pushing to a certain user, adopt nearest neighbor algorithm to investigate this user's relevant historical user's information, be formed at the relevant similar users circle of this user, according to the historical behavior of similar users circle, investigate the preference degree of these users to pushed information, then carrying out information pushing according to preference degree.So, the information pushing to user, with regard to there being larger probability to meet user's demand, has improved the utilance of Internet resources.
One of ordinary skill in the art will appreciate that all or part of flow process realizing in above-described embodiment method, to come the hardware that instruction is relevant to complete by computer program, described program can be stored in a computer read/write memory medium, this program, when carrying out, can comprise as the flow process of the embodiment of above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
Above disclosed is only a kind of preferred embodiment of the present invention, certainly can not limit with this interest field of the present invention, and the equivalent variations of therefore doing according to the claims in the present invention, still belongs to the scope that the present invention is contained.
Claims (15)
1. an information-pushing method, is characterized in that, described method comprises:
Obtain active user's user profile and historical user's user profile;
According to described active user's user profile, historical user's user profile, obtain described active user's similar users circle, described similar users circle comprises the one or more historical users relevant with described active user;
Obtain historical user in the described similar users circle preference degree to each information to be pushed, and according to described preference degree, choose information to be pushed and be pushed to described active user.
2. the method for claim 1, it is characterized in that, described user profile is the array that quantizes, and claim that described array is user profile array, the value that quantizes of one or more attributes of the element respective user in described user profile array, described according to described active user's user profile, historical user's user profile, the similar users circle that obtains described active user comprises:
Calculate the total amount of the difference of corresponding element between described active user's user profile array and each historical user's user profile array;
Determine that historical user that the total amount of described difference is less than predetermined value is as the historical user in described active user's similar users circle.
3. method as claimed in claim 2, is characterized in that, between the user profile array of each the historical user in the described active user's of described calculating user profile array and described similar users circle, the total amount of the difference of corresponding element comprises:
According to following formula, calculate the total amount of described difference:
Wherein, K (n) is the value of k historical user's n attribute, the value of n the attribute that X (n) is described active user, D (k) is the total amount of described active user and described k historical user's difference, n is the sum of the element in described array, m is described historical user's sum, and n and m are the integer that is more than or equal to 1;
The historical user that the total amount of described definite described difference is less than predetermined value comprises as the historical user in described active user's similar users circle:
From D (k), the user of the D obtaining in k=1～m (k)≤υ is as the historical user in described active user's similar users circle, and wherein, υ is predetermined threshold.
4. method as claimed in claim 2, is characterized in that, between the user profile array of each the historical user in the described active user's of described calculating user profile array and described similar users circle, the total amount of the difference of corresponding element comprises:
According to following formula, calculate the total amount of described active user and described historical user's difference:
Wherein, K (n) is the value of k historical user's n attribute, the value of n the attribute that X (n) is described active user, H (n) is the mean value of described k n attribute of historical user, D (k) is the total amount of described active user and described k historical user's difference, n is the sum of the element in described array, the sum that m is described historical user, and n and m are the integer that is more than or equal to 1;
The historical user that the total amount of described definite described difference is less than predetermined value comprises as the historical user in described active user's similar users circle:
From D (k), the user of the D obtaining in k=1～m (k)≤υ is as the historical user in described active user's similar users circle, and wherein, υ is predetermined threshold.
5. the method as described in any one in claim 1 to 4, is characterized in that, described in the historical user that obtains in described similar users circle the preference degree of each information to be pushed is comprised:
Preference degree according to the historical user in described similar users circle to described each information to be pushed of one or more calculating in the number of processes of each information to be pushed, processing density, processes complete degree.
6. method as claimed in claim 5, it is characterized in that, describedly according to the historical user in described similar users circle, the number of processes of each information to be pushed, one or more preference degrees that calculate described each information to be pushed of processing in density, processes complete degree are comprised:
According to the historical user in described similar users circle, play the number of times of described each information to be pushed and the density that time weighting calculates described each information to be pushed;
According to the historical user in described similar users circle, click number of times and the time weighting of described each information to be pushed, and the click degree of each information to be pushed described in the density calculation of described each information to be pushed;
According to number of times and the time weighting of each information to be pushed described in the complete broadcasting of historical user in described similar users circle, and the integrity degree of each information to be pushed described in the density calculation of described each information to be pushed;
According to the preference degree of described click degree and described each information to be pushed of integrity degree calculating.
7. method as claimed in claim 6, is characterized in that, is calculated as follows described density:
Wherein, the broadcasting number of days that d is pushed information, t is the initial calculation time, qv
ifor the historical user in similar users circle described in when the time is i plays the overall number of times of this message, Intensity (l) is historical user in the described similar users circle density to the 1st information to be pushed;
Calculate according to the following equation described click degree:
Click(l)＝Click_num(l)/Intensity(l)，
Wherein, click
ihits during for time i, Click (l) is historical user in the described similar users circle click degree to the 1st information to be pushed;
Calculate according to the following equation described integrity degree:
Integrity(l)＝Integrity_num(l)/Intensity(l)，
Wherein, Integrity
icomplete broadcasting time during for time i, Integrity (l) is historical user in the described similar users circle integrity degree to the 1st information to be pushed;
Calculate according to the following equation described preference degree:
Adc(l)＝Click(l)
α*Integrity(l)
β
Wherein, α, β are constant parameter, and 0≤α≤1,0≤β≤1, alpha+beta=1, and Adc (l) is the preference degree of the historical user in described similar users circle to the 1st information to be pushed.
8. method as claimed in claim 6, is characterized in that, describedly according to described preference degree, chooses information to be pushed and is pushed to described active user and comprises:
The information to be pushed of described preference degree maximum is pushed to described active user.
9. an information push-delivery apparatus, is characterized in that, described device comprises:
Acquisition of information module, for obtaining active user's user profile and historical user's user profile;
User encloses acquisition module, for according to described active user's user profile, historical user's user profile, obtains described active user's similar users circle, and described similar users circle comprises the one or more historical users relevant with described active user;
Preference degree acquisition module, the preference degree for the historical user that obtains described similar users circle to each information to be pushed;
Pushing module, is pushed to described active user for choosing information to be pushed according to described preference degree.
10. device as claimed in claim 9, it is characterized in that, described user profile is the array that quantizes, and claims that described array is user profile array, the value that quantizes of one or more attributes of the element respective user in described user profile array, described user encloses acquisition module and comprises:
Difference computing unit, for calculating the total amount of the difference of corresponding element between described active user's user profile array and each historical user's user profile array;
Similar circle determining unit, for determining that the total amount of described difference is less than the historical user of predetermined value as the historical user of described active user's similar users circle.
11. devices as claimed in claim 10, is characterized in that, described difference computing unit, specifically for calculate the total amount of described active user and described historical user's difference according to following formula:
Or,
Wherein K (n) is the value of k historical user's n attribute, the value of n the attribute that X (n) is described active user, H (n) is the mean value of described k n attribute of historical user, D (k) is the total amount of described active user and described k historical user's difference, n is the sum of the element in described array, m is described historical user's sum, and n and m are the integer that is more than or equal to 1;
Described similar circle determining unit specifically for, from D (k), the user of the D obtaining in k=1～m (k)≤υ is as the historical user in described active user's similar users circle, wherein, υ is predetermined threshold.
12. devices as described in any one in claim 9 to 11, it is characterized in that, described preference degree acquisition module also for, according to the historical user in described similar users circle to the number of processes of each information to be pushed, process one or more in density, processes complete degree and calculate the preference degree of described each information to be pushed.
13. devices as claimed in claim 12, is characterized in that, described preference degree acquisition module comprises:
Density calculation submodule, for playing the number of times of described each information to be pushed and the density that time weighting calculates described each information to be pushed according to the historical user of described similar users circle;
Click degree calculating sub module, for click number of times and the time weighting of described each information to be pushed according to the historical user of described similar users circle, and the click degree of each information to be pushed described in the density calculation of described each information to be pushed;
Integrity degree calculating sub module, for according to number of times and the time weighting of each information to be pushed described in the complete broadcasting of historical user of described similar users circle, and the integrity degree of each information to be pushed described in the density calculation of described each information to be pushed;
Preference degree calculating sub module, for calculating the preference degree of described each information to be pushed according to described click degree and integrity degree.
14. devices as claimed in claim 13, is characterized in that, described density calculation submodule, specifically for being calculated as follows described density:
Wherein, the broadcasting number of days that d is pushed information, t is the initial calculation time, qv
ifor the historical user in similar users circle described in when the time is i plays the overall number of times of this message, Intensity (l) is historical user in the described similar users circle density to the 1st information to be pushed;
Described click degree calculating sub module, specifically for calculating according to the following equation described click degree:
Click(l)＝Click_num(l)/Intensity(l)，
Wherein, click
ihits during for time i, Click (l) is historical user in the described similar users circle click degree to the 1st information to be pushed;
Described integrity degree calculating sub module, specifically for calculating according to the following equation described integrity degree:
Integrity(l)＝Integrity_num(l)/Intensity(l)，
Wherein, Integrity
icomplete broadcasting time during for time i, Integrity (l) is historical user in the described similar users circle integrity degree to the 1st information to be pushed;
Described preference degree calculating sub module, specifically for calculating according to the following equation described preference degree:
Adc(l)＝Click(l)
α*Integrity(l)
β
Wherein, α, β are constant parameter, and 0≤α≤1,0≤β≤1, alpha+beta=1, and Adc (l) is the preference degree of the historical user in described similar users circle to the 1st information to be pushed.
15. devices as claimed in claim 13, is characterized in that, described pushing module also for, the information to be pushed of described preference degree maximum is pushed to described active user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210370622.4A CN103716338B (en) | 2012-09-28 | 2012-09-28 | A kind of information-pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210370622.4A CN103716338B (en) | 2012-09-28 | 2012-09-28 | A kind of information-pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103716338A true CN103716338A (en) | 2014-04-09 |
| CN103716338B CN103716338B (en) | 2018-08-17 |
Family
ID=50408918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210370622.4A Active CN103716338B (en) | 2012-09-28 | 2012-09-28 | A kind of information-pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103716338B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104636470A (en) * | 2015-02-11 | 2015-05-20 | 广州华多网络科技有限公司 | Method and device for recommending business information |
| CN104918070A (en) * | 2015-06-02 | 2015-09-16 | 四川九天揽月文化传媒有限公司 | Smart television-based video program push system and push method |
| CN104935964A (en) * | 2015-06-02 | 2015-09-23 | 四川九天揽月文化传媒有限公司 | Program grouping screening and push method for intelligent television |
| CN104967690A (en) * | 2015-06-30 | 2015-10-07 | 北京奇艺世纪科技有限公司 | Information push method and device |
| CN105159910A (en) * | 2015-07-03 | 2015-12-16 | 安一恒通（北京）科技有限公司 | Information recommendation method and device |
| CN105354724A (en) * | 2015-11-04 | 2016-02-24 | 北京金山安全软件有限公司 | Advertisement information pushing method and server |
| CN106294457A (en) * | 2015-05-29 | 2017-01-04 | 腾讯科技（深圳）有限公司 | Network information push method and device |
| CN106407361A (en) * | 2016-09-07 | 2017-02-15 | 北京百度网讯科技有限公司 | Method and device for pushing information based on artificial intelligence |
| CN106445932A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Information pushing method and apparatus |
| CN106575418A (en) * | 2014-05-16 | 2017-04-19 | 邻客音公司 | Suggested keywords |
| CN106919580A (en) * | 2015-12-25 | 2017-07-04 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method and device |
| CN107066582A (en) * | 2017-04-14 | 2017-08-18 | 聚好看科技股份有限公司 | Realize the method and device that virtual resource is recommended |
| CN107846463A (en) * | 2017-11-08 | 2018-03-27 | 北京摩拜科技有限公司 | Information-pushing method, server, client and Vehicular system |
| CN108875043A (en) * | 2018-06-27 | 2018-11-23 | 腾讯科技（北京）有限公司 | User data processing method, device, computer equipment and storage medium |
| CN109657140A (en) * | 2018-12-13 | 2019-04-19 | 平安普惠企业管理有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109816414A (en) * | 2017-11-22 | 2019-05-28 | 北京国双科技有限公司 | Advertisement effectiveness data prediction technique and device |
| CN110246002A (en) * | 2019-04-25 | 2019-09-17 | 深圳壹账通智能科技有限公司 | Method for pushing, device and the computer equipment of financing recommendation information |
| WO2019218450A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Message pushing method, storage medium, server and device |
| CN113032662A (en) * | 2021-03-31 | 2021-06-25 | 龙关玲 | Block chain big data recommendation method and system based on artificial intelligence and cloud platform |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090271826A1 (en) * | 2008-04-24 | 2009-10-29 | Samsung Electronics Co., Ltd. | Method of recommending broadcasting contents and recommending apparatus therefor |
| CN101681469A (en) * | 2007-03-31 | 2010-03-24 | 索尼德国有限责任公司 | Method and system for recommending content items |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN101937547A (en) * | 2010-09-15 | 2011-01-05 | 宇龙计算机通信科技(深圳)有限公司 | Software and/or software information pushing method, system, acquisition device, software shop service system and mobile terminal |
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
| CN102592223A (en) * | 2011-01-18 | 2012-07-18 | 卓望数码技术（深圳）有限公司 | Commodity recommending method and commodity recommending system |
-
2012
- 2012-09-28 CN CN201210370622.4A patent/CN103716338B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101681469A (en) * | 2007-03-31 | 2010-03-24 | 索尼德国有限责任公司 | Method and system for recommending content items |
| US20090271826A1 (en) * | 2008-04-24 | 2009-10-29 | Samsung Electronics Co., Ltd. | Method of recommending broadcasting contents and recommending apparatus therefor |
| CN101685458A (en) * | 2008-09-27 | 2010-03-31 | 华为技术有限公司 | Recommendation method and system based on collaborative filtering |
| CN101937547A (en) * | 2010-09-15 | 2011-01-05 | 宇龙计算机通信科技(深圳)有限公司 | Software and/or software information pushing method, system, acquisition device, software shop service system and mobile terminal |
| CN102592223A (en) * | 2011-01-18 | 2012-07-18 | 卓望数码技术（深圳）有限公司 | Commodity recommending method and commodity recommending system |
| CN102332006A (en) * | 2011-08-03 | 2012-01-25 | 百度在线网络技术（北京）有限公司 | Information push control method and device |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106575418A (en) * | 2014-05-16 | 2017-04-19 | 邻客音公司 | Suggested keywords |
| CN106575418B (en) * | 2014-05-16 | 2021-06-08 | 微软技术许可有限责任公司 | Suggested keywords |
| CN104636470B (en) * | 2015-02-11 | 2018-04-24 | 广州华多网络科技有限公司 | A kind of method and device of recommendation business information |
| CN104636470A (en) * | 2015-02-11 | 2015-05-20 | 广州华多网络科技有限公司 | Method and device for recommending business information |
| CN106294457A (en) * | 2015-05-29 | 2017-01-04 | 腾讯科技（深圳）有限公司 | Network information push method and device |
| CN104918070A (en) * | 2015-06-02 | 2015-09-16 | 四川九天揽月文化传媒有限公司 | Smart television-based video program push system and push method |
| CN104935964A (en) * | 2015-06-02 | 2015-09-23 | 四川九天揽月文化传媒有限公司 | Program grouping screening and push method for intelligent television |
| CN104967690A (en) * | 2015-06-30 | 2015-10-07 | 北京奇艺世纪科技有限公司 | Information push method and device |
| CN104967690B (en) * | 2015-06-30 | 2019-04-12 | 北京奇艺世纪科技有限公司 | A kind of information-pushing method and device |
| CN105159910A (en) * | 2015-07-03 | 2015-12-16 | 安一恒通（北京）科技有限公司 | Information recommendation method and device |
| CN106445932A (en) * | 2015-08-04 | 2017-02-22 | 阿里巴巴集团控股有限公司 | Information pushing method and apparatus |
| CN106445932B (en) * | 2015-08-04 | 2019-09-17 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method and device |
| CN105354724A (en) * | 2015-11-04 | 2016-02-24 | 北京金山安全软件有限公司 | Advertisement information pushing method and server |
| CN106919580A (en) * | 2015-12-25 | 2017-07-04 | 腾讯科技（深圳）有限公司 | A kind of information-pushing method and device |
| CN106919580B (en) * | 2015-12-25 | 2021-04-13 | 腾讯科技（深圳）有限公司 | Information pushing method and device |
| CN106407361A (en) * | 2016-09-07 | 2017-02-15 | 北京百度网讯科技有限公司 | Method and device for pushing information based on artificial intelligence |
| CN107066582A (en) * | 2017-04-14 | 2017-08-18 | 聚好看科技股份有限公司 | Realize the method and device that virtual resource is recommended |
| CN107066582B (en) * | 2017-04-14 | 2020-06-26 | 聚好看科技股份有限公司 | Method and device for realizing virtual resource recommendation |
| CN107846463A (en) * | 2017-11-08 | 2018-03-27 | 北京摩拜科技有限公司 | Information-pushing method, server, client and Vehicular system |
| CN109816414A (en) * | 2017-11-22 | 2019-05-28 | 北京国双科技有限公司 | Advertisement effectiveness data prediction technique and device |
| WO2019218450A1 (en) * | 2018-05-14 | 2019-11-21 | 平安科技（深圳）有限公司 | Message pushing method, storage medium, server and device |
| CN108875043A (en) * | 2018-06-27 | 2018-11-23 | 腾讯科技（北京）有限公司 | User data processing method, device, computer equipment and storage medium |
| CN108875043B (en) * | 2018-06-27 | 2022-02-25 | 腾讯科技（北京）有限公司 | User data processing method and device, computer equipment and storage medium |
| CN109657140A (en) * | 2018-12-13 | 2019-04-19 | 平安普惠企业管理有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN110246002A (en) * | 2019-04-25 | 2019-09-17 | 深圳壹账通智能科技有限公司 | Method for pushing, device and the computer equipment of financing recommendation information |
| CN113032662A (en) * | 2021-03-31 | 2021-06-25 | 龙关玲 | Block chain big data recommendation method and system based on artificial intelligence and cloud platform |
| CN113032662B (en) * | 2021-03-31 | 2021-11-26 | 艾普深瞳(北京)智能科技有限公司 | Block chain big data recommendation method and system based on artificial intelligence and cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103716338B (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103716338A (en) | Information push method and device | |
| US11409717B1 (en) | Overspend control in a messaging platform | |
| US9892431B1 (en) | Temporal features in a messaging platform | |
| KR102159274B1 (en) | Methods and systems for creating a data-driven attribution model for assigning attribution credit to a plurality of events | |
| US8893012B1 (en) | Visual indicator based on relative rating of content item | |
| US20160063523A1 (en) | Feedback instrument management systems and methods | |
| CN104035926B (en) | A kind of dispensing of internet information and system | |
| US10769677B1 (en) | Temporal features in a messaging platform | |
| US20140068407A1 (en) | Identifying web pages that are likely to guide browsing viewers to improve conversion rate | |
| KR20130005295A (en) | Conversion path performance measures and reports | |
| WO2015027442A1 (en) | Content selection with precision controls | |
| US20140372202A1 (en) | Predicting performance of content items using loss functions | |
| US20140058793A1 (en) | Forecasting a number of impressions of a prospective advertisement listing | |
| US20150046467A1 (en) | Ranking content items using predicted performance | |
| CN103700004A (en) | Method and device for pushing microblog advertising service information | |
| JP2014006684A (en) | Content distribution device | |
| Lee et al. | A generalized Bass model for predicting the sales patterns of motion pictures having seasonality and herd behavior | |
| Song et al. | Evaluation model of click rate of electronic commerce advertising based on fuzzy genetic algorithm | |
| US20160342699A1 (en) | Systems, methods, and devices for profiling audience populations of websites | |
| CN113535991B (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| WO2005066864A1 (en) | Online advertising method and online advertising system | |
| CN110796465B (en) | Resource display equipment determining method, advertisement display screen determining method and device | |
| US9786014B2 (en) | Earnings alerts | |
| CN113011912B (en) | Media information processing method, device, electronic equipment and storage medium | |
| US10068249B1 (en) | Inventory forecasting for bidded ad exchange |
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 |