CN109636479A - A kind of advertisement recommended method, device, electronic equipment and storage medium - Google Patents
A kind of advertisement recommended method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109636479A CN109636479A CN201811558203.7A CN201811558203A CN109636479A CN 109636479 A CN109636479 A CN 109636479A CN 201811558203 A CN201811558203 A CN 201811558203A CN 109636479 A CN109636479 A CN 109636479A
- Authority
- CN
- China
- Prior art keywords
- advertisement
- user
- behavioural information
- history
- vector set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000003542 behavioural effect Effects 0.000 claims abstract description 127
- 239000013598 vector Substances 0.000 claims description 92
- 230000006399 behavior Effects 0.000 claims description 26
- 230000015654 memory Effects 0.000 claims description 20
- 239000000463 material Substances 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of advertisement recommended method, device, electronic equipment and storage mediums, which comprises obtains the history advertisement behavioural information of user;The hobby similarity between user is determined according to the history advertisement behavioural information;Based on the hobby similarity between user to user's recommended advertisements.It by using above-mentioned technical proposal, realizes and pushes interested advertisement for user, and then guide user's click and consumer advertising, improve the purpose of advertisement position value.
Description
Technical field
Technical field is launched the present embodiments relate to advertisement more particularly to a kind of advertisement recommended method, device, electronics are set
Standby and storage medium.
Background technique
Main economic source one of of the advertisement as internet live streaming company, how effectively to carry out advertisement dispensing is live streaming
The technical ability that company must grasp.
Currently, live streaming platform does not accomplish personalized dispensing to the dispensing of advertisement, the advertisement of dispensing cannot be with live content
It is associated with, so that the popularization advertisement of outdoor goods occurs in the direct broadcasting room that often will appear leading game, greatly drops well
Usage experience of the low user to live streaming platform;Meanwhile the advertisement of dispensing is also not bound with the hobby progress special project of user
Recommend, user caused to receive advertisement much with no interest, influence direct broadcasting room beauty, causes advertisement to contradict psychology to user,
To directly affect the income of live streaming company.
Summary of the invention
The embodiment of the present invention provides a kind of advertisement recommended method, device, electronic equipment and storage medium, to be embodied as user
Interested advertisement is pushed, and then guides user's click and consumer advertising, improves advertisement position value.
In a first aspect, the embodiment of the invention provides a kind of advertisement recommended methods, which comprises
Obtain the history advertisement behavioural information of user;
The history advertisement behavioural information vector set of each user is constructed according to the history advertisement behavioural information of each user;
Calculate the Euclidean distance between the history advertisement behavioural information vector set of every two user;
Using the Euclidean distance as the hobby similarity between two users;
Based on the hobby similarity between user to user's recommended advertisements.
Second aspect, the embodiment of the invention provides a kind of advertisement recommendation apparatus, described device includes:
Module is obtained, for obtaining the history advertisement behavioural information of user;
Module is constructed, the history advertisement behavior of each user is constructed for the history advertisement behavioural information according to each user
Information vector set;
Computing module, the Euclidean distance between history advertisement behavioural information vector set for calculating every two user;
Determining module, for using the Euclidean distance as the hobby similarity between two users;
Recommending module, for based on the hobby similarity between user to user's recommended advertisements.
The third aspect the embodiment of the invention provides a kind of electronic equipment, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, the processor realizes such as above-mentioned the when executing the computer program
Advertisement recommended method described in one side.
Fourth aspect, the embodiment of the invention provides a kind of storage medium comprising computer executable instructions, the meters
Calculation machine executable instruction realizes the advertisement recommended method as described in above-mentioned first aspect when being executed as computer processor.
A kind of advertisement recommended method provided in an embodiment of the present invention, by obtaining the history advertisement behavioural information of user, and
The hobby similarity between user is determined according to the history advertisement behavioural information, finally based on the hobby similarity between user
It to the technological means of user's recommended advertisements, realizes and pushes interested advertisement for user, and then user is guided to click and consume
Advertisement improves advertisement position value.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, institute in being described below to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without creative efforts, can also implement according to the present invention
The content of example and these attached drawings obtain other attached drawings.
Fig. 1 is a kind of advertisement recommended method flow diagram that the embodiment of the present invention one provides;
Fig. 2 is a kind of advertisement recommended method flow diagram provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of advertisement recommendation apparatus structural schematic diagram that the embodiment of the present invention three provides;
Fig. 4 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.
Specific embodiment
To keep the technical problems solved, the adopted technical scheme and the technical effect achieved by the invention clearer, below
It will the technical scheme of the embodiment of the invention will be described in further detail in conjunction with attached drawing, it is clear that described embodiment is only
It is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those skilled in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall within the protection scope of the present invention.
Embodiment one
Fig. 1 is a kind of advertisement recommended method flow diagram that the embodiment of the present invention one provides.It is wide disclosed in the present embodiment
It accuses recommended method to be suitable for the case where each large platform carries out advertisement dispensing, the present embodiment is applied to flat in live streaming in this way
Platform be illustrated in case where advertisement dispensing, and the method can be executed by advertisement recommendation apparatus, wherein the device
It can be implemented by software and/or hardware, and be typically integrated in terminal, such as server etc..Referring specifically to shown in Fig. 1, this method
Include the following steps:
Step 110, the history advertisement behavioural information for obtaining user.
Wherein, the history advertisement behavioural information refers specifically to user in the set time period and what which advertisement has occurred
The mutual-action behavior of sample, such as user click an advertisement or user about " education " in 0 o'clock sharp of on November 11st, 2018
An advertisement etc. about " sport " is seen in 0 o'clock sharp of on November 11st, 2018, the set period of time can be nearly three
The time of the moon, i.e., by the acquisition closely trimestral time at moment.The specific acquisition modes of the history advertisement behavioural information of user can
To be directly to read from the background data base of system, when every advertisement state being launched changes, system can be anti-to backstage
Corresponding state change information is presented, such as which user sees Current ad or which user at what at what time
Time clicks Current ad, and system can be to corresponding state change information be fed back from the background, these state change informations can quilt
It stores to backstage specified data library.
When the history advertisement behavioural information of the user includes Customs Assigned Number, advertisement behavior and advertisement number, behavior
Between, advertisement type number, advertisement bit number, advertisement group # and material number at least one dimension;The Customs Assigned Number
Can specifically refer to the IP address used when user logs in live streaming platform, or log in the pet name etc.;The advertisement behavior refers specifically to " point
Hit " or " exposure ";The advertisement number refers specifically to the identification number of advertisement, for identifying unique advertisement;The time of the act
The time for referring specifically to advertisement behavior generation, for example, user clicks one about " education " in 0 o'clock sharp of on November 11st, 2018
Advertisement, wherein " 0 o'clock sharp of on November 11st, 2018 " is time of the act, and " click " is advertisement behavior, and " education " is advertisement type;
The advertisement type number refers specifically to the mark for identifying different advertisement types, such as the advertisement number of " education " class is
" 0000 ", the advertisement number of " sport " class are " 0001 " etc., and certain advertisement type can also divide thinner, such as " education " class
The advertisement of type can be further subdivided into " children education ", " adult education " and " early childhood education " etc.;Advertisement bit number refers to extensively
Accuse the number for showing position in live streaming platform;Advertisement group # refers to that group belonging to advertisement is numbered, and the group is, for example, " clothes
Dress ", " footwear " or " skin care category " etc.;Material number refers to that material used in advertisement is numbered.
The data format of the history advertisement behavioural information can indicate are as follows:
Ad_info=(user_id, ad_id, active_type, active_time, type_id, pos_id, group_
Id, material_id), wherein ad_info indicates history advertisement behavioural information, each parameter in history advertisement behavioural information
Meaning is referring to as shown in table 1 below:
Table 1: the data format of history advertisement behavioural information
Every advertisement launched away is then by background monitoring, such as when the advertisement launched away is clicked by user
System (system for example can be the terminals such as mobile phone) meeting Xiang Houtai (being can refer to from the background dedicated for launching the server of advertisement) is corresponding
A history advertisement behavioural information is fed back, the advertisement behavior in the history advertisement behavioural information is 1.Each word shown in table 1
Duan Jun represents a dimension of history advertisement behavioural information, such as user_id represents Customs Assigned Number dimension, and ad_id represents advertisement
Number dimension etc..
Step 120, the history advertisement behavioural information that each user is constructed according to the history advertisement behavioural information of each user
Vector.
Specifically, using each dimensional information in history advertisement behavioural information as in history advertisement behavioural information vector
One element, the history advertisement behavioural information vector include advertisement behavior and advertisement number, time of the act, advertisement type
Number, advertisement bit number, advertisement group # and material number at least one dimension, i.e., the described history advertisement behavioural information to
Amount does not include Customs Assigned Number dimension.
Step 130, calculate every two user history advertisement behavioural information vector between Euclidean distance.
Specifically, according to following formula calculate every two user history advertisement behavioural information vector between it is European away from
From:
Wherein, x indicate user A history advertisement behavioural information vector, y indicate user B history advertisement behavioural information to
Amount, d (x, y) indicate that the Euclidean distance between vector x and vector y, n indicate the dimension sum of vector.In order to improve between user
Like the computational accuracy of similarity, available each a certain number of history advertisement behavioural information vectors of user, such as obtains
1000 history advertisement behavioural information vectors of each user, this 1000 history advertisement behavioural information vectors can be according to certain
Rule (such as every history advertisement behavioural information vector end to end) one long vector of composition, then by calculating two
The Euclidean distance between two long vectors between user determines the hobby similarity between two users, or calculates separately two
Euclidean distance between every history advertisement behavioural information vector of a user, finally seeks the average value of all Euclidean distances again,
The hobby similarity average value being determined as between two users.
Step 140, using the Euclidean distance as the hobby similarity between two users.
Step 150, based on the hobby similarity between user to user's recommended advertisements.
Specifically, if the hobby similarity between two users reaches given threshold, then it is assumed that two users have phase
With hobby, that is, one of interested advertisement of user is also the interested advertisement of another user, therefore can will wherein one
Another user is recommended in a interested advertisement of user.For example, it is " education " that user A and user B, which click advertisement type,
Advertisement, then it is assumed that user A and user B has identical demand, i.e. user A is identical with the hobby of user B, while user A also is ordered
The advertisement that advertisement type is " sport " has been hit, and user B was not concerned with the advertisement that advertisement type is " sport ", thought to use at this time
Family B also has the demand to " sport " advertisement, therefore " sport " advertisement can be recommended user B, thus realize according to user it
Between hobby similarity to the purpose of user's recommended advertisements, realize that advertisement based on user interest is recommended.
A kind of advertisement recommended method provided in this embodiment, by the history advertisement behavioural information of acquisition user, and according to
The history advertisement behavioural information determines the hobby similarity between user, finally based on the hobby similarity between user to
The technological means of family recommended advertisements realizes and pushes interested advertisement for user, and then guides user's click and consumer advertising,
Improve advertisement position value.
Embodiment two
Fig. 2 is a kind of advertisement recommended method flow diagram provided by Embodiment 2 of the present invention.In the base of above-described embodiment
On plinth, the present embodiment is to " constructing the history advertisement behavioural information of each user according to the history advertisement behavioural information of each user
The step of vector ", is optimized, and the benefit of optimization can further improve the computational accuracy that similarity is liked between two users.Tool
Body is shown in Figure 2, and described method includes following steps:
Step 210, the history advertisement behavioural information for obtaining user.
Step 220, the history advertisement behavioural information that each user is constructed according to the history advertisement behavioural information of each user
Vector set.
Illustratively, the history advertisement behavioural information according to each user constructs the history advertisement behavior of each user
Information vector set, comprising:
The dimensional information composition first of setting quantity is selected from the history advertisement behavioural information based on combined mode
History advertisement behavioural information vector set;
By it is described setting quantity numerical value increase by 1, repeat said combination mode, obtain the second history advertisement behavioural information to
Duration set;
The numerical value of the setting quantity is continued growing 1, and repeats said combination mode, until the number of the setting quantity
Value increases to the dimension sum of the history advertisement behavioural information;
Wherein, the initial value of the setting quantity is more than or equal to the one of the dimension sum of the history advertisement behavioural information
Half.Vector in the history advertisement behavioural information vector set includes advertisement behavior and advertisement number, time of the act, wide
Accuse at least one dimension in type number, advertisement bit number, advertisement group # and material number.It is i.e. shared advertisement behavior, wide
Accusing number, time of the act, advertisement type number, the information of advertisement bit number, advertisement group # and 7 dimensions of material number can be with
The hobby similarity between two users is measured, and if directly carrying out hobby similarity calculation using the information of this 7 dimensions,
It then can not accurately handle influence of some secondary dimensions to hobby similarity.Such as advertisement number, advertisement type number, advertisement position
The information similarity that number, advertisement group # and material number this 6 dimensions is very high, and " time of the act " this dimensional information
It is widely different, but " time of the act " influence to the hobby similarity between two users and little, therefore " behavior should be reduced as far as possible
Influence of this secondary dimension of time " to hobby similarity.For this purpose, the present embodiment propose it is a kind of based on combined mode according to every
The history advertisement behavioural information of a user constructs the history advertisement behavioural information vector of each user, allows and participates in Euclidean distance every time
The vector dimension of calculating has from M to NThe problem of planting combination, while considering calculation amount, can set M >=N/2,
N=7 in the present embodiment, therefore the value of M is 4,5,6 or 7.As M=4, (the advertisement row from above-mentioned 7 dimensional informations is indicated
For, advertisement number, time of the act, advertisement type number, advertisement bit number, advertisement group # and material number) arbitrarily select 4
Dimensional information forms history advertisement behavioural information vector, there will beKind combination, that is, have 35
History advertisement behavioural information vector, the history advertisement behavioural information vector of 35 4 dimensions form the first history advertisement behavior letter
Vector set is ceased, the history advertisement behavior letter of above-mentioned 35 4 dimensions of two users is then calculated separately according to above-mentioned formula (1)
Cease the Euclidean distance between vector, obtain 35 Euclidean distances as a result, and further seek the sums of this 35 Euclidean distances, be denoted as
V1.In the manner described above, it as M=5, hasThe history advertisement behavioural information vector of a 5 dimension, should
The history advertisement behavioural information vector of 21 5 dimensions forms the second history advertisement behavioural information vector set, and is calculated 21
The sum of a Euclidean distance, is denoted as V2.Continue aforesaid way to have as M=6The history advertisement behavior of a 6 dimension
Information vector, the history advertisement behavioural information vector of 76 dimensions form third history advertisement behavioural information vector set, and
The sum of 7 Euclidean distances is calculated, is denoted as V3.As M=7, haveThe history advertisement behavioural information of a 7 dimension
The history advertisement behavioural information vector of vector, 17 dimension forms the 4th history advertisement behavioural information vector set, and calculates
1 Euclidean distance is obtained, V4 is denoted as.The hobby similarity sim between two users is finally calculated according to following formula:
Step 230, calculate in each history advertisement behavioural information vector set of two users between each vector it is European away from
From.
Wherein, in each history advertisement behavioural information vector set for calculating two users between each vector it is European away from
From specifically, calculating the Euclidean distance in each history advertisement behavioural information vector set of two users between each vector.
Operation is normalized to each Euclidean distance in step 240, obtains the normalized value of each Euclidean distance, and count
Calculate the average value of the normalized value of each Euclidean distance.
In order to fall in the hobby similarity between user between 0-1, when acquiring going through for two users according to above-mentioned formula (1)
After Euclidean distance between history advertisement behavioural information vector, obtained Euclidean distance is normalized according to following formula (3)
Operation obtains the normalized value of Euclidean distance:
Step 250, using the average value as the hobby similarity between two users.
Step 260, based on the hobby similarity between user to user's recommended advertisements.
A kind of advertisement recommended method provided in this embodiment, by way of based on combination, from the history advertisement behavior
The dimensional information that setting quantity is selected in information forms each history advertisement behavioural information vector set, and is based further on each history
The total technological means for calculating the hobby similarity between two users of advertisement behavioural information vector set, fully considered important dimension with
And secondary dimension improves the computational accuracy of hobby similarity to the Different Effects for liking similarity between user, realizes wide
The recommendation accuracy of announcement.
Further, based on the above technical solution, the history advertisement behavioural information structure according to each user
Build the history advertisement behavioural information vector of each user, further includes:
New history advertisement behavior letter is combined into from each history advertisement behavioural information vector set based on combined mode
Cease vector;Specifically, 4 dimensional information composition history are arbitrarily selected in expression from above-mentioned 7 dimensional informations for example as M=4
Advertisement behavioural information vector, there will beKind combination, that is, have 35 history advertisement behavioural informations
The history advertisement behavioural information vector of vector, 35 4 dimensions forms the first history advertisement behavioural information vector set, then at this
It can continue to combine according to identical combination in first history advertisement behavioural information vector set, such as from this 35
18 history advertisement behavioural information vectors are arbitrarily selected in history advertisement behavioural information vector to believe as new history advertisement behavior
Vector is ceased, then can be obtainedA new history advertisement behavioural information vector, wherein T indicates new
Dimension, the value rule of T and the value rule of above-mentioned M are identical;Two are calculated based on new history advertisement behavioural information vector again
Hobby similarity between a user can further improve the computational accuracy for liking similarity between user, and then improve advertisement
Recommendation precision.
Embodiment three
Fig. 3 is a kind of advertisement recommendation apparatus structural schematic diagram that the embodiment of the present invention three provides.It is shown in Figure 3, it is described
Device includes: to obtain module 310, building module 320, computing module 330, determining module 340 and recommending module 350;
Wherein, module 310 is obtained, for obtaining the history advertisement behavioural information of user;Module 320 is constructed, basis is used for
The history advertisement behavioural information of each user constructs the history advertisement behavioural information vector set of each user;Computing module 330,
The Euclidean distance between history advertisement behavioural information vector set for calculating every two user;Determining module 340, being used for will
The Euclidean distance is as the hobby similarity between two users;;Recommending module 350, for based on the hobby between user
Similarity is to user's recommended advertisements.The history advertisement behavioural information include: Customs Assigned Number, advertisement behavior and advertisement number,
At least one dimension in time of the act, advertisement type number, advertisement bit number, advertisement group # and material number.Wherein, institute
Stating the vector in history advertisement behavioural information vector set includes advertisement behavior and advertisement number, advertisement type number, advertisement
At least one dimension in bit number, advertisement group # and material number.
Further, the building module 320 is specifically used for:
The dimensional information composition first of setting quantity is selected from the history advertisement behavioural information based on combined mode
History advertisement behavioural information vector set;
By it is described setting quantity numerical value increase by 1, repeat said combination mode, obtain the second history advertisement behavioural information to
Duration set;
The numerical value of the setting quantity is continued growing 1, and repeats said combination mode, until the number of the setting quantity
Value increases to the dimension sum of the history advertisement behavioural information;
Wherein, the initial value of the setting quantity is more than or equal to the one of the dimension sum of the history advertisement behavioural information
Half.
Further, the computing module 330 is specifically used for: calculating each history advertisement behavioural information vector of two users
Euclidean distance in set between each vector.
Further, the computing module 330 includes:
Normalization unit obtains the normalization of each Euclidean distance for operation to be normalized to each Euclidean distance
Value;
Computing unit, the average value of the normalized value for calculating each Euclidean distance;
It is corresponding, it is described using the Euclidean distance as the hobby similarity between two users are as follows:
Using the average value as the hobby similarity between two users.
Further, the building module 320 is also used to:
New history advertisement behavior letter is combined into from each history advertisement behavioural information vector set based on combined mode
Cease vector.
A kind of advertisement recommendation apparatus provided in this embodiment, by the history advertisement behavioural information of acquisition user, and according to
The history advertisement behavioural information determines the hobby similarity between user, finally based on the hobby similarity between user to
The technological means of family recommended advertisements realizes and pushes interested advertisement for user, and then guides user's click and consumer advertising,
Improve advertisement position value.
Example IV
Fig. 4 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.As shown in figure 4, the electronics is set
It is standby to include: processor 670, memory 671 and be stored in the computer journey that run on memory 671 and on processor 670
Sequence;Wherein, the quantity of processor 670 can be one or more, in Fig. 4 by taking a processor 670 as an example;Processor 670 is held
The advertisement recommended method as described in above-described embodiment one is realized when the row computer program.As shown in figure 4, the electronics is set
Standby can also include input unit 672 and output device 673.Processor 670, memory 671, input unit 672 and output dress
Setting 673 can be connected by bus or other modes, in Fig. 4 for being connected by bus.
Memory 671 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if advertisement recommendation apparatus/module in the embodiment of the present invention is (for example, obtain module 310, building module 320, meter
Calculate module 330, determining module 340 and recommending module 350 etc.).Processor 670 is stored in soft in memory 671 by operation
Part program, instruction and module are realized above-mentioned wide thereby executing the various function application and data processing of electronic equipment
Accuse recommended method.
Memory 671 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 671 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 671 can be into one
Step includes the memory remotely located relative to processor 670, these remote memories can be set by network connection to electronics
Standby/storage medium.The example of above-mentioned network include but is not limited to internet, intranet, local area network, mobile radio communication and its
Combination.
Input unit 672 can be used for receiving the number or character information of input, and generates and set with the user of electronic equipment
It sets and the related key signals of function control inputs.Output device 673 may include that display screen etc. shows equipment.
Embodiment five
The embodiment of the present invention five also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction is used to execute a kind of advertisement recommended method when being executed by computer processor, this method comprises:
Obtain the history advertisement behavioural information of user;
The history advertisement behavioural information vector set of each user is constructed according to the history advertisement behavioural information of each user;
Calculate the Euclidean distance between the history advertisement behavioural information vector set of every two user;
Using the Euclidean distance as the hobby similarity between two users;
Based on the hobby similarity between user to user's recommended advertisements.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed advertisement provided by any embodiment of the invention and recommends
Relevant operation.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, storage medium or the network equipment etc.) executes described in each embodiment of the present invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of advertisement recommended method characterized by comprising
Obtain the history advertisement behavioural information of user;
The history advertisement behavioural information vector set of each user is constructed according to the history advertisement behavioural information of each user;
Calculate the Euclidean distance between the history advertisement behavioural information vector set of every two user;
Using the Euclidean distance as the hobby similarity between two users;
Based on the hobby similarity between user to user's recommended advertisements.
2. the method according to claim 1, wherein the history advertisement behavioural information include: Customs Assigned Number, it is wide
In announcement behavior and advertisement number, time of the act, advertisement type number, advertisement bit number, advertisement group # and material number
At least one dimension;
Vector in the history advertisement behavioural information vector set includes that advertisement behavior and advertisement number, advertisement type are compiled
Number, advertisement bit number, advertisement group # and material number at least one dimension.
3. according to the method described in claim 2, it is characterized in that, the history advertisement behavioural information structure according to each user
Build the history advertisement behavioural information vector set of each user, comprising:
The dimensional information for selecting setting quantity from the history advertisement behavioural information based on combined mode forms the first history
Advertisement behavioural information vector set;
The numerical value of the setting quantity is increased by 1, said combination mode is repeated, obtains the second history advertisement behavioural information vector set
It closes;
The numerical value of the setting quantity is continued growing 1, and repeats said combination mode, until the numerical value of the setting quantity increases
Add to the dimension sum of the history advertisement behavioural information;
Wherein, the initial value of the setting quantity is more than or equal to the half of the dimension sum of the history advertisement behavioural information.
4. according to the method described in claim 3, it is characterized in that, the history advertisement behavioural information for calculating every two user
Euclidean distance between vector set, comprising:
Calculate the Euclidean distance in each history advertisement behavioural information vector set of two users between each vector.
5. according to the method described in claim 4, it is characterized in that, the history advertisement behavioural information for calculating every two user
Euclidean distance between vector set, further includes:
Operation is normalized to each Euclidean distance, obtains the normalized value of each Euclidean distance;
Calculate the average value of the normalized value of each Euclidean distance;
It is corresponding, it is described using the Euclidean distance as the hobby similarity between two users are as follows:
Using the average value as the hobby similarity between two users.
6. according to the method described in claim 3, it is characterized in that, the history advertisement behavioural information structure according to each user
Build the history advertisement behavioural information vector set of each user, further includes:
Be combined into from each history advertisement behavioural information vector set based on combined mode new history advertisement behavioural information to
Amount.
7. a kind of advertisement recommendation apparatus, which is characterized in that described device includes:
Module is obtained, for obtaining the history advertisement behavioural information of user;
Module is constructed, the history advertisement behavioural information of each user is constructed for the history advertisement behavioural information according to each user
Vector set;
Computing module, the Euclidean distance between history advertisement behavioural information vector set for calculating every two user;
Determining module, for using the Euclidean distance as the hobby similarity between two users;
Recommending module, for based on the hobby similarity between user to user's recommended advertisements.
8. device according to claim 7, which is characterized in that the history advertisement behavioural information includes: Customs Assigned Number, wide
In announcement behavior and advertisement number, time of the act, advertisement type number, advertisement bit number, advertisement group # and material number
At least one dimension;
Vector in the history advertisement behavioural information vector set includes that advertisement behavior and advertisement number, advertisement type are compiled
Number, advertisement bit number, advertisement group # and material number at least one dimension.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized as described in any one of claim 1-6 when executing the computer program
Advertisement recommended method.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
Such as advertisement recommended method of any of claims 1-6 is realized when device executes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811558203.7A CN109636479A (en) | 2018-12-19 | 2018-12-19 | A kind of advertisement recommended method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811558203.7A CN109636479A (en) | 2018-12-19 | 2018-12-19 | A kind of advertisement recommended method, device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109636479A true CN109636479A (en) | 2019-04-16 |
Family
ID=66075546
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811558203.7A Pending CN109636479A (en) | 2018-12-19 | 2018-12-19 | A kind of advertisement recommended method, device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109636479A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223107A (en) * | 2019-05-23 | 2019-09-10 | 中国银行股份有限公司 | Method, apparatus and equipment are determined based on the reference advertisement of analogical object |
CN110969486A (en) * | 2019-11-29 | 2020-04-07 | 中国银行股份有限公司 | Advertisement putting method, user terminal, server, system and storage medium |
CN111210258A (en) * | 2019-12-23 | 2020-05-29 | 北京三快在线科技有限公司 | Advertisement putting method and device, electronic equipment and readable storage medium |
CN111861542A (en) * | 2020-06-15 | 2020-10-30 | 北京雷石天地电子技术有限公司 | Method, device, terminal and non-transitory computer readable storage medium for delivering advertisement |
CN112070524A (en) * | 2020-07-24 | 2020-12-11 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
CN112241894A (en) * | 2019-07-16 | 2021-01-19 | 百度时代网络技术(北京)有限公司 | Content delivery method and device and terminal |
CN112347375A (en) * | 2019-08-07 | 2021-02-09 | 腾讯科技(深圳)有限公司 | Method and device for pushing sports pattern and storage medium |
CN112819492A (en) * | 2019-11-15 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Advertisement recommendation method and device and electronic equipment |
CN113065896A (en) * | 2021-03-29 | 2021-07-02 | 上海酷量信息技术有限公司 | Advertisement recommendation method and device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
CN103632280A (en) * | 2012-08-24 | 2014-03-12 | 腾讯科技(深圳)有限公司 | Online advertisement accuracy measurement method and device |
CN104063801A (en) * | 2014-06-23 | 2014-09-24 | 广州优蜜信息科技有限公司 | Mobile advertisement recommendation method based on cluster |
CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
CN106570031A (en) * | 2015-10-13 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Service object recommending method and device |
CN107424015A (en) * | 2017-08-09 | 2017-12-01 | 星光物语(北京)电子商务有限公司 | Magnanimity commodity are supported to press the system and method for client's dimension price |
CN107688984A (en) * | 2017-07-27 | 2018-02-13 | 上海壹账通金融科技有限公司 | Product information method for pushing, device, storage medium and computer equipment |
CN107784066A (en) * | 2017-08-25 | 2018-03-09 | 上海壹账通金融科技有限公司 | Information recommendation method, device, server and storage medium |
-
2018
- 2018-12-19 CN CN201811558203.7A patent/CN109636479A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
CN103632280A (en) * | 2012-08-24 | 2014-03-12 | 腾讯科技(深圳)有限公司 | Online advertisement accuracy measurement method and device |
CN105095256A (en) * | 2014-05-07 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Information push method and apparatus based on similarity degree between users |
CN104063801A (en) * | 2014-06-23 | 2014-09-24 | 广州优蜜信息科技有限公司 | Mobile advertisement recommendation method based on cluster |
CN106570031A (en) * | 2015-10-13 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Service object recommending method and device |
CN107688984A (en) * | 2017-07-27 | 2018-02-13 | 上海壹账通金融科技有限公司 | Product information method for pushing, device, storage medium and computer equipment |
CN107424015A (en) * | 2017-08-09 | 2017-12-01 | 星光物语(北京)电子商务有限公司 | Magnanimity commodity are supported to press the system and method for client's dimension price |
CN107784066A (en) * | 2017-08-25 | 2018-03-09 | 上海壹账通金融科技有限公司 | Information recommendation method, device, server and storage medium |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110223107A (en) * | 2019-05-23 | 2019-09-10 | 中国银行股份有限公司 | Method, apparatus and equipment are determined based on the reference advertisement of analogical object |
CN112241894A (en) * | 2019-07-16 | 2021-01-19 | 百度时代网络技术(北京)有限公司 | Content delivery method and device and terminal |
CN112347375B (en) * | 2019-08-07 | 2023-09-26 | 腾讯科技(深圳)有限公司 | Method and device for pushing exercise document and storage medium |
CN112347375A (en) * | 2019-08-07 | 2021-02-09 | 腾讯科技(深圳)有限公司 | Method and device for pushing sports pattern and storage medium |
CN112819492A (en) * | 2019-11-15 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Advertisement recommendation method and device and electronic equipment |
CN110969486A (en) * | 2019-11-29 | 2020-04-07 | 中国银行股份有限公司 | Advertisement putting method, user terminal, server, system and storage medium |
CN110969486B (en) * | 2019-11-29 | 2024-02-27 | 中国银行股份有限公司 | Advertisement putting method, user, server, system and storage medium |
CN111210258A (en) * | 2019-12-23 | 2020-05-29 | 北京三快在线科技有限公司 | Advertisement putting method and device, electronic equipment and readable storage medium |
CN111861542A (en) * | 2020-06-15 | 2020-10-30 | 北京雷石天地电子技术有限公司 | Method, device, terminal and non-transitory computer readable storage medium for delivering advertisement |
CN111861542B (en) * | 2020-06-15 | 2024-02-02 | 北京雷石天地电子技术有限公司 | Method, device, terminal and non-transitory computer readable storage medium for advertising |
CN112070524A (en) * | 2020-07-24 | 2020-12-11 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
CN112070524B (en) * | 2020-07-24 | 2024-02-13 | 广州阿凡提电子科技有限公司 | Advertisement service recommendation method and device |
CN113065896A (en) * | 2021-03-29 | 2021-07-02 | 上海酷量信息技术有限公司 | Advertisement recommendation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109636479A (en) | A kind of advertisement recommended method, device, electronic equipment and storage medium | |
CN110941740B (en) | Video recommendation method and computer-readable storage medium | |
Garcin et al. | Offline and online evaluation of news recommender systems at swissinfo. ch | |
CN106462565B (en) | Text is updated in document | |
CN105493057B (en) | The content selection controlled using accuracy | |
CN109347986A (en) | A kind of voice messaging method for pushing, device, electronic equipment and storage medium | |
CN110474944B (en) | Network information processing method, device and storage medium | |
CN106294830A (en) | The recommendation method and device of multimedia resource | |
CN105426548A (en) | Video recommendation method and device based on multiple users | |
Fulgoni et al. | The power of political advertising: Lessons for practitioners: How data analytics, social media, and creative strategies shape US presidential election campaigns | |
CN106415644A (en) | Dynamic content item creation | |
CN109582872A (en) | A kind of information-pushing method, device, electronic equipment and storage medium | |
CN106168980A (en) | Multimedia resource recommends sort method and device | |
CN105389361A (en) | Search recommendation method and apparatus | |
CN103038769A (en) | System and method for directing content to users of a social networking engine | |
CN105528388A (en) | Search recommendation method and device | |
CN105302880A (en) | Content correlation recommendation method and apparatus | |
CN108777701A (en) | A kind of method and device of determining receiver | |
CN111344696B (en) | System and method for evaluating advertisements | |
US20190066200A1 (en) | Bid optimization | |
CN107992500A (en) | A kind of information processing method and server | |
CN109348262A (en) | A kind of calculation method, device, equipment and the storage medium of main broadcaster's similarity | |
CN106919692B (en) | Method and device for pushing message | |
CN102754117A (en) | Method, system and controller for providing goods and /or services to consumers | |
CN112118489B (en) | Group management method, device, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190416 |