CN109242544A - Processing method, device, computer equipment and the storage medium of product information push - Google Patents
Processing method, device, computer equipment and the storage medium of product information push Download PDFInfo
- Publication number
- CN109242544A CN109242544A CN201810946521.4A CN201810946521A CN109242544A CN 109242544 A CN109242544 A CN 109242544A CN 201810946521 A CN201810946521 A CN 201810946521A CN 109242544 A CN109242544 A CN 109242544A
- Authority
- CN
- China
- Prior art keywords
- product
- push
- behavior
- attribute
- product information
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000006399 behavior Effects 0.000 claims description 194
- 238000000034 method Methods 0.000 claims description 30
- 230000003542 behavioural effect Effects 0.000 claims description 24
- 238000012512 characterization method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 230000010365 information processing Effects 0.000 abstract description 2
- 230000006854 communication Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 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
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
Abstract
The invention discloses processing method, device, computer equipment and the storage mediums of a kind of push of product information, for based on big data technical field of information processing, comprising: obtain the product information of product to be pushed；The first push index of the product to be pushed is calculated according to the attribute factor of the product information and user；The second push index of the product to be pushed is calculated according to the product information and the behavior factor of user；The comprehensive push index of the product to be pushed is determined according to preset rules according to the first push index and the second push index.The present invention is by combining two kinds of mode classifications of individual's classification and product preference categories, according to the recommendation index of corresponding each classification, to recommend information products, classify more accurate, when not having historied product preference categories data, recommended according to individual's classification default information, improves the exposure of product to be promoted, more conducively popularization of the businessman to information products.
Description
Technical field
The present invention relates to information advancing technique fields, specifically, the present invention relates to a kind of, the product based on big data is believed
Cease processing method, device, computer equipment and the storage medium of push.
Background technique
With the development of internet, e-commerce platform becomes the medium of mainstream because of its advantage such as intelligent, convenient, possesses big
The customer resources and information of amount.At present no matter in web page browing or purchase platform, the browsing content according to client is all realized
Hobby recommendation is carried out, selects the time in order to save the product of client.
But the basis recommended is the previous browsing data of client, usually according to the data of a period of time browsing recently
Recommended, or is searched for according to user in certain time period.The content recommended in this way is single, and customer browses not recently
Certain still to like and have at present demand, recommendation accuracy is inadequate, for example, certain man once browsed Ms's product into
Certain primary purchase of row, does not need actually often to buy, must without too big if often recommending related Ms's product
It wants.It is this hobby is carried out according to browsing content to push away for businessman in addition, recommend fully according to customer's browsing
The mode recommended cannot recommend businessman really to want the product recommended well, and can not be artificial according to the mode of hobby push product
Operation.
Summary of the invention
The purpose of the present invention is intended at least can solve above-mentioned one of technological deficiency, discloses a kind of place of product information push
Method, apparatus, computer equipment and storage medium are managed, the information processing based on big data can be accurately according to the individual of user
Attribute and behavioral rudiment carry out the push of product information, while can also be by there is the user of administration authority that some product is specified to make
It is pushed for recommended products information, push mode is more diversified.
In order to achieve the above object, the present invention discloses a kind of processing method of product information push, comprising:
Obtain the product information of product to be pushed；
The first push index of the product to be pushed is calculated according to the attribute factor of the product information and user, simultaneously
The second push index of the product to be pushed is calculated according to the product information and the behavior factor of user；
The product to be pushed is determined according to preset rules according to the first push index and the second push index
Comprehensive push index.
Further, the attribute factor includes the multiple attribute classifications and Attribute Weight weight values of user, each Attribute class
It is not corresponding with one or more products, includes product to be pushed in the product；
The first push index that the product to be pushed is calculated according to the attribute factor of the product information and user
Method include:
Obtain the attribute product library that there is corresponding relationship with the attribute factor, wherein attribute factor includes characterization user
Multiple attribute classifications of relation on attributes, each attribute classification include one or more product form attribute product information libraries,
The attribute product library is the set in all attribute product information libraries；
Occur in the attribute product information library that product to be pushed described in determining includes in the attribute product library
Total frequency is first frequency；
The product for calculating first frequency and the Attribute Weight weight values obtains the first push index of the product to be pushed.
Further, the behavior factor includes characterizing the behavior classification and behavior weighted value of user's history behavioral rudiment,
Each behavior classification is corresponding with one or more products；
The second push index that the product to be pushed is calculated according to the product information and the behavior factor of user
Method include:
Obtain the behavior product library that there is corresponding relationship with the behavior factor, wherein behavior factor includes characterization user
The behavior classification of historical behavior trace, each behavior classification are mapped with one or more product form behavior product information libraries,
The behavior product library is the set in all behavior product information libraries；
Occur in the behavior product information library that product to be pushed described in determining includes in the behavior product library
Total frequency is second frequency；
The product for calculating second frequency and the behavior weighted value obtains the second push index of the product to be pushed.
Further, the preset rules include: the sum of the first push index and second push index of product to be pushed
Divided by the sum of corresponding Attribute Weight weight values and behavior weighted value.
Further, the processing method of the product information push further include:
Push list is determined according to the comprehensive push index of the product to be pushed, and is pushed according to push list wait push
Product information.
Further, before the comprehensive push index for executing the product to be pushed according to determines push list also
Include:
Detect whether specified recommended products information；
Judge the instruction of the recommended products information whether from the designated user with administration authority；
When recommended products information meets condition, the comprehensive push index of the recommended products information is arranged to peak.
Further, the acquisition methods of the behavior classification include:
Extract the Feature Words of the historical behavior Trace Data information；
The Feature Words of extraction are matched with preset classification dictionary, to obtain corresponding behavior classification.
Invention additionally discloses a kind of processing units of product information push, comprising:
Obtain module；For obtaining the product information of product to be pushed；
Processing module: for calculating the first of the product to be pushed according to the attribute factor of the product information and user
Push index；Meanwhile being referred to according to the second push that the product information and the behavior factor of user calculate the product to be pushed
Number；
Execution module: according to the first push index and the second push index according to preset rules determine it is described to
Push the comprehensive push index of product.
Further, the attribute factor includes the multiple attribute classifications and Attribute Weight weight values of user, each Attribute class
It is not corresponding with one or more products, includes product to be pushed in the product；
The processing unit of the product information push further include:
First acquisition submodule: for obtaining the attribute product library that there is corresponding relationship with the attribute factor, wherein belong to
Sex factor includes the multiple attribute classifications for characterizing user property relationship, and each attribute classification includes one or more product groups
At attribute product information library, the attribute product library is the set in all attribute product information libraries；
First statistic submodule: the attribute for including in the attribute product library for determining the product to be pushed
The total frequency occurred in product information library is first frequency；
First computational submodule: the product for calculating first frequency and the Attribute Weight weight values obtains described wait push
First push index of product.
Further, the behavior factor includes characterizing the behavior classification and behavior weighted value of user's history behavioral rudiment,
Each behavior classification is corresponding with one or more products；
The processing unit of product information push includes:
Second acquisition submodule: for obtaining the behavior product library that there is corresponding relationship with the behavior factor, wherein row
It include characterizing the behavior classification of user's history behavioral rudiment for the factor, each behavior classification is mapped with one or more product groups
It embarks on journey for product information library, the behavior product library is the set in all behavior product information libraries；
Second statistic submodule: the behavior for including in the behavior product library for determining the product to be pushed
The total frequency occurred in product information library is second frequency；
Second computational submodule: the product for calculating second frequency and the behavior weighted value obtains described wait push
Second push index of product.
Further, the preset rules include: the sum of the first push index and second push index of product to be pushed
Divided by the sum of corresponding Attribute Weight weight values and behavior weighted value.
Further, the processing unit of the product information push further include:
First push submodule: it for determining push list according to the comprehensive push index of the product to be pushed, and presses
Product information to be pushed is pushed according to push list.
Further, the processing unit of the product information push further include:
First detection sub-module: for detecting whether there is specified recommended products information；
First judging submodule: for judging the instruction of the recommended products information whether from administration authority
Designated user；
First setting submodule: when recommended products information meets condition, the comprehensive push of the recommended products information is referred to
Number is arranged to peak.
Further, the processing unit of the product information push further include:
First extracting sub-module: for extracting the Feature Words of the historical behavior Trace Data information；
First matched sub-block: for matching the Feature Words of extraction with preset classification dictionary, to be corresponded to
Behavior classification.
Invention additionally discloses a kind of computer equipment, including memory and processor, calculating is stored in the memory
Machine readable instruction, when the computer-readable instruction is executed by the processor, so that the processor executes such as claim 1
To product information described in any one of 7 claims push processing method the step of.
Invention additionally discloses a kind of storage mediums for being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute, so that one or more processors are executed such as any one of claims 1 to 7 claim institute
The step of processing method for the product information push stated.
The beneficial effects of the present invention are:
1) this programme proposes a kind of processing method of product information push, by the way that individual classifies and product preference categories
Two kinds of mode classifications combine, and according to the recommendation index of corresponding each classification, to recommend information products, classify more smart
It is quasi-；
2) when not having historied product preference categories data, recommended according to individual's classification default information；
3) backstage grading control, upper level terminal can be arranged by backstage, the way that control next stage end message is recommended
Diameter and the information content of recommendation, the specified next stage client recommended, to reach the wish orientation pair according to upper level terminal
Products Show content is controlled, and the exposure of product to be promoted, more conducively popularization of the businessman to information products are improved.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the processing method flow chart of product of the present invention information push；
Fig. 2 is the flow chart that product of the present invention information pushes step；
Fig. 3 is the method flow diagram that the present invention obtains the first push index；
Fig. 4 is the method flow diagram that the present invention obtains the second push index；
Fig. 5 is that the specified recommended products of the present invention pushes flow chart；
Fig. 6 is that behavioral rudiment Feature Words of the present invention extract flow chart；
Fig. 7 is that product of the present invention information pushes processing unit module diagram；
Fig. 8 is computer equipment basic structure block diagram of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can execute two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, data processing, fax and/or communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
In order to allow any people can device of the remote control for traveling, and execute shooting function, realize real time inspection
The purpose of the image of shooting, the present invention provide a kind of method of the processing method of product information push, wherein when this method uses
When remotely seeing in the application scenarios in room, the product information push processing method method include at least two terminals, one
It is remote terminal, image and state of a control is checked for user, and sends the remote terminal of control instruction, it should
Remote terminal can be computer, notebook, mobile phone perhaps other terminals and the unmanned machine can be robot or nothing
It is man-machine, the unmanned equipment such as telecar.And another is then that be controlled to be moved and be able to carry out related shooting dynamic
The unmanned machine of work.Telecommunication between the two, unmanned machine carry out the dependent instruction of transmission according to the motion state of itself
It analyzes and determines, execute or the first state is forbidden to instruct, see room to achieve the purpose that remotely to control, while unmanned machine has
There are automatic obstacle avoidance functions, intelligence degree is high, and control mode is simple.
Specifically, please refer to Fig. 1-Fig. 2, the present invention discloses a kind of processing method of product information push, mainly include with
Lower step:
S100, the product information for obtaining product to be pushed；
The present invention is a kind of processing method of product information push, and product to be pushed here includes but is not limited to conduct
The advertising information of product in kind further includes that Domestic News, coupon information or other any one can be used as message load also
The information that body is pushed.
In the present invention, product information includes but is not limited to the letter such as the type of product, the ownership of product, number of product
Breath.In this application, it due to needing to push product information, in order to preferably distinguish each information, and carries out accurate
Push can formulate the product information that each can be pushed a number, to facilitate identification and push.
S200, the first push that the product to be pushed is calculated according to the attribute factor of the product information and user refer to
Number；Meanwhile the second push index of the product to be pushed is calculated according to the product information and the behavior factor of user；
First push index refers to the push index of the attribute of product information combination user itself described above and determination.
The height of push index may determine whether to be pushed.
The attribute of user itself includes the attributes classification such as attribute in terms of physiology, such as gender, age level, can also be wrapped
Include the psychological attribute classification such as hobby, for example, be risk or conservative or mixed type etc..Further
, it can be classified according to the above-mentioned attribute of itself, classification and matching is carried out according to the case where active user itself.
Attribute factor includes multiple attribute classifications of user, and each attribute classification is corresponding with one or more products.
The aforementioned plurality of attribute classification indicates that attributes classification, each attribute classification such as gender, age, hobby include
Corresponding one or more product, it can be understood as respectively include an attribute product information library, the category inside an attribute classification
Property product information library is composed of the information of one or more products.It should be noted that product information can basis
Specific type and applicable group, are assigned in above-mentioned different attribute classification, can be with identical product information simultaneously upper
It states in different attribute classifications.
Further, in order to preferably be distinguished to product, the said goods information can be numbered, passes through volume
Number the distribution of product information is managed collectively.It should be noted that the step for be before executing push task, backstage
What completion was previously-completed.The product information that i.e. each can be pushed requires before being added into system to product information
It is numbered, and determines its type and attribute, the attribute product information of different attribute classification mappings is assigned to according to attribute
In library.Equally, a product information can be assigned to simultaneously in multiple and different attribute classifications.
In addition, attribute factor further includes Attribute Weight weight values, Attribute Weight weight values are the coefficients for being directed to attribute factor, please be joined
Fig. 3 is read, the first push index that the product to be pushed is calculated according to the attribute factor of the product information and user
Method includes:
S210, the attribute product library that there is corresponding relationship with the attribute factor is obtained, wherein attribute factor includes characterization
Multiple attribute classifications of user property relationship, each attribute classification include one or more product form attribute product informations
Library, the attribute product library are the set in all attribute product information libraries；
Since attribute classification can map multiple and different attribute product information libraries, such as the first attribute product at characterization age
Information bank, representational other second product information library characterize the third attribute product information library of hobby, when attribute classification quilt
In the case that definition only has these three classifications, attribute product library is then the first above-mentioned attribute product information library, the production of the second attribute
The set of product information bank and third attribute product information library.
S220, determine described in product to be pushed include in the attribute product library attribute product information library in go out
Existing total frequency is first frequency；
When confirming the first of product information of the product to be pushed the push index, corresponding attribute product is first obtained
Affiliated attribute product information library is found in library, then dependence product library, due to the same product information can be stored in it is multiple
In attribute product information library, so when an available appearance about the product information in attribute product library total frequency
It is secondary.
The product of S230, calculating first frequency and the Attribute Weight weight values obtain the first push of the product to be pushed
Index.
Since it is determined total frequency, then can obtain the first push index according to the product of total frequency and Attribute Weight weight values,
Formula can be expressed as:
A1=KX
Wherein, A1 is the first push index, and K is Attribute Weight weight values, and X is what the product information occurred in attribute product library
Total frequency.
It but in another embodiment, can be to above-mentioned multiple in order to which product information is more accurately matched user
Attribute product information library is all correspondingly arranged a weighted value, for example, the weighted value in the first attribute product information library is k1, second belongs to
Property product information library weighted value be k2, the weighted value in third attribute product information library is k3.Although product information can be not
Occur simultaneously in same attribute product information library, but in each specific attribute product information library, can only at most occur once,
Therefore it is corresponding, in the present embodiment, the expression formula of the first push index are as follows:
A1=K (k1*x1+k2*x2+k3*x3)
Wherein, A1 is the first push index, and K is Attribute Weight weight values, and k1 is the weighted value in the first attribute product information library, k2
For the weighted value in the second attribute product information library, k3 is the weighted value in third attribute product information library, and x1 is product information the
The number occurred in one attribute product information library, x2 are the number that product information occurs in the second attribute product information library, x3
The number occurred in third attribute product information library for product information, wherein x1, x2 and x3 believe in corresponding attribute product
It ceases in library, occurring is 1, does not occur being 0, can calculate corresponding first push index with this.
The present invention also needs to calculate the second of the product to be pushed according to the product information and the behavior factor of user
Push index；
Second push index refers to the push index of the behavior property of product information combination user described above and determination.
The height of the push index can also be used to determine whether to be pushed.
The behavior factor includes characterizing the behavior classification of user's history behavioral rudiment.The system of different function, to be supervised
The behavioral rudiment of control is different, by the behavioral rudiment data of monitoring, classifies to related data, so as to obtain multiple rows
For classification, for example in the financial system page, user may browse or buy the product of the classifications such as fund, stock, insurance,
Each behavior classification includes corresponding one or more products, as the behavior classification of above-mentioned introduction, a behavior classification
The inside respectively includes a behavior product information library, behavior product information library be combined by the information of one or more products and
At.It should be noted that product information can be assigned in above-mentioned different behavior classification according to specific type, also
It can be with identical product information while in above-mentioned different behavior classification.
In addition, behavior factor further includes behavior weighted value, behavior weighted value is the coefficient for being directed to behavior factor, please be joined
Fig. 4 is read, the second push index that the product to be pushed is calculated according to the product information and the behavior factor of user
Method includes:
S240, the behavior product library that there is corresponding relationship with the behavior factor is obtained, wherein behavior factor includes characterization
The behavior classification of user's history behavioral rudiment, each behavior classification are mapped with one or more product form behavior product informations
Library, the behavior product library are the set in all behavior product information libraries；
Since behavior classification can map multiple and different behavior product information libraries, such as the first behavior product of characterization fund
Information bank characterizes library at the second behavior product information of stock, the third product information library of insurance is characterized, when behavior classification is determined
In the case that justice only has these three classifications, behavior product library is then the first above-mentioned behavior product information library, the second behavior product
The set of information bank and third behavior product information library.
S250, determine described in product to be pushed include in the behavior product library behavior product information library in go out
Existing total frequency is second frequency；
When confirming the second of product information of the product to be pushed the push index, corresponding behavior product is first obtained
Affiliated behavior product information library is found in library, then subordinate act product library, due to the same product information can be stored in it is multiple
In behavior product information library, so when an available appearance about the product information in behavior product library total frequency
It is secondary.
The product of S260, calculating second frequency and the behavior weighted value obtain the second push of the product to be pushed
Index.
Since it is determined total frequency that product information to be pushed occurs in behavior product library, then it can be according to total frequency
The first push index is obtained with the product of Attribute Weight weight values, formula can be expressed as:
A2=JY
Wherein, A2 is the second push index, and J is behavior weighted value, and Y is what the product information occurred in behavior product library
Total frequency.
It but in another embodiment, can be to above-mentioned multiple in order to which product information is more accurately matched user
Behavior product information library is all correspondingly arranged a weighted value, for example, the weighted value in the first behavior product information library is j1, the second row
Weighted value for product information library is j2, and the weighted value in third behavior product information library is j3.Although product information can be not
Occur simultaneously in same behavior product information library, but in each specific behavior product information library, can only at most occur once,
Therefore it is corresponding, in the present embodiment, the expression publicity of the second push index are as follows:
A2=J (j1*y1+j2*y2+j3*y3)
Wherein, A2 is the first push index, and J is Attribute Weight weight values, and j1 is the weighted value in the first behavior product information library, j2
For the weighted value in the second behavior product information library, j3 is the weighted value in third behavior product information library, and y1 is product information the
The number occurred in one behavior product information library, y2 are the number that product information occurs in the second behavior product information library, y3
The number occurred in third behavior product information library for product information, wherein y1, y2 and y3 believe in corresponding behavior product
It ceases in library, occurring is 1, does not occur being 0, can calculate corresponding first push index with this.
Further, behavior factor and attribute factor the difference is that, the Attribute Weight weight values characterized in attribute factor,
And the weighted value in attribute product information library is fixed, and is pushed according to attribute predetermined and weight calculation first
Index.Behavior factor characterization behavior weighted value be fixed, but the weighted value being different in behavior product information library be can
It is changed with the behavioral rudiment according to user.Specifically, according to belonging to the content that user is browsed in specific time
Type is ranked up the hobby of user, for example, within the nearly trimestral time, being used for when statistical time is nearly three months
Browsing time is at most fund class product information, is stock class product mostly second, is insurance class product information mostly third,
It can will characterize the weighted value j1 in the first behavior product information library of fund class, characterize the second behavior product information library of stock class
Weighted value j2 and characterization insurance class third behavior product information library weighted value j3 weighted value size is defined as: j1 > j2 >
j3.Over time, when the browsing type of user changes, the size of the weighted value of corresponding behavior classification also can
It changes.
Further, can be for behavior class weight value variation is changed according to certain rule, is also possible to solid
Fixed value, for example, determining in the unit time, the weighted value of the most corresponding classification of product of the browsing frequency is 0.8, more than second
Be 0.6, be 0.5 mostly third, then the behavior classification sequence that the behavioral rudiment according to active user within the unit time obtains,
To determine corresponding weighted value size.
S300, determined according to the first push index and the second push index according to preset rules it is described wait push
The comprehensive push index of product.
Comprehensive push Index A is true according to preset rules according to the first above-mentioned push Index A 1 and the second push Index A 2
Surely it obtains.
The preset rules include: that the first push index of product to be pushed pushes the sum of index divided by corresponding with second
The sum of Attribute Weight weight values and behavior weighted value, i.e. expression formula are as follows:
A=(A1+A2)/(K+J)
Corresponding above-mentioned two different modes, when attribute factor and behavior factor are without corresponding attribute product information library
When weighted value and the weighted value in behavior product information library, further expression formula can be with are as follows:
A=(KX+JY)/(K+J)；
When there are the weighted values in corresponding attribute product information library and behavior product information library for attribute factor and behavior factor
Weighted value when, further expression formula can be with are as follows:
A=[K (k1*x1+k2*x2+k3*x3)+J (j1*y1+j2*y2+j3*y3)]/(K+J).
When attribute classification and behavior categorical measure are n, expression formula are as follows:
S400, push list is determined according to the comprehensive push index of the product to be pushed.
According to the operation of above-mentioned formula, the comprehensive push index of some available product to be pushed.Foundation the method,
The calculating that all products to be pushed are carried out with comprehensive push index, can be obtained a synthesis about all products to be recommended
Push index, it is easy to obtain a ranking about the comprehensive push index for needing to be pushed product, further, the present invention
In, it can be according to the sequence of comprehensive push index to be pushed, the forward certain amount of product to be pushed that will sort, which is included in, to be pushed away
Send in list, or some standard value reached according to comprehensive push index, come determine be included in push list wait push away
Send product.According to above-mentioned push list, to be pushed to push product.
Further, referring to Fig. 5, determining push in the comprehensive push index for executing the product to be pushed according to
Before list further include:
S510, specified recommended products information is detected whether；
Specified recommended products information refers to the wish according to user, certain a specific product information is specified artificially to arrange
Enter into push list.It is included in the mode of push list, can be and increase a push planned number in push list, be also possible to
A wherein product information is replaced in push list.
S520, judge the instruction of the recommended products information whether from the designated user with administration authority；
When detecting specified recommended products information, then judge whether the recommended products information derives from administrative power
The designated user of limit.In the present embodiment, the designated user with administration authority refers to the tool other than backstage, in addition opened up
There is the user account of administration authority, this administration authority can be by being defined from the background.When monitoring specified recommended products
After information derives from the designated user with administration authority, then assert its for valid operation, when specified recommended products information not
It is derived from the above-mentioned designated user with administration authority, then regards as illegal operation.
S530, meet condition when recommended products information, the comprehensive push index of the recommended products information is arranged to most
High level.
According to above-mentioned steps, when regarding as valid operation, then by the product information of the specified recommended products
Comprehensive push index be automatically set to peak, in order to which it will be included in recommendation list.
In another embodiment, in fact, the comprehensive push index of the recommended products information is not necessarily and passes through system
It is automatically set to peak, can also be through the above-mentioned comprehensive push index of designated user's manual definition with administration authority
Numerical value.For example, it is existing push list in push index before 6 be respectively as follows: 5.0,4.9,4.6,4.5,4.4,4.3, then when
It can be manually 4.8 by the comprehensive push Index Definition of above-mentioned product to be pushed, then it is arranged in 4.9 when needing to push
Between 4.6, when the push of push list be ranked up according to the size of comprehensive push index, and successively pushed when
It waits, then the specified recommended products is pushed in third.Certainly, in another embodiment, producing in list wait push is pushed
Product can also be to be pushed at random.
Further, referring to Fig. 6, in the present invention, how to obtain corresponding to hobby by the historical behavior trace of user
Behavior classification.Its method specifically includes that
S610, the Feature Words for extracting the historical behavior Trace Data information；
Historical behavior trace can use API (Application Programming Inerface) interface from network
Side acquires the behavioral data of user, starts specifically, can use the browser that API is got in terminal device to the network equipment
Before reporting behavioral data, user executes produced by network access and is stored in the behavioral data of network side.
The product information of the browsing as involved in historical behavior trace, such as the spy of the characterization content about the product information
Sign word, therefore the data obtained can pass through Feature Words extracting mode and extract keyword.About the mode that Feature Words extract, can adopt
With document frequency (DF, Document Frequency), mutual information (MI, Mutual Information), expectation cross entropy
(ECE, Expected Cross Entropy), information gain (IG, Information Gain), text weight evidence (WET, the
Weight of Evidence for Text), probability ratio (OR, Odds Ratio) and gamma function probability statistics etc. carry out
Feature Words extract.
S620, the Feature Words of extraction are matched with preset classification dictionary, to obtain corresponding behavior classification.
The corresponding entity dictionary of classification can by the behavioral data sample size to each user statistically analyze, clustering with
And the method for combining machine learning obtains, that is, the classification being arranged can be the vector entity word being made of one or more entity words
Library.For example, being obtained by the statistical analysis of the behavioral data to a large number of users, clustering and the method for combining machine learning
To classification may include: fund, stock, insurance etc., for insurance, the entity words such as life insurance, health insurance, business risk can be passed through
Classification marker is carried out, for stock, can be classified with A-share, B strands, H-share, N strands and S strands etc., and so on.It can be set
Multistage classification, in order to exact classification.
It is extracted by Feature Words, behavior that available user goes within a certain period of time hobby, so as to according to hobby,
Obtain the size of the corresponding weighted value in behavior product information library.
Invention additionally discloses a kind of processing units of product information push, referring to Fig. 7, including:
Obtain module 100；For obtaining the product information of product to be pushed；Here product to be pushed includes still unlimited
It also in the advertising information as product in kind, further include that Domestic News, coupon information or other any one can be used as
The information that message carrier is pushed.
Processing module 200: for calculating the product to be pushed according to the attribute factor of the product information and user
First push index；Meanwhile the second of the product to be pushed is calculated according to the product information and the behavior factor of user and is pushed away
Send index；
First push index refers to the push index of the attribute of product information combination user itself described above and determination.
The height of push index may determine whether to be pushed.
Attribute factor includes multiple attribute classifications of user, for example, the first attribute product information library at such as characterization age,
Library at representational other second product information characterizes third attribute product information library or the N attribute product of hobby
Information bank.
Attribute factor further includes Attribute Weight weight values, and Attribute Weight weight values are the coefficients for being directed to attribute factor.
Assistance of the acquisition of first push index also by following device:
First acquisition submodule: with for obtaining the attribute product library that there is corresponding relationship with the attribute factor, wherein
Attribute factor includes the multiple attribute classifications for characterizing user property relationship, and each attribute classification includes one or more products
Attribute product information library is formed, the attribute product library is the set in all attribute product information libraries；Due to attribute classification
Can map multiple and different attribute product information libraries, for example, the characterization age the first attribute product information library, representational other the
Library at two product informations characterizes the third attribute product information library of hobby, when attribute classification is defined only these three classes
In other situation, attribute product library is then above-mentioned the first attribute product information library, the second attribute product information library and third category
The set in property product information library.
First statistic submodule: the attribute for including in the attribute product library for determining the product to be pushed
The total frequency occurred in product information library is first frequency；In the first push index for confirming the product information of the product to be pushed
When, corresponding attribute product library is first obtained, then affiliated attribute product information library is found in dependence product library, due to same
One product information can be stored in multiple attribute product informations library, so when available one exist about the product information
Total frequency of appearance in attribute product library.
First computational submodule: the product for calculating first frequency and the Attribute Weight weight values obtains described wait push
First push index of product.
Since it is determined total frequency, then can obtain the first push index according to the product of total frequency and Attribute Weight weight values,
Formula can be expressed as:
A1=KX
Wherein, A1 is the first push index, and K is Attribute Weight weight values, and X is what the product information occurred in attribute product library
Total frequency.
For the first attribute product information corresponding in attribute product library library, the second attribute product information library and third attribute
When there is corresponding weighted value in product information library to N attribute product information library, the expression formula of the first push index are as follows:
Wherein, A1 is the first push index, and K is Attribute Weight weight values, and k1 is the weighted value in the first attribute product information library, k2
For the weighted value in the second attribute product information library, k3 is the weighted value in third attribute product information library, and x1 is product information the
The number occurred in one attribute product information library, x2 are the number that product information occurs in the second attribute product information library, x3
The number occurred in third attribute product information library for product information, wherein x1, x2 and x3 believe in corresponding attribute product
It ceases in library, occurring is 1, does not occur being 0, can calculate corresponding first push index with this.
Second push index refers to the push index of the behavior property of product information combination user described above and determination.
The height of the push index can also be used to determine whether to be pushed.
The behavior factor includes characterizing the behavior classification of user's history behavioral rudiment, for example characterize the first behavior of fund
Product information library characterizes library at the second behavior product information of stock, characterizes the third product information library of insurance.
Behavior factor further includes behavior weighted value, and behavior weighted value is the coefficient for being directed to behavior factor, passes through the row
The second push index can be obtained for weighted value.
The second push index is obtained to assist by following device:
Second acquisition submodule: for obtaining the behavior product library that there is corresponding relationship with the behavior factor, wherein row
It include characterizing the behavior classification of user's history behavioral rudiment for the factor, each behavior classification is mapped with one or more product groups
It embarks on journey for product information library, the behavior product library is the set in all behavior product information libraries；
Since behavior classification can map multiple and different behavior product information libraries, such as the first behavior product of characterization fund
Information bank characterizes library at the second behavior product information of stock, the third product information library of insurance is characterized, when behavior classification is determined
In the case that justice only has these three classifications, behavior product library is then the first above-mentioned behavior product information library, the second behavior product
The set of information bank and third behavior product information library.
Second statistic submodule: the behavior for including in the behavior product library for determining the product to be pushed
The total frequency occurred in product information library is second frequency；
When confirming the second of product information of the product to be pushed the push index, corresponding behavior product is first obtained
Affiliated behavior product information library is found in library, then subordinate act product library, due to the same product information can be stored in it is multiple
In behavior product information library, so when an available appearance about the product information in behavior product library total frequency
It is secondary.
Second computational submodule: the product for calculating second frequency and the behavior weighted value obtains described wait push
Second push index of product.
Since it is determined total frequency that product information to be pushed occurs in behavior product library, then it can be according to total frequency
The first push index is obtained with the product of Attribute Weight weight values, formula can be expressed as:
A2=JY
Wherein, A2 is the second push index, and J is behavior weighted value, and Y is what the product information occurred in behavior product library
Total frequency.
For the first behavior product information corresponding in attribute product library library, the second behavior product information library and third behavior
When product information library to Nth row is that product information library has corresponding weighted value, the expression formula of the second push index are as follows:
Execution module 300: institute is determined according to preset rules according to the first push index and the second push index
State the comprehensive push index of product to be pushed.
Comprehensive push Index A is true according to preset rules according to the first above-mentioned push Index A 1 and the second push Index A 2
Surely it obtains.
The preset rules include: that the first push index of product to be pushed pushes the sum of index divided by corresponding with second
The sum of Attribute Weight weight values and behavior weighted value, i.e. expression formula are as follows:
A=(A1+A2)/(K+J)
Corresponding above-mentioned two different modes, when attribute factor and behavior factor are without corresponding attribute product information library
When weighted value and the weighted value in behavior product information library, further expression formula can be with are as follows:
A=(KX+JY)/(K+J)；
When there are the weighted values in corresponding attribute product information library and behavior product information library for attribute factor and behavior factor
Weighted value when, the first push index of product to be pushed pushes the sum of index divided by corresponding Attribute Weight weight values and row with second
For the sum of weighted value, further expression formula can be with are as follows:
Further, the processing unit of the product information push further include:
First push submodule: it for determining push list according to the comprehensive push index of the product to be pushed, and presses
Product information to be pushed is pushed according to push list.
According to the operation of above-mentioned formula, the comprehensive push index of some available product to be pushed.Pass through the synthesis
Index is pushed, available a ranking about the comprehensive push index for needing to be pushed product can be used according to ranking
In the push list of push.
Further, in the device of the application further include:
First detection sub-module: for detecting whether there is specified recommended products information；
Specified recommended products information refers to the wish according to user, certain a specific product information is specified artificially to arrange
Enter into push list.It is included in the mode of push list, can be and increase a push planned number in push list, be also possible to
A wherein product information is replaced in push list.
First judging submodule: for judging the instruction of the recommended products information whether from administration authority
Designated user；
When detecting specified recommended products information, then judge whether the recommended products information derives from administrative power
The designated user of limit.In the present embodiment, the designated user with administration authority refers to the tool other than backstage, in addition opened up
There is the user account of administration authority, this administration authority can be by being defined from the background.When monitoring specified recommended products
After information derives from the designated user with administration authority, then assert its for valid operation, when specified recommended products information not
It is derived from the above-mentioned designated user with administration authority, then regards as illegal operation.
First setting submodule: when recommended products information meets condition, the comprehensive push of the recommended products information is referred to
Number is arranged to peak.
According to above-mentioned steps, when regarding as valid operation, then by the product information of the specified recommended products
Comprehensive push index be automatically set to peak, in order to which it will be included in recommendation list.
In the application, how to obtain corresponding to device involved in the behavior classification of hobby by the historical behavior trace of user
Include:
First extracting sub-module: for extracting the Feature Words of the historical behavior Trace Data information；
Historical behavior trace can use API (Application Programming Inerface) interface from network
Side acquires the behavioral data of user, starts specifically, can use the browser that API is got in terminal device to the network equipment
Before reporting behavioral data, user executes produced by network access and is stored in the behavioral data of network side.
The product information of the browsing as involved in historical behavior trace, such as the spy of the characterization content about the product information
Sign word, therefore the data obtained can pass through Feature Words extracting mode and extract keyword.About the mode that Feature Words extract, can adopt
With document frequency (DF, Document Frequency), mutual information (MI, Mutual Information), expectation cross entropy
(ECE, Expected Cross Entropy), information gain (IG, Information Gain), text weight evidence (WET, the
Weight of Evidence for Text), probability ratio (OR, Odds Ratio) and gamma function probability statistics etc. carry out
Feature Words extract.
First matched sub-block: for matching the Feature Words of extraction with preset classification dictionary, to be corresponded to
Behavior classification.
The corresponding entity dictionary of classification can by the behavioral data sample size to each user statistically analyze, clustering with
And the method for combining machine learning obtains, that is, the classification being arranged can be the vector entity word being made of one or more entity words
Library.For example, being obtained by the statistical analysis of the behavioral data to a large number of users, clustering and the method for combining machine learning
To classification may include: fund, stock, insurance etc., for insurance, the entity words such as life insurance, health insurance, business risk can be passed through
Classification marker is carried out, for stock, can be classified with A-share, B strands, H-share, N strands and S strands etc., and so on.It can be set
Multistage classification, in order to exact classification.
It is extracted by Feature Words, behavior that available user goes within a certain period of time hobby, so as to according to hobby,
Obtain the size of the corresponding weighted value in behavior product information library.
Invention additionally discloses a kind of computer equipment, including memory and processor, calculating is stored in the memory
Machine readable instruction, when the computer-readable instruction is executed by the processor, so that processor execution is above-mentioned any one
The method of the processing of the item product information push.
The embodiment of the present invention provides computer equipment basic structure block diagram and please refers to Fig. 8.
The computer equipment includes processor, non-volatile memory medium, memory and the net connected by system bus
Network interface.Wherein, the non-volatile memory medium of the computer equipment is stored with operating system, database and computer-readable finger
It enables, control information sequence can be stored in database, when which is executed by processor, may make that processor is real
A kind of processing method of existing product information push.The processor of the computer equipment is for providing calculating and control ability, support
The operation of entire computer equipment.Computer-readable instruction can be stored in the memory of the computer equipment, which can
When reading instruction is executed by processor, processor may make to execute a kind of processing method of product information push.The computer equipment
Network interface be used for and terminal connection communication.It will be understood by those skilled in the art that structure shown in Fig. 8, only with
The block diagram of the relevant part-structure of application scheme, does not constitute the computer equipment being applied thereon to application scheme
Limit, specific computer equipment may include than more or fewer components as shown in the figure, perhaps combine certain components or
With different component layouts.
The status information for prompting behavior that computer equipment is sent by receiving associated client, i.e., whether associated terminal
It opens prompt and whether user closes the prompt task.By verifying whether above-mentioned task condition is reached, and then eventually to association
End sends corresponding preset instructions, so that associated terminal can execute corresponding operation according to the preset instructions, to realize
Effective supervision to associated terminal.Meanwhile when prompt information state and preset status command be not identical, server end control
Associated terminal persistently carries out jingle bell, the problem of to prevent the prompt task of associated terminal from terminating automatically after executing a period of time.
The present invention also provides a kind of storage mediums for being stored with computer-readable instruction, and the computer-readable instruction is by one
When a or multiple processors execute, so that one or more processors execute the push of product information described in any of the above-described embodiment
The method of processing method.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, which can be stored in a computer-readable storage and be situated between
In matter, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, storage medium above-mentioned can be
The non-volatile memory mediums such as magnetic disk, CD, read-only memory (Read-Only Memory, ROM) or random storage note
Recall body (Random Access Memory, RAM) etc..
It should be understood that although each step in the flow chart of attached drawing is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, can execute in the other order.Moreover, at least one in the flow chart of attached drawing
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, execution sequence, which is also not necessarily, successively to be carried out, but can be with other
At least part of the sub-step or stage of step or other steps executes in turn or alternately.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of processing method of product information push characterized by comprising
Obtain the product information of product to be pushed；
The first push index of the product to be pushed, while basis are calculated according to the attribute factor of the product information and user
The product information and the behavior factor of user calculate the second push index of the product to be pushed；
The comprehensive of the product to be pushed is determined according to preset rules according to the first push index and the second push index
Close push index.
2. the processing method of product information push according to claim 1, which is characterized in that the attribute factor includes using
Multiple attribute classifications and Attribute Weight weight values at family, each attribute classification are corresponding with one or more products, in the product
Including product to be pushed；
It is described to include: according to the first push index of the attribute factor of the product information and user the calculating product to be pushed
Obtain the attribute product library that there is corresponding relationship with the attribute factor, wherein attribute factor includes characterization user property
Multiple attribute classifications of relationship, each attribute classification includes one or more product form attribute product information libraries, described
Attribute product library is the set in all attribute product information libraries；
The total frequency occurred in the attribute product information library that product to be pushed described in determining includes in the attribute product library
Secondary is first frequency；
The product for calculating first frequency and the Attribute Weight weight values obtains the first push index of the product to be pushed.
3. the processing method of product information push according to claim 2, which is characterized in that the behavior factor includes table
Take over the behavior classification and behavior weighted value of family historical behavior trace for use, each behavior classification is corresponding with one or more productions
Product；
The side of the second push index that the product to be pushed is calculated according to the product information and the behavior factor of user
Method includes:
Obtain the behavior product library that there is corresponding relationship with the behavior factor, wherein behavior factor includes characterization user's history
The behavior classification of behavioral rudiment, each behavior classification is mapped with one or more product form behavior product information libraries, described
Behavior product library is the set in all behavior product information libraries；
The total frequency occurred in the behavior product information library that product to be pushed described in determining includes in the behavior product library
Secondary is second frequency；
The product for calculating second frequency and the behavior weighted value obtains the second push index of the product to be pushed.
4. the processing method of product information according to claim 3 push, which is characterized in that the preset rules include:
First push index of product to be pushed and second push the sum of index divided by corresponding Attribute Weight weight values and behavior weighted value it
With.
5. the processing method of product information push according to claim 1, which is characterized in that the product information push
Processing method further include:
Push list is determined according to the comprehensive push index of the product to be pushed, and pushes product to be pushed according to push list
Information.
6. the processing method of product information push according to claim 5, which is characterized in that
Before the comprehensive push index for executing the product to be pushed according to determines push list further include:
Detect whether specified recommended products information；
Judge the instruction of the recommended products information whether from the designated user with administration authority；
When recommended products information meets condition, the comprehensive push index of the recommended products information is arranged to peak.
7. the processing method of product information push according to claim 3, which is characterized in that the acquisition of the behavior classification
Method includes:
Extract the Feature Words of the historical behavior Trace Data information；
The Feature Words of extraction are matched with preset classification dictionary, to obtain corresponding behavior classification.
8. a kind of processing unit of product information push characterized by comprising
Obtain module；For obtaining the product information of product to be pushed；
Processing module: for calculating the first push of the product to be pushed according to the attribute factor of the product information and user
Index；Meanwhile the second push index of the product to be pushed is calculated according to the product information and the behavior factor of user；
Execution module: determining described wait push according to preset rules according to the first push index and the second push index
The comprehensive push index of product.
9. a kind of computer equipment, including memory and processor, it is stored with computer-readable instruction in the memory, it is described
When computer-readable instruction is executed by the processor, so that the processor executes such as any one of claims 1 to 7 right
It is required that the step of processing method of the product information push.
10. a kind of storage medium for being stored with computer-readable instruction, the computer-readable instruction is handled by one or more
When device executes, so that one or more processors execute the product information as described in any one of claims 1 to 7 claim
The step of processing method of push.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946521.4A CN109242544A (en) | 2018-08-20 | 2018-08-20 | Processing method, device, computer equipment and the storage medium of product information push |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810946521.4A CN109242544A (en) | 2018-08-20 | 2018-08-20 | Processing method, device, computer equipment and the storage medium of product information push |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242544A true CN109242544A (en) | 2019-01-18 |
Family
ID=65071657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810946521.4A Pending CN109242544A (en) | 2018-08-20 | 2018-08-20 | Processing method, device, computer equipment and the storage medium of product information push |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242544A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110290144A (en) * | 2019-07-01 | 2019-09-27 | 深圳市元征科技股份有限公司 | A kind of user right information update method, system, storage medium and electronic equipment |
| CN111143670A (en) * | 2019-12-09 | 2020-05-12 | 中国平安财产保险股份有限公司 | Information determination method and related product |
| CN111581518A (en) * | 2020-05-14 | 2020-08-25 | 北京易数科技有限公司 | Information pushing method and device |
| CN115795172A (en) * | 2023-02-06 | 2023-03-14 | 湖南出头科技有限公司 | Information push drainage system based on big data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
| CN103970753A (en) * | 2013-01-28 | 2014-08-06 | 北大方正集团有限公司 | Pushing method and pushing device for related knowledge |
| CN105956146A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Article information recommending method and device |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| CN106503006A (en) * | 2015-09-07 | 2017-03-15 | 阿里巴巴集团控股有限公司 | The sort method and device of application App neutron applications |
| CN106682013A (en) * | 2015-11-09 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Method and device used for data pushing |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN107729473A (en) * | 2017-10-13 | 2018-02-23 | 东软集团股份有限公司 | Article recommends method and its device |
| CN108256907A (en) * | 2018-01-09 | 2018-07-06 | 北京腾云天下科技有限公司 | A kind of construction method and computing device of customer grouping model |
-
2018
- 2018-08-20 CN CN201810946521.4A patent/CN109242544A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970753A (en) * | 2013-01-28 | 2014-08-06 | 北大方正集团有限公司 | Pushing method and pushing device for related knowledge |
| CN103886090A (en) * | 2014-03-31 | 2014-06-25 | 北京搜狗科技发展有限公司 | Content recommendation method and device based on user favorites |
| CN106503006A (en) * | 2015-09-07 | 2017-03-15 | 阿里巴巴集团控股有限公司 | The sort method and device of application App neutron applications |
| CN106682013A (en) * | 2015-11-09 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Method and device used for data pushing |
| CN105956146A (en) * | 2016-05-12 | 2016-09-21 | 腾讯科技（深圳）有限公司 | Article information recommending method and device |
| CN106251174A (en) * | 2016-07-26 | 2016-12-21 | 北京小米移动软件有限公司 | Information recommendation method and device |
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Merchandise news method for pushing, device, storage medium and server |
| CN107391680A (en) * | 2017-07-24 | 2017-11-24 | 北京京东尚科信息技术有限公司 | Content recommendation method, device and equipment |
| CN107729473A (en) * | 2017-10-13 | 2018-02-23 | 东软集团股份有限公司 | Article recommends method and its device |
| CN108256907A (en) * | 2018-01-09 | 2018-07-06 | 北京腾云天下科技有限公司 | A kind of construction method and computing device of customer grouping model |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110290144A (en) * | 2019-07-01 | 2019-09-27 | 深圳市元征科技股份有限公司 | A kind of user right information update method, system, storage medium and electronic equipment |
| CN110290144B (en) * | 2019-07-01 | 2022-02-25 | 深圳市元征科技股份有限公司 | User authority information updating method, system, storage medium and electronic equipment |
| CN111143670A (en) * | 2019-12-09 | 2020-05-12 | 中国平安财产保险股份有限公司 | Information determination method and related product |
| CN111581518A (en) * | 2020-05-14 | 2020-08-25 | 北京易数科技有限公司 | Information pushing method and device |
| CN115795172A (en) * | 2023-02-06 | 2023-03-14 | 湖南出头科技有限公司 | Information push drainage system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7252969B2 (en) | Target recommendation method and device, storage medium and terminal device | |
| JP6708717B2 (en) | News recommendation method and device | |
| CN109242544A (en) | Processing method, device, computer equipment and the storage medium of product information push | |
| US9449271B2 (en) | Classifying resources using a deep network | |
| WO2020077889A1 (en) | Big data-based information pushing method, apparatus, computer device and storage medium | |
| CN111444428A (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| WO2018040069A1 (en) | Information recommendation system and method | |
| CN102197394A (en) | Digital image retrieval by aggregating search results based on visual annotations | |
| CN113627447B (en) | Label identification method, label identification device, computer equipment, storage medium and program product | |
| US20220261591A1 (en) | Data processing method and apparatus | |
| CN109063000A (en) | Question sentence recommended method, customer service system and computer readable storage medium | |
| CN111125528A (en) | Information recommendation method and device | |
| CN110555753A (en) | recommendation-based ranking control method and device, computer equipment and storage medium | |
| CN110909222A (en) | User portrait establishing method, device, medium and electronic equipment based on clustering | |
| KR102284393B1 (en) | Apparatus and method for recommending learning contents | |
| CN110852785B (en) | User grading method, device and computer readable storage medium | |
| CN111291217B (en) | Content recommendation method, device, electronic equipment and computer readable medium | |
| CN113420166A (en) | Commodity mounting, retrieving, recommending and training processing method and device and electronic equipment | |
| US20220366138A1 (en) | Rule-based machine learning classifier creation and tracking platform for feedback text analysis | |
| CN110019813A (en) | Life insurance case retrieving method, retrieval device, server and readable storage medium storing program for executing | |
| CN110348006A (en) | Generation method, device, computer equipment and its storage medium of problem information | |
| CN113327151A (en) | Commodity object recommendation method and device, computer equipment and storage medium | |
| CN117216393A (en) | Information recommendation method, training method and device of information recommendation model and equipment | |
| CN109391679A (en) | Method, apparatus, computer equipment and the storage medium that information and welfare are sent | |
| CN115760315A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and commodity recommendation 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 |