CN110245999A - Information recommendation method, information display method, device and calculating equipment - Google Patents
Information recommendation method, information display method, device and calculating equipment Download PDFInfo
- Publication number
- CN110245999A CN110245999A CN201810195795.4A CN201810195795A CN110245999A CN 110245999 A CN110245999 A CN 110245999A CN 201810195795 A CN201810195795 A CN 201810195795A CN 110245999 A CN110245999 A CN 110245999A
- Authority
- CN
- China
- Prior art keywords
- content
- user
- evaluation index
- behavior
- recommended
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application provides a kind of information recommendation method, information display method, device and calculates equipment, the described method includes: determining the respective evaluation index of at least one described object based on for user behavior performed by content where at least one object and/or at least one described object;Wherein, the evaluation index is concerned degree to assess object;Based on the evaluation index of each object, recommended is determined from least one described object, and recommend the recommended to user.Technical solution provided by the embodiments of the present application realizes fast and accurately information recommendation.
Description
Technical field
The invention relates to computer application technology more particularly to a kind of information recommendation methods, a kind of information
Display methods, a kind of information recommending apparatus, a kind of information display device and calculating equipment.
Background technique
With the development of internet technology, e-commerce is surging forward, and the transaction realized by internet is growing day by day.?
When carrying out online transaction, transaction system knows the merchandise news of commodity first to decide whether to buy the quotient to user's needs from network
Product.Online transaction system is in addition to that can provide function of search so that user knows merchandise news by the way of keyword search
Except, it can also be provide product information to users with content-form, wherein content can carry for information such as picture, text, videos
Body.
In addition, reducing transaction cost in order to improve user experience, can be combined with the historical transaction record of user to analyze
The commodity of user preference, to recommend the commodity of preference to user.But the historical transaction record of this way of recommendation combination user
It carries out, it is not accurate enough.
Summary of the invention
The embodiment of the present application provides a kind of information recommendation method, information display method, device and calculates equipment, to solve
The not accurate enough technical problem of information recommendation in the prior art.
In a first aspect, providing a kind of information recommendation method in the embodiment of the present application, comprising:
Based on user behavior performed by content where being directed at least one object and/or at least one described object, really
The respective evaluation index of at least one fixed described object;Wherein, the evaluation index is concerned degree to assess object;
Based on the evaluation index of each object, recommended is determined from least one described object, and recommend to user
The recommended.
Second aspect provides a kind of information display method in the embodiment of the present application, comprising:
Show multiple objects;
In response to being directed to the selection operation of the multiple object, at least one object is determined;
Wherein, for user performed by content where at least one at least one object and/or described object
Behavior is to determine the respective evaluation index of at least one described object;The evaluation index is to from least one described object
Middle determining recommended.
The third aspect provides a kind of information recommending apparatus in the embodiment of the present application, comprising:
Index determining module, for based on for content institute where at least one object and/or at least one described object
The user behavior of execution determines the respective evaluation index of at least one described object;Wherein, the evaluation index is to assess pair
Elephant is concerned degree;
Object recommendation module determines from least one described object and recommends for the evaluation index based on each object
Object, and recommend the recommended to user.
Fourth aspect provides a kind of information display device in the embodiment of the present application, a display interface is provided, to show
Multiple objects;
The display interface supports the selection operation for being directed to the multiple object, to determine at least one object;
Wherein, for user performed by content where at least one at least one object and/or described object
Evaluation index of the behavior to each object of determination;The evaluation index is to the true directional user from least one described object
The recommended of recommendation.
In terms of 5th, a kind of calculating equipment, including processing component and memory are provided in the embodiment of the present application;
The memory stores one or more computer instructions;One or more of computer instructions are to described
Processing component, which calls, to be executed;
The processing component is used for:
Based on user behavior performed by content where being directed at least one object and/or at least one described object, really
The respective evaluation index of at least one fixed described object;Wherein, the evaluation index is concerned degree to assess object;
Based on the evaluation index of each object, recommended is determined from least one described object, and recommend to user
The recommended.
In the embodiment of the present application, based on for performed by content where at least one object and/or at least one object
User behavior, determine the respective evaluation index of at least one object;The evaluation index is to assess being concerned for object
Degree;Based on the evaluation index of each object, recommended is determined from least one object, and push away to described in user's recommendation
Recommend object.Namely combine for user behavior performed by content and/or object, it can be found that the object of user preference, thus
It can precisely be recommended to user, realize fast and accurately information recommendation.
These aspects or other aspects of the application can more straightforward in the following description.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this Shen
Some embodiments please for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 shows the application and provides a kind of flow chart of information recommendation method one embodiment;
Fig. 2 shows the application to provide a kind of flow chart of another embodiment of information recommendation method;
Fig. 3 shows the application and provides a kind of flow chart of another embodiment of information recommendation method;
Fig. 4 shows the application and provides a kind of flow chart of another embodiment of information recommendation method;
Fig. 5 shows the application and provides a kind of flow chart of information display method one embodiment;
Fig. 6 shows the application and provides a kind of structural schematic diagram of information recommending apparatus one embodiment;
Fig. 7 shows the application and provides a kind of structural schematic diagram of another embodiment of information recommending apparatus;
Fig. 8 shows the application and provides a kind of structural schematic diagram of another embodiment of information recommending apparatus;
Fig. 9 shows a kind of structural schematic diagram for calculating equipment one embodiment provided by the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described.
In some processes of the description in the description and claims of this application and above-mentioned attached drawing, contain according to
Multiple operations that particular order occurs, but it should be clearly understood that these operations can not be what appears in this article suitable according to its
Sequence is executed or is executed parallel, and serial number of operation such as 101,102 etc. is only used for distinguishing each different operation, serial number
It itself does not represent and any executes sequence.In addition, these processes may include more or fewer operations, and these operations can
To execute or execute parallel in order.It should be noted that the description such as " first " herein, " second ", is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, does not also limit " first " and " second " and be different type.
The technical solution of the application can be applied in online transaction scene, naturally it is also possible to suitable for carrying out letter with content
Breath is shown, needs to carry out in the various scenes of information recommendation.
By taking online transaction scene as an example, with the development of information age, it is flat that content marketing becomes current major online transaction
The main way of platform, causes user that the plenty of time has been spent in content information, so that also big batch stream is irrigated into content
In, influence of the content to user is gradually incremented by.Content information how to be made full use of to be conducive to the progress of online transaction, improves and uses
Family experience also becomes the following main problem faced.
And when due to carrying out commercial product recommending in the prior art, in order to improve user experience, it will usually according to user preference needle
Property is recommended, to improve recommendation effect.And at present be analyzed in conjunction with the historical transaction record of user obtain user it is inclined
Good commodity, but the commodity of user preference that this mode obtains often compare lag, can only there is transaction record Shi Caike
To obtain, and a possibility that commodity bought of user are usually bought again, is also smaller, causes to recommend also not accurate enough.
The plenty of time has been spent in content in view of current user, the big batch stream of online trade platform also irrigated into
In content, trade link is elongated, therefore user can characterize its consumption propensity for user behavior performed by content, mention accordingly
The technical solution of the application is gone out.
In the embodiment of the present application, based on for user's row performed by content where each object and/or each object
To determine the evaluation index of each object;The evaluation index is concerned degree to assess object;Based on each object
Evaluation index determines recommended, and recommends the recommended to user.Namely it combines for performed by content and/or object
User behavior, it can be found that the object of user preference, so as to precisely be recommended to user, it is quick, accurate to realize
Information recommendation.
When the embodiment of the present application is applied in online transaction scene, object namely the commodity shown in the content.
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, those skilled in the art's every other implementation obtained without creative efforts
Example, shall fall in the protection scope of this application.
Fig. 1 is a kind of flow chart of information recommendation method one embodiment provided by the embodiments of the present application, and this method can be with
Including the following steps:
101: based on for user's row performed by content where at least one object and/or at least one described object
To determine the respective evaluation index of at least one described object.
Wherein, the evaluation index is concerned degree to assess object.This is concerned degree and can also indicate to use
Family is to the preference of the object or the object to the influence degree etc. of user.
Step 101, which that is to say, to be based on being held for content where each object at least one object and/or each object
Capable user determines the evaluation index of each object at least one object
Optionally, several objects which can refer to all objects or be determined based on actual demand.
It is alternatively possible to be based on for use performed by content where at least one object and at least one object
Family behavior determines the evaluation index of each object
Object is information shown in content, the information carriers such as content typically text, picture, video.Online
In scene of trading, object can specifically refer to commodity, and content can be businessman or other content publishers provide and issue
In online transaction system, so that user checks.
In practical applications, multiple content channel can be divided into, visitor is passed through according to the object type etc. of object in content
Family end can show different content channel to user, and corresponding content is exported in different content channel.Each interior
Multiple contents can be exported by holding in channel, and each content can correspond to one or more objects, and each object is likely to be present in
In multiple contents.
Wherein, each content of output, user can read it, comment on, forward, collect, thumb up etc., to every
Object user in one content can collect, trade, being added and buy inventory etc..
Therefore, the user behavior for each object for example may include: access, collection, transaction and add purchase etc., for every
The user behavior of a content for example may include: access, reading, comment, forwarding, collect, thumbs up.
By analyzing for where the user behavior, and/or each object of each content object at least one object
The user behavior of content, it can obtain user to the degree of concern of object, such as the number of visiting people or access times it is more
Object, show the object is concerned that degree is higher namely it is higher by user's favorable rating and influenced journey to user
It spends bigger.It therefore, can be based on the user behavior for content where object or object, by the quilt of object in the present embodiment
Degree of concern is quantified as evaluation index, is concerned degree to assess object.
102: the evaluation index based on each object determines recommended from least one described object, and to user
Recommend the recommended.
Wherein, recommend the recommended to can be to all registration users to user to recommend the recommended, certainly may be used
To be to select user to be promoted etc. from all registration users, the recommended only is promoted to user to be promoted, optionally, by
Be in recommended obtained based on the user behavior for interior perhaps object, therefore can will at least one object and/
Or content where at least one object executes the content user of user behavior as user to be promoted.
Since the evaluation index of each object can indicate that it is concerned degree, it is higher to be concerned degree, shows the object
More welcome, the influence to user is bigger, and user is interested in it, therefore the evaluation index based on each object, can be with
The higher object of degree will be concerned as recommended and recommend user, fast and accurately information pushes away so as to realize
It recommends.
By above description it is found that if there is multiple content channel, multiple contents can be exported in each content channel,
Each content can correspond to one or more objects, and each object can reside in multiple contents.
In certain embodiments, based on for performed by content where at least one object and/or at least one object
User behavior, determine that the respective evaluation index of at least one object may include:
Based in any content channel, for content institute where at least one object and/or at least one described object
The user behavior of execution determines that at least one described object respectively corresponds to the evaluation index of any content channel;
It that is to say and be based in any content channel, for each object and/or each object at least one object
User behavior performed by the content of place determines that each object at least one described object corresponds to any content channel
Evaluation index.
Wherein, which can be selects from corresponding object in any content channel, is also possible to
It is selected from the corresponding object of all the elements channel.
Wherein, to that is to say in any one content channel that there are this right for content where each object at least one object
The content of elephant.
Since an object may occur in the content in multiple content channel, can calculate acquisition this at least one
A object respectively corresponds to the evaluation index of different content channel.
The evaluation index based on each object determines recommended from least one described object, and to user
The recommended is recommended to may include:
Determine at least one content channel;
Each content at least one described content channel is respectively corresponded based on each object at least one described object
The evaluation index of channel determines the overall target of corresponding at least one content channel of each object;
Based on the overall target of each object, recommended is determined from least one described object, and recommend to user
The recommended.
Wherein, if there is no appointing at least one corresponding described content channel for any object at least one object
When the evaluation index of one content channel, then it is sky that any object, which corresponds to the evaluation index of any one content channel, can
To be set as 0.
Wherein, which can determine that recommended requirements can be according to reality according to current recommended requirements
Using determination, optionally, which can carry object type, so that at least one content channel is the object class
The corresponding content channel of type;
Wherein, the evaluation index that each object at least one described object respectively corresponds each content channel that is to say
Based in each content channel, for user performed by each object at least one described object and/or each object
Behavior and determination.
Optionally, which can carry content channel mark, may thereby determine that content channel mark is corresponding
At least one content channel.
If only including a content channel, overall target that is to say that object corresponds to the assessment of a content channel and refers to
Mark.
If, can be right respectively by each object according to the weight coefficient of different content channel including multiple content channel
The evaluation index for answering multiple content channel, be weighted summation perhaps weighted average etc. by weighted sum value or weighted average
Value corresponds to the overall target of multiple content channel as each object.
In the embodiment of the present application, recommending the recommended to user, there are many possible implementations, such as can incite somebody to action
The relevant information of recommended is sent to corresponding user equipment of user etc..
In a practical application, by taking online transaction scene as an example, online trade platform can release various promotion business to quotient
Product are promoted, and improve the exposure rate of commodity in different ways.For example, carrying out the promotion business of product promotion in a manner of purchasing by group
In, it is preferential that user can both obtain purchase, while can also be improved commodity or the exposure rate of businessman etc..
If product promotion can be carried out in conjunction with user preferences in these promotion business, quotient will be can be further improved
Product exposure rate improves number of transaction, improves promotion effect.
Therefore a kind of possible implementation, another embodiment of information recommendation method as shown in Figure 2, this method are used as
May include:
201: based on for user behavior performed by content where at least one object and/or at least one object,
Determine the respective evaluation index of at least one object.
Wherein, the evaluation index is concerned degree to assess object.
Optionally, it that is to say for content execution where each object and/or each object at least one object
User behavior determines the evaluation index of each object at least one object.
At least one object can be all objects or several objects determine according to actual needs.
202: the content where at least one object and/or at least one object executes the content of user behavior
In user, target user is determined.
Namely the content where for each object and/or each object at least one object executes user behavior
Content user in, determine target user.
In the present embodiment, description is distinguished for convenience, will be directed to including at least one object and/or at least one object institute
The user for holding execution user behavior is known as " content user ".
Alternatively, content user can be regard as target user.
As another optional way, due to the behavior type and behavior frequency of the user behavior that different content user executes
Rate is different, content user can be divided into multiple grades accordingly.It can be according to the user behavior that each content user executes
Behavior type and behavior frequency, determine the user gradation of each content user.It therefore can be according to the user to promotion business
Class requirement determines the target user for meeting class requirement from content user.Such as user behavior is executed only for content
Content user grade is lower, and the content user for being performed both by user behavior for the object in content and content is higher ranked;Needle
To the same user behavior of the same content, behavior frequency is higher, and user gradation is higher etc..
In addition, the object type that different content is shown is different, and different content users also have different user tags, example
Such as, in online transaction scene, object type for example may include women's dress, men's clothing, electronics, household etc., and user tag can be with
For the pre-set object type of user or according to customer transaction record in the object type that determines of object, such as can wrap
Include electronics, clothes, furniture etc..Therefore content user can also be determined according to the matching degree of user tag and object type
User gradation, for example, user tag and object type matching degree it is higher, user gradation namely higher.
In addition, can establish content user and object according to the content that the user behavior that each content user executes is directed to
Corresponding relationship, object corresponding with content user that is to say that content user performs user behavior for it or for its institute
The object of user behavior is performed in content.
After obtaining target user, the corresponding relationship of target user and object can be also obtained.
203: determining and belong to any active ues of the target user in group to enlivening for promotion business.
Wherein, it may include multiple users that this, which is enlivened in group,.This enlivens group and can be by participating in being somebody's turn to do to promotion business
Consumption user constitute.In online transaction scene, participate in the promotion business for example and can refer to have purchased the industry to be promoted
The commodity that business is promoted.
In addition, optionally, enlivening group can be by participating in the consumption user for waiting for promotion business in order to improve accuracy
In, participate in what number was constituted greater than the consumption user of preset times.
It is distinguished in order to facilitate description, the target user enlivened in group is known as any active ues.
204: the corresponding relationship based on different target user from different objects determines institute from least one described object
State the corresponding object of any active ues.
205: the evaluation index based on each object determines recommended from the corresponding object of any active ues.
Wherein it is possible to promote demand in conjunction with the object to promotion business, determine that evaluation index meets the object and promotes demand
Recommended.Difference promotes demand to the object of promotion business can be different.
The recommended is the higher object of any active ues degree of concern.
206: by the corresponding target user of the recommended be added to it is described enliven group, obtain core population.
Since recommended not only corresponds to any active ues, the corresponding relationship based on different target user from different objects,
The corresponding all target users of the recommended can also be obtained, and can add it to and enliven in group, obtain core group
Body.
207: the popularization user to promotion business is screened from the core population.
208: described to promote the recommended to the popularization user in promotion business, being recommended with realizing to user
The purpose of the recommended.
Since the user group that different promotion business face is different, for example some promotion business are primarily adapted for use in youth and use
Family carries out object popularization, and some promotion business are mainly suitable for carrying out object popularization etc. towards old user.
Therefore, can be screened from core population, optionally can according to the target orientation range to promotion business,
The popularization user for meeting the target orientation range is determined from core population, which for example can be an age
Range etc..
Screening puts it over after user, and executing should be when promotion business, it can to described in popularization user popularization
Recommended.
In the present embodiment, the object promoted in promotion business, the recommendation pair determined for object-based evaluation index
As, therefore fast and accurately information recommendation had both been realized, while improving the promotion effect to promotion business, in promotion business
The recommended of popularization is to promote the higher object of user's degree of concern, therefore customer transaction wish is stronger, so as to mention
Trading volume of the height to promotion business.
Wherein, if there is multiple content channel, as another possible implementation:
The evaluation index based on each object determines recommended from least one described object, and to user
The recommended is recommended to may include:
It determines at least one corresponding content channel of promotion business;
It determines at least one described content channel, each object at least one object and/or each
Content executes the content user of user behavior where object;
The selection target user from least one described content channel corresponding content user;
It determines and belongs to any active ues of the target user in group to enlivening for promotion business;
Corresponding relationship based on different target user from the different objects at least one described content channel, from it is described to
The corresponding object of any active ues is determined in a few object;
The assessment for respectively corresponding at least one content channel based on each object at least one described object refers to
Mark determines the overall target of corresponding at least one content channel of each object;
Based on the overall target of each object, recommended is determined from the corresponding object of any active ues;
By the corresponding target user of the recommended be added to it is described enliven group, obtain core population;
The popularization user to promotion business is screened from the core population;
Described to promote the recommended to the popularization user in promotion business.
Wherein, the assessment that each object at least one described object respectively corresponds at least one content channel refers to
Mark can determine as follows:
Based in each content channel of at least one content channel, for every at least one described object
User behavior performed by content where a object and/or each object, determines that each object corresponds to commenting for each content channel
Estimate index;
It is respectively corresponded based on each object at least one described object each interior at least one described content channel
The evaluation index for holding channel determines the overall target of corresponding at least one content channel of each object.
In addition, as another possible implementation, the evaluation index based on each object, from described at least one
Recommended is determined in a object, and may include: to user's recommendation recommended
The content where at least one described object and/or at least one described object executes the content of user behavior
In user, target user is determined;
Will at least one described object, evaluation index meet the object for promoting demand to the object of promotion business be used as to
Promote object;
It determines and belongs to any active ues of content user in group to enlivening for promotion business;
Corresponding relationship based on different target user from different objects to be promoted, from described wait promote in object described in determination
The corresponding recommended of any active ues;
By the corresponding target user of the recommended be added to it is described enliven group, obtain core population;
The popularization user to promotion business is screened from the core population;
Described to recommend the recommended in promotion business.
Also demand can be promoted according to the object to promotion business first, determination obtains object to be promoted, then from wait push away
The corresponding recommendation of any active ues is directly determined in wide object.
It is all with can look into per family for the commodity that some promotion business are promoted in addition, still by taking online transaction scene as an example
It sees and can request to trade etc., such as carry out the promotion business of product promotion in the form of purchasing by group, but due to different popularizations
The target orientation range of business is different, and the commodity that promotion business is promoted also serve primarily in its corresponding use of target orientation range
Family, if it will be seen that the hobby of the corresponding user of its target orientation range, in conjunction with user preferences come can if carrying out product promotion
To improve commodity exposure rate, the promotion effect of promotion business is improved.Therefore it is used as another possible implementation, such as Fig. 3 institute
Another embodiment of the information recommendation method shown, this method may include:
301: based on for user performed by content where at least one described object and/or at least one described object
Behavior determines the respective evaluation index of at least one described object.
Wherein, the evaluation index is concerned degree to assess object.
302: the content where at least one described object and/or at least one described object executes user behavior
In content user, target user is determined.
Namely content where each object and/or each object from least one described object executes user's row
For content user in, determine target user.
Wherein, the selection of target user may refer to described in above-described embodiment, and details are not described herein.
303: determining to promotion business wait promote the core customer for belonging to target user in group.
Optionally, should group be promoted can by promotion business enliven group and target group are constituted.
The determination for enlivening group may refer to described in above-described embodiment, and details are not described herein.
It can be in target group and be made of the registration user for meeting the target orientation range to promotion business.
In addition, description is distinguished for convenience, the target user wait promote in group is known as any active ues.
304: the corresponding relationship based on different target user from different objects, from least one described object described in determination
The corresponding object of core customer.
305: the evaluation index based on each object determines recommended from the corresponding object of the core customer.
It is alternatively possible to promote demand in conjunction with the object to promotion business, determine that evaluation index meets the object and promotes need
The recommended asked.Difference promotes demand to the object of promotion business can be different.
Wherein, recommended is the higher object of core customer's degree of concern.
306: described to promote the recommended in promotion business, to realize the mesh for recommending the recommended to user
's.
After obtaining recommended, executing should be to promotion business, it can promotes the recommended, such as can trigger visitor
Wait for that the corresponding business channels of promotion business export the relevant information etc. of the recommended at this in family end.
In the present embodiment, the object promoted in promotion business is the determination of object-based evaluation index wait push away
The corresponding recommended of core customer of wide business, the core customer namely to the user in promotion business target orientation range,
To both realize fast and accurately information recommendation, while the promotion effect to promotion business is improved, in online transaction scene
In, due to recommended to be concerned degree higher, user's purchase intention can be improved, from can be improved to promotion business
Number of transaction.
Wherein, if there is multiple content channel, as another possible implementation:
The evaluation index based on each object determines recommended, and recommends the recommended can wrap to user
It includes:
It determines at least one corresponding content channel of promotion business;
It determines at least one described content channel, each object at least one object and/or each
Content executes the content user of user behavior where object;
The selection target user from least one described content channel corresponding content user;
It determines to promotion business wait promote the core customer for belonging to target user in group;
Corresponding relationship based on different target user from the different objects at least one described content channel, from it is described to
In a few object, the corresponding object of the core customer is determined;
The assessment for respectively corresponding at least one content channel based on each object at least one described object refers to
Mark determines the overall target of corresponding at least one content channel of each object;
It is corresponding right from the core customer based on the overall target of corresponding at least one content channel of each object
As middle determining recommended;
Described to promote the recommended in promotion business.
Wherein, the assessment that each object at least one described object respectively corresponds at least one content channel refers to
Mark can determine as follows:
Based in each content channel of at least one content channel, for every at least one described object
User behavior performed by content where a object and/or each object, determines that each object corresponds to commenting for each content channel
Estimate index;
It is respectively corresponded based on each object at least one described object each interior at least one described content channel
The evaluation index for holding channel determines the overall target of corresponding at least one content channel of each object.
In said one or multiple embodiments, the evaluation index of each object may include: that object hot value, temperature become
Gesture value and/or at least one flow parameter.
Alternatively, described based at least one if the evaluation index includes object hot value
User behavior performed by content where object and/or at least one described object determines that the evaluation index of each object can be with
Include:
Based on for user behavior performed by content where each object and/or each object at least one object
Behavior weight and behavior frequency, calculate the object hot value for obtaining each object.
The object hot value may act as evaluation index.
It is described based on for each object at least one object and/or each when if there is multiple content channel
User behavior performed by content where object determines that the evaluation index of each object at least one described object can wrap
It includes:
For any content channel, it is based in any content channel, it is right for each of at least one object
As and/or each object where user behavior performed by content behavior weight and behavior frequency, determine described at least one
Each object in a object corresponds to the object hot value of any channel for content.
In the embodiment of the present application, it is alternatively possible to which the behavior type based on user behavior, determines the behavior power of user behavior
Weight, the user behavior for being concerned degree and being affected of object, behavior weight are also higher.Such as " collection " for content
Behavior weight, greater than the behavior weight of " click " for content.
It is alternatively possible to determine the user behavior that content user executes according to the matching degree of user tag and object
The high content user of the object type matching degree of behavior weight, user tag and object, the behavior weight that object is executed
It is high;
It is alternatively possible to according to the matching journey of the object type of the object search of user's search and the object type of object
Degree determines the behavior weight for the user behavior that content user executes.The object type of object search and the object type of object
With the high content user of degree, to the behavior weight height for the user behavior that object executes;Wherein, object search can be according to interior
Hold determining namely user in the historical search record of user and passes through the corresponding object of keyword search.The behavior frequency representation use
Execution number of the family behavior to the object.
Wherein, the behavior weight and row of the different user behavior executed for each object at least one object
For frequency, the first hot value of each object can be obtained;
For the behavior weight and behavior frequency of the different user behavior that content where each object executes, can obtain
Second hot value of each object, namely each object in content can be acted on for the user behavior of content.
It can be using the first hot value of each object or the second hot value as the object hot value of each object;
In order to improve accuracy, it can also be and acquisition object temperature is calculated based on the first hot value and the second hot value
Value.
The object hot value can indicate each object by the influence degree of user behavior, and object hot value is higher, shows
Object to be concerned degree higher.
Assuming that including A, B, C for user behavior performed by any object, the behavior weight of user behavior A is X1, row
It is Y1 for frequency;The behavior weight of user behavior B is X2, and behavior frequency is Y2;The behavior weight of user behavior C is X3, behavior
Frequency is Y3;Then the first hot value can be X1*Y1+X2*Y2+X3*Y3;
Assuming that including D, E, F, the behavior weight of user behavior D for user behavior performed by content where any object
For X4, behavior frequency is Y4;The behavior weight of user behavior E is X5, and behavior frequency is Y5;The behavior weight of user behavior F is
X6, behavior frequency are Y6;Then the first hot value Q1 can be X4*Y4+X5*Y5+X6*Y6;
If based on the behavior weight for user behavior performed by content where each object and each object with
And behavior frequency, the object hot value for obtaining each object is calculated, then object hot value Q2 can be with are as follows: X1*Y1+X2*Y2+
X3*Y3+X4*Y4+X5*Y5+X6*Y6。
It should be noted that above-mentioned be merely illustrative of the possible calculation of object hot value, the application is simultaneously not only limited
Due to this.
Optionally, in addition, since the content publisher of each content may be different, the content of different content publisher publication
It is also different to the influence power of user, therefore the publication grade of content publisher can be determined first, publication higher grade, publication
Content is bigger to the influence power of user, namely the content of publication can introduce more various flow.Therefore, in order to improve object hot value
Accuracy in computation, the behavior weight based on the user behavior executed for content where each object and/or each object
And behavior frequency, the object hot value for calculating each object of acquisition include:
Based on the behavior weight and behavior frequency of the user behavior executed for each object, calculates and obtain the first temperature
Value;
Based on the behavior weight and behavior frequency of the user behavior executed for content where each object, calculates and obtain
Second hot value;
The publication grade of the corresponding content publisher of content where determining each object;
According to first hot value, second hot value and the corresponding grade score value of the publication grade, calculate
Obtain the object hot value of each object.
It, can since the significance level of the first hot value, the second hot value and grade score value to each object is different
With according to the first hot value, the second hot value and the respective weight coefficient of grade score value, by first hot value, described
The weighted average or weighted sum value etc. of two hot values and the grade score value.Calculate the object heat for obtaining each object
Angle value.
Such as assume that the first hot value is expressed as Q1, weight coefficient a, the second hot value is expressed as Q2, its weight system
Number is b, and the grade score value for issuing grade can be expressed as Q3, weight coefficient c, which can be a*Q1+b*
Q2+c*Q3, wherein a can be greater than b and be greater than c.
Wherein, described to be held based on content where being directed to each object and/or each object if including multiple content channel
Capable user behavior determines that the evaluation index of each object may include:
For any one content channel, it is based in any one described content channel, at least one object
The behavior weight and behavior frequency for the user behavior that each object executes, calculate that obtain each object corresponding described in any one
Hold the first hot value of channel;
Behavior weight based on the user behavior executed for content where each object in any one described content channel
And behavior frequency, it calculates and obtains the second hot value that each object corresponds to each and every one any content channel;
Determine the publication grade of the corresponding content publisher of content where each object in any one described content channel;
According to the first hot value of corresponding any one content channel of object each at least one object, the second heat
Angle value and the corresponding grade score value of publication grade, calculate obtain each object at least one object it is corresponding it is described any one
The object hot value of content channel.
In addition, counted for convenience, it is described based on each object being directed at least one object and/or each right
The behavior weight and behavior frequency of the user behavior as performed by the content of place calculate every in acquisition at least one object
The object hot value of a object may include:
Based on for user behavior performed by content where each object and/or each object at least one object
Behavior weight and behavior frequency, calculate the influence power score value for obtaining each object;
According to the influence power score value, at least one described object is ranked up;
Based on ranking results, continuous digital number is set gradually at least one described object;
Using the digital number of each object at least one described object as the object hot value of each object.
Wherein it is possible to be ordered from large to small according to influence power score value, digital number for example can be using Arab
Number 1,2,3,4 ..., influence power score value is bigger, and digital number is bigger.
If to determine recommended based on the evaluation index of each object using object hot value as evaluation index
When, selecting object hot value is greater than the object of first threshold as object, since the object temperature of object is that continuous number is compiled
Number, therefore can also quickly determine the quantity etc. of recommended.
Wherein, if including multiple content channel, it that is to say and be performed both by aforesaid operations for any content channel, first really
Fixed each object corresponds to the influence power score value of any content channel, for any one content channel, according to influence power score value
Its corresponding each object is ranked up;And according to ranking results, continuous digital number is set gradually to each object;It will
The digital number of each object corresponds to the object hot value of any content channel as each object.
It, can be with due to that may be carried out always for the user behavior of interior perhaps object as another optional way
With certain time for an assessment cycle, the object hot value for obtaining each object in each assessment cycle is calculated, by more
The object hot value of a assessment cycle carries out trend prediction, can also predict the object hot value after object.
Therefore described based on for user behavior performed by content where each object and/or each object, it determines every
The evaluation index of a object may include:
In each assessment cycle, including for each object and/or each object at least one object
Hold the behavior weight and behavior frequency of each user behavior executed, calculates and obtain each object at least one object
Object hot value;
It is predicted based on each object in corresponding object hot value of multiple assessment cycles, obtains at least one object
In each object temperature Trend value.
Wherein, object hot value may refer to it is the above.
When wherein, if there is multiple content channel, held based on content where being directed to each object and/or each object
Capable user behavior determines that the evaluation index of each object may include:
It is based in any content channel, for any content channel at least one in each assessment cycle
User behavior performed by content where each object and/or each object in a object, determines at least one object
Each object correspond to the object hot value of any channel for content;
It is predicted based on each object in any content channel in corresponding object hot value of multiple assessment cycles,
Obtain the temperature Trend value that each object corresponds to any content channel.
Therefore, the temperature Trend value and/or each assessment cycle can be calculated to the object hot value obtained as every
The evaluation index of a object.
Optionally, PCA can be used in corresponding object hot value of multiple assessment cycles based on each object
(Principal components analysis, principal component analysis) model or time series models scheduling algorithm predicted,
To obtain temperature Trend value.
It is described based at least one object and/or including an at least slap on the face object institute as another optional way
Hold performed user behavior, determines that the respective evaluation index of at least one object may include:
Based on for user behavior performed by content where at least one object and/or at least one object, determine every
The flow parameter that a object introduces.
Wherein, the flow parameter may act as the evaluation index of object.Flow parameter may include multiple, Ke Yixuan
At least one flow parameter is selected as evaluation index.
If can be directed in any one content channel, including multiple content channel at least one object
User behavior performed by content where each object and/or each object, to determine that each of at least one object is right
As the flow parameter of the introducing of any one corresponding content channel.
In this embodiment, which may include conclusion of the business parameter, outburst parameter, Transformation Parameters, expansion
It dissipates parameter and/or draws new parameter;
Wherein, conclusion of the business parameter can refer to: the object conclusion of the business quantity in the unit time;Wherein, object conclusion of the business quantity refers to
The transaction success quantity of object.
Outburst parameter can refer to: object conclusion of the business quantity of the specific discharge within the unit time;Wherein flow can refer to
The number of users of click on content in certain time.
Transformation Parameters can refer to: the conclusion of the business number of users in specific discharge;Conclusion of the business number of users refers to that transaction is successful
Number of users.
Diffusion parameter can refer to: the content in the unit time reads quantity;
It draws new parameter that can refer to: after each object exports in the content, the new use of the content is clicked in the unit time
Amount amount.
Seen from the above description, the evaluation index of each object may include that object hot value, the temperature of each object become
Gesture value and/or at least one flow parameter.
, can be according to the index request to promotion business in embodiment as shown in Figure 2 or Figure 3, determination assesses any one
The object hot value in period or the temperature Trend value and/or at least one flow parameter are as evaluation index.
Any one assessment cycle can choose a nearest assessment cycle.
It is thereby possible to select each flow parameter of object hot value, temperature Trend value and/or at least one flow parameter
Meeting respectively respectively recommends the object of condition as recommended.
Wherein, the recommendation condition of object hot value for example can be object hot value greater than first threshold;
The recommendation condition of temperature Trend value for example can be temperature Trend value greater than second threshold;
The recommendation condition of each flow parameter for example can be each flow parameter and be in its corresponding first parameter area
It is interior etc..
Wherein, the first threshold, the second threshold and the first parameter area can in conjunction with practical application or combine to
The object of promotion business is promoted demand and is determined.
Wherein, if there is multiple content channel, in certain embodiments, based on each of at least one described object
Object respectively corresponds the evaluation index of each content channel at least one described content channel, determines described in each object correspondence
The overall target of at least one content channel may include:
It is respectively corresponded based on each object at least one described object each interior at least one described content channel
Each evaluation index for holding channel, determines the corresponding overall target of each evaluation index, can also obtain multiple synthesis
Index.Multiple overall target may include the corresponding total hot value of object hot value, the corresponding general trend value of temperature Trend value,
The corresponding total flow parameter of each flow parameter;
Respectively recommend the object of condition as recommended so as to select each overall target to meet.Such as total heat
Angle value is greater than third threshold value, temperature Trend value is greater than the 4th threshold value, each total flow parameter is in its corresponding second parameter
In range etc..
The embodiment of the present application can be applied in online transaction scene in a practical application, and online transaction system is logical
Often it is made of front end and server-side, front end is used to show object to user, and receive various user's requests etc..Server-side can be with
User behavior is recorded, so that information recommendation object can be thus achieved in the user behavior based on server-side record.Front end can for
The browser being placed in electronic equipment or client etc..
Below by taking online transaction scene as an example, technical scheme is described in detail.It is as shown in Figure 4 this Shen
It please the flow chart of information recommendation method another embodiment that provides of embodiment.
In online transaction scene, object namely the commodity shown in the content, for convenience of the differentiation in description, by including
Commodity shown in appearance are known as " content items ", are properly termed as the user that interior perhaps content items execute user behavior " interior
Hold consumer ", in an online transaction system, it will usually provide multiple content channel, these content channel can be according to right
The object type answered is divided, naturally it is also possible to be divided according to other business games.
This method may include following steps:
401: determining in any content channel, for each content items at least one content items and each
User behavior performed by content where content items.
Wherein, the user behavior for each content items for example may include: access, collection, transaction and add purchase etc., needle
User behavior to each content for example may include: access, reading, comment, forwarding, collect, thumbs up.
At least one content items can full content commodity described in the content for all the elements channel, can also be with
It is a part of content items selected from the corresponding full content commodity of all the elements channel.
402: in each assessment cycle, behavior frequency and row based on the corresponding user behavior of any content channel
For weight, determine that each content items correspond to the object hot value of any content channel.
Further, it is also possible to which the publication grade of combined content publisher, calculates and obtains the object hot value.
It wherein, can be according to behavior type, user for the behavior weight of each object or the user behavior of each content
The matching degree of label and object, object type matching degree of the object search of user and object etc. determine.
403: based on each content items multiple assessment cycles correspond to the object hot value of any content channel into
Row prediction, obtains the temperature Trend value that each content items correspond to any content channel.
404: being based on the corresponding user behavior of any content channel, determine that each object corresponds to any content frequency
The flow parameter in road.
Wherein, which may include conclusion of the business parameter, outburst parameter, Transformation Parameters, diffusion parameter and/or draws new ginseng
Number;
In online transaction scene:
Conclusion of the business parameter refers to: the commodity conclusion of the business quantity in the unit time;Wherein, commodity conclusion of the business quantity is to refer to purchase quotient
The quantity of product.
Outburst parameter can refer to: commodity conclusion of the business quantity of the specific discharge within the unit time;Wherein flow can refer to
The number of users of click on content in certain time.
Transformation Parameters can refer to: the conclusion of the business number of users in specific discharge;Conclusion of the business number of users refers to purchase commodity
Number of users.
Diffusion parameter can refer to: the content in the unit time reads quantity;
It draws new parameter that can refer to: after each object exports in the content, the new use of the content is clicked in the unit time
Amount amount.
405: using the object hot value, the temperature Trend value and/or at least one flow parameter as each content
Commodity correspond to the evaluation index of any content channel.
It is alternatively possible to by each of object hot value, the temperature Trend value or at least one flow parameter
Flow parameter corresponds to an evaluation index of each content channel respectively as each object.
406: determining at least one corresponding content channel of promotion business.
407: determining at least one described content channel, for each content at least one described content items
Content executes the content consumer of user behavior where commodity and each content items.
408: the selection target consumer from least one described content channel corresponding content consumer.
409: determine to promotion business enliven belong to target consumer in group enliven consumer.
410: based on different target consumer pass corresponding with the different content commodity at least one described content channel
System, determination is described from least one described content items enlivens the corresponding content items of consumer.
411: at least one described content channel, based on each content items at least one described content items
The same evaluation index 409 of corresponding each content channel determines at least one corresponding described content channel of each content items
Overall target.
Wherein it is possible to according to the index demand to promotion business, selecting object hot value, temperature Trend value and/or at least
Each flow parameter of one flow parameter is as an evaluation index.At least one flow parameter can for conclusion of the business parameter,
Diffusion parameter, Transformation Parameters draw new parameter and break out the one or more of parameter.
If evaluation index includes multiple, it can obtain the corresponding overall target of each evaluation index.
Multiple overall targets of each object can be corresponding each by each object based on the weight coefficient of each content channel
The same evaluation index of a content channel is weighted and averaged or the calculating such as weighted sum obtain.
412: the overall target based on corresponding at least one content channel of each content items, from the active consumption
Recommendations are determined in the corresponding content items of person.
It is alternatively possible to be to select each overall target to meet respectively to recommend the content items of condition as recommendation quotient
Product.
The recommendation condition of each overall target can be combined and be set to promotion business.
413: by the corresponding target consumer of the Recommendations be added to it is described enliven group, obtain core population.
414: the popularization user to promotion business is screened from the core population.
415: described to promote the Recommendations to the popularization user in promotion business.
Since Recommendations are to promote the higher commodity of user's degree of concern, commodity transaction probability can be improved, together
When can also improve user experience.
Through this embodiment, fast and accurately commercial product recommending is realized, user experience is improved, allows user fast
Short-term training is buyer, to reduce transaction cost.
By above description it is found that the respective evaluation index of at least one calculation and object can be directed to.
Wherein, which can refer to all objects described in all the elements, naturally it is also possible to by user
Selection obtains, and therefore, as shown in Figure 5, the embodiment of the present application also provides a kind of information display method, this method may include
Following steps:
501: showing multiple objects.
502: the selection operation in response to being directed to the multiple object determines at least one object.
Wherein, for user performed by content where at least one at least one object and/or described object
Behavior is to determine the respective evaluation index of at least one described object;The evaluation index is to from least one described object
Middle determining recommended.
Determine that the detailed process of recommended may refer to described in above-described embodiment from least one object, herein not
It repeats again.
In certain embodiments, may have much for user behavior performed by each object, it is same for each interior
Holding performed user behavior may have very much, therefore the method can also include:
Show multiple behavior types;
In response to being directed to the selection operation of the multiple behavior type, goal behavior type is determined;The goal behavior class
Type is for determining for user behavior performed by content where at least one described object and/or at least one described object.
Namely use performed by content where at least one object for described in determined and/or at least one described object
Family behavior can be only the corresponding user behavior of goal behavior type.
Further, since there may be multiple content channel, in certain embodiments, the method can also include:
Show multiple content channel;
In response to being directed to the selection operation of the multiple content channel, at least one content channel is determined;
Wherein, the goal behavior type namely be specifically used for from least one described content channel, determine be directed to institute
User behavior performed by content where stating at least one object and/or at least one described object;
It is described at least one described content channel, at least one described object and/or described at least one is right
The user behavior as performed by the content of place is at least one content frequency described at least one object described in determination respectively correspondence
The evaluation index of each content channel in road.
The evaluation index that each content channel is corresponded to based on each object at least one object can calculate synthesis and refer to
Mark, so as to determine recommended based on the overall target of each object.Specific implementation may refer to above-mentioned implementation
Shown in example, details are not described herein.
In addition, in certain embodiments, the method can also include:
Show multiple evaluation index types;
In response to being directed to the selection operation of the multiple evaluation index type, at least one evaluation index type is determined;Institute
Stating at least one evaluation index type includes object temperature Value Types, temperature trend Value Types and/or at least one flow parameter
Type;
Wherein, at least one described evaluation index type namely for based at least one object and/or
User behavior performed by content where at least one described object determines pair of each object at least one described object
As hot value, temperature Trend value and/or at least one flow parameter.
In addition, in certain embodiments, the method can also include:
Show the recommended;
In response to being directed to the selection operation of the recommended, target object is determined;Wherein, the target object be used for
User recommends.
Namely can not be and recommended is directly recommended into user, but selected based on user, it will be in recommended
Target object recommends user.
In addition, in certain embodiments, the method can also include:
Display executes the interior of user behavior for content where at least one described object and/or at least one described object
Hold user;
Response and the selection operation for being directed to the content user, determine target user;Wherein, the recommended be used for
The target user recommends.
Wherein, the target user can be used for promoting user perhaps core customer with to promoting user or core customer
Recommend the recommended.
The selection for promoting user or core customer may refer to described in above-described embodiment, and details are not described herein.
Fig. 6 is a kind of structural schematic diagram of information recommending apparatus one embodiment provided by the embodiments of the present application, the device
May include:
Index determining module 601, for based on for content where at least one object and/or at least one described object
Performed user behavior determines the respective evaluation index of at least one described object;
Wherein, the evaluation index is concerned degree to assess object;
Object recommendation module 602, for the evaluation index based on each object, determination is pushed away from least one described object
Object is recommended, and recommends the recommended to user.
In the present embodiment, since the evaluation index of each object can indicate that it is concerned degree, the degree of being concerned is got over
Height shows that the object is more welcome, and user is interested in it, therefore the evaluation index based on each object, will be concerned journey
Higher object is spent as recommended and recommends user, so as to realize fast and accurately information recommendation.
Since there may be multiple content channel for online transaction system, can be exported in each content channel in multiple
Hold, each content can correspond to one or more objects, and each object can reside in multiple contents.
Therefore, in certain embodiments, the index determining module can be specifically used for
Based in any content channel, held for content where at least one object and/or at least one described object
Capable user behavior determines that at least one described object respectively corresponds to the evaluation index of any content channel;
Wherein, content where each object that is to say that there are the contents of the object in any one content channel.
For any content channel, the evaluation index for obtaining each object can be calculated, and since an object may
Occur in the content in multiple content channel, therefore each object can be obtained by index determining module and respectively correspond difference
The evaluation index of content channel.
The object recommendation module is specifically used for determining at least one content channel;Based on every at least one described object
A object respectively corresponds the evaluation index of each content channel at least one described content channel, determines that each object corresponds to institute
State the overall target of at least one content channel;Based on the overall target of each object, determined from least one described object
Recommended, and recommend the recommended to user.
Wherein, if there is no at least one corresponding described content channel for any object at least one described object
Any content channel evaluation index when, then correspond to any content channel evaluation index be sky, can be set as 0.
In a practical application, by taking online transaction scene as an example, online trade platform can release various promotion business to quotient
Product are promoted, and improve the exposure rate of commodity in different ways.For example, carrying out the promotion business of product promotion in a manner of purchasing by group
In, it is preferential that user can both obtain purchase, while can also be improved commodity or the exposure rate of businessman etc..
If product promotion can be carried out in conjunction with user preferences in these promotion business, quotient will be can be further improved
Product exposure rate improves number of transaction, improves promotion effect.Therefore, as another embodiment, as shown in Figure 7, with Fig. 6 institute
Show embodiment the difference is that, the object recommendation module 602 may include:
First user's determination unit 701, for from least one described object and/or at least one described object institute
In the content user that content executes user behavior, target user is determined;
Second user determination unit 702 belongs to the target user's to enlivening for promotion business for determining in group
Any active ues;
First object determination unit 703, for the corresponding relationship based on different target user from different objects, from it is described to
The corresponding object of any active ues is determined in a few content object;
Second object determination unit, for the evaluation index based on each object, from the corresponding object of any active ues
Middle determining recommended;
First group's determination unit 704 described enlivens group for the corresponding target user of the recommended to be added to
Body obtains core population;
User's screening unit 705, for screening the popularization user to promotion business from the core population;
First recommendation unit 706 is used for described to promote the recommended to the popularization user in promotion business.
In addition, first subscriber unit 701 can be specifically for determining at least one described object and/or described
Content executes the content user of user behavior where at least one object;Based on user's row performed by each content user
For behavior type and behavior frequency, determine the user gradation of each content user;User gradation is met described wait promote
The content user of the class requirement of business is as target user.
In the present embodiment, the object promoted in promotion business, the recommendation pair determined for object-based evaluation index
As, therefore fast and accurately information recommendation had both been realized, while improving the promotion effect to promotion business, in promotion business
The recommended of popularization is to promote the higher object of user's degree of concern, therefore customer transaction wish is stronger, so as to mention
Trading volume of the height to promotion business.
In addition, if there is multiple content channel, the index determining module is specifically used for as another embodiment:
Based in any content channel, at least one described object each object and/or each object institute
User behavior performed by content determines that each object corresponds to the evaluation index of any content channel, so as to obtain
Obtain the evaluation index that each object corresponds to different content channel.
The object recommendation module can be specifically used for:
It determines at least one corresponding content channel of promotion business;
Determine for it is described at least in a content channel, each object at least one object and/
Or content executes the content user of user behavior where each object;
The selection target user from least one described content channel corresponding content user;
It determines and belongs to any active ues of the target user in group to enlivening for promotion business;
Corresponding relationship based on different target user from the different objects at least one described content channel, from it is described to
The corresponding object of any active ues is determined in a few object;
The assessment for respectively corresponding at least one content channel based on each object at least one described object refers to
Mark determines the overall target of corresponding at least one content channel of each object;
It is corresponding right from any active ues based on the overall target of corresponding at least one content channel of each object
As middle determining recommended;
By the corresponding target user of the recommended be added to it is described enliven group, obtain core population;
The popularization user to promotion business is screened from the core population;
Described to promote the recommended to the popularization user in promotion business.
In addition, the object recommendation module can be specifically used for as another embodiment:
In user behavior performed by the content where at least one described object and/or at least one described object
Hold in user, determines target user;
Will at least one described object, evaluation index meet the object for promoting demand to the object of promotion business be used as to
Promote object;
It determines and belongs to any active ues of the content user in group to enlivening for promotion business;
Corresponding relationship based on different target user from different objects to be promoted, from described wait promote in object described in determination
The corresponding recommended of any active ues;
By the corresponding target user of the recommended be added to it is described enliven group, obtain core population;
The popularization user to promotion business is screened from the core population;
Described to recommend the recommended in promotion business.
Also demand can be promoted according to the object to promotion business first, determination obtains user to be promoted, then from wait push away
The corresponding recommendation of any active ues is directly determined in wide object.
It is all with can look into per family for the commodity that some promotion business are promoted in addition, still by taking online transaction scene as an example
It sees and can request to trade etc., such as carry out the promotion business of product promotion in the form of purchasing by group, but due to different popularizations
The target orientation range of business is different, and the commodity that promotion business is promoted also serve primarily in its corresponding use of target orientation range
Family, if it will be seen that the hobby of the corresponding user of its target orientation range, in conjunction with user preferences come can if carrying out product promotion
To improve commodity exposure rate, the promotion effect of promotion business is improved.
Therefore, as another embodiment, as shown in Figure 8, with embodiment illustrated in fig. 6 the difference is that, it is described right
As recommending module 602 may include:
Third user determination unit 801, for from least one described object and/or at least one described object institute
In the content user that content executes user behavior, target user is determined;
Fourth user determination unit 802, for determining to promotion business wait promote the core for belonging to target user in group
Heart user;
Corresponding relationship based on different target user from different objects determines the core from least one described object
The corresponding object of user;
Third object determination unit 803 is corresponding right from the core customer for the evaluation index based on each object
As middle determining recommended;
Second recommendation unit 804, for described to promote the recommended in promotion business.
Optionally, the fourth user determination unit 802 can be specifically used for determining by the enlivening to promotion business
The group to be promoted that group and target group are constituted;It determines described wait promote the core use for belonging to the target user in group
Family.
In addition, the third subscriber unit 801 can be specifically used for determining for where each object and/or each object
The content user of content execution user behavior;Behavior type and behavior based on user behavior performed by each content user
Frequency determines the user gradation of each content user;Determine that user gradation meets the mesh of the class requirement to promotion business
Mark user.
In the present embodiment, the object promoted in promotion business is the determination of object-based evaluation index wait push away
The corresponding recommended of core customer of wide business, the core customer namely to the user in promotion business target orientation range,
To both realize fast and accurately information recommendation, while the promotion effect to promotion business is improved, in online transaction scene
In, due to recommended to be concerned degree higher, user's purchase intention can be improved, from can be improved to promotion business
Number of transaction.
As another embodiment, if there is multiple content channel, the index determining module can be specifically used for:
Based on each object and/or each object place content in any content channel, at least one object
Performed user behavior determines that each object corresponds to the evaluation index of any content channel, it is hereby achieved that described
Each object at least one object corresponds to the evaluation index of different content channel.
The object recommendation module can be specifically used for:
It determines at least one corresponding content channel of promotion business;
It determines at least one described content channel, for each object at least one described object and/or often
Content executes the content user of user behavior where a object;
The selection target user from least one described content channel corresponding content user;
It determines to promotion business wait promote the core customer for belonging to target user in group;
Corresponding relationship based on different target user from the different objects at least one described content channel, from it is described to
The corresponding object of the core customer is determined in a few object;
The evaluation index that at least one content channel is respectively corresponded based on each object, determines that each object corresponds to institute
State the overall target of at least one content channel;
It is corresponding right from the core customer based on the overall target of corresponding at least one content channel of each object
As middle determining recommended;
Described to promote the recommended in promotion business.
In said one or multiple embodiments, the evaluation index of each object may include the object temperature of each object
Value, temperature Trend value and/or at least one flow parameter.
If the evaluation index is object hot value, the index determining module may include:
First index determination unit, for based on each object and/or each object institute being directed at least one object
The behavior weight and behavior frequency of user behavior performed by content calculate and obtain each of at least one described object
The object hot value of object.
It is alternatively possible to be in stipulated time section, based at least one described object each object and/
Or the behavior weight and behavior frequency of user behavior performed by content where each object, calculate at least one described in obtaining
The object hot value of each object in object.
Optionally, if there is multiple content channel, the first index determination unit can be specifically used for:
Based on each object and/or each object place in any content channel, at least one object
The behavior weight and behavior frequency of user behavior performed by content determine each object pair at least one described object
Answer the object hot value of any content channel.
Optionally, the first index determination unit can be specifically used for: based at least one described object
The behavior weight and behavior frequency of user behavior performed by each object calculate and obtain the first hot value;Based on for institute
The behavior weight and behavior frequency of user behavior performed by content where stating each object at least one object calculate
Obtain the second hot value;The publication of the corresponding content publisher of content where determining each object at least one described object
Grade;According to first hot value, second hot value and the corresponding grade score value of the publication grade, calculates and obtain
The object hot value of each object at least one described object.
If there is multiple content channel, then the first index determination unit can be specifically used for: based on any interior
Hold in channel, behavior weight and behavior frequency for user behavior performed by each object at least one described object
Rate calculates and obtains the first hot value;Based in any content channel, for each object institute at least one described object
The behavior weight and behavior frequency of user behavior performed by content calculate and obtain the second hot value;It determines described any
In content channel, the publication grade of the corresponding content publisher of content where each object at least one described object;Root
According to first hot value, second hot value and the corresponding grade score value of the publication grade, calculate described in obtaining extremely
Each object in a few object corresponds to the object hot value of any content channel.
In addition, being counted for convenience, the first index determination unit can be specifically used for:
Based on for user behavior performed by content where each object and/or each object at least one object
Behavior weight and behavior frequency, calculate the influence power score value for obtaining each object at least one described object;According to
At least one described object is ranked up by the influence power score value;Based on ranking results, successively at least one described object
Continuous digital number is set;Using the digital number of each object as the object hot value of each object.
If there is multiple content channel, then the first index determination unit is to be specifically: it is directed to any content channel,
Determine that each object at least one described object corresponds to the influence power score value of any content channel, in any one
Hold channel, is ranked up at least one described object according to influence power score value;And according to ranking results, to it is described at least one
Object sets gradually continuous digital number;Any content channel is corresponded to using the digital number of each object as each object
Object hot value.
If the evaluation index is temperature Trend value, the index determining module may include:
Second index determination unit, in each assessment cycle, each of at least one object to be right based on being directed to
As and/or each object where content execute each user behavior behavior weight and behavior frequency, calculate obtain described in
The object hot value of each object at least one object;It is commented based on each object at least one described object multiple
Estimate period corresponding object hot value to be predicted, obtains the temperature Trend value of each object at least one described object.
Wherein, if there is multiple content channel, the second index determination unit can be specifically used for commenting at each
Estimate the period, be based in any content channel, for where each object and/or each object at least one described object
The behavior weight and behavior frequency of user behavior performed by content determine each object pair at least one described object
Answer the object hot value of any channel for content;
It is predicted based on each object in any content channel in corresponding object hot value of multiple assessment cycles,
Obtain the temperature Trend value that each object corresponds to any content channel.
If the evaluation index is at least one flow parameter, the index determining module may include:
Third index determination unit, for based on each object and/or each object institute being directed at least one object
User behavior performed by content determines the flow parameter that each object at least one described object introduces.
If there is multiple content channel, can be based in any content channel, at least one described object
Each object and/or each object where user behavior performed by content, to determine that each object corresponds to any content
The flow parameter of the introducing of channel.
Optionally, the index determining module may include the first index determination unit, the second index determination unit and/or
Third index determination unit.
If the evaluation index of object may include the object hot value of each object, temperature Trend value and/or at least one
A flow parameter.In certain embodiments, the object recommendation module can be specifically used for selecting the object hot value, described
Each flow parameter of temperature Trend value, and/or at least one flow parameter meets pushing away for corresponding recommendation condition
Object is recommended, and recommends the recommended to user.
Information recommending apparatus described in any of the above-described embodiment can be used for executing information described in any of the above-described embodiment
Recommended method, implementing principle and technical effect repeat no more.It is wherein each for the information recommending apparatus in above-described embodiment
The concrete mode that module, unit execute operation is described in detail in the embodiment of the method, herein will not
Elaborate explanation.
Corresponding with information display method shown in fig. 5, the embodiment of the present application also provides a kind of information display devices, mention
For a display interface, to show multiple objects;
The display interface branch is to the selection operation for being directed to the multiple object, to determine at least one object;
Wherein, for user performed by content where at least one at least one object and/or described object
Evaluation index of the behavior to each object of determination;The evaluation index is to the true directional user from least one described object
The recommended of recommendation.
In addition, the display interface is also used to show multiple behavior types;
The display interface supports the selection operation for being directed to the multiple behavior type, to determine goal behavior type;Institute
State goal behavior type for determine for performed by least one described object and/or at least one described object place content
User behavior.
In addition, the display interface is also used to show multiple content channel;
The display interface supports the selection operation for being directed to the multiple content channel, to determine at least one content frequency
Road;
Wherein, the goal behavior type is specifically used for from least one described content channel, determines for described in extremely
User behavior performed by content where a few object and/or at least one described object;
It is described at least one described content channel, at least one described object and/or described at least one is right
The user behavior as performed by the content of place is at least one content frequency described at least one object described in determination respectively correspondence
The evaluation index of each content channel in road.
In addition, the display interface is also used to show multiple evaluation index types;
The display interface supports the selection operation for being directed to the multiple evaluation index type, to determine at least one assessment
Pointer type;At least one described evaluation index type includes object temperature Value Types, temperature trend Value Types and/or at least one
A flow parameter type;
Wherein, at least one described evaluation index type is used for based at least one object and/or described
User behavior performed by content where at least one object determines the object heat of each object at least one described object
Angle value, temperature Trend value and/or at least one flow parameter.
In addition, the display interface is also used to show the recommended;
The display interface supports the selection operation for being directed to the recommended, to determine target object;Wherein, the mesh
Object is marked to be used to recommend to user.
In addition, the display interface is also used to show at least one described object and/or at least one described object
The content user of place content execution user behavior;
The display interface supports the selection operation for being directed to the content user, to determine target user;Wherein, described to push away
Object is recommended for recommending to the target user.
In a possible design, information recommending apparatus described in any of the above-described embodiment can be implemented as a calculating and set
It is standby.As shown in figure 9, the calculating equipment is to include processing component 901 and memory 902;
The memory 902 stores one or more computer instructions;One or more of computer instructions are to quilt
The processing component 901, which calls, to be executed;
The processing component 901 is used for:
Based on user behavior performed by content where being directed at least one object and/or at least one described object, really
The respective evaluation index of at least one fixed described object;Wherein, the evaluation index is concerned degree to assess object;
Based on the evaluation index of each object, recommended is determined from at least one object, and recommend institute to user
State recommended.
Optionally, which can be used for executing information recommendation method described in any of the above-described embodiment.
Processing component 901 may include that one or more processors carry out computer instructions, to complete above-mentioned method
In all or part of the steps.Certain processing component may be one or more application specific integrated circuit (ASIC), number
Signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
Memory 902 is configured as storing various types of data to support the operation in XX equipment.Memory can be by
Any kind of volatibility or non-volatile memory device or their combination realization, such as static random access memory
(SRAM), electrically erasable programmable read-only memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM) may be programmed
Read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or CD.
Certainly, which necessarily can also include other component, such as input/output interface, communication component etc..
Input/output interface provides interface between processing component and peripheral interface module, and above-mentioned peripheral interface module can
To be output equipment, input equipment etc..
Communication component is configured to facilitate the communication etc. for calculating wired or wireless way between equipment and other equipment.
In addition, the calculating equipment can also include a display component, which provides a display interface, to show
Multiple objects;
The display interface can support the selection operation for the multiple object, so that processing component is in response to being directed to
The selection operation of the multiple object can determine at least one object;And it can continue to execute based on right at least one
As and/or at least one described object where user behavior performed by content, determine that described at least one object is respective comments
The step of estimating index.
The embodiment of the present application also provides a kind of computer readable storage mediums, are stored with computer program, the calculating
The information recommendation method of any of the above-described embodiment may be implemented in machine program when being computer-executed.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that above embodiments are only to illustrate the technical solution of the application, rather than its limitations;Although
The application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (23)
1. a kind of information recommendation method characterized by comprising
Based on for user behavior performed by content where at least one object and/or at least one described object, institute is determined
State the respective evaluation index of at least one object;Wherein, the evaluation index is concerned degree to assess object;
Based on the evaluation index of each object, recommended is determined from least one described object, and to described in user's recommendation
Recommended.
2. the method according to claim 1, wherein the evaluation index determines that step includes:
Based in any content channel, for performed by content where at least one object and/or at least one described object
User behavior determines that at least one described object respectively corresponds to the evaluation index of any content channel.
3. according to the method described in claim 2, it is characterized in that, the evaluation index based on each object, from it is described to
Recommended is determined in a few object, and includes: to user's recommendation recommended
Determine at least one content channel;
Each content frequency at least one described content channel is respectively corresponded based on each object at least one described object
The evaluation index in road determines the overall target of corresponding at least one content channel of each object;
Based on the overall target of each object, recommended is determined from least one described object, and to described in user's recommendation
Recommended.
4. the method according to claim 1, wherein the evaluation index based on each object, from it is described to
Recommended is determined in a few content object, and includes: to user's recommendation recommended
The content where at least one described object and/or at least one described object executes the content user of user behavior
In, determine target user;
It determines and belongs to any active ues of the target user in group to enlivening for promotion business;
Corresponding relationship based on different target user from different objects determines any active ues from least one described object
Corresponding object;
Based on the evaluation index of each object, recommended is determined from the corresponding object of any active ues;
By the corresponding target user of the recommended be added to it is described enliven group, obtain core population;
The popularization user to promotion business is screened from the core population;
Described to promote the recommended to the popularization user in promotion business.
5. the method according to claim 1, wherein the evaluation index based on each object, from it is described to
Recommended is determined in a few object, and includes: to user's recommendation recommended
The content where at least one described object and/or at least one described object executes the content user of user behavior
In, determine target user;
It determines to promotion business wait promote the core customer for belonging to target user in group;
Corresponding relationship based on different target user from different objects determines the core customer from least one described object
Corresponding object;
Based on the evaluation index of each object, recommended is determined from the corresponding object of the core customer;
Described to promote the recommended in promotion business.
6. according to the method described in claim 5, it is characterized in that, the determination belonging to wait promote in group to promotion business
The core customer of content user includes:
It determines by the group to be promoted for enlivening group and target group are constituted to promotion business;
It determines described wait promote the core customer for belonging to the target user in group.
7. method described in claim 4 or 5, which is characterized in that it is described from least one described object and/or it is described to
Content where a few object executes in the content user of user behavior, determines that target user includes:
Determine that the content for executing user behavior for content where at least one described object and/or at least one described object is used
Family;
Behavior type and behavior frequency based on the user behavior that each content user executes, determine the use of each content user
Family grade;
User gradation is met into the content user of the class requirement to promotion business as target user.
8. the method according to claim 1, wherein the evaluation index of each object includes the object of each object
Hot value, temperature Trend value and/or at least one flow parameter.
9. according to the method described in claim 8, it is characterized in that, the evaluation index determines that step includes:
Based on the row for user behavior performed by content where each object and/or each object at least one object
For weight and behavior frequency, the object hot value for obtaining each object at least one described object is calculated.
10. according to the method described in claim 8, it is characterized in that, the evaluation index determines that step includes:
In each assessment cycle, based on for content institute where each object and/or each object at least one object
The behavior weight and behavior frequency of each user behavior executed calculate each object obtained at least one described object
Object hot value;
It is predicted, is obtained in corresponding object hot value of multiple assessment cycles based on each object at least one described object
Obtain the temperature Trend value of each object at least one described object.
11. according to the method described in claim 8, it is characterized in that, the evaluation index determines that step includes:
Based on for user behavior performed by content where at least one object and/or at least one described object, institute is determined
State the flow parameter that each object at least one object introduces.
12. according to the method described in claim 8, it is characterized in that, the evaluation index based on each object, from it is described to
Recommended is determined in a few object, and includes: to user's recommendation recommended
From at least one described object, select the object hot value, the temperature Trend value, and/or it is described at least one
Each flow parameter of flow parameter is all satisfied the recommended of corresponding recommendation condition, and recommends the recommendation to user
Object.
13. according to the method described in claim 9, it is characterized in that, described based on right for each of at least one object
As and/or each object where user behavior performed by content behavior weight and behavior frequency, calculate obtain it is described extremely
The object hot value of each object includes: in a few object
Based on the behavior weight and behavior frequency for user behavior performed by each object at least one described object
Rate calculates and obtains the first hot value;
Based on the behavior weight and behavior frequency for user behavior performed by content where each object, calculates and obtain the
Two hot values;
The publication grade of the corresponding content publisher of content where determining each object;
According to first hot value, second hot value and the corresponding grade score value of the publication grade, calculates and obtain
The object hot value of each object at least one described object.
14. according to the method described in claim 9, it is characterized in that, described based on right for each of at least one object
As and/or each object where user behavior performed by content behavior weight and behavior frequency, calculate obtain it is described extremely
The object hot value of each object in an object includes: less
Based on for user behavior performed by content where each object and/or each object at least one described object
Behavior weight and behavior frequency, calculate the influence power score value for obtaining each object;
According to the influence power score value, at least one described object is ranked up;
Based on ranking results, continuous digital number is set gradually at least one described object;
Using the digital number of each object as the object hot value of each object.
15. a kind of information display method characterized by comprising
Show multiple objects;
In response to being directed to the selection operation of the multiple object, at least one object is determined;
Wherein, for user behavior performed by content where at least one at least one object and/or described object
To determine the respective evaluation index of at least one described object;The evaluation index is to true from least one described object
Determine recommended.
16. according to the method for claim 15, which is characterized in that further include:
Show multiple behavior types;
In response to being directed to the selection operation of the multiple behavior type, goal behavior type is determined;The goal behavior type is used
User behavior performed by the content where determining at least one object for described in and/or at least one described object.
17. according to the method for claim 16, which is characterized in that further include:
Show multiple content channel;
In response to being directed to the selection operation of the multiple content channel, at least one content channel is determined;
Wherein, the goal behavior type is specifically used for from least one described content channel, determines for described at least one
User behavior performed by content where a object and/or at least one described object;
It is described at least one described content channel, at least one described object and/or at least one described object institute
User behavior performed by content is to determine at least one described object respectively at least one corresponding described content channel
Each content channel evaluation index.
18. according to the method for claim 15, which is characterized in that further include:
Show multiple evaluation index types;
In response to being directed to the selection operation of the multiple evaluation index type, at least one evaluation index type is determined;It is described extremely
A few evaluation index type includes object temperature Value Types, temperature trend Value Types and/or at least one flow parameter type;
Wherein, at least one described evaluation index type be used for based on for it is at least one object and/or it is described at least
User behavior performed by content where one object determines the object temperature of each object at least one described object
Value, temperature Trend value and/or at least one flow parameter.
19. according to the method for claim 15, which is characterized in that further include:
Show the recommended;
In response to being directed to the selection operation of the recommended, target object is determined;Wherein, the target object is used for user
Recommend.
20. according to the method for claim 15, which is characterized in that further include:
The content that display executes user behavior for content where at least one described object and/or at least one described object is used
Family;
In response to being directed to the selection operation of the content user, target user is determined;Wherein, the recommended is used for described
Target user recommends.
21. a kind of information recommending apparatus characterized by comprising
Index determining module, for based on for performed by content where at least one object and/or at least one described object
User behavior, determine the respective evaluation index of at least one object;Wherein, the evaluation index is to assess object
It is concerned degree;
Object recommendation module determines recommended for the evaluation index based on each object from least one described object,
And recommend the recommended to user.
22. a kind of information display device, which is characterized in that a display interface is provided, to show multiple objects;
The display interface supports the selection operation for being directed to the multiple object, to determine at least one object;
Wherein, for user behavior performed by content where at least one at least one object and/or described object
Evaluation index to each object of determination;The evaluation index is recommended to directional user true from least one described object
Recommended.
23. a kind of calculating equipment, which is characterized in that including processing component and memory;
The memory stores one or more computer instructions;One or more of computer instructions are to by the processing
Component call executes;
The processing component is used for:
Based on for user behavior performed by content where at least one object and/or at least one described object, institute is determined
State the respective evaluation index of at least one object;Wherein, the evaluation index is concerned degree to assess object;
Based on the evaluation index of each object, recommended is determined from least one described object, and to described in user's recommendation
Recommended.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810195795.4A CN110245999A (en) | 2018-03-09 | 2018-03-09 | Information recommendation method, information display method, device and calculating equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810195795.4A CN110245999A (en) | 2018-03-09 | 2018-03-09 | Information recommendation method, information display method, device and calculating equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110245999A true CN110245999A (en) | 2019-09-17 |
Family
ID=67882770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810195795.4A Pending CN110245999A (en) | 2018-03-09 | 2018-03-09 | Information recommendation method, information display method, device and calculating equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110245999A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111539791A (en) * | 2020-04-26 | 2020-08-14 | 北京三快在线科技有限公司 | Method, device and equipment for processing group bill and storage medium |
CN112884533A (en) * | 2021-04-07 | 2021-06-01 | 上海哔哩哔哩科技有限公司 | Service processing method and device |
CN112883267A (en) * | 2021-02-22 | 2021-06-01 | 深圳市星网储区块链有限公司 | Data heat degree statistical method and device based on deep learning |
CN113377849A (en) * | 2021-05-24 | 2021-09-10 | 上海钧正网络科技有限公司 | Information recommendation method, device and equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140074863A1 (en) * | 2012-09-12 | 2014-03-13 | Flipboard, Inc. | Generating an implied object graph based on user behavior |
CN103841122A (en) * | 2012-11-20 | 2014-06-04 | 阿里巴巴集团控股有限公司 | Target-object information recommending method, server and client |
CN105868332A (en) * | 2016-03-28 | 2016-08-17 | 百度在线网络技术(北京)有限公司 | hot topic recommendation method and device |
CN105912729A (en) * | 2016-05-19 | 2016-08-31 | 华南理工大学 | Three-dimensional time sequence dynamic model based mobile phone game recommendation system |
-
2018
- 2018-03-09 CN CN201810195795.4A patent/CN110245999A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140074863A1 (en) * | 2012-09-12 | 2014-03-13 | Flipboard, Inc. | Generating an implied object graph based on user behavior |
CN103841122A (en) * | 2012-11-20 | 2014-06-04 | 阿里巴巴集团控股有限公司 | Target-object information recommending method, server and client |
CN105868332A (en) * | 2016-03-28 | 2016-08-17 | 百度在线网络技术(北京)有限公司 | hot topic recommendation method and device |
CN105912729A (en) * | 2016-05-19 | 2016-08-31 | 华南理工大学 | Three-dimensional time sequence dynamic model based mobile phone game recommendation system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111539791A (en) * | 2020-04-26 | 2020-08-14 | 北京三快在线科技有限公司 | Method, device and equipment for processing group bill and storage medium |
CN112883267A (en) * | 2021-02-22 | 2021-06-01 | 深圳市星网储区块链有限公司 | Data heat degree statistical method and device based on deep learning |
CN112884533A (en) * | 2021-04-07 | 2021-06-01 | 上海哔哩哔哩科技有限公司 | Service processing method and device |
CN113377849A (en) * | 2021-05-24 | 2021-09-10 | 上海钧正网络科技有限公司 | Information recommendation method, device and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Beladev et al. | Recommender systems for product bundling | |
JP7105700B2 (en) | Time-division recommendation method and apparatus for service target | |
CN103823908B (en) | Content recommendation method and server based on user preference | |
CN110245999A (en) | Information recommendation method, information display method, device and calculating equipment | |
Tongxiao (Catherine) Zhang et al. | The value of IT-enabled retailer learning: personalized product recommendations and customer store loyalty in electronic markets | |
Liang et al. | The informational aspect of the group-buying mechanism | |
CN107360222A (en) | Merchandise news method for pushing, device, storage medium and server | |
CN103140868B (en) | The possibility of applicability is determined based on historical data | |
CN106997358A (en) | Information recommendation method and device | |
Jiang et al. | Online pricing with bundling and coupon discounts | |
CN106980999A (en) | The method and apparatus that a kind of user recommends | |
CN110933472B (en) | Method and device for realizing video recommendation | |
CN110197404A (en) | The personalized long-tail Method of Commodity Recommendation and system of popularity deviation can be reduced | |
CN110969512B (en) | Commodity recommendation method and device based on user purchasing behavior | |
CN113689259A (en) | Commodity personalized recommendation method and system based on user behaviors | |
CN110602532A (en) | Entity article recommendation method, device, server and storage medium | |
CN113689258A (en) | Commodity recommendation heat generation method and system | |
KR102097045B1 (en) | Method and apparatus to recommend products reflecting characteristics of users | |
CN110134783A (en) | Method, apparatus, equipment and the medium of personalized recommendation | |
CN110751537A (en) | Online and offline intelligent marketing method and device | |
CN114880560A (en) | Content recommendation method and device, storage medium and electronic device | |
JP5299199B2 (en) | Product recommendation method and product recommendation system | |
US11216863B2 (en) | System and methods for advanced personalized retail shopping platform | |
CN112950322A (en) | Power retail package recommendation method and system based on collaborative filtering optimization | |
JP5348617B2 (en) | Initial purchaser extraction processing method, initial purchaser recommendation method, initial purchaser extraction system, initial purchaser recommendation system |
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: 20190917 |