CN107273538A - Information recommends method, device and server - Google Patents
Information recommends method, device and server Download PDFInfo
- Publication number
- CN107273538A CN107273538A CN201710530877.5A CN201710530877A CN107273538A CN 107273538 A CN107273538 A CN 107273538A CN 201710530877 A CN201710530877 A CN 201710530877A CN 107273538 A CN107273538 A CN 107273538A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- crowd
- colony
- label
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
Abstract
The embodiment of the present invention provides a kind of information and recommends method, device and server, and methods described includes：Recorded according to the corresponding historic user of each information in information set, each user into the first colony recommends information respectively；Information of the exposure frequency less than predetermined threshold value is selected from the information set as recommendation information, each user into the second colony recommends the recommendation information respectively, and respectively each user in the second colony to it is described recommendation information feedback result, update the user record in the corresponding historic user record of each information in the information set and renewal user list, wherein, the user in user and second colony in first colony is that the number of users of the user for possessing new user tag in the user list and second colony is less than the number of users of first colony.Methods described improves the accuracy rate recommended to new user, and further increases the experience of new user.
Description
Technical field
The present invention relates to computer application field, method, device and server are recommended in particular to a kind of information.
Background technology
With the fast development of internet, the information that user receives daily starts expansion.Be currently, there are some according to
The method for the information that family oneself behavior over custom is recommended, still, the problem of this mode can not solve new user is right
In a new user, how to recommend information interested to it, as urgent problem to be solved.
The content of the invention
In view of this, the purpose of the embodiment of the present invention is that providing a kind of information recommends method, device and server, to solve
Certainly above mentioned problem.
To achieve these goals, the technical scheme that the embodiment of the present invention is used is as follows：
In a first aspect, recommending method the embodiments of the invention provide a kind of information, methods described includes：According to information set
In each information corresponding historic user record, respectively each user into the first colony recommend information；From the information collection
Information of the exposure frequency less than predetermined threshold value is selected in conjunction as information is recommended, each user into the second colony recommends respectively
The recommendation information, and each user in the second colony, to the feedback result of the recommendation information, updates described respectively
The corresponding historic user of each information records and updated the user record in user list in information set, wherein, described first
The user in user and second colony in colony be the user for possessing new user tag in the user list and
The number of users of second colony is less than the number of users of first colony.
Second aspect, method is recommended the embodiments of the invention provide a kind of information, and methods described includes：According to possessing new use
The corresponding crowd's label of user of family label, the corresponding historic user record of each information, obtains each in inquiry information set
Clicking rate of the information in the crowd for possessing crowd's label；According to crowd's label, and each described information exists
Possess the clicking rate in the crowd of crowd's label, calculate the corresponding click index of each described information；According to each
Index is clicked on, information is recommended to the user for possessing new user tag.
The third aspect, the embodiments of the invention provide a kind of information recommendation apparatus, described device includes：First recommends mould
Block, for being recorded according to the corresponding historic user of each information in information set, each user into the first colony pushes away respectively
Recommend information；Second recommending module, for selecting information of the exposure frequency less than predetermined threshold value from the information set as pushing away
Information is recommended, each user into the second colony recommends the recommendation information respectively, and respectively in the second colony each
User updates the corresponding historic user record of each information in the information set and more to the feedback result of the recommendation information
User record in new user list, wherein, the user in user and second colony in first colony is institute
State the user for possessing new user tag in user list and use of the number of users less than first colony of second colony
Amount.
Fourth aspect, the embodiments of the invention provide a kind of information recommendation apparatus, described device includes：Enquiry module, is used
According to the corresponding crowd's label of user for possessing new user tag, the corresponding historic user of each information in information set is inquired about
Record, obtains clicking rate of each described information in the crowd for possessing crowd's label；Computing module, for according to described
Crowd's label, and clicking rate of each described information in the crowd for possessing crowd's label, calculate each information pair
The click index answered；3rd recommending module, for according to each click index, to the user for possessing new user tag
Recommend information.
5th aspect, the embodiments of the invention provide a kind of server, the server includes memory and processor, institute
State memory and be couple to the processor, the memory store instruction, when executed by the processor so that
Operated below the computing device：According to the corresponding historic user record of each information in information set, respectively to first group
Each user in body recommends information；Information of the exposure frequency less than predetermined threshold value is selected from the information set as recommendation
Information, respectively each user recommendation recommendation information into the second colony, and each use in the second colony respectively
Family updates the corresponding historic user record of each information in the information set and updated to the feedback result of the recommendation information
User record in user list, wherein, the user in user and second colony in first colony is described
The number of users of the user for possessing new user tag and second colony in user list are less than the user of first colony
Number.
6th aspect, the embodiments of the invention provide a kind of server, the server includes memory and processor, institute
State memory and be couple to the processor, the memory store instruction, when executed by the processor so that
Operated below the computing device：According to the corresponding crowd's label of the user for possessing new user tag, in inquiry information set
The corresponding historic user record of each information, obtains click of each described information in the crowd for possessing crowd's label
Rate；According to crowd's label, and clicking rate of each described information in the crowd for possessing crowd's label, calculate each
The corresponding click index of the information；According to each click index, recommend to provide to the user for possessing new user tag
News.
Compared with prior art, a kind of information provided in an embodiment of the present invention recommends method, device and server, passes through root
Recorded according to the corresponding historic user of each information in information set, each user into the first colony recommends information respectively；From
Information of the exposure frequency less than predetermined threshold value is selected in the information set as information is recommended, it is each into the second colony respectively
Individual user recommends the recommendation information, and feedback knot of each user in the second colony to the recommendation information respectively
Really, the user record in the corresponding historic user record of each information in the information set and renewal user list is updated, its
In, the user in user and second colony in first colony is to possess new user's mark in the user list
The number of users of the user of label and second colony is less than the number of users of first colony, and this programme is by using " exploration is pushed away
Recommend " mode recommend information to the new user of fraction, and high-quality information is found according to the feedback of this certain customers, while basis
In information set the corresponding historic user of each information record recommend to have verified that to most of new user be high-quality information, carry
The high accuracy rate recommended to new user, and further increase the experience of new user.
A kind of information provided in an embodiment of the present invention recommends method, device and server, and possessing new user by basis marks
The corresponding crowd's label of user of label, the corresponding historic user record of each information, is obtained described in each in inquiry information set
Clicking rate of the information in the crowd for possessing crowd's label；According to crowd's label, and each described information is possessing
Clicking rate in the crowd of crowd's label, calculates the corresponding click index of each described information；According to each click
Index, information is recommended to the user for possessing new user tag, and this programme passes through according to each information correspondence in information set
Other historic users record to new user recommend have verified that be high-quality information, improve to new user recommend it is accurate
Rate, and further increase the experience of new user.
To enable the above objects, features and advantages of the present invention to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be attached to what is used required in embodiment
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore is not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the schematic diagram that a kind of server provided in an embodiment of the present invention is interacted with user terminal.
Fig. 2 is a kind of structured flowchart of server provided in an embodiment of the present invention.
Fig. 3 is the flow chart that a kind of information that first embodiment of the invention is provided recommends method.
Fig. 4 is the Part I flow chart that a kind of information that first embodiment of the invention is provided recommends method.
Fig. 5 is the Part II flow chart that a kind of information that first embodiment of the invention is provided recommends method.
Fig. 6 is the Part III flow chart that a kind of information that first embodiment of the invention is provided recommends method.
Fig. 7 is the Part IV flow chart that a kind of information that first embodiment of the invention is provided recommends method.
Fig. 8 is the flow chart that a kind of information that second embodiment of the invention is provided recommends method.
Fig. 9 is the partial process view that a kind of information that second embodiment of the invention is provided recommends method.
Figure 10 is a kind of structured flowchart for information recommendation apparatus that third embodiment of the invention is provided.
Figure 11 is a kind of structured flowchart for information recommendation apparatus that fourth embodiment of the invention is provided.
Embodiment
Below in conjunction with accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Generally exist
The component of the embodiment of the present invention described and illustrated in accompanying drawing can be arranged and designed with a variety of configurations herein.Cause
This, the detailed description of the embodiments of the invention to providing in the accompanying drawings is not intended to limit claimed invention below
Scope, but it is merely representative of the selected embodiment of the present invention.Based on embodiments of the invention, those skilled in the art are not doing
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that：Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined in individual accompanying drawing, then it further need not be defined and explained in subsequent accompanying drawing.Meanwhile, the present invention's
In description, term " first ", " the 3rd " etc. are only used for distinguishing description, and it is not intended that indicating or implying relative importance.
Fig. 1 shows the schematic diagram that server 200 provided in an embodiment of the present invention is interacted with user terminal 100.Institute
State server 200 to be communicatively coupled with one or more user terminals 100 by network, to enter row data communication or interaction.
The server 200 can be the webserver, database server etc..The user terminal 100 can be PC
(personal computer, PC), tablet personal computer, smart mobile phone, wearable device etc..
Fig. 2 shows the block diagram for the server 200 that can be applied in the embodiment of the present invention.The server 200
Including memory 201, processor 202 and mixed-media network modules mixed-media 203.
The information that memory 201 can be used in storage software program and module, such as embodiment of the present invention recommend method and
Corresponding programmed instruction/the module of device, processor 202 is stored in software program and module in memory 201 by operation,
So as to perform various function application and data processing, that is, realize that the information in the embodiment of the present invention recommends method.Memory 201
May include high speed random access memory, may also include nonvolatile memory, such as one or more magnetic storage device, flash memory,
Or other non-volatile solid state memories.Further, the software program and module in above-mentioned memory 201 can also be wrapped
Include：Operating system 221 and service module 222.Wherein operating system 221, for example, can be LINUX, UNIX, WINDOWS, it can
Including the various component softwares for management system task (such as memory management, storage device control, power management) and/or
Driving, and can mutually be communicated with various hardware or component software, so as to provide the running environment of other software component.Service module
222 operate on the basis of operating system 221, and are monitored by the network service of operating system 221 come the request of automatic network, root
Corresponding data processing is completed according to request, and returns to result to client.That is, service module 222 is used for visitor
Family end provides network service.
Mixed-media network modules mixed-media 203 is used to receiving and sending network signal.Above-mentioned network signal may include wireless signal or have
Line signal.
It is appreciated that the structure shown in Fig. 2 be only signal, the server 200 may also include it is more more than shown in Fig. 2 or
The less component of person, or with the configuration different from shown in Fig. 2.Each component shown in Fig. 2 can using hardware, software or
It, which is combined, realizes.In addition, the server in the embodiment of the present invention can also include the server of multiple specific difference in functionalitys.
Fig. 3 shows that a kind of information that first embodiment of the invention is provided recommends the flow chart of method, referring to Fig. 3, should
Information recommends method to run in above-mentioned server, and this method includes：
Step S300, is recorded according to the corresponding historic user of each information in information set, respectively into the first colony
Each user recommends information.
The embodiment of information has a lot, for example, Domestic News, video, advertisement, Taobao's connection, video etc..
Further, in the Mobile solution epoch, user more gladly goes some fresh information of understanding by some short-sighted frequencies, because
This, as a kind of embodiment, the information is the short-sighted frequency that playing duration is less than preset duration.Wherein, preset duration can be with
It is configured according to demand, for example, 10 seconds, 30 seconds, one minute etc..
As a kind of embodiment, each the corresponding historic user record of the information includes information identifier, Ren Qunbiao
Exposure frequency, number of clicks and the click of label, the corresponding information of information identifier in the crowd for possessing crowd's label
Rate.
Include the corresponding historic user record of each information in information set, should as a kind of specific embodiment
Information is short-sighted frequency, and the corresponding historic user record of each short-sighted frequency is stored in database in the way of list, specific storage
Mode refers to table 1 below：
Table 1
| Short-sighted frequency identifier | Crowd's label | Exposure frequency | Number of clicks | Clicking rate |
| 12345 | Male | 300 | 60 | 0.2 |
| 12345 | Women | 500 | 50 | 0.1 |
| 67890 | University student | 500 | 150 | 0.3 |
| … | … | … | … |
Every record is together decided on by short-sighted frequency identifier and crowd's label in the table, and every record, which represents the short-sighted frequency, to be known
Alias in exposure frequency of the corresponding short-sighted frequency of the short-sighted frequency identifier in the crowd for possessing crowd's label, click on time
Number and clicking rate.Wherein, clicking rate=number of clicks/impression.
When operation personnel adds a new short-sighted frequency in the short video collection, initialization data is short video identification
Number, the short-sighted frequency identifier is the unique identifier of short-sighted frequency；Crowd's label is the label in the short video collection；Exposure frequency
It is initialized as 0；Number of clicks is initialized as 0；Clicking rate is initialized as 0.
As a kind of embodiment, referring to Fig. 4, step S300 can include：
Step S310, is recorded according to the corresponding historic user of each information in information set, in calculating and the first colony
Each user distinguishes the click index of each corresponding information.
As a kind of specific embodiment, referring to Fig. 5, step S310 can include：
Step S311, obtains crowd's label of each user in first colony respectively.
User in first colony is the user for possessing new user tag in the user list.As a kind of real
Mode is applied, the new user tag is new user tag.That is, the user in the first colony is new user.
Can be by inquiring about user list, to obtain crowd's label of each user in the first colony.
As a kind of embodiment, the user list can be stored in database in the form of a list, specific storage side
Formula refers to table 2 below：
Table 2
| Customer identification number | Crowd's label | New user tag |
| 1 | Male | 1 |
| 1 | University student | 1 |
| 2 | Women | 0 |
| 3 | University student | 1 |
| … | … | … |
Every record is together decided on by customer identification number and crowd's label in the table, and it is the people that every record, which represents the user,
User under group's label, and the whether new user of the user.Wherein, new user tag is 1, and it is new user to represent the user.
Further, the approach that new user tag is obtained has a lot, for example：Obtained and used by the personal log-on message of user
Sex, region, the occupational information at family etc.；Judge whether user is " online game " user by the mounted application of user；With
Recommend a collection of label, the label interested of user's selection to user when family starts product first.
Step S312, respectively according to crowd's label of each user, inquires about each information pair in the information set
The historic user record answered, obtains the clicking rate of each information corresponding with each user.
Illustrated by taking the user 1 in the first colony as an example, the people of user 1 in user list (shown in table 2) is inquired about first
Group's label, crowd's label of user 1 includes：Male and university student.
According to crowd's label of user 1, i.e. male and university student, each information pair in inquiry information set (shown in table 1)
The historic user record answered, obtains the clicking rate of each information corresponding with each user.Possess in inquiry table 1
Crowd's label is male to the clicking rate of each video and to possess crowd's label be clicking rate of the university student to each video.
Step S313, according to crowd's label of each user, and each corresponding described information of each user
Clicking rate, the click index of each each corresponding information of the user is calculated respectively.
As a kind of embodiment, by clicking rate of each described information in the crowd of crowd's label of the user is possessed
It is added, is used as the corresponding click index of each corresponding described information of the user.Specifically, can be counted according to following formula
Calculate：
Wherein, ctrI, tTo possess user tag t clicking rate of the crowd to information i；utU, tRepresent whether user u has
User tag t (0 is expressed as not being that 1 expression is)；eU, iFor click indexes of the user u to information i.
Step S320, according to each click index, each user into first colony recommends information respectively.
As a kind of embodiment, referring to Fig. 6, step S320 can include：
Step S321, respectively will be each according to each corresponding described click index of each user in first colony
Corresponding each information sequence of the user.
For example, for user a, click indexes of the user a to each information is calculated according to formula, according to each information
Click on index and carry out descending sort.
Step S322, is respectively that each user selects and recommended according to the corresponding ranking results of each user
The recommendation information of predetermined number.
Wherein, predetermined number can be configured according to demand.For example, being selected for each user and recommending 100
Recommend information.
Step S400, selects information of the exposure frequency less than predetermined threshold value as recommendation information from the information set,
Each user into the second colony recommends the recommendation information respectively.
Wherein, the user in second colony is the user for possessing new user tag in the user list and institute
The number of users for stating the second colony is less than the number of users of first colony.
First crowd and the second crowd can obtain according to preset rules, as a kind of embodiment, referring to Fig. 7, institute
Stating method also includes：
Step S410, obtains multiple users for possessing new user tag from the user list.
As a kind of embodiment, the new user tag is new user tag.Table 2 is referred to, multiple gather around is obtained from table 2
There is the user of new user tag.
Step S420, is proportionally divided into the first colony and second group by the multiple user for possessing new user tag
Body.
Wherein, ratio can be set according to according to user's request.If being gathered around for example, obtaining 100 from the user list
There is the user of new user tag, 90% user is divided into the first colony, 10% user is divided into the second colony.
Exposure frequency refers to the number of times that information occurred on the user's screen.For example, information goes out on the user's screen
Now cross is once single exposure.
Predetermined threshold value can be configured according to demand.For example, value can be 500, i.e., exposure is selected from information set
Information of the light number of times less than 500 times is as information is recommended, and each user into the second colony recommends the recommendation information respectively.
Step S500, each user in the second colony is to the feedback result of the recommendation information, renewal institute respectively
State the user record in the corresponding historic user record of each information in information set and renewal user list.
As a kind of embodiment, the feedback result include each user in the second colony information and each described in
Whether user clicks on the information of the recommendation information.As a kind of specific embodiment, if information is short-sighted frequency, each user
Feedback data may refer to table 3 below：
Table 3
| Customer identification number | Short-sighted frequency identifier | Expose click data |
| 1 | 11 | 1 |
| 1 | 22 | 0 |
| 2 | 11 | - 1 |
| … | … | … |
Wherein, the value of exposure click data represents that the short-sighted frequency does not expose for -1, and the value of exposure click data is 0 table
Show that the short-sighted frequency has exposed not click on to user but user, the value of exposure click data represents to have exposed short-sighted frequency and use for 1
There is click at family.
The corresponding historic user record of each information in the renewal information set, including：Update the information collection
Information corresponding with the feedback result is in the crowd of crowd's label of each user in possessing second colony in conjunction
Exposure frequency, number of clicks and clicking rate.
As a kind of specific embodiment, it can be updated according to following formula：
(1) exposure frequency shows of the information i in user crowd's label t crowd is updatedI, t
showI, t←showI, t+∑u∈UutU, t*f(is_clickU, i)
Wherein, function f (is_clickU, i) be defined as follows：
Wherein, (is_clickU, i) it is the value that click data is exposed in user feedback result, utU, tRepresent user u whether be
Possess crowd's label t user's (0 is expressed as not being that 1 expression is), showI, tRepresent crowds of the information i in user crowd's label t
In exposure frequency.
(2) number of clicks clicks of the information i in user crowd's label t crowd is updatedI, t
Wherein, g (is_clickU, i) function is defined as follows：
Wherein, is_clickU, iIt is the value of exposure click data in user feedback result, utU, tRepresent whether user u gathers around
There are crowd's label t user's (0 is expressed as not being that 1 expression is), clickI, tRepresent crowds of the information i in user crowd's label t
In number of clicks.
(3) clicking rate ctrs of the information i in user crowd's label t crowd is updatedI, t
Wherein, ctrI, tFor clicking rates of the information i in user crowd's label t crowd, clickI, tRepresent information i with
Number of clicks in family crowd's label t crowd, showI, tRepresent exposures of the information i in user crowd's label t crowd
Number of times.
User record in the renewal user list, including：Update in the user list with the feedback result pair
The new user tag of the user answered.
As a kind of specific embodiment, it can be updated according to following formula：
Wherein, g (is_clickU, i) function is defined as follows：
Wherein, sgn (x) functions are defined as follows：
Wherein, I represents information set；is_new_useruIt is that (1, which represents new, uses for the value of new user tag in user list
Family, 0 represents it is not new user)；is_clickU, iIt is the value of exposure click data in user feedback result.
Information provided in an embodiment of the present invention recommends method, by being used according to the corresponding history of each information in information set
Family is recorded, and each user into the first colony recommends information respectively；Exposure frequency is selected from the information set less than pre-
If the information of threshold value is as information is recommended, each user into the second colony recommends the recommendation information, and root respectively respectively
According to feedback result of each user in the second colony to the recommendation information, each information correspondence in the information set is updated
Historic user record and update user list in user record, wherein, the user in first colony and described second
User in colony is that the number of users of the user for possessing new user tag in the user list and second colony is few
In the number of users of first colony, this programme recommends information by using the mode of " sound out and recommend " to the new user of fraction,
And high-quality information is found according to the feedback of this certain customers, while according to the corresponding historic user of each information in information set
Record recommend to have verified that to most of new user be high-quality information, improve the accuracy rate recommended to new user, go forward side by side one
Step improves the experience of new user.
Fig. 8 shows that a kind of information that second embodiment of the invention is provided recommends the flow chart of method, referring to Fig. 8, should
Information recommends method to run in above-mentioned server, and this method includes：
Step S610, according to the corresponding crowd's label of the user for possessing new user tag, each in inquiry information set is provided
Corresponding historic user record is interrogated, clicking rate of each described information in the crowd for possessing crowd's label is obtained.
As a kind of embodiment, the information is the short information that playing duration is less than preset duration.
Step S620, according to crowd's label, and each described information is in the crowd for possessing crowd's label
Clicking rate, calculates the corresponding click index of each described information.
As a kind of embodiment, by clicking rate phase of each described information in the crowd for possessing crowd's label
Plus, it is used as the corresponding click index of each corresponding described information of the user for possessing new user tag.
Step S610 to step S620 embodiment and the implementation of the step S312 to step S313 in a upper embodiment
Mode is similar, and here is omitted.
Step S630, according to each click index, information is recommended to the user for possessing new user tag.
As a kind of embodiment, referring to Fig. 9, step S530 includes：
Step S631, according to each click index, each described information is sorted；
Step S632, according to ranking results, selects and recommends predetermined number to the user for possessing new user tag
Recommend information.
Step S631 to step S632 embodiment and the implementation of the step S321 to step S322 in a upper embodiment
Mode is similar, and here is omitted.
Information provided in an embodiment of the present invention recommends method, by according to the corresponding crowd of user for possessing new user tag
Label, the corresponding historic user record of each information, obtains each described information and is possessing the crowd in inquiry information set
Clicking rate in the crowd of label；According to crowd's label, and each described information is possessing the crowd of crowd's label
In clicking rate, calculate the corresponding click index of each described information；According to each click index, possess new use to described
The user of family label recommends information, this programme by according to the corresponding other historic users of each information in information set record to
New user recommend to have verified that be high-quality information, improve the accuracy rate recommended to new user, and further increase new use
The experience at family.
Referring to Fig. 10, being the high-level schematic functional block diagram for the information recommendation apparatus 700 that third embodiment of the invention is provided.Institute
Stating information recommendation apparatus 700 includes the first recommending module 710, the second recommending module 720.
First recommending module 710, for being recorded according to the corresponding historic user of each information in information set, respectively to the
Each user in one colony recommends information.
As a kind of embodiment, the information is the short-sighted frequency that playing duration is less than preset duration.
As a kind of embodiment, first recommending module 710 is additionally operable to according to each information correspondence in information set
Historic user record, calculate the click index of corresponding with each user difference in the first colony each information；Root
According to click index each described, each user into first colony recommends information respectively.
As a kind of embodiment, first recommending module 710 is additionally operable to obtain every in first colony respectively
Crowd's label of individual user；Respectively according to crowd's label of each user, each information pair in the information set is inquired about
The historic user record answered, obtains the clicking rate of each information corresponding with each user；According to each use
Crowd's label at family, and each clicking rate of each corresponding information of the user, calculate each user couple respectively
The click index for each information answered.
As a kind of embodiment, first recommending module 710 is additionally operable to each information possessing the user
Crowd's label crowd in clicking rate be added, be used as the corresponding click index of each corresponding described information of the user.
As a kind of embodiment, first recommending module 710 is additionally operable to according to each user in first colony
Each corresponding described click index, respectively will each corresponding each information sequence of the user；According to each user
Corresponding ranking results, are respectively that each user selects and recommends the recommendation information of predetermined number.
As a kind of embodiment, described device also includes division module 730, for obtaining many from the user list
The individual user for possessing new user tag；The multiple user for possessing new user tag is proportionally divided into the first colony and
Two colonies.
Second recommending module 720, makees for selecting exposure frequency from the information set less than the information of predetermined threshold value
To recommend information, each user into the second colony recommends the recommendation information respectively, and respectively according in the second colony
Each user updates the corresponding historic user record of each information in the information set to the feedback result of the recommendation information
And the user record in renewal user list, wherein, the use in user and second colony in first colony is per family
First colony is less than for the number of users of the user for possessing new user tag in the user list and second colony
Number of users.
As a kind of embodiment, the feedback result include each user in the second colony information and each described in
Whether user clicks on the information of the recommendation information；The corresponding historic user record of each information include information identifier,
Exposure frequency in the crowd for possessing crowd's label of crowd's label, the corresponding information of information identifier, number of clicks,
And clicking rate；Second recommending module 720, is additionally operable to update information corresponding with the feedback result in the information set
Exposure frequency, number of clicks and clicking rate in the crowd of crowd's label of each user in possessing second colony.
As a kind of embodiment, each user record in the user list includes customer identification number, crowd's label,
And new user tag；Second recommending module 720, is additionally operable to update corresponding with the feedback result in the user list
The new user tag of user.
Each module can be that now, above-mentioned each module can be stored in depositing for server 200 by software code realization above
In reservoir 201.Each module can equally be realized by hardware such as IC chip above.
Figure 11 is referred to, is the high-level schematic functional block diagram for the information recommendation apparatus 800 that fourth embodiment of the invention is provided.Institute
Stating information recommendation apparatus 800 includes enquiry module 810, computing module 820, and the 3rd recommending module 830.
Enquiry module 810, for according to the corresponding crowd's label of user for possessing new user tag, inquiring about in information set
The corresponding historic user record of each information, obtains click of each described information in the crowd for possessing crowd's label
Rate.
As a kind of embodiment, the information is the short-sighted frequency that playing duration is less than preset duration.
Computing module 820, for according to crowd's label, and each described information is possessing the people of crowd's label
Clicking rate in group, calculates the corresponding click index of each described information.
As a kind of embodiment, the computing module 820 is additionally operable to each information possessing crowd's mark
Clicking rate in the crowd of label is added, and is referred to as corresponding corresponding click on of each described information of the user for possessing new user tag
Number.
3rd recommending module 830, for according to each click index, being pushed away to the user for possessing new user tag
Recommend information.
As a kind of embodiment, the 3rd recommending module 830 is additionally operable to according to each click index, will be each
The individual information sequence；According to ranking results, select and recommend pushing away for predetermined number to the user for possessing new user tag
Recommend information.
Each module can be that now, above-mentioned each module can be stored in depositing for server 200 by software code realization above
In reservoir 201.Each module can equally be realized by hardware such as IC chip above.
Fifth embodiment of the invention provides a kind of server, and the server includes memory and processor, described to deposit
Reservoir is couple to the processor, the memory store instruction, when executed by the processor so that described
Operated below computing device：
According to the corresponding historic user record of each information in information set, each user into the first colony pushes away respectively
Recommend information；
Information of the exposure frequency less than predetermined threshold value is selected from the information set as information is recommended, respectively to second
Each user in colony recommends the recommendation information, and respectively each user in the second colony to the recommendation information
Feedback result, update the corresponding historic user record of each information in the information set and update user in user list
Record, wherein, the user in user and second colony in first colony is possessing in the user list
The user of new user tag and number of users of the number of users less than first colony of second colony.
Sixth embodiment of the invention provides a kind of server, and the server includes memory and processor, described to deposit
Reservoir is couple to the processor, the memory store instruction, when executed by the processor so that described
Operated below computing device：
According to the corresponding crowd's label of the user for possessing new user tag, each information is corresponding in inquiry information set goes through
History user record, obtains clicking rate of each described information in the crowd for possessing crowd's label；
According to crowd's label, and clicking rate of each described information in the crowd for possessing crowd's label, meter
Calculate the corresponding click index of each described information；
According to each click index, information is recommended to the user for possessing new user tag.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation be all between difference with other embodiment, each embodiment identical similar part mutually referring to.
The technique effect and preceding method of the information recommendation apparatus that the embodiment of the present invention is provided, its realization principle and generation
Embodiment is identical, to briefly describe, and device embodiment part does not refer to part, refers in corresponding in preceding method embodiment
Hold.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it can also pass through
Other modes are realized.Device embodiment described above is only schematical, for example, flow chart and block diagram in accompanying drawing
Show according to the device of multiple embodiments of the present invention, the architectural framework in the cards of method and computer program product,
Function and operation.At this point, each square frame in flow chart or block diagram can represent the one of a module, program segment or code
Part a, part for the module, program segment or code is used to realize holding for defined logic function comprising one or more
Row instruction.It should also be noted that in some implementations as replacement, the function of being marked in square frame can also with different from
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially be performed substantially in parallel, they are sometimes
It can perform in the opposite order, this is depending on involved function.It is also noted that every in block diagram and/or flow chart
The combination of individual square frame and block diagram and/or the square frame in flow chart, can use the special base for performing defined function or action
Realize, or can be realized with the combination of specialized hardware and computer instruction in the system of hardware.
In addition, each functional module in each embodiment of the invention can integrate to form an independent portion
Point or modules individualism, can also two or more modules be integrated to form an independent part.
If the function is realized using in the form of software function module and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Understood based on such, technical scheme is substantially in other words
The part contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are to cause a computer equipment (can be individual
People's computer, server, or network equipment etc.) perform all or part of step of each of the invention embodiment methods described.
And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access
Memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.Need
It is noted that herein, such as first and 3rd or the like relational terms be used merely to an entity or operation
Made a distinction with another entity or operation, and not necessarily require or imply these entities or exist between operating any this
Actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to nonexcludability
Comprising so that process, method, article or equipment including a series of key elements are not only including those key elements, but also wrap
Include other key elements being not expressly set out, or also include for this process, method, article or equipment intrinsic want
Element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that wanted including described
Also there is other identical element in process, method, article or the equipment of element.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.It should be noted that：Similar label and letter exists
Similar terms is represented in following accompanying drawing, therefore, once being defined in a certain Xiang Yi accompanying drawing, is then not required in subsequent accompanying drawing
It is further defined and explained.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (28)
1. a kind of information recommends method, it is characterised in that methods described includes：
According to the corresponding historic user record of each information in information set, each user recommendation into the first colony respectively is provided
News；
Information of the exposure frequency less than predetermined threshold value is selected from the information set as information is recommended, respectively to the second colony
In each user recommend the recommendation information,
And each user in the second colony, to the feedback result of the recommendation information, is updated in the information set respectively
User record in the corresponding historic user record of each information and renewal user list,
Wherein, the user in first colony and the user in second colony are to possess new in the user list
The number of users of the user of user tag and second colony is less than the number of users of first colony.
2. according to the method described in claim 1, it is characterised in that the corresponding history of each information in the set according to information
User record, respectively each user into the first colony recommend information, including：
According to the corresponding historic user of each information in information set record, calculate right respectively with each user in the first colony
The click index for each information answered；
According to each click index, each user into first colony recommends information respectively.
3. method according to claim 2, it is characterised in that the corresponding history of each information in the set according to information
User record, calculates the click index of each information corresponding with each user difference in the first colony, including：
Crowd's label of each user in first colony is obtained respectively；
Respectively according to crowd's label of each user, the corresponding historic user note of each information in the information set is inquired about
Record, obtains the clicking rate of each information corresponding with each user；
According to crowd's label of each user, and each clicking rate of each corresponding information of the user, respectively
Calculate the click index of each corresponding information of each user.
4. method according to claim 3, it is characterised in that crowd's label of each user of the basis, and often
The clicking rate of each corresponding information of the individual user, calculates each corresponding information of each user respectively
Index is clicked on, including：
Clicking rate of each described information in the crowd of crowd's label of the user is possessed is added, it is corresponding as the user
The corresponding click index of each described information.
5. method according to claim 2, it is characterised in that described according to each click index, respectively to described
Each user in first colony recommends information, including：
It is respectively that each user is corresponding according to each corresponding described click index of each user in first colony
Each information sorts；
It is respectively that each user selects and recommends the recommendation of predetermined number according to the corresponding ranking results of each user
Information.
6. according to the method described in claim 1, it is characterised in that methods described also includes：
Multiple users for possessing new user tag are obtained from the user list；
The multiple user for possessing new user tag is proportionally divided into the first colony and the second colony.
7. according to the method described in claim 1, it is characterised in that the feedback result includes each user in the second colony
Information and each described user whether click on it is described recommendation information information；Each the corresponding historic user of the information is recorded
Including information identifier, crowd's label, the exposure of the corresponding information of information identifier in the crowd for possessing crowd's label
Light number of times, number of clicks and clicking rate,
The corresponding historic user record of each information in the renewal information set, including：
Update each user of information corresponding with the feedback result in second colony is possessed in the information set
Crowd's label crowd in exposure frequency, number of clicks and clicking rate.
8. according to the method described in claim 1, it is characterised in that each user record in the user list includes user
Identifier, crowd's label, and new user tag；
User record in the renewal user list, including：
Update the new user tag of user corresponding with the feedback result in the user list.
9. method according to any one of claim 1 to 8, it is characterised in that the information is that playing duration is less than in advance
If the short-sighted frequency of duration.
10. a kind of information recommends method, it is characterised in that methods described includes：
According to the corresponding crowd's label of the user for possessing new user tag, the corresponding history of each information is used in inquiry information set
Family is recorded, and obtains clicking rate of each described information in the crowd for possessing crowd's label；
According to crowd's label, and clicking rate of each described information in the crowd for possessing crowd's label, calculate each
The corresponding click index of the individual information；
According to each click index, information is recommended to the user for possessing new user tag.
11. method according to claim 10, it is characterised in that described according to crowd's label, and each described money
Clicking rate in the crowd for possessing crowd's label is interrogated, the corresponding click index of each described information is calculated, including：
Clicking rate of each described information in the crowd for possessing crowd's label is added, as possessing new user tag
The corresponding click index of each corresponding described information of user.
12. method according to claim 10, it is characterised in that according to each click index, possess new to described
The user of user tag recommends information, including：
According to each click index, each described information is sorted；
According to ranking results, the recommendation information of predetermined number is selected and recommended to the user for possessing new user tag.
13. the method according to any one of claim 10 to 12, it is characterised in that the information is less than for playing duration
The short-sighted frequency of preset duration.
14. a kind of information recommendation apparatus, it is characterised in that described device includes：
First recommending module, for being recorded according to the corresponding historic user of each information in information set, respectively to the first colony
In each user recommend information；
Second recommending module, is provided for selecting exposure frequency from the information set less than the information of predetermined threshold value as recommendation
News, respectively each user recommendation recommendation information into the second colony, and each user in the second colony respectively
To the feedback result of the recommendation information, update the corresponding historic user record of each information in the information set and update and use
User record in the list of family, wherein, the user in user and second colony in first colony is the use
The number of users of the user for possessing new user tag and second colony in the list of family are less than the number of users of first colony.
15. device according to claim 14, it is characterised in that first recommending module, is additionally operable to according to information collection
The corresponding historic user record of the information of each in conjunction, calculates each described money corresponding with each user difference in the first colony
The click index of news；According to each click index, each user into first colony recommends information respectively.
16. device according to claim 15, it is characterised in that first recommending module, is additionally operable to obtain institute respectively
State crowd's label of each user in the first colony；Respectively according to crowd's label of each user, the information is inquired about
The corresponding historic user record of the information of each in set, obtains the click of each information corresponding with each user
Rate；According to crowd's label of each user, and each clicking rate of each corresponding information of the user, count respectively
Calculate the click index of each corresponding information of each user.
17. device according to claim 16, it is characterised in that first recommending module, is additionally operable to described in each
Clicking rate of the information in the crowd of crowd's label of the user is possessed is added, and is used as each corresponding described information pair of the user
The click index answered.
18. device according to claim 15, it is characterised in that first recommending module, is additionally operable to according to described
Each corresponding described click index of each user in one colony, respectively will each corresponding each information sequence of the user；
It is respectively that each user selects and recommends the recommendation of predetermined number to provide according to the corresponding ranking results of each user
News.
19. device according to claim 14, it is characterised in that described device also includes division module, for from described
Multiple users for possessing new user tag are obtained in user list；By the multiple user for possessing new user tag proportionally
It is divided into the first colony and the second colony.
20. device according to claim 14, it is characterised in that the feedback result includes each use in the second colony
Whether the information at family and each described user click on the information of the recommendation information；Each the corresponding historic user of the information is remembered
Record includes information identifier, crowd's label, the corresponding information of information identifier in the crowd for possessing crowd's label
Exposure frequency, number of clicks and clicking rate；Second recommending module, be additionally operable to update in the information set with it is described anti-
Present exposure frequency, the point in the crowd of crowd's label of the corresponding information of result in each user in possessing second colony
Hit number of times and clicking rate.
21. device according to claim 14, it is characterised in that each user record in the user list includes using
Family identifier, crowd's label, and new user tag；Second recommending module, is additionally operable to update in the user list and institute
State the new user tag of the corresponding user of feedback result.
22. the device according to any one of claim 14 to 22, it is characterised in that the information is less than for playing duration
The short-sighted frequency of preset duration.
23. a kind of information recommendation apparatus, it is characterised in that described device includes：
Enquiry module, for according to the corresponding crowd's label of user for possessing new user tag, each in inquiry information set to be provided
Corresponding historic user record is interrogated, clicking rate of each described information in the crowd for possessing crowd's label is obtained；
Computing module, for according to crowd's label, and each described information is in the crowd for possessing crowd's label
Clicking rate, calculates the corresponding click index of each described information；
3rd recommending module, for according to each click index, information to be recommended to the user for possessing new user tag.
24. device according to claim 23, it is characterised in that the computing module, is additionally operable to each information
Clicking rate in the crowd for possessing crowd's label is added, corresponding described in each as the user for possessing new user tag
The corresponding click index of information.
25. device according to claim 23, it is characterised in that the 3rd recommending module, is additionally operable to according to each institute
Click index is stated, each described information is sorted；According to ranking results, select and pushed away to the user for possessing new user tag
Recommend the recommendation information of predetermined number.
26. the device according to any one of claim 23 to 25, it is characterised in that the information is less than for playing duration
The short-sighted frequency of preset duration.
27. a kind of server, it is characterised in that the server includes memory and processor, the memory is couple to institute
State processor, the memory store instruction, when executed by the processor so that the computing device with
Lower operation：
According to the corresponding historic user record of each information in information set, each user recommendation into the first colony respectively is provided
News；
Information of the exposure frequency less than predetermined threshold value is selected from the information set as information is recommended, respectively to the second colony
In each user recommend the recommendation information, and respectively each user in the second colony to the anti-of the recommendation information
Result is presented, the user for updating the corresponding historic user record of each information in the information set and updating in user list remembers
Record, wherein, the user in user and second colony in first colony is to possess new in the user list
The number of users of the user of user tag and second colony is less than the number of users of first colony.
28. a kind of server, it is characterised in that the server includes memory and processor, the memory is couple to institute
State processor, the memory store instruction, when executed by the processor so that the computing device with
Lower operation：
According to the corresponding crowd's label of the user for possessing new user tag, the corresponding history of each information is used in inquiry information set
Family is recorded, and obtains clicking rate of each described information in the crowd for possessing crowd's label；
According to crowd's label, and clicking rate of each described information in the crowd for possessing crowd's label, calculate each
The corresponding click index of the individual information；
According to each click index, information is recommended to the user for possessing new user tag.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530877.5A CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530877.5A CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107273538A true CN107273538A (en) | 2017-10-20 |
| CN107273538B CN107273538B (en) | 2020-07-07 |
Family
ID=60070468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710530877.5A Active CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107273538B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804577A (en) * | 2018-05-24 | 2018-11-13 | 联通在线信息科技有限公司 | A kind of predictor method of information label interest-degree |
| CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556622A (en) * | 2008-04-11 | 2009-10-14 | 纳珀企业有限责任公司 | Providing expected desirability information prior to sending a recommendation |
| CN103425703A (en) * | 2012-05-25 | 2013-12-04 | 深圳市腾讯计算机***有限公司 | Method and device for processing network information |
| CN104504098A (en) * | 2014-12-29 | 2015-04-08 | 北京奇虎科技有限公司 | Information recommending method and device |
| CN105335509A (en) * | 2015-10-29 | 2016-02-17 | 广州神马移动信息科技有限公司 | Method and device for recommending activity information and server |
| CN106446189A (en) * | 2016-09-29 | 2017-02-22 | 广州艾媒数聚信息咨询股份有限公司 | Message-recommending method and system |
-
2017
- 2017-06-29 CN CN201710530877.5A patent/CN107273538B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556622A (en) * | 2008-04-11 | 2009-10-14 | 纳珀企业有限责任公司 | Providing expected desirability information prior to sending a recommendation |
| CN103425703A (en) * | 2012-05-25 | 2013-12-04 | 深圳市腾讯计算机***有限公司 | Method and device for processing network information |
| CN104504098A (en) * | 2014-12-29 | 2015-04-08 | 北京奇虎科技有限公司 | Information recommending method and device |
| CN105335509A (en) * | 2015-10-29 | 2016-02-17 | 广州神马移动信息科技有限公司 | Method and device for recommending activity information and server |
| CN106446189A (en) * | 2016-09-29 | 2017-02-22 | 广州艾媒数聚信息咨询股份有限公司 | Message-recommending method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804577A (en) * | 2018-05-24 | 2018-11-13 | 联通在线信息科技有限公司 | A kind of predictor method of information label interest-degree |
| CN108804577B (en) * | 2018-05-24 | 2022-11-01 | 联通在线信息科技有限公司 | Method for estimating interest degree of information tag |
| CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
| CN111523050B (en) * | 2020-04-16 | 2023-09-19 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107273538B (en) | 2020-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105960656B (en) | Method and system for creating a data-driven attribution model for assigning an attribution score to a plurality of events | |
| CN107222566A (en) | Information-pushing method, device and server | |
| US10304113B2 (en) | Method and medium for determining whether a target item is related to a candidate affinity item | |
| CA2700030C (en) | Touchpoint customization system | |
| CN102594870B (en) | Cloud computing platform, cloud computing system and service information publishing method for cloud computing system | |
| US8799814B1 (en) | Automated targeting of content components | |
| US8893012B1 (en) | Visual indicator based on relative rating of content item | |
| CN105898209A (en) | Video platform monitoring and analyzing system | |
| CN104035926B (en) | A kind of dispensing of internet information and system | |
| CN107341245A (en) | Data processing method, device and server | |
| CN106503015A (en) | A kind of method for building user's portrait | |
| CN102033883A (en) | Method, device and system for improving data transmission speed of website | |
| CN106504099A (en) | A kind of system for building user's portrait | |
| CN104008184A (en) | Method and device for pushing information | |
| WO2014105622A2 (en) | Selecting an advertisement for a traffic source | |
| CN103164804A (en) | Personalized method and personalized device of information push | |
| CN102332006A (en) | Information push control method and device | |
| JP2014510972A (en) | Determining preference categories based on user access attribute values | |
| CN103678518A (en) | Method and device for adjusting recommendation lists | |
| CN106446189A (en) | Message-recommending method and system | |
| CN111815375B (en) | User portrayal method and device in advertisement putting | |
| CN104239335B (en) | User-specific information acquisition methods and device | |
| KR20180137351A (en) | Item recommendation method and apparatus based on user behavior | |
| CN112150227A (en) | Commodity recommendation method, system, device and medium | |
| CN106919692B (en) | Method and device for pushing message |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200529 Address after: 310051 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 (only for office use) Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |