CN109299349A - Application recommendation method and device, equipment and computer-readable storage medium - Google Patents
Application recommendation method and device, equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN109299349A CN109299349A CN201811060586.5A CN201811060586A CN109299349A CN 109299349 A CN109299349 A CN 109299349A CN 201811060586 A CN201811060586 A CN 201811060586A CN 109299349 A CN109299349 A CN 109299349A
- Authority
- CN
- China
- Prior art keywords
- application
- recommended
- recommendation
- record
- similarity
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000002349 favourable effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an application recommendation method, an application recommendation device, application recommendation equipment and a computer readable storage medium. The application recommendation method comprises the following steps: obtaining a first application recommendation list; the first application recommendation list comprises a first recommendation degree corresponding to at least one application to be recommended; obtaining a historical recommendation record corresponding to each application to be recommended; each historical recommendation record comprises a first application use record corresponding to at least one recommended user; obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record; and recommending the corresponding application to be recommended to the target user according to each second recommendation degree. By adopting the method and the device, the application recommendation accuracy can be improved.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of application recommended method and device, equipment, computer can
Read storage medium.
Background technique
It is the important component of application shop using recommendation, is one of core function of application shop.In the prior art
In, the application that application shop recommends user is usually all to be had used according to user or application currently in use determines
, specifically, application shop would generally be selected will to have used with user or currently in use be pushed away using similar application
It recommends to user.The judgment criteria as based on this recommended method is single, and the accuracy recommended is not high, and recommendation effect is not
It is good.
Summary of the invention
The embodiment of the present invention proposes a kind of application recommended method and device, equipment, computer readable storage medium, Neng Gouti
Accuracy is recommended in height application.
It is provided in an embodiment of the present invention a kind of using recommended method, it specifically includes:
It obtains first and applies recommendation list;Wherein, it to be recommended is answered in the first application recommendation list comprising at least one
With corresponding first recommendation;
Obtain the corresponding history recommendation record of each application to be recommended;Wherein, in each history recommendation record
User corresponding first is recommended using record comprising at least one;
According to each described first using record, corresponding second recommendation of each application to be recommended is obtained;
According to each second recommendation, recommend corresponding application to be recommended to target user.
Further, described to obtain first using recommendation list, it specifically includes:
Obtain the target user it is corresponding at least one used using and each described use apply corresponding the
Two using record;
According to it is each it is described used application, obtain at least one application to be recommended;
According to each described second using record and it is preset it is each described use application with it is each it is described to
Recommend the application similarity between application, obtains and each described to be recommended apply corresponding first recommendation;
According to each first recommendation, generates described first and apply recommendation list.
Further, described using record and preset each described to have used application according to each described second
With the application similarity between each application to be recommended, corresponding first recommendation of each application to be recommended is obtained,
It specifically includes:
According to each described second using record rui, it is preset it is each described use using i and it is each described in
Recommend using the application similarity w between jijAnd preset first recommendation computation modelCalculating obtains
The corresponding first recommendation P of each application j to be recommendeduj;Wherein, u indicates the target user;N (u) is indicated by owning
The set used using i composition;The S (i, K) indicates by all set to be recommended formed using j.
Further, described according to each described second using record and preset each described using answering
With the application similarity between each application to be recommended, corresponding first recommendation of each application to be recommended is obtained
Before, further includes:
At least one training application and the corresponding third of each training application are obtained using record;
According to each third using record, calculate obtain between training application described in every two using similar
Degree;
According to it is each it is described apply similarity, generate apply similarity set;
Then it is described according to each described second using record and it is preset it is each described use application with it is each
Application similarity between the application to be recommended obtains corresponding first recommendation of each application to be recommended, specific to wrap
It includes:
Inquire the application similarity set, obtain it is each it is described use application between each application to be recommended
Application similarity;
According to described each described second using record and it is each described using application with it is each described wait push away
The application similarity between application is recommended, obtains and each described to be recommended applies corresponding first recommendation.
Further, it is described according to each third using record, calculate and obtain training application described in every two
Between application similarity, specifically include:
Similarity calculation is applied with preset using record according to each thirdCalculate the application similarity w obtained between training application described in every twoij;Wherein, N (i) is indicated
Training is using the corresponding third of i using the total number of record;N (j) indicates training using the corresponding third of j using note
The total number of record.
Further, described according to each described first using record, obtain each application pair to be recommended
Before the second recommendation answered, further includes:
Each recommended user corresponding second is obtained using recommendation list;
Recommendation list is applied according to the first application recommendation list and each described second, the target is obtained respectively and uses
User's similarity between family and each recommended user;
It is described according to each described first using record, obtain each application corresponding second to be recommended and recommend
Degree, specifically includes:
According to each described first using record and each user's similarity, each described to be recommended answer is obtained
With corresponding second recommendation.
Further, it is described according to each described first using record and each user's similarity, obtain every
Corresponding second recommendation of a application to be recommended, specifically includes:
According to each described first using record rvx, each user's similarity wuvRecommend with preset second
Spend computation modelIt calculates and obtains the corresponding second recommendation N of each application to be recommendedux;Its
In, u indicates the target user;V indicates the recommended user;X indicates the application to be recommended;K is all described pushed away
Recommend the total number of user v;A is preset constant.
Correspondingly, recommendation apparatus is applied the embodiment of the invention also provides a kind of, specifically included:
Module is obtained using recommendation list, applies recommendation list for obtaining first;Wherein, column are recommended in first application
Include at least one corresponding first recommendation of application to be recommended in table;
History recommendation record obtains module, for obtaining the corresponding history recommendation record of each application to be recommended;Its
In, comprising at least one recommended user corresponding first using record in each history recommendation record;
Module is obtained using recommendation, for, using record, obtaining each described wait push away according to each described first
It recommends using corresponding second recommendation;And
Using recommending module, for recommending to be recommended accordingly answer to target user according to each second recommendation
With.
The embodiment of the invention also provides a kind of equipment, specifically includes processor, memory and be stored in the storage
In device and it is configured as the computer program executed by the processor, wherein the processor executes the computer program
Shi Shixian applies recommended method as described above.
The embodiment of the invention also provides a kind of computer readable storage mediums, specifically include the computer program of storage,
Wherein, it is executed when the computer program is run and applies recommended method as described above.
The implementation of the embodiments of the present invention has the following beneficial effects:
Application recommended method provided in an embodiment of the present invention and device, equipment, computer readable storage medium, by answering
During with recommendation, speculate target user to each to be recommended the service condition of application to be recommended by using for reference other users
The interest level of application to optimize to using recommendation list, therefore can be improved using the accuracy recommended, reduce
The case where recommending the target user and uninterested application to target user, to optimize using recommendation effect.
Detailed description of the invention
Fig. 1 is the flow diagram of a preferred embodiment provided by the invention using recommended method;
Fig. 2 is the structural schematic diagram of a preferred embodiment provided by the invention using recommendation apparatus;
Fig. 3 is the structural schematic diagram of a preferred embodiment of equipment provided by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, being the flow diagram of a preferred embodiment provided by the invention using recommended method, packet
Step S11 to S14 is included, specific as follows:
S11: it obtains first and applies recommendation list;Wherein, it waits pushing away comprising at least one in the first application recommendation list
It recommends using corresponding first recommendation.
It should be noted that the embodiment of the present invention is by having the system using recommendation function to execute.Wherein, which can be with
For the system in server-side, or the system in other equipment.In order to facilitate narration, following embodiments are to be installed on service
It is illustrated for system in end.
It include the corresponding application identities code of each application to be recommended and the first recommendation in above-mentioned first application recommendation list.
Server-side optimizes the first application recommendation list after recommendation list is applied in acquisition first, according to following step, from
And final application recommendation list is obtained, and corresponding application is recommended to target user according to the final application recommendation list.
In another preferred embodiment, above-mentioned steps S11 further comprises step S1101 to S1104, specifically such as
Under:
S1101: obtain the target user it is corresponding at least one used using and each described use apply pair
Second answered is using record.
It should be noted that above-mentioned be client (hereinafter referred to as " the target visitor for being installed on target user using application
Family end ") in application.Above-mentioned second can access the corresponding number for having used application using record for target user,
Or target user is to the corresponding scoring for having used application, can also be that target user has used application to corresponding
Favorable rating.
Specifically, when target user registers in server-side for the first time, which passes through DPI (Deep Packet
Inspection, deep message detection) mode obtain the data packet in network key node, and by being removed in the data packet
Content other than packet header header is detected and analyzed, obtain the target user destination client identification code and
It is each used application application identities code, application name, application type, using scoring etc..Wherein, application scoring can pass through
Target user is accessed and corresponding acquisition has been normalized using the number of application.In some specific embodiments,
Above-mentioned server-side is the network service end at telecom operation end.
In some specific embodiments, server-side can also be by recording the user behavior stored in destination client
It is analyzed, is applied with corresponding second to obtain corresponding used of target user using record.
S1102: according to it is each it is described used application, obtain at least one application to be recommended.
It should be noted that above-mentioned application to be recommended is pre-stored in server-side.Server-side is obtaining target user couple
Answer it is each used application after, use application for each, has obtained this respectively and be stored in advance with each using applying
Application similarity between local application, and wherein will be greater than preset threshold using similarity or be arranged using similarity
Application in preceding n (n >=1) position is used as above-mentioned application to be recommended.It circuits sequentially, is respectively corresponded using application until acquisition is all
Application to be recommended.
S1103: according to each described second using record and it is preset it is each described use application with it is each
Application similarity between the application to be recommended obtains corresponding first recommendation of each application to be recommended.
Further, above-mentioned steps S1103 further comprises S1103_11, specific as follows:
S1103_11: according to each described second using record rui, it is preset it is each described use using i with often
A application similarity w to be recommended using between jijAnd preset first recommendation computation modelIt calculates and obtains the corresponding first recommendation P of each application j to be recommendeduj;Wherein, u indicates the mesh
Mark user;N (u) is indicated by all described using the set formed using i;The S (i, K) indicates by all described to be recommended
The set formed using j.
It should be noted that N (u) ∩ S (i, K) indicate it is all use apply in it is similar used application, thus
The special applications in destination client are excluded during using recommendation, improve the accuracy that application is recommended.
S1104: it according to each first recommendation, generates described first and applies recommendation list.
It should be noted that server-side is after calculating and obtaining corresponding first recommendation of each application to be recommended, to each
First recommendation is ranked up, so that the first recommendation according to wherein ranking in forefront, which generates first, applies recommendation list.Clothes
End be engaged in after the application recommendation list of generation first, will can also wherein be installed on mesh using record according to above-mentioned second
The application marked in client is deleted, to improve the novelty of the first application recommendation list, is further increased using the standard recommended
Exactness.
S12: the corresponding history recommendation record of each application to be recommended is obtained;Wherein, each history recommends note
Comprising at least one recommended user corresponding first using record in record.
It should be noted that before this, each application to be recommended has been recommended to other users.According to each recommended
User generates corresponding first using record to the service condition of these applications to be recommended, and further generates corresponding
History recommendation record.Wherein, this first using record can be recommended access of the user to corresponding recommended application
Number, or recommended scoring of the user to corresponding recommended application can also be recommended user to corresponding quilt
Recommend the favorable rating of application.
For example, server-side will recommend respectively user a and user b using A, user a does not have after receiving the recommendation
Installation and using this apply A, then record user a to application A access times be 0, and generate content be " 0 " first application make
With record;User b is installed after receiving the recommendation and this is used for multiple times using A, it is assumed that the user b is using this using A's
Number is 4 times, then recording user b is 4 to the access times of application A, and generating content is " 4 " first using record.
Finally, composition is answered according to first that the content is " 0 " using first that record and the content are " 4 " using record
With the corresponding history recommendation record of A.
S13: it according to each described first using record, obtains each application corresponding second to be recommended and recommends
Degree.
It in yet another preferred embodiment, further include step S01 to S02 before above-mentioned steps S13, specific as follows:
S01: it obtains each recommended user corresponding second and applies recommendation list.
It should be noted that after obtaining corresponding recommended user list according to above-mentioned history recommendation record, according to
The recommended user list, obtain each recommended user second apply recommendation list.Wherein, this second apply recommendation list
For the list of the previous application recommended to recommended user.
S02: recommendation list is applied according to the first application recommendation list and each described second, obtains the mesh respectively
Mark user's similarity between user and each recommended user.
It should be noted that user's similarity can recommend column with the second application by calculating the first application recommendation list
Similarity between table determines, can also be answered by calculating the first application recommendation list and second using identical between recommendation list
Number determines.
Above-mentioned steps S13 further comprises step S1301, specific as follows:
S1301: according to each described first using record and each user's similarity, obtain it is each described to
Recommend to apply corresponding second recommendation.
Further, above-mentioned steps S1301 further comprises step S1301_1, specific as follows:
S1301_1: according to each described first using record rvx, each user's similarity wuvWith it is preset
Second recommendation computation modelThe each application corresponding second to be recommended of acquisition is calculated to recommend
Spend Nux;Wherein, u indicates the target user;V indicates the recommended user;X indicates the application to be recommended;K is all institutes
State the total number of recommended user v;A is preset constant.
S14: according to each second recommendation, recommend corresponding application to be recommended to target user.
It should be noted that server-side is after calculating and obtaining corresponding second recommendation of each application to be recommended, according to
The sequence of each second recommendation from high to low is ranked up each application to be recommended, so that preceding m (m >=1) position will be arranged in
Application to be recommended recommend target user.
The embodiment of the present invention passes through use during application is recommended, by reference other users to application to be recommended
Situation speculates target user to the interest level of each application to be recommended, to optimize to using recommendation list, therefore
It can be improved using the accuracy recommended, reduce the feelings for recommending the target user and uninterested application to target user
Condition, to optimize using recommendation effect.
It in yet another preferred embodiment, further include step S1103_01 to S1103_ before above-mentioned steps S1103
03, specific as follows:
S1103_01: at least one training application and the corresponding third of each training application are obtained using note
Record.
It should be noted that before above-mentioned steps S1103, it is also necessary to pre-set it is each used using with it is each
Application similarity between application to be recommended.This using similarity by a large amount of third using situation carry out statistics and
Analysis obtains.Wherein, which is that each application is corresponding using situation using situation.
S1103_02: it according to each third using record, calculates and obtains between training application described in every two
Application similarity.
Further, above-mentioned steps S1103_02 further comprises step S1103_02_1, specific as follows:
S1103_02_1: similarity calculation is applied with preset using record according to each thirdCalculate the application similarity w obtained between training application described in every twoij;Wherein, N (i) is indicated
Training is using the corresponding third of i using the total number of record;N (j) indicates training using the corresponding third of j using note
The total number of record.
S1103_03: according to it is each it is described apply similarity, generate apply similarity set.
Then above-mentioned steps S1103 further comprises step S1103_21 to S1103_22, specific as follows:
S1103_21: the inquiry application similarity set, obtain it is each it is described using using with it is each described wait push away
Recommend the application similarity between application.
S1103_22: according to described each described second using record and it is each described use application with it is each
Application similarity between the application to be recommended obtains corresponding first recommendation of each application to be recommended.
It should be noted that above-mentioned steps label is only used for indicating different step, without to the execution between each step
Sequence is defined.
It is provided in an embodiment of the present invention apply recommended method, by application recommend during, by using for reference other use
Family speculates target user to the interest level of each application to be recommended, to push away to application to the service condition of application to be recommended
It recommends list to optimize, therefore can be improved using the accuracy recommended, reduce to target user and recommend the target user simultaneously
The case where uninterested application, to optimize using recommendation effect.
Correspondingly, recommendation apparatus is applied the present invention also provides a kind of, can be realized in above-described embodiment and applies recommendation side
All processes of method.
As shown in Fig. 2, being the structural schematic diagram of a preferred embodiment provided by the invention using recommendation apparatus, tool
Body is as follows:
Module 21 is obtained using recommendation list, applies recommendation list for obtaining first;Wherein, first application is recommended
Include at least one corresponding first recommendation of application to be recommended in list;
History recommendation record obtains module 22, for obtaining the corresponding history recommendation record of each application to be recommended;
Wherein, user corresponding first is recommended using record comprising at least one in each history recommendation record;
Obtain module 23 using recommendation, for using record, obtained according to each described first it is each it is described to
Recommend to apply corresponding second recommendation;And
Using recommending module 24, for recommending to target user corresponding to be recommended according to each second recommendation
Using.
Further, the application recommendation list obtains module, specifically includes:
Using record obtaining unit, for obtain the target user it is corresponding at least one use application and often
It has been used described in a using corresponding second using record;
It is to be recommended to apply obtaining unit, for having used application according to each described, obtain at least one application to be recommended;
Using recommendation computing unit, for according to each described second using record and preset each described
Used using and the application similarity between each application to be recommended, obtain and each described to be recommended apply corresponding the
One recommendation;And
Using recommendation list generation unit, for generating first application and recommending according to each first recommendation
List.
Further, the application recommendation computing unit, specifically includes:
Using recommendation computation subunit, it is used for according to each described second using record rui, preset each institute
It states and has used using i and each application similarity w to be recommended using between jijAnd preset first recommendation calculates
ModelIt calculates and obtains the corresponding first recommendation P of each application j to be recommendeduj;Wherein, u indicates institute
State target user;N (u) is indicated by all described using the set formed using i;The S (i, K) indicate by it is all it is described to
Recommend the set using j composition.
It is further, described to apply recommendation apparatus, further includes:
Module is obtained using record, is corresponded to for obtaining at least one training application and each training application
Third using record;
Using similarity calculation module, for, using record, calculating according to each third and obtaining every two institute
State the application similarity between training application;And
Similarity set generation module, for according to it is each it is described apply similarity, generate apply similarity set;
The then application recommendation computing unit, specifically includes:
Obtain subelement using similarity, for inquiring the application similarity set, obtain it is each described in using answering
With the application similarity between each application to be recommended;And
Using recommendation computation subunit, for using record and each described according to described each described second
Used using and the application similarity between each application to be recommended, obtain and each described to be recommended apply corresponding the
One recommendation.
Further, described to apply similarity calculation module, it specifically includes:
Using similarity calculated, for applying similarity with preset using record according to each third
Computation modelCalculate the application similarity w obtained between training application described in every twoij;Wherein, N
(i) total number of the training using the corresponding third of i using record is indicated;N (j) indicates that training is answered using the corresponding third of j
With the total number of usage record.
It is further, described to apply recommendation apparatus, further includes:
Module is obtained using recommendation list, for obtaining each recommended user corresponding second using recommendation column
Table;And
User's similarity calculation module, for being recommended according to the first application recommendation list and each second application
List obtains user's similarity between the target user and each recommended user respectively;
The application recommendation obtains module, specifically includes:
Using recommendation obtaining unit, for similar with each user using recording according to each described first
Degree obtains corresponding second recommendation of each application to be recommended.
Further, the application recommendation obtaining unit, specifically includes;
Using recommendation computation subunit, it is used for according to each described first using record rvx, each user
Similarity wuvWith preset second recommendation computation modelIt calculates and obtains each described to be recommended answer
With corresponding second recommendation Nux;Wherein, u indicates the target user;V indicates the recommended user;X indicates described wait push away
Recommend application;K is the total number of all recommended user v;A is preset constant.
It is provided in an embodiment of the present invention apply recommendation apparatus, by application recommend during, by using for reference other use
Family speculates target user to the interest level of each application to be recommended, to push away to application to the service condition of application to be recommended
It recommends list to optimize, therefore can be improved using the accuracy recommended, reduce to target user and recommend the target user simultaneously
The case where uninterested application, to optimize using recommendation effect.
The present invention also provides a kind of equipment.
As shown in figure 3, the structural schematic diagram of a preferred embodiment for equipment provided by the invention, including processor
31, memory 32 and it is stored in the memory 32 and is configured as the computer program executed by the processor 31,
The processor 31 realizes application recommended method described in any embodiment as above when executing the computer program.
It should be noted that Fig. 3 only by the equipment a memory and a processor be connected for shown
Meaning can also be specific including multiple memories and/or multiple processors in the equipment in some specific embodiments
Number and connection type can need to be configured and be adaptively adjusted according to the actual situation.
Equipment provided in an embodiment of the present invention, by being treated and being pushed away by reference other users during application is recommended
Recommend application service condition speculate target user to the interest level of each application to be recommended, thus to application recommendation list into
Row optimization, therefore can be improved using the accuracy recommended, it reduces and recommends the target user to target user and lose interest in
Application the case where, to optimize using recommendation effect.
The present invention also provides a kind of computer readable storage mediums, specifically include the computer program of storage, wherein
Equipment executes described in any embodiment as above the computer program controls the computer readable storage medium when running where
Application recommended method.
It should be noted that the present invention realizes all or part of the process in above-described embodiment method, meter can also be passed through
Calculation machine program is completed to instruct relevant hardware, and the computer program can be stored in a computer readable storage medium
In, the computer program is when being executed by processor, it can be achieved that the step of above-mentioned each embodiment of the method.Wherein, the calculating
Machine program includes computer program code, and the computer program code can be source code form, object identification code form, can hold
Style of writing part or certain intermediate forms etc..The computer-readable medium may include: that can carry the computer program code
Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunications letter
Number and software distribution medium etc..It should be further noted that the content that the computer-readable medium includes can basis
Legislation and the requirement of patent practice carry out increase and decrease appropriate in jurisdiction, such as in certain jurisdictions, according to legislation
And patent practice, computer-readable medium do not include electric carrier signal and telecommunication signal.
Computer readable storage medium provided in an embodiment of the present invention, by passing through reference during application is recommended
Other users speculate target user to the interest level of each application to be recommended, thus right to the service condition of application to be recommended
It optimizes, therefore is can be improved using the accuracy recommended using recommendation list, reduce to target user and recommend the target
User and the case where uninterested application, to optimize using recommendation effect.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principle of the present invention, it can also make several improvements and retouch, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. a kind of apply recommended method characterized by comprising
It obtains first and applies recommendation list;It wherein, include at least one application pair to be recommended in the first application recommendation list
The first recommendation answered;
Obtain the corresponding history recommendation record of each application to be recommended;Wherein, include in each history recommendation record
At least one recommended user corresponding first is using record;
According to each described first using record, corresponding second recommendation of each application to be recommended is obtained;
According to each second recommendation, recommend corresponding application to be recommended to target user.
2. applying recommended method as described in claim 1, which is characterized in that described to obtain first using recommendation list, specifically
Include:
Obtain the target user it is corresponding at least one each described answered using application and using application corresponding second
Use usage record;
According to it is each it is described used application, obtain at least one application to be recommended;
According to each described second using record and it is preset it is each described use application with it is each described to be recommended
Application similarity between obtains corresponding first recommendation of each application to be recommended;
According to each first recommendation, generates described first and apply recommendation list.
3. as claimed in claim 2 apply recommended method, which is characterized in that it is described according to each described second using note
Record and it is preset it is each described use application and the application similarity between each application to be recommended, obtain each institute
Corresponding first recommendation of application to be recommended is stated, is specifically included:
According to each described second using record rui, it is preset it is each described use apply i with it is each described to be recommended
Using the application similarity w between jijAnd preset first recommendation computation modelIt calculates and obtains often
The corresponding first recommendation P of a application j to be recommendeduj;Wherein, u indicates the target user;N (u) is indicated by all described
The set using i composition is used;The S (i, K) indicates by all set to be recommended formed using j.
4. as claimed in claim 2 apply recommended method, which is characterized in that it is described according to each described second using
Record and it is preset it is each described use using with the application similarity between each application to be recommended, acquisition is each
Before corresponding first recommendation of the application to be recommended, further includes:
At least one training application and the corresponding third of each training application are obtained using record;
According to each third using record, the application similarity obtained between training application described in every two is calculated;
According to it is each it is described apply similarity, generate apply similarity set;
Then it is described according to each described second using record and it is preset it is each described use application with it is each described
Application similarity between application to be recommended obtains corresponding first recommendation of each application to be recommended, specifically includes:
The application similarity set is inquired, is obtained each described using application and answering between each application to be recommended
Use similarity;
It using record and each described described to be recommended has been answered using application with each according to described each described second
Application similarity between obtains corresponding first recommendation of each application to be recommended.
5. as claimed in claim 4 apply recommended method, which is characterized in that it is described according to each third using note
Record calculates the application similarity obtained between training application described in every two, specifically includes:
Similarity calculation is applied with preset using record according to each thirdMeter
Calculate the application similarity w obtained between training application described in every twoij;Wherein, N (i) indicates that training is answered using the corresponding third of i
With the total number of usage record;N (j) indicates total number of the training using the corresponding third of j using record.
6. as described in claim 1 apply recommended method, which is characterized in that it is described according to each described first using
Record, before obtaining corresponding second recommendation of each application to be recommended, further includes:
Each recommended user corresponding second is obtained using recommendation list;
According to it is described first application recommendation list and each described second apply recommendation list, obtain respectively the target user with
User's similarity between each recommended user;
It is described according to each described first using record, obtain corresponding second recommendation of each application to be recommended,
It specifically includes:
According to each described first using record and each user's similarity, each application pair to be recommended is obtained
The second recommendation answered.
7. as claimed in claim 6 apply recommended method, which is characterized in that it is described according to each described first using note
Record and each user's similarity obtain corresponding second recommendation of each application to be recommended, specifically include:
According to each described first using record rvx, each user's similarity wuvIt is calculated with preset second recommendation
ModelIt calculates and obtains the corresponding second recommendation N of each application to be recommendedux;Wherein, u table
Show the target user;V indicates the recommended user;X indicates the application to be recommended;K is all recommended user v
Total number;A is preset constant.
8. a kind of apply recommendation apparatus characterized by comprising
Module is obtained using recommendation list, applies recommendation list for obtaining first;Wherein, in the first application recommendation list
Include at least one corresponding first recommendation of application to be recommended;
History recommendation record obtains module, for obtaining the corresponding history recommendation record of each application to be recommended;Wherein, often
Comprising at least one recommended user corresponding first using record in a history recommendation record;
Module is obtained using recommendation, for using record, obtaining each described to be recommended answer according to each described first
With corresponding second recommendation;And
Using recommending module, for recommending corresponding application to be recommended to target user according to each second recommendation.
9. a kind of equipment, which is characterized in that including processor, memory and storage in the memory and be configured as by
The computer program that the processor executes, wherein the processor realizes such as claim 1 when executing the computer program
It is described in any item using recommended method to 7.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program, wherein the computer program executes as described in any one of claim 1 to 7 using recommended method when running.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811060586.5A CN109299349B (en) | 2018-09-11 | 2018-09-11 | Application recommendation method and device, equipment and computer-readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811060586.5A CN109299349B (en) | 2018-09-11 | 2018-09-11 | Application recommendation method and device, equipment and computer-readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109299349A true CN109299349A (en) | 2019-02-01 |
CN109299349B CN109299349B (en) | 2021-02-19 |
Family
ID=65166538
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811060586.5A Active CN109299349B (en) | 2018-09-11 | 2018-09-11 | Application recommendation method and device, equipment and computer-readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109299349B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101853463A (en) * | 2009-03-30 | 2010-10-06 | 北京邮电大学 | Collaborative filtering recommending method and system based on client characteristics |
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | 中国移动通信集团公司 | Recommending method, system and equipment based on mobile Internet |
CN102880501A (en) * | 2012-07-24 | 2013-01-16 | 北京奇虎科技有限公司 | Realizing method, device and system for recommending applications |
CN102915307A (en) * | 2011-08-02 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Device and method for recommending personalized information and information processing system |
CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
CN103578007A (en) * | 2012-07-20 | 2014-02-12 | 三星电子(中国)研发中心 | Mixed recommendation system and method for intelligent device |
US20140181117A1 (en) * | 2011-08-19 | 2014-06-26 | Tencent Technology (Shenzhen) Company Limited | Person search method and apparatus |
CN105677715A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Multiuser-based video recommendation method and apparatus |
CN107807935A (en) * | 2016-09-09 | 2018-03-16 | 腾讯科技(深圳)有限公司 | Using recommendation method and device |
CN108182268A (en) * | 2018-01-16 | 2018-06-19 | 浙江工商大学 | A kind of collaborative filtering recommending method and system based on community network |
-
2018
- 2018-09-11 CN CN201811060586.5A patent/CN109299349B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101853463A (en) * | 2009-03-30 | 2010-10-06 | 北京邮电大学 | Collaborative filtering recommending method and system based on client characteristics |
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | 中国移动通信集团公司 | Recommending method, system and equipment based on mobile Internet |
CN102915307A (en) * | 2011-08-02 | 2013-02-06 | 腾讯科技(深圳)有限公司 | Device and method for recommending personalized information and information processing system |
US20140181117A1 (en) * | 2011-08-19 | 2014-06-26 | Tencent Technology (Shenzhen) Company Limited | Person search method and apparatus |
CN103578007A (en) * | 2012-07-20 | 2014-02-12 | 三星电子(中国)研发中心 | Mixed recommendation system and method for intelligent device |
CN102880501A (en) * | 2012-07-24 | 2013-01-16 | 北京奇虎科技有限公司 | Realizing method, device and system for recommending applications |
CN103198418A (en) * | 2013-03-15 | 2013-07-10 | 北京亿赞普网络技术有限公司 | Application recommendation method and application recommendation system |
CN105677715A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Multiuser-based video recommendation method and apparatus |
CN107807935A (en) * | 2016-09-09 | 2018-03-16 | 腾讯科技(深圳)有限公司 | Using recommendation method and device |
CN108182268A (en) * | 2018-01-16 | 2018-06-19 | 浙江工商大学 | A kind of collaborative filtering recommending method and system based on community network |
Non-Patent Citations (1)
Title |
---|
尹利: "Hadoop下的个性化推荐应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN109299349B (en) | 2021-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105335409B (en) | A kind of determination method, equipment and the network server of target user | |
CN109597606B (en) | Method, apparatus and storage medium for making business decisions using a rules engine | |
CN105045818A (en) | Picture recommending method, apparatus and system | |
CN104750760A (en) | Application software recommending method and device | |
CN111125521A (en) | Information recommendation method, device, equipment and storage medium | |
CN106682949A (en) | Service recommending method and service information receiving method, device and system | |
CN110413926A (en) | A kind of questionnaire method and device | |
CN105589714B (en) | The method and apparatus for using application behavior for analyzing user | |
CN106156173A (en) | Cheating identification method and device and terminal | |
CN110516162A (en) | A kind of information recommendation method, device, equipment and storage medium | |
CN110188276A (en) | Data sending device, method, electronic equipment and computer readable storage medium | |
CN111045735B (en) | Personalized guide page pushing method, device and system | |
CN107483565A (en) | A kind of service background recognition methods, proxy server and computer-readable storage medium | |
CN109299349A (en) | Application recommendation method and device, equipment and computer-readable storage medium | |
CN104599092A (en) | Order business monitoring method and equipment | |
CN105848155B (en) | Terminal illegal flashing recognition method and device | |
CN113139102B (en) | Data processing method, device, nonvolatile storage medium and processor | |
CN114285896B (en) | Information pushing method, device, equipment, storage medium and program product | |
CN110362540A (en) | A kind of storage of data, visitor's number acquisition methods and device | |
CN105893286A (en) | Data processing method and apparatus | |
CN109783718A (en) | Repetitive requests judgment method and device | |
CN111581487B (en) | Information processing method and device | |
CN106469086B (en) | Event processing method and device | |
CN110555182A (en) | User portrait determination method and device and computer readable storage medium | |
CN110347683B (en) | Data table merging processing method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |