CN109299349B - 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
- CN109299349B CN109299349B CN201811060586.5A CN201811060586A CN109299349B CN 109299349 B CN109299349 B CN 109299349B CN 201811060586 A CN201811060586 A CN 201811060586A CN 109299349 B CN109299349 B CN 109299349B
- Authority
- CN
- China
- Prior art keywords
- application
- recommended
- recommendation
- obtaining
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004590 computer program Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
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 the field of computer technologies, and in particular, to an application recommendation method, an application recommendation apparatus, and a computer-readable storage medium.
Background
Application recommendations are an important component of an application store, and are one of the core functions of an application store. In the prior art, the applications recommended to the user by the application store are generally determined according to the applications used or used by the user, and particularly, the application store generally selects applications similar to the applications used or used by the user to be recommended to the user. Because the judgment standard of the recommendation method is single, the recommendation accuracy is not high, and the recommendation effect is not good.
Disclosure of Invention
The embodiment of the invention provides an application recommendation method, an application recommendation device, application recommendation equipment and a computer readable storage medium, which can improve application recommendation accuracy.
The application recommendation method provided by the embodiment of the invention specifically 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;
recommending corresponding applications to be recommended to the target user according to each second recommendation degree;
the obtaining of the first application recommendation list specifically includes:
obtaining at least one used application corresponding to the target user and a second application use record corresponding to each used application;
obtaining at least one application to be recommended according to each used application;
obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and preset application similarity between each used application and each application to be recommended;
and generating the first application recommendation list according to each first recommendation degree.
Further, the obtaining a first recommendation degree corresponding to each application to be recommended according to each second application usage record and a preset application similarity between each used application and each application to be recommended specifically includes:
according to each said second application usage record ruiAnd the preset application similarity w between each used application i and each application j to be recommendedijAnd a preset first recommendation calculation modelCalculating to obtain a first recommendation degree P corresponding to each application j to be recommendeduj(ii) a Wherein u represents the target user; n (u) represents a set consisting of all of the used applications i; the S (i, K) represents a set consisting of all the applications j to be recommended.
Further, before obtaining the first recommendation degree corresponding to each application to be recommended according to each second application usage record and the preset application similarity between each used application and each application to be recommended, the method further includes:
obtaining at least one training application and a third application usage record corresponding to each training application;
calculating and obtaining the application similarity between every two training applications according to the third application use records;
generating an application similarity set according to each application similarity;
then, the obtaining a first recommendation degree corresponding to each application to be recommended according to each second application usage record and a preset application similarity between each used application and each application to be recommended specifically includes:
querying the application similarity set to obtain the application similarity between each used application and each application to be recommended;
and obtaining a first recommendation degree corresponding to each application to be recommended according to the use record of each second application and the application similarity between each used application and each application to be recommended.
Further, the calculating, according to each third application usage record, to obtain an application similarity between each two training applications specifically includes:
calculating a model according to each third application usage record and preset application similarityCalculating to obtain the application similarity w between every two training applicationsij(ii) a Wherein, n (i) represents the total number of the third application usage records corresponding to the training application i; and N (j) represents the total number of the third application use records corresponding to the training application j.
Further, before the obtaining a second recommendation degree corresponding to each application to be recommended according to each first application usage record, the method further includes:
obtaining a second application recommendation list corresponding to each recommended user;
according to the first application recommendation list and each second application recommendation list, respectively obtaining user similarity between the target user and each recommended user;
the obtaining, according to each first application usage record, a second recommendation degree corresponding to each application to be recommended specifically includes:
and obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record and each user similarity.
Further, the obtaining a second recommendation degree corresponding to each application to be recommended according to the usage record of each first application and the similarity of each user specifically includes:
according to each said first application usage record rvxEach of the user similarities wuvAnd a preset second recommendation degree calculation modelCalculating to obtain a second recommendation degree N corresponding to each application to be recommendedux(ii) a Wherein u represents the target user; v represents the recommended user; x represents the application to be recommended; k is the total number of all the recommended users v; a is a preset constant.
Correspondingly, an embodiment of the present invention further provides an application recommendation apparatus, which specifically includes:
the application recommendation list obtaining module is used for 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;
the historical recommendation record obtaining module is used for 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;
the application recommendation degree obtaining module is used for obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record; and the number of the first and second groups,
the application recommending module is used for recommending corresponding applications to be recommended to the target user according to each second recommending degree;
the application recommendation list obtaining module specifically includes:
an application usage record obtaining unit, configured to obtain at least one used application corresponding to the target user and a second application usage record corresponding to each used application;
the application to be recommended obtaining unit is used for obtaining at least one application to be recommended according to each used application;
the application recommendation degree calculating unit is used for obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and application similarity between each preset used application and each application to be recommended; and the number of the first and second groups,
and the application recommendation list generating unit is used for generating the first application recommendation list according to each first recommendation degree.
An embodiment of the present invention further provides an apparatus, which specifically includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor implements the application recommendation method as described above when executing the computer program.
The embodiment of the present invention further provides a computer-readable storage medium, which specifically includes a stored computer program, where the computer program executes the application recommendation method described above when running.
The embodiment of the invention has the following beneficial effects:
according to the application recommendation method, device and computer-readable storage medium provided by the embodiment of the invention, the interest degree of the target user in each application to be recommended is presumed by using the use conditions of the applications to be recommended of other users for reference in the application recommendation process, so that the application recommendation list is optimized, the application recommendation accuracy can be improved, the conditions that the target user does not have interest in the applications are recommended to the target user are reduced, and the application recommendation effect is optimized.
Drawings
FIG. 1 is a flow chart diagram of a preferred embodiment of an application recommendation method provided by the present invention;
FIG. 2 is a schematic structural diagram of a preferred embodiment of the application recommendation device provided by the present invention;
fig. 3 is a schematic structural diagram of a preferred embodiment of the apparatus provided by the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a flowchart of a preferred embodiment of the application recommendation method provided by the present invention includes steps S11 to S14, which are as follows:
s11: 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.
It should be noted that the embodiment of the present invention is executed by a system having an application recommendation function. The system may be a system in a server or a system in other devices. For convenience of description, the following embodiments are described taking a system installed in a server as an example.
The first application recommendation list comprises an application identification code and a first recommendation degree corresponding to each application to be recommended. After obtaining the first application recommendation list, the server side optimizes the first application recommendation list according to the following steps so as to obtain a final application recommendation list, and recommends a corresponding application to a target user according to the final application recommendation list.
In another preferred embodiment, the step S11 further includes steps S1101 to S1104, which are as follows:
s1101: and obtaining at least one used application corresponding to the target user and a second application use record corresponding to each used application.
It should be noted that the used application is an application installed in a client of a target user (hereinafter, simply referred to as a "target client"). The second application usage record may be the number of times that the target user accesses the corresponding used application, the score of the target user on the corresponding used application, or the like of the target user on the corresponding used application.
Specifically, when a target user registers in a server for the first time, the server acquires a data Packet in a network key node in a Deep Packet Inspection (DPI) manner, and acquires a target client identification code of the target user and an application identification code, an application name, an application type, an application score, and the like of each used application by detecting and analyzing contents of the data Packet except a header of the data Packet. The application score can be obtained by normalizing the number of times that the target user accesses the corresponding used application. In some specific embodiments, the service end is a network service end of a telecommunication operator.
In some specific embodiments, the server may further analyze the user behavior record stored in the target client to obtain a used application corresponding to the target user and a corresponding second application usage record.
S1102: and obtaining at least one application to be recommended according to each used application.
It should be noted that the application to be recommended is stored in the server in advance. After the server side obtains each used application corresponding to the target user, for each used application, respectively obtaining application similarity between the used application and each application stored in the local area in advance, and taking the application of which the application similarity is larger than a preset threshold or the application similarity is arranged at the front n (n is larger than or equal to 1) bits as the application to be recommended. And sequentially circulating until all the applications to be recommended respectively corresponding to the used applications are obtained.
S1103: and obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and the preset application similarity between each used application and each application to be recommended.
Further, the step S1103 further includes step S1103_11, which is as follows:
s1103_ 11: according to each said second application usage record ruiAnd the preset application similarity w between each used application i and each application j to be recommendedijAnd a preset first recommendation calculation modelCalculating to obtain a first recommendation degree P corresponding to each application j to be recommendeduj(ii) a Wherein u represents the target user; n (u) represents a set consisting of all of the used applications i; the S (i, K) represents a set consisting of all the applications j to be recommended.
It should be noted that n (u) and S (i, K) represent similar used applications in all used applications, so that the specific applications in the target client are excluded in the application recommendation process, and the accuracy of the application recommendation is improved.
S1104: and generating the first application recommendation list according to each first recommendation degree.
It should be noted that, after the server calculates and obtains the first recommendation degrees corresponding to the applications to be recommended, the server sorts the first recommendation degrees, so as to generate a first application recommendation list according to the first recommendation degrees ranked in the front. After the server generates the first application recommendation list, the application installed in the target client can be deleted according to the second application use record, so that the novelty of the first application recommendation list is improved, and the accuracy of application recommendation is further improved.
S12: obtaining a historical recommendation record corresponding to each application to be recommended; and each historical recommendation record comprises a first application use record corresponding to at least one recommended user.
It should be noted that, before this time, each application to be recommended has been recommended to other users. And generating corresponding first application use records according to the use conditions of the recommended users to the applications to be recommended, and further generating corresponding historical recommendation records. The first application usage record may be the number of times that the recommended user accesses the corresponding recommended application, the rating of the recommended user on the corresponding recommended application, or the like.
For example, the server side recommends the application a to the user a and the user b respectively, and after the user a receives the recommendation, the user a does not install and use the application a, the number of times of access of the user a to the application a is recorded to be 0, and a first application use record with the content of "0" is generated; and after receiving the recommendation, the user b installs and uses the application A for multiple times, and if the user b uses the application A for 4 times, the access times of the user b to the application A are recorded to be 4, and a first application use record with the content of 4 is generated. And finally, forming a historical recommendation record corresponding to the application A according to the first application use record with the content of 0 and the first application use record with the content of 4.
S13: and obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record.
In another preferred embodiment, before the step S13, steps S01 to S02 are further included, specifically as follows:
s01: and obtaining a second application recommendation list corresponding to each recommended user.
It should be noted that after the corresponding recommended user list is obtained according to the historical recommendation record, the second application recommendation list of each recommended user is obtained according to the recommended user list. Wherein the second application recommendation list is a list of applications previously recommended to the recommended user.
S02: and respectively obtaining the user similarity between the target user and each recommended user according to the first application recommendation list and each second application recommendation list.
It should be noted that the user similarity may be determined by calculating the similarity between the first application recommendation list and the second application recommendation list, or may be determined by calculating the number of the same applications between the first application recommendation list and the second application recommendation list.
The step S13 further includes a step S1301, which is as follows:
s1301: and obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record and each user similarity.
Further, the step S1301 further includes a step S1301_1, which specifically includes:
s1301_ 1: according to each said first application usage record rvxEach of the user similarities wuvAnd a preset second recommendation degree calculation modelCalculating to obtain a second recommendation degree N corresponding to each application to be recommendedux(ii) a Wherein u represents the target user; v represents the recommended user; x represents the application to be recommended; k is the total number of all the recommended users v; a is a preset constant.
S14: and recommending the corresponding application to be recommended to the target user according to each second recommendation degree.
It should be noted that after the server obtains the second recommendation degrees corresponding to the applications to be recommended through calculation, the applications to be recommended are sorted according to the sequence of the second recommendation degrees from high to low, so that the applications to be recommended arranged in the top m (m is greater than or equal to 1) are recommended to the target user.
In the application recommendation process, the interest degree of the target user in each application to be recommended is presumed by using the use conditions of the applications to be recommended of other users for reference, so that the application recommendation list is optimized, the accuracy of application recommendation can be improved, the condition that the applications which are not interested by the target user are recommended to the target user is reduced, and the application recommendation effect is optimized.
In another preferred embodiment, before the step S1103, steps S1103_01 to S1103_03 are further included, specifically as follows:
s1103_ 01: at least one training application and a third application usage record corresponding to each training application are obtained.
Before the step S1103, the application similarity between each used application and each application to be recommended needs to be set in advance. The application similarity is obtained by counting and analyzing a large number of third application use cases. And the third application use condition is the application use condition corresponding to each application.
S1103_ 02: and calculating and obtaining the application similarity between every two training applications according to each third application use record.
Further, the step S1103_02 further includes a step S1103_02_1, which is as follows:
s1103_02_ 1: calculating a model according to each third application usage record and preset application similarityCalculating to obtain the application similarity w between every two training applicationsij(ii) a Wherein, n (i) represents the total number of the third application usage records corresponding to the training application i; and N (j) represents the total number of the third application use records corresponding to the training application j.
S1103_ 03: and generating an application similarity set according to each application similarity.
The step S1103 further includes steps S1103_21 to S1103_22, which are as follows:
s1103_ 21: and querying the application similarity set to obtain the application similarity between each used application and each application to be recommended.
S1103_ 22: and obtaining a first recommendation degree corresponding to each application to be recommended according to the use record of each second application and the application similarity between each used application and each application to be recommended.
It should be noted that the step numbers are only used for indicating different steps, and the execution sequence between the steps is not limited.
According to the application recommendation method provided by the embodiment of the invention, in the application recommendation process, the interest degree of the target user in each application to be recommended is presumed by using the use conditions of the applications to be recommended of other users for reference, so that the application recommendation list is optimized, the accuracy of application recommendation can be improved, the conditions that the target user does not have interest in the applications are recommended to the target user are reduced, and the application recommendation effect is optimized.
Correspondingly, the invention further provides an application recommendation device, which can realize all the processes of the application recommendation method in the embodiment.
As shown in fig. 2, a schematic structural diagram of a preferred embodiment of the application recommendation device provided by the present invention is specifically as follows:
an application recommendation list obtaining module 21, configured to obtain a first application recommendation list; the first application recommendation list comprises a first recommendation degree corresponding to at least one application to be recommended;
a historical recommendation record obtaining module 22, configured to obtain 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;
an application recommendation obtaining module 23, configured to obtain, according to each first application usage record, a second recommendation corresponding to each application to be recommended; and the number of the first and second groups,
and the application recommending module 24 is configured to recommend the corresponding application to be recommended to the target user according to each second recommendation degree.
Further, the application recommendation list obtaining module specifically includes:
an application usage record obtaining unit, configured to obtain at least one used application corresponding to the target user and a second application usage record corresponding to each used application;
the application to be recommended obtaining unit is used for obtaining at least one application to be recommended according to each used application;
the application recommendation degree calculating unit is used for obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and application similarity between each preset used application and each application to be recommended; and the number of the first and second groups,
and the application recommendation list generating unit is used for generating the first application recommendation list according to each first recommendation degree.
Further, the application recommendation degree calculating unit specifically includes:
an application recommendation calculation subunit for calculating a second application usage record r according to each of the second application usage recordsuiAnd the preset application similarity w between each used application i and each application j to be recommendedijAnd a preset first recommendation calculation modelCalculating to obtain a first recommendation degree P corresponding to each application j to be recommendeduj(ii) a Wherein u represents the target user; n (u) represents a set consisting of all of the used applications i; the S (i, K) represents a set consisting of all the applications j to be recommended.
Further, the application recommendation apparatus further includes:
the application use record obtaining module is used for obtaining at least one training application and a third application use record corresponding to each training application;
the application similarity calculation module is used for calculating and obtaining the application similarity between every two training applications according to the third application use records; and the number of the first and second groups,
the similarity set generating module is used for generating an application similarity set according to each application similarity;
the application recommendation degree calculating unit specifically includes:
the application similarity obtaining subunit is configured to query the application similarity set to obtain an application similarity between each used application and each application to be recommended; and the number of the first and second groups,
and the application recommendation degree calculation subunit is used for obtaining a first recommendation degree corresponding to each application to be recommended according to each second application usage record and the application similarity between each used application and each application to be recommended.
Further, the application similarity calculation module specifically includes:
an application similarity calculation unit for calculating a model according to each of the third application usage records and a preset application similarityCalculating to obtain the application similarity w between every two training applicationsij(ii) a Wherein, n (i) represents the total number of the third application usage records corresponding to the training application i; and N (j) represents the total number of the third application use records corresponding to the training application j.
Further, the application recommendation apparatus further includes:
an application recommendation list obtaining module, configured to obtain a second application recommendation list corresponding to each recommended user; and the number of the first and second groups,
the user similarity calculation module is used for respectively obtaining the user similarity between the target user and each recommended user according to the first application recommendation list and each second application recommendation list;
the application recommendation degree obtaining module specifically comprises:
and the application recommendation degree obtaining unit is used for obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record and each user similarity.
Further, the application recommendation degree obtaining unit specifically includes;
an application recommendation calculation subunit for calculating a recommendation for each of the first application usage records rvxEach of the user similarities wuvAnd a preset second recommendation degree calculation modelCalculating to obtain a second recommendation degree N corresponding to each application to be recommendedux(ii) a Wherein u represents the target user; v represents the recommended user; x represents the application to be recommended; k is the total number of all the recommended users v; a is a preset constant.
According to the application recommendation device provided by the embodiment of the invention, in the application recommendation process, the interest degree of the target user in each application to be recommended is presumed by using the use conditions of the applications to be recommended of other users for reference, so that the application recommendation list is optimized, the accuracy of application recommendation can be improved, the conditions that the target user does not have interest in the applications are recommended to the target user are reduced, and the application recommendation effect is optimized.
The invention also provides equipment.
As shown in fig. 3, a schematic structural diagram of a preferred embodiment of the apparatus provided by the present invention includes a processor 31, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 31, where the processor 31 implements the application recommendation method according to any of the above embodiments when executing the computer program.
It should be noted that fig. 3 only illustrates an example in which one memory and one processor in the apparatus are connected, and in some specific embodiments, the apparatus may further include a plurality of memories and/or a plurality of processors, and the specific number and the connection mode thereof may be set and adapted according to actual needs.
According to the device provided by the embodiment of the invention, in the application recommendation process, the interest degree of the target user in each application to be recommended is presumed by using the use conditions of the applications to be recommended of other users for reference, so that the application recommendation list is optimized, the application recommendation accuracy can be improved, the conditions that the target user is not interested in the applications are recommended to the target user, and the application recommendation effect is optimized.
The present invention further provides a computer-readable storage medium, which specifically includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the application recommendation method according to any one of the above embodiments.
It should be noted that, all or part of the flow in the method according to the above embodiments of the present invention may also be implemented by a computer program instructing related hardware, where the computer program may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above embodiments of the method may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be further noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The computer-readable storage medium provided by the embodiment of the invention can be used for estimating the interest degree of the target user in each application to be recommended by using the use conditions of the applications to be recommended of other users for reference in the application recommendation process, so as to optimize the application recommendation list, thereby improving the accuracy of application recommendation, reducing the conditions of recommending the applications which are not interested by the target user to the target user, and optimizing the application recommendation effect.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (9)
1. An application recommendation method, comprising:
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;
recommending corresponding applications to be recommended to the target user according to each second recommendation degree;
the obtaining of the first application recommendation list specifically includes:
obtaining at least one used application corresponding to the target user and a second application use record corresponding to each used application;
obtaining at least one application to be recommended according to each used application;
obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and preset application similarity between each used application and each application to be recommended;
and generating the first application recommendation list according to each first recommendation degree.
2. The application recommendation method according to claim 1, wherein the obtaining a first recommendation degree corresponding to each to-be-recommended application according to each second application usage record and a preset application similarity between each used application and each to-be-recommended application specifically comprises:
according to each said second application usage record ruiAnd the preset application similarity w between each used application i and each application j to be recommendedijAnd a preset first recommendation calculation modelCalculating to obtain a first recommendation degree P corresponding to each application j to be recommendeduj(ii) a Wherein u represents the target user; n (u) represents a set consisting of all of the used applications i; the S (i, K) represents a set consisting of all the applications j to be recommended.
3. The application recommendation method according to claim 1, before obtaining the first recommendation degree corresponding to each of the applications to be recommended according to each of the second application usage records and a preset application similarity between each of the used applications and each of the applications to be recommended, further comprising:
obtaining at least one training application and a third application usage record corresponding to each training application;
calculating and obtaining the application similarity between every two training applications according to the third application use records;
generating an application similarity set according to each application similarity;
then, the obtaining a first recommendation degree corresponding to each application to be recommended according to each second application usage record and a preset application similarity between each used application and each application to be recommended specifically includes:
querying the application similarity set to obtain the application similarity between each used application and each application to be recommended;
and obtaining a first recommendation degree corresponding to each application to be recommended according to the use record of each second application and the application similarity between each used application and each application to be recommended.
4. The application recommendation method according to claim 3, wherein the calculating to obtain the application similarity between each two training applications according to each third application usage record specifically comprises:
calculating a model according to each third application usage record and preset application similarityCalculating to obtain the application similarity w between every two training applicationsij(ii) a Wherein, n (i) represents the total number of the third application usage records corresponding to the training application i; and N (j) represents the total number of the third application use records corresponding to the training application j.
5. The application recommendation method according to claim 1, before obtaining the second recommendation degree corresponding to each of the applications to be recommended according to each of the first application usage records, further comprising:
obtaining a second application recommendation list corresponding to each recommended user;
according to the first application recommendation list and each second application recommendation list, respectively obtaining user similarity between the target user and each recommended user;
the obtaining, according to each first application usage record, a second recommendation degree corresponding to each application to be recommended specifically includes:
and obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record and each user similarity.
6. The application recommendation method according to claim 5, wherein the obtaining a second recommendation degree corresponding to each application to be recommended according to each first application usage record and each user similarity specifically includes:
according to each said first application usage record rvxEach of the user similarities wuvAnd a preset second recommendation degree calculation modelCalculating to obtain a second recommendation degree N corresponding to each application to be recommendedux(ii) a Wherein u represents the target user; v represents the recommended user; x represents the application to be recommended; k is the total number of all the recommended users v; a is a preset constant.
7. An application recommendation device, comprising:
the application recommendation list obtaining module is used for 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;
the historical recommendation record obtaining module is used for 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;
the application recommendation degree obtaining module is used for obtaining a second recommendation degree corresponding to each application to be recommended according to each first application use record; and the number of the first and second groups,
the application recommending module is used for recommending corresponding applications to be recommended to the target user according to each second recommending degree;
the application recommendation list obtaining module specifically includes:
an application usage record obtaining unit, configured to obtain at least one used application corresponding to the target user and a second application usage record corresponding to each used application;
the application to be recommended obtaining unit is used for obtaining at least one application to be recommended according to each used application;
the application recommendation degree calculating unit is used for obtaining a first recommendation degree corresponding to each application to be recommended according to each second application use record and application similarity between each preset used application and each application to be recommended; and the number of the first and second groups,
and the application recommendation list generating unit is used for generating the first application recommendation list according to each first recommendation degree.
8. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the application recommendation method of any of claims 1-6 when executing the computer program.
9. A computer-readable storage medium, comprising a stored computer program, wherein the computer program is operable to perform the application recommendation method of any of claims 1 to 6.
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 CN109299349A (en) | 2019-02-01 |
CN109299349B true 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 (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | ***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 |
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 |
Family Cites Families (5)
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 |
CN102915307B (en) * | 2011-08-02 | 2018-01-02 | 腾讯科技(深圳)有限公司 | The method, apparatus and information processing system of a kind of recommendation of personalized information |
CN102955781B (en) * | 2011-08-19 | 2016-04-20 | 腾讯科技(深圳)有限公司 | A kind of personage's searching method and device |
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 |
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 |
-
2018
- 2018-09-11 CN CN201811060586.5A patent/CN109299349B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102130933A (en) * | 2010-01-13 | 2011-07-20 | ***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 |
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 |
---|
Hadoop下的个性化推荐应用研究;尹利;《中国优秀硕士学位论文全文数据库 信息科技辑》;20170115;I138-848 * |
Also Published As
Publication number | Publication date |
---|---|
CN109299349A (en) | 2019-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105678587B (en) | Recommendation feature determination method, information recommendation method and device | |
CN108763274B (en) | Access request identification method and device, electronic equipment and storage medium | |
CN111090807B (en) | Knowledge graph-based user identification method and device | |
CN113383362B (en) | User identification method and related product | |
CN108269122B (en) | Advertisement similarity processing method and device | |
CN105404631B (en) | Picture identification method and device | |
CN108764951B (en) | User similarity obtaining method and device, equipment and storage medium | |
CN112966081A (en) | Method, device, equipment and storage medium for processing question and answer information | |
CN112364014B (en) | Data query method, device, server and storage medium | |
CN107885716A (en) | Text recognition method and device | |
CN108076032B (en) | Abnormal behavior user identification method and device | |
CN110209780B (en) | Question template generation method and device, server and storage medium | |
CN110516162A (en) | A kind of information recommendation method, device, equipment and storage medium | |
CN111984867B (en) | Network resource determining method and device | |
CN116469039B (en) | Hot video event determination method and system, storage medium and electronic equipment | |
CN109101541A (en) | Newly-increased INDEX MANAGEMENT method, equipment and computer readable storage medium | |
CN109299349B (en) | Application recommendation method and device, equipment and computer-readable storage medium | |
CN111353860A (en) | Product information pushing method and system | |
CN111309706A (en) | Model training method and device, readable storage medium and electronic equipment | |
CN115393100A (en) | Resource recommendation method and device | |
CN113157788B (en) | Big data mining method and system | |
CN115203556A (en) | Score prediction model training method and device, electronic equipment and storage medium | |
CN115375494A (en) | Financial product recommendation method, device, storage medium and equipment | |
CN108880935B (en) | Method and device for obtaining importance of network node, equipment and storage medium | |
CN108509560B (en) | User similarity obtaining method and device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |