Information recommendation method, device and electronic device

Abstract

An embodiment of the present invention provides an information recommendation method, device and electronic device, wherein the method includes: determining a target user and applications installed by the target user, and determining the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; determining the target user's interest in non-installed applications based on the target user's interest in the installed applications; and recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications; thereby solving the problem in the prior art that it is difficult to determine user interest information due to the lack of historical data, resulting in poor accuracy in information recommendation, thereby improving the accuracy of information recommendation for users.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an information recommendation method, device and electronic equipment. Background Art

[0002] At present, in order to acquire more customers, major platforms usually recommend information to users based on their interests. However, as market competitiveness continues to increase, the cost of acquiring customers is also increasing. How to effectively use data to analyze user interests has become one of the urgent problems that all platforms need to solve.

[0003] In the prior art, each platform mainly relies on the user's historical behavior on the platform, such as click behavior, browsing behavior, etc., to analyze the user's interests. However, for new users on the platform, since they have no historical behavior on the platform, it is difficult for the platform to analyze the user's interests and cannot accurately recommend information to them. Summary of the invention

[0004] The embodiment of the present invention provides an information recommendation method to improve the accuracy of information recommendation.

[0005] Correspondingly, the embodiment of the present invention further provides an information recommendation device and an electronic device to ensure the implementation and application of the above method.

[0006] In order to solve the above problems, an embodiment of the present invention discloses an information recommendation method, which specifically includes: determining a target user and applications installed by the target user, and determining the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; determining the target user's interest in non-installed applications based on the target user's interest in the installed applications; and recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0007] Optionally, determining the target user's interest in the installed application includes: acquiring usage information of the installed application; and determining the target user's interest in the installed application based on the usage information.

[0008] Optionally, determining the target user's interest in non-installed applications based on the target user's interest in the installed applications includes at least one of the following: using a collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a matrix decomposition algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a neural collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications.

[0009] Optionally, recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications includes: determining, based on a preset mapping relationship, an interest category to which each application belongs, the applications including installed applications and non-installed applications; for each interest category, calculating the target user's interest in the interest category using the target user's interest in the applications belonging to the interest category; and recommending information to the target user based on the interest of each interest category.

[0010] Optionally, recommending information to the target user based on the interest level of each interest category includes: determining top N interest categories with the highest interest levels; and recommending information corresponding to the top N interest categories to the target user.

[0011] An embodiment of the present invention also discloses an information recommendation device, which specifically includes: a first information determination module, used to determine a target user and applications installed by the target user, and determine the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; a second information determination module, used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; and a recommendation module, used to recommend information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0012] Optionally, the first information determination module is used to obtain usage information of the installed application; and determine the target user's interest in the installed application based on the usage information.

[0013] Optionally, the second information determination module includes: a first interest determination submodule, used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications by adopting a collaborative filtering algorithm; a second interest determination submodule, used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications by adopting a matrix decomposition algorithm; and a third interest determination submodule, used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications by adopting a neural collaborative filtering algorithm.

[0014] Optionally, the recommendation module includes: a category determination submodule, used to determine the interest category to which each application belongs based on a preset mapping relationship, the application including installed applications and non-installed applications; a category interest determination submodule, used to calculate the target user's interest in the interest category for each interest category using the target user's interest in the applications belonging to the interest category; and an information recommendation submodule, used to recommend information to the target user based on the interest of each interest category.

[0015] Optionally, the information recommendation submodule is used to determine the top N interest categories with the highest interest; and recommend information corresponding to the top N interest categories to the target user.

[0016] An embodiment of the present invention further discloses a readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the information recommendation method as described in any one of the embodiments of the present invention.

[0017] An embodiment of the present invention also discloses an electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: determining a target user and applications installed by the target user, and determining the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; determining the target user's interest in non-installed applications based on the target user's interest in the installed applications; and recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0018] Optionally, determining the target user's interest in the installed application includes: acquiring usage information of the installed application; and determining the target user's interest in the installed application based on the usage information.

[0019] Optionally, determining the target user's interest in non-installed applications based on the target user's interest in the installed applications includes at least one of the following: using a collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a matrix decomposition algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a neural collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications.

[0020] Optionally, recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications includes: determining, based on a preset mapping relationship, an interest category to which each application belongs, the applications including installed applications and non-installed applications; for each interest category, calculating the target user's interest in the interest category using the target user's interest in the applications belonging to the interest category; and recommending information to the target user based on the interest of each interest category.

[0021] Optionally, recommending information to the target user based on the interest level of each interest category includes: determining top N interest categories with the highest interest levels; and recommending information corresponding to the top N interest categories to the target user.

[0022] The embodiments of the present invention include the following advantages:

[0023] In an embodiment of the present invention, a target user, applications installed by the target user, and the target user's interest in the installed applications can be first determined; then, based on the target user's interest in the installed applications, the target user's interest in non-installed applications can be determined; and then, information is recommended to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications; thereby solving the problem in the prior art that it is difficult to determine user interest information due to the lack of historical data, resulting in poor accuracy in information recommendation, and improving the accuracy of information recommendation for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1is a flowchart of steps of an information recommendation method embodiment of the present invention;

[0025] Figure 2 is a flowchart of steps of an optional embodiment of an information recommendation method of the present invention;

[0026] Figure 3 is a structural block diagram of an embodiment of an information recommendation device of the present invention;

[0027] Figure 4 is a structural block diagram of an optional embodiment of an information recommendation device of the present invention;

[0028] Figure 5 A structural block diagram of an electronic device for information recommendation according to an exemplary embodiment;

[0029] Figure 6 It is a structural schematic diagram of an electronic device for information recommendation according to another exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] One of the core concepts of the embodiments of the present invention is to determine the user's interest in non-installed applications based on the user's interest in installed applications; then recommend information to the user based on the user's interests in installed applications and non-installed applications; thereby, the embodiments of the present invention solves the problem of poor accuracy of information recommendation in the prior art due to the difficulty in determining user interests due to the lack of historical behavior data, thereby improving the accuracy of information recommendation for users.

[0032] Reference Figure 1 , shows a flowchart of an information recommendation method embodiment of the present invention, which may specifically include the following steps:

[0033] Step 102: Determine a target user and applications installed by the target user, and determine the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications.

[0034] Step 104: Determine the target user's interest in the non-installed application program based on the target user's interest in the installed application program.

[0035] Step 106: Recommend information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0036] In an embodiment of the present invention, a user who needs information recommendation can be determined as a target user. Since the applications installed on the terminal device corresponding to the target user can reflect the interests of the target user, the embodiment of the present invention can obtain the application installation list on the terminal device corresponding to the target user, and determine the applications installed on the terminal device corresponding to the target user. Among them, the applications installed in the terminal device include pre-installed applications and applications actively installed by the user; the pre-installed applications may refer to applications installed on the terminal device when it leaves the factory. Since the pre-installed applications are not actively installed by the user, and the pre-installed applications of many users are the same, they cannot reflect the interests of the users. In order to improve the accuracy of determining the interest information corresponding to the target user, the installed applications determined in the embodiment of the present invention may refer to applications other than pre-installed applications.

[0037] In the embodiment of the present invention, the target user's interest in the installed application can be analyzed based on the target user's usage information of the installed application; and then information recommendation can be made to the user based on the target user's interest in the installed application.

[0038] In one embodiment of the present invention, the target user's interest in the installed application can be determined based on the target user's interest in the installed application; and then information is recommended to the user based on the target user's interest in the installed application and the interest in the installed application. In the absence of historical behavior data of the target user, information is accurately recommended to the user. The information recommended to the target user can include multiple types, such as pictures, texts, videos, animations, etc., which are not limited in the embodiment of the present invention.

[0039] In summary, in the embodiments of the present invention, the target user, the target user's installed applications, and the target user's interest in the installed applications can be first determined; then, based on the target user's interest in the installed applications, the target user's interest in non-installed applications can be determined; and then, information is recommended to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications; thereby solving the problem in the prior art that it is difficult to determine user interests due to the lack of historical data, resulting in poor accuracy in information recommendation, and improving the accuracy of information recommendation for users.

[0040] Reference Figure 2 , shows a flowchart of an optional embodiment of an information recommendation method of the present invention, which may specifically include the following steps:

[0041] Step 202: Determine the target user and the applications installed by the target user.

[0042] In an example of the present invention, the application installation list of the terminal device corresponding to the target user obtained may be as follows:

[0043]

[0044]

[0045] Table 1

[0046] Each item in the application installation list is a package name of an application. According to Table 1, it can be determined that the target user has installed 7 applications.

[0047] Step 204: Determine the target user's interest in the installed application.

[0048] In an example of the present invention, a method for determining the target user's interest in the installed application may be to use a first preset value as the target user's interest in the installed application; the first preset value may be set as required, such as 1; the embodiment of the present invention is not limited to this.

[0049] As an example of the present invention, the first preset value is 1, and the interest levels of the installed applications in Table 1 may be as shown in Table 2:

[0050] Application List Interest com.abc.momo 1 com.asssd.bangbang 1 com.ddfgg.newsclient 1 com.tggbnh.news 1 com.hffrj.mybus 1 com.jiaj 1 com.suhsuhiuhui.haofenshu 1

[0051] Table 2

[0052] Of course, in another example of the present invention, in order to improve the accuracy of determining the target user's interest information, a method for determining the target user's interest in the installed application may include the following sub-steps:

[0053] Sub-step 22: obtaining usage information of the installed application;

[0054] Sub-step 24: determining the target user's interest in the installed application based on the usage information.

[0055] In an embodiment of the present invention, the usage information may refer to information about the target user's use of an installed application, such as frequency of use, duration of use, date of use, etc., which is not limited in the embodiment of the present invention. Then, for each installed application, the target user's interest in the installed application may be determined based on the usage information of the installed application. When the usage information of the installed application contains multiple pieces of information, a corresponding weight may be set in advance for each piece of information, and then the target user's interest in the installed application may be determined by weighted calculation of each piece of information in the usage information. The greater the interest, the greater the target user's interest in the installed application.

[0056] As an example of the present invention, the interest of the target user in the installed application may be determined by referring to the following formula:

[0057]

[0058] Where G(k) represents the target user's interest in the installed application k. Δd represents the number of days between the last use of application k and the current time. numall represents the total number of applications installed by the target user. count represents the frequency of use of application k by the target user. countall represents the total frequency of use of all installed applications by the target user. usertime represents the duration of use of application k by the target user. usertimeall represents the total duration of use of all installed applications by the target user.

[0059] For example, numall=15, countall=700, usertimeall=5000. If the target user's usage information for the installed application (com.abc.momo) is obtained as follows: usage frequency count=100, usage duration usertime=500 hours, usage date (2019.11.10 (last usage date)). The target user's usage information for the installed application (com.asssd.bangbang) is as follows: usage frequency count=200, usage duration usertime=700 hours, usage date (2019.11.01 (last usage date)). If the current date is 2019.12.23, according to the above formula, the target user's interest in the installed application (com.abc.momo) is: 0.007369; the target user's interest in the installed application (com.asssd.bangbang) is: 0.007135.

[0060] As an example of the present invention, the interest level calculated for each installed application in Table 1 using sub-steps 22-24 may be as shown in Table 3:

[0061] Application List Interest com.abc.momo 0.007369 com.asssd.bangbang 0.007135 com.ddfgg.newsclient 0.006001 com.tggbnh.news 0.005021 com.hffrj.mybus 0.009136 com.jiaj 0.008335 com.suhsuhiuhui.haofenshu 0.007996

[0062] Table 3

[0063] Step 206: Determine the target user's interest in the non-installed application program based on the target user's interest in the installed application program.

[0064] Similarly, the embodiment of the present invention can determine the target user's interest in the non-installed application, and use the target user's interest in the non-installed application to represent the target user's interest in the non-installed application.

[0065] In an embodiment of the present invention, a method for determining the target user's interest in non-installed applications based on the target user's interest in the installed applications may be to use a collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications. Among them, a user-based collaborative filtering algorithm may be used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; or an item-based (which may refer to an application in the embodiment of the present invention) collaborative filtering algorithm may be used to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications, and the embodiment of the present invention does not limit this.

[0066] In an example of the present invention, the user-based collaborative filtering algorithm can refer to the following expression:

[0067]

[0068] Where p(u,i) represents the interest of the target user (identified by u) in the uninstalled application i; S(u,K) contains the K other users with the most similar interests to the target user u, where the other users are users in the entire network except the target user, N(i) is the set of users among the K other users that have installed the application i, and W uv is the interest similarity between the target user u and other users (identified by v), R vi Represents the interest of other users v in the installed application i.

[0069] Among them, the method of determining the interest of other users in the installed applications is similar to the method of determining the interest of the target user in the installed applications in the above step 204, and will not be repeated here. Now, the determination of the associated user set S(u,K) with similar interests to the target user is described. Among them, an empty vector with a dimension of X can be established for each user in the entire network. Among them, X is the sum of the types of applications installed by users in the entire network, and each dimension of the empty vector corresponds to a type of application installed by users in the entire network. Then, the interest of each application installed by each user is added to the corresponding dimension of the empty vector; and the value corresponding to the dimension without adding interest in the empty vector is set to a second preset value; and the interest vector of each user corresponding to the installed application is obtained. Among them, the second preset value can be set to 0 as required, and the embodiment of the present invention does not limit this. Then, the interest vector corresponding to each other user in the entire network can be calculated respectively, and the interest similarity with the interest vector corresponding to the target user; the associated user set S(u,K) is generated using the top K users with the highest interest similarity.

[0070] In one example of the present invention, the expression of the item-based collaborative filtering algorithm can be as follows:

[0071]

[0072] Where q(u,m) represents the interest of the target user (identified by u) in the uninstalled application m; N(u) represents the set of applications installed by the target user u (n represents one of the installed applications), S(n,K) is the application set, which contains the K other applications that are most similar to the installed application n (m is an application in this set that is not installed by the target user u); W mn is the similarity between the uninstalled application m and the installed application n, R un Represents the interest of target user u in installed application n.

[0073] Now, the determination of the similarity between the uninstalled application m and the installed application n with respect to the set S(n,K) is described. Based on the applications installed by all network users, the number of first users who installed application x, the number of second users who installed application y, and the number of third users who installed both application x and application y can be counted. Then, based on the number of first users, the number of second users, and the number of third users, the similarity between application x and application y is calculated. The following expression can be used:

[0074]

[0075] Wherein, N(x) is the first number of users, N(y) is the second number of users, and |N(x)&N(y)| is the third number of users. Then, according to the above formula, the similarity between the uninstalled application m and the installed application n can be determined; and the top K applications with the highest similarity can be used to form a set S(n,K).

[0076] In an embodiment of the present invention, a method for determining the target user's interest in an installed application based on the target user's interest in the installed application may be to use a matrix decomposition algorithm to determine the target user's interest in an installed application based on the target user's interest in the installed application. Among them, the interest of each user in the entire network in the application (including the interest in installed applications and the interest in installed applications; the interest in installed applications may be an unknown number f) to generate an A*B matrix Z, where A is the number of users in the entire network, and B is the sum of the types of installed applications corresponding to the users in the entire network. Any element Z in the matrix ab is the interest of user a in application b. Then the matrix Z can be decomposed (e.g., using alternating least squares method) into two matrices Z1 and Z2; Z1 is A*C, Z2 is B*C, and Z is the product of the transposition of Z1 and Z2. The dot product of the transposition of Z1 and Z2 can be used to obtain the interest of the target user in the uninstalled application.

[0077] In an embodiment of the present invention, a method for determining the target user's interest in an installed application based on the target user's interest in the installed application may be to use a neural collaborative filtering algorithm to determine the target user's interest in the installed application based on the target user's interest in the installed application. The target user and the installed application corresponding to the target user may be encoded such as (one-hot encoding) to obtain a feature vector corresponding to the target user and a feature vector of the installed application corresponding to the target user. The feature vector corresponding to the target user and the feature vector of the installed application corresponding to the target user are then input into a trained neural network model, and the neural network model predicts the target user's interest in the installed application.

[0078] Of course, other methods of determining the target user's interest in the non-installed application may also be included, and the embodiment of the present invention does not limit this.

[0079] As an example of the present invention, according to the interest of the target user in each installed application in Table 3, the interest of the target user in the non-installed application is determined as shown in Table 4:

[0080] Application List Interest com.agg.next 0.008995 org.xinkb.blackboard.android 0.006733 com.baanana.homework 0.005636

[0081] Table 4

[0082] Step 208: Determine the interest categories to which the installed applications and non-installed applications of the target user belong based on a preset mapping relationship.

[0083] Step 210: Use the interest levels of installed applications and / or non-installed applications that belong to the same interest category to calculate the interest level of the corresponding interest category.

[0084] In the embodiment of the present invention, the applications installed by users on the entire network can be divided in advance to obtain multiple interest categories, and a mapping relationship between each application and the corresponding interest category can be established. There are many ways to divide the application categories, such as dividing according to the functions of the application, dividing according to the user groups of the application, etc., which are not limited in the embodiment of the present invention.

[0085] In an embodiment of the present invention, the interest categories to which the applications installed by the target user belong, and the interest categories to which the applications not installed by the target user belong can be determined based on a preset mapping relationship. Each interest category may include only the applications installed by the target user; it may also include only the applications not installed by the target user; it may also include both the applications installed by the target user and the applications not installed. For each interest category, the average interest of the target user in the applications belonging to the interest category is calculated to obtain the interest of the target user in the interest category. As an example, the interest of the target user in each interest category can be determined with reference to the following expression:

[0086]

[0087] Among them, G h is the target user's interest in the hth interest category; num h The number of applications included in the hth interest category; app p represents the target user’s interest in the p-th application in the h-th interest category.

[0088] As an example of the present invention, the target user's installed applications are shown in Table 3, and the non-installed applications are shown in Table 4. Among them, based on the mapping relationship, the interest categories to which the installed applications in Table 3 and the non-installed applications in Table 4 belong are determined as follows: com.abc.momo—social chat category, com.asssd.bangban, com.suhsuhiuhui.haofenshu, org.xinkb.blackboard.android, com.baanana.homework—primary and secondary education category, com.ddfgg.newsclient, com.tggbnh.news, com.agg.next—news reading category, com.hffrj.mybus—transportation category, com.jiaj—shopping category. Then, according to the interest in Table 3 and Table 4, the interest corresponding to each interest category can be calculated as follows: interest corresponding to social chat: 0.007369, interest corresponding to primary and secondary education: 0.006875, interest corresponding to news reading: 0.006672, interest corresponding to transportation: 0.009136, interest corresponding to shopping: 0.008335. Then, the interest information of the target user is obtained as follows: {interest corresponding to social chat: 0.007369, interest corresponding to primary and secondary education: 0.006875, interest corresponding to news reading: 0.006672, interest corresponding to transportation: 0.009136, interest corresponding to shopping: 0.008335}.

[0089] Step 212: Recommend information to the target user based on the interest level of each interest category.

[0090] In an embodiment of the present invention, a method for recommending information to the target user based on the interest level of each interest category may include the following sub-steps 42 to 44:

[0091] Sub-step 42: Determine the top N interest categories with the highest interest.

[0092] Sub-step 44: recommending information corresponding to the first N interest categories to the target user.

[0093] In an optional embodiment of the present invention, the top N interest categories with the highest interest can be selected from the interest information of the target user; wherein N can be set as required, and the embodiment of the present invention does not limit this. For example, if N is 3, then social chat category, transportation category and shopping category can be selected from the above determined interest information. Then, information associated with the top N interest categories, such as videos, pictures, etc., is recommended to the target user.

[0094] Of course, other methods of recommending information to the target user based on the interest level of each interest category may also be included, such as determining the interest categories in the interest information whose interest level is higher than an interest level threshold, and recommending information corresponding to the interest categories whose interest level is higher than the interest level threshold to the target user; the interest level threshold may be set as required; the embodiments of the present invention do not impose any restrictions on this.

[0095] In summary, in the embodiments of the present invention, by obtaining the usage information of the installed application and then determining the target user's interest in the installed application based on the usage information, the accuracy of determining the target user's interest in the installed application can be improved.

[0096] Furthermore, in an embodiment of the present invention, the interest category to which each application belongs is determined based on a preset mapping relationship, and then for each interest category, the target user's interest in the application belonging to the interest category is used to calculate the target user's interest in the interest category, and then information is recommended to the user based on the interest in each interest category; thereby, the user's interest in different interest categories can be determined, which increases the granularity of determining the user's interests, thereby enabling more fine-grained information recommendations to be made to the user, thereby improving the accuracy of information recommendations.

[0097] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0098] Reference Figure 3 , shows a structural block diagram of an information recommendation device embodiment of the present invention, which may specifically include the following modules:

[0099] The first information determination module 302 is used to determine the target user and the applications installed by the target user, and determine the interest of the target user in the installed applications, wherein the installed applications are applications other than pre-installed applications;

[0100] A second information determination module 304, configured to determine the target user's interest in the non-installed application program according to the target user's interest in the installed application program;

[0101] The recommendation module 306 is used to recommend information to the target user according to the interest of the target user in the installed application and the interest of the non-installed application.

[0102] Reference Figure 4 , shows a structural block diagram of an optional embodiment of an information recommendation device of the present invention.

[0103] In an optional embodiment of the present invention, the first information determination module 302 is used to obtain usage information of the installed application; and determine the target user's interest in the installed application based on the usage information.

[0104] In an optional embodiment of the present invention, the second information determination module 304 includes:

[0105] A first interest level determination submodule 3042, configured to determine the interest level of the target user in the non-installed application program according to the interest level of the target user in the installed application program by using a collaborative filtering algorithm;

[0106] A second interest level determination submodule 3044 is configured to determine the interest level of the target user in the non-installed application program according to the interest level of the target user in the installed application program by using a matrix decomposition algorithm;

[0107] The third interest level determination submodule 3046 is configured to determine the interest level of the target user in the non-installed application program based on the interest level of the target user in the installed application program by using a neural collaborative filtering algorithm.

[0108] In an optional embodiment of the present invention, the recommendation module 306 includes:

[0109] The category determination submodule 3062 is used to determine the interest category to which each application belongs according to a preset mapping relationship, wherein the application includes installed applications and non-installed applications;

[0110] The category interest determination submodule 3064 is used to calculate the interest degree of the target user in the interest category by using the interest degree of the target user in the application program belonging to the interest category for each interest category;

[0111] The information recommendation submodule 3066 is used to recommend information to the target user based on the interest level of each interest category.

[0112] In an optional embodiment of the present invention, the information recommendation submodule 3066 is used to determine the top N interest categories with the highest interest; and recommend information corresponding to the top N interest categories to the target user.

[0113] In summary, in the embodiments of the present invention, the target user, the target user's installed applications, and the target user's interest in the installed applications can be first determined; then, based on the target user's interest in the installed applications, the target user's interest in non-installed applications can be determined; and then, information is recommended to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications; thereby solving the problem in the prior art that it is difficult to determine user interests due to the lack of historical data, resulting in poor accuracy in information recommendation, and improving the accuracy of information recommendation for users.

[0114] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0115] Figure 5 1 is a block diagram of an electronic device 500 for information recommendation according to an exemplary embodiment. For example, the electronic device 500 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0116] Reference Figure 5 , the electronic device 500 may include one or more of the following components: a processing component 502 , a memory 504 , a power component 506 , a multimedia component 508 , an audio component 510 , an input / output (I / O) interface 512 , a sensor component 514 , and a communication component 516 .

[0117] The processing component 502 generally controls the overall operation of the electronic device 500, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 502 may include one or more processors 520 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 502 may include one or more modules to facilitate the interaction between the processing component 502 and other components. For example, the processing component 502 may include a multimedia module to facilitate the interaction between the multimedia component 508 and the processing component 502.

[0118] The memory 504 is configured to store various types of data to support operations on the device 500. Examples of such data include instructions for any application or method operating on the electronic device 500, contact data, phone book data, messages, pictures, videos, etc. The memory 504 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0119] The power component 506 provides power to the various components of the electronic device 500. The power component 506 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 500.

[0120] The multimedia component 508 includes a screen that provides an output interface between the electronic device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 508 includes a front camera and / or a rear camera. When the electronic device 500 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0121] The audio component 510 is configured to output and / or input audio signals. For example, the audio component 510 includes a microphone (MIC), and when the electronic device 500 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 504 or sent via the communication component 516. In some embodiments, the audio component 510 also includes a speaker for outputting audio signals.

[0122] I / O interface 512 provides an interface between processing component 502 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0123] The sensor assembly 514 includes one or more sensors for providing various aspects of status assessment for the electronic device 500. For example, the sensor assembly 514 can detect the open / closed state of the device 500, the relative positioning of components, such as the display and keypad of the electronic device 500, and the sensor assembly 514 can also detect the position change of the electronic device 500 or a component of the electronic device 500, the presence or absence of user contact with the electronic device 500, the orientation or acceleration / deceleration of the electronic device 500, and the temperature change of the electronic device 500. The sensor assembly 514 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 514 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0124] The communication component 516 is configured to facilitate wired or wireless communication between the electronic device 500 and other devices. The electronic device 500 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0125] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0126] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 504 including instructions, and the instructions can be executed by a processor 520 of an electronic device 500 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0127] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform an information recommendation method, the method comprising: determining a target user and applications installed by the target user, and determining the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; determining the target user's interest in non-installed applications based on the target user's interest in the installed applications; and recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0128] Optionally, determining the target user's interest in the installed application includes: acquiring usage information of the installed application; and determining the target user's interest in the installed application based on the usage information.

[0129] Optionally, determining the target user's interest in non-installed applications based on the target user's interest in the installed applications includes at least one of the following: using a collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a matrix decomposition algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a neural collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications.

[0130] Optionally, recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications includes: determining, based on a preset mapping relationship, an interest category to which each application belongs, the applications including installed applications and non-installed applications; for each interest category, calculating the target user's interest in the interest category using the target user's interest in the applications belonging to the interest category; and recommending information to the target user based on the interest of each interest category.

[0131] Optionally, recommending information to the target user based on the interest level of each interest category includes: determining top N interest categories with the highest interest levels; and recommending information corresponding to the top N interest categories to the target user.

[0132] Figure 6: is a structural diagram of an electronic device 600 for information recommendation according to another exemplary embodiment of the present invention. The electronic device 600 may be a server, which may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 622 (for example, one or more processors) and a memory 632, and one or more storage media 630 (for example, one or more mass storage devices) storing application programs 642 or data 644. Among them, the memory 632 and the storage medium 630 may be temporary storage or permanent storage. The program stored in the storage medium 630 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processor 622 may be configured to communicate with the storage medium 630 and execute a series of instruction operations in the storage medium 630 on the server.

[0133] The server may also include one or more power supplies 626, one or more wired or wireless network interfaces 650, one or more input and output interfaces 658, one or more keyboards 656, and / or one or more operating systems 641, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0134] An electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: determining a target user and applications installed by the target user, and determining the target user's interest in the installed applications, wherein the installed applications are applications other than pre-installed applications; determining the target user's interest in non-installed applications based on the target user's interest in the installed applications; and recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications.

[0135] Optionally, determining the target user's interest in the installed application includes: acquiring usage information of the installed application; and determining the target user's interest in the installed application based on the usage information.

[0136] Optionally, determining the target user's interest in non-installed applications based on the target user's interest in the installed applications includes at least one of the following: using a collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a matrix decomposition algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications; using a neural collaborative filtering algorithm to determine the target user's interest in non-installed applications based on the target user's interest in the installed applications.

[0137] Optionally, recommending information to the target user based on the target user's interest in the installed applications and the interest in the non-installed applications includes: determining, based on a preset mapping relationship, an interest category to which each application belongs, the applications including installed applications and non-installed applications; for each interest category, calculating the target user's interest in the interest category using the target user's interest in the applications belonging to the interest category; and recommending information to the target user based on the interest of each interest category.

[0138] Optionally, recommending information to the target user based on the interest level of each interest category includes: determining top N interest categories with the highest interest levels; and recommending information corresponding to the top N interest categories to the target user.

[0139] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0140] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0141] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0142] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0143] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0144] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0145] The above is a detailed introduction to an information recommendation method, an information recommendation device and an electronic device provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An information recommendation method, characterized in that: include: Determining a target user and applications installed by the target user, and determining the interest of the target user in the installed applications, wherein the installed applications are applications other than pre-installed applications; Determining the target user's interest in the non-installed application program according to the target user's interest in the installed application program; Determining the interest category to which each application belongs according to a preset mapping relationship, wherein the application includes an installed application and an uninstalled application; For each interest category, using the target user's interest in the application belonging to the interest category, calculate the target user's interest in the interest category; According to the interest level of each interest category, information is recommended to the target user.

2. The method according to claim 1, characterized in that The determining the target user's interest in the installed application comprises: Obtaining usage information of the installed application; The target user's interest in the installed application is determined based on the usage information.

3. The method according to claim 1, characterized in that The determining, based on the target user's interest in the installed application, the target user's interest in the non-installed application comprises at least one of the following: Determine the target user's interest in the non-installed application program by using a collaborative filtering algorithm based on the target user's interest in the installed application program; Determine the target user's interest in the non-installed application program based on the target user's interest in the installed application program by using a matrix decomposition algorithm; A neural collaborative filtering algorithm is used to determine the target user's interest in the non-installed application according to the target user's interest in the installed application.

4. The method according to claim 1, characterized in that: The recommending information to the target user based on the interest level of each interest category includes: Determine the top N interest categories with the highest interest; Recommend information corresponding to the top N interest categories to the target user.

5. An information recommendation device, characterized in that: include: A first information determination module, configured to determine a target user and applications installed by the target user, and determine the interest of the target user in the installed applications, wherein the installed applications are applications other than pre-installed applications; A second information determination module, configured to determine the target user's interest in the non-installed application program according to the target user's interest in the installed application program; A recommendation module, configured to recommend information to the target user based on the target user's interest in the installed application and the interest in the non-installed application; Wherein, the recommendation module includes: A category determination submodule, used to determine the interest category to which each application belongs according to a preset mapping relationship, wherein the application includes installed applications and non-installed applications; A category interest determination submodule, for calculating the target user's interest in the interest category by using the target user's interest in the application program belonging to the interest category for each interest category; The information recommendation submodule is used to recommend information to the target user based on the interest level of each interest category.

6. The device according to claim 5, characterized in that The first information determination module is used to obtain usage information of the installed application; and determine the target user's interest in the installed application based on the usage information.

7. The device according to claim 5, characterized in that The second information determination module includes: A first interest determination submodule, configured to determine the interest of the target user in the non-installed application program according to the interest of the target user in the installed application program by using a collaborative filtering algorithm; A second interest determination submodule, configured to determine the target user's interest in the non-installed application program based on the target user's interest in the installed application program by using a matrix decomposition algorithm; The third interest determination submodule is used to determine the interest of the target user in the non-installed application program according to the interest of the target user in the installed application program by using a neural collaborative filtering algorithm.

8. The device according to claim 5, characterized in that The information recommendation submodule is used to determine the top N interest categories with the highest interest; and recommend information corresponding to the top N interest categories to the target user.

9. An electronic device, characterized in that: The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the information recommendation method according to any one of method claims 1-4.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information recommendation method as described in any one of method claims 1-4.

Images