WO2021016760A1 - 应用推送方法及相关装置 - Google Patents

应用推送方法及相关装置 Download PDF

Info

Publication number
WO2021016760A1
WO2021016760A1 PCT/CN2019/098006 CN2019098006W WO2021016760A1 WO 2021016760 A1 WO2021016760 A1 WO 2021016760A1 CN 2019098006 W CN2019098006 W CN 2019098006W WO 2021016760 A1 WO2021016760 A1 WO 2021016760A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
target
user
ranking
favorable
Prior art date
Application number
PCT/CN2019/098006
Other languages
English (en)
French (fr)
Inventor
王小龙
Original Assignee
深圳市欢太科技有限公司
Oppo广东移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳市欢太科技有限公司, Oppo广东移动通信有限公司 filed Critical 深圳市欢太科技有限公司
Priority to PCT/CN2019/098006 priority Critical patent/WO2021016760A1/zh
Priority to CN201980097278.6A priority patent/CN113950678A/zh
Publication of WO2021016760A1 publication Critical patent/WO2021016760A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering

Definitions

  • This application relates to the technical field of mobile terminals, and in particular to an application push method and related devices.
  • smart phones can support more and more applications and more powerful functions. Smart phones are developing in a diversified and personalized direction and become an indispensable electronic product in users’ lives. . There are many types of applications on the app store for users to choose from for downloading, but the app store cannot intelligently perform statistical learning based on the applications that users have downloaded, so as to obtain applications suitable for users and recommend them to users, or recommended applications Not suitable for users, resulting in the failure to increase the download volume of the app store.
  • the embodiments of the present application provide an application pushing method and related devices, which are beneficial for recommending applications suitable for users to use.
  • an embodiment of the present application provides an application push method applied to a server, and the method includes:
  • an embodiment of the present application provides an application pushing device applied to a server, the application pushing device includes a processing unit and a communication unit, wherein:
  • the processing unit is configured to determine a target application type whose target user's interest degree is greater than a preset interest degree; and to obtain multiple applications in an application store whose application type is the target application type, and obtain information about the multiple applications Comment information; and used to determine a target application according to the comment information of the multiple applications; and used to output a push message recommending a user to download the target application through the communication unit, the push message including the download of the target application Links and introduction information.
  • an embodiment of the present application provides an electronic device, including a controller, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be controlled by the above
  • the above-mentioned program includes instructions for executing the steps in any method of the first aspect of the embodiments of the present application.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the foregoing computer-readable storage medium stores a computer program for electronic data exchange, wherein the foregoing computer program enables a computer to execute In one aspect, some or all of the steps described in any method.
  • embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute For example, some or all of the steps described in any method of the first aspect.
  • the computer program product may be a software installation package.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • FIG. 1A is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • FIG. 1B is a schematic flowchart of an application pushing method provided by an embodiment of the present application.
  • FIG. 2 is a schematic flowchart of another application pushing method provided by an embodiment of the present application.
  • FIG. 3 is a schematic flowchart of another application push method provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Fig. 5 is a block diagram of functional units of an application pushing device provided by an embodiment of the present application.
  • Electronic devices can include various handheld devices with wireless communication functions, vehicle-mounted devices, wearable devices (such as smart watches, smart bracelets, pedometers, etc.), computing devices or other processing devices connected to wireless modems, and various Forms of user equipment (User Equipment, UE), mobile station (Mobile Station, MS), terminal equipment (terminal device), and so on.
  • UE User Equipment
  • MS Mobile Station
  • terminal device terminal device
  • FIG. 1A is a schematic structural diagram of an electronic device 100 provided by an embodiment of the present application.
  • the electronic device 100 includes a housing 110, a circuit board 120 disposed in the housing 110, and The touch screen 130 and the camera 140 on the housing 110 are provided with a processor 121 and a memory 122 on the circuit board 120.
  • the memory 122 is connected to the processor 121, and the processor 121 is connected to the touch Display 130; among them,
  • the touch screen 130 is used to display push messages of the target application
  • the memory 122 is used to store the download link and introduction information of the target application
  • the processor 121 is configured to determine a target application type with a target user's interest level greater than a preset interest level; and to obtain multiple applications in an application store whose application type is the target application type, and to obtain the multiple applications And used to determine the target application according to the comment information of the multiple applications; and used to output a push message recommending downloading the target application through the electronic device held by the target user, the push message including all The download link and introduction information of the target application are described.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • FIG. 1B is a schematic flowchart of an application pushing method provided in an embodiment of the present application, which is applied to a server.
  • the application push method includes:
  • S101 The server determines a target application type whose interest degree of the target user is greater than a preset interest degree.
  • the server is the server corresponding to the application store.
  • the merchants of the application store have various types of applications.
  • the server can determine that the target is based on the application download record of the target electronic device held by the user, or the user's footprint when browsing the application store.
  • the target application type that the application is more interested in that is, the application type whose user interest is greater than the preset interest.
  • the target application type may be a game application type, or a social application type, or a video application type.
  • the target application type may include multiple applications Types of.
  • S102 The server obtains multiple applications of the target application type in the application store, and obtains comment information of the multiple applications.
  • the server can obtain multiple applications in the application store whose application type is the target application type.
  • the number of multiple applications can be preset by the user.
  • the target application type is a game application type
  • multiple applications can be the top ten downloads.
  • you can further obtain comment information for these multiple applications.
  • S103 The server determines a target application according to the review information of the multiple applications.
  • the server can perform semantic analysis based on the review information of multiple applications, or combine all records of the user's usual use of the application store, or combine the current network environment of the electronic device, that is, the traffic environment or the WIFI environment, etc.
  • the target application is determined in each application, so that the target application can be pushed to the electronic device.
  • the server outputs a push message recommending to download the target application through the electronic device held by the target user, the push message including the download link and introduction information of the target application.
  • the server sends the push message of the target application to the electronic device, and outputs the push message displaying the download target application through the electronic device.
  • the target user holding the electronic device can determine whether to download the target application according to the download link and introduction information of the target application.
  • the target application needs to be downloaded so as to realize the application push to the target user.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • the determining the target application type with the target user's interest level greater than the preset interest level includes: determining the application types of multiple applications downloaded by the electronic device from the application store, and determining each application The number of applications corresponding to the type; according to the number of applications of each application type, a target application type with a user interest level greater than a preset interest level is determined.
  • the server may first determine the application types of multiple applications downloaded by the electronic device from the application store, and determine the number of applications corresponding to each application type. For the number of applications of each application type, determine the target application type whose user interest is greater than the preset interest.
  • the target application type may be the most downloaded application among multiple application types, or the most frequently downloaded application, for example, Application type A corresponds to 8 applications, application type B corresponds to 5 applications, and application type C corresponds to 4 applications.
  • Application type A can be used as the target application type, and the download time of 8 applications of application type A is detected , That is, the time period between the time when the download of the first application is completed to the time when the download of the last application is completed, which is 4 months, the download duration corresponding to application type B is 2 months, and the download duration of application type C is 2 At the end of the month, you can use application type B as the target application type. It is not that the more applications of a certain application type are downloaded, the more users are interested in this application type.
  • the application type of each application downloaded by the electronic device is determined first, and then the number of applications corresponding to each application type is determined, so that According to the number of applications of each application type, the target application type with high interest of the target user is obtained more accurately, which is beneficial to the application push to the user for the target application type.
  • the determining the target application according to the review information of the multiple applications includes: performing semantic analysis on the review information of each application in the multiple applications to obtain characteristic information of the reviewing user; and obtaining pre-stored The feature information of the target user is selected, and an application whose matching degree between the feature information of the comment user and the feature information of the target user is higher than a first preset threshold is selected as the target application.
  • the review information of each application in multiple applications includes multi-day user reviews.
  • the semantic analysis of the review information of each application is performed to determine the characteristic information of each application.
  • the characteristic information may include the annual salary information and occupation of the reviewing user.
  • Information, hobby information and other information for example, the characteristic information of the review user corresponding to application 1 is that the user age group is concentrated in 15-18 years old, and the characteristic information of the review user corresponding to application 2 is that the user age group is concentrated in 19-25 years old, the application 3
  • the characteristic information of the corresponding comment users is that the age group of users is between 26-30 years old.
  • the pre-stored characteristic information of the target user can be obtained, and the application with the highest matching degree between the characteristic information of the comment user and the characteristic information of the target user can be selected as Target application, for example, if the target user is 24 years old, then application 2 is selected as the target application.
  • the semantic analysis of the comment information of each application in multiple applications can determine the characteristic information of the comment user of each application, so that the degree of matching between the characteristic information of the comment user and the characteristic information of the target user can be selected
  • the application larger than the first preset threshold is used as the target application. Since the comment user and the target user are similar, it is easy to resonate, so the pushed target application is more suitable for the target user.
  • the determining the target application according to the review information of the multiple applications includes: determining multiple user reviews of each of the multiple applications according to the review information of the multiple applications; Determine the keyword set of each application according to the multiple user reviews of each application, wherein the keywords in the keyword set are vocabularies in a preset vocabulary set, and each keyword corresponds to a user comment
  • the number of favorable comments and the favorable rate of each application is determined according to the keyword set of each application; the target application is determined according to the number of favorable comments and the favorable rate of each application.
  • a keyword set for each application can be obtained according to multiple user reviews of each application, and the words in the keyword set are pre- Set the vocabulary in the vocabulary set, the preset vocabulary set can be set by the user in advance, or the server provides some vocabularies for the user to select to obtain the preset vocabulary set, each keyword corresponds to a user comment, and a user comment may include At least one keyword.
  • users can search for keywords to find the application corresponding to the keyword.
  • the number of favorable comments and favorable rate of each application can be determined.
  • the more keywords in the keyword set corresponding to an application the more favorable comments of the application, combined with the comments of the application
  • the number can determine the favorable rate and thus the target application.
  • the user who downloads the application can comment or evaluate the application, and obtain a set of keywords for each application after obtaining multiple user comments for each application in multiple applications .
  • the keyword set the number of favorable comments and the frequency of each application can be quickly determined, and the user reviews of each application can be combined to select target users that can be pushed to download target applications, which is beneficial to help target users download easy-to-use and suitable applications.
  • the determining the number of favorable comments and the favorable rate of each application according to the keyword set of each application includes: detecting whether the keyword set of each application contains user sentiment If yes, determine whether the emotion expressed by the first target vocabulary is a positive emotion; if yes, determine that the user comment corresponding to the first target vocabulary is favorable, and determine the number of the first target vocabulary; according to The number of first target words of each application determines the number of favorable comments and the favorable rate of each application.
  • the keyword set of each application contains the first target vocabulary indicating the user’s emotions, such as like, easy to use, difficult Use, happy, disgusting, irritable, etc. can indicate the user’s emotions when using the application. If there is, determine whether the emotion expressed by the first target vocabulary is a positive emotion, if so, determine the corresponding to the first target vocabulary
  • the user comments are favorable, so the number of favorable comments of the corresponding application can be determined according to the number of first target words, and then the favorable rate can be calculated.
  • the keyword set of each application may contain vocabulary that can indicate the user's emotions, so that it can be determined whether the user's emotions in the process of using the application are positive emotions. If it is a positive emotion, it can indicate The vocabulary corresponding to the positive emotion is praise. According to the user's emotional tendency, the number of favorable comments in multiple user reviews is quickly obtained and the number of favorable comments is determined. Combining the number of favorable comments and the good frequency of each application is conducive to determining the target application suitable for users.
  • the determining the number of favorable comments and the favorable rate of each application according to the keyword set of each application includes: detecting whether the keyword set of each application contains an indication of user behavior If yes, determine whether the user will use the application again according to the user behavior indicated by the second target vocabulary; if yes, determine that the user comment corresponding to the second target vocabulary is favorable, and determine the second target The number of words; the number of favorable comments and the favorable rate of each application are determined according to the number of second target words of each application.
  • the keyword set of each application contains a second target vocabulary indicating user behavior, such as sensitive response and multiple functions.
  • Good operation or stuttering, no click, long waiting time, abandoned pit, uninstall and other vocabulary, according to the user behavior indicated by the second target vocabulary to determine whether the user will respond again, if it is, determine the second target vocabulary corresponding
  • the user comments are favorable, so the number of favorable comments and the good frequency of each application can be determined according to the number of second target words.
  • the keyword set of each application may contain vocabulary that can indicate user behavior, so that the user's behavior in the process of using the application can be determined to determine whether the user will use the application again, and if it will be used again, then It can indicate that the vocabulary is favorable, and if the user does not use the application, it can indicate that the vocabulary is negative. According to whether the user continues to use an application to determine the positive reviews and the number of positive reviews in the multiple user reviews of the application, combined with the number of positive reviews and good frequency of each application, it is beneficial to determine the target application suitable for the user.
  • the determining the target application according to the number of favorable comments and the favorable rate of each application includes sorting the multiple applications in descending order of the number of favorable comments of each application, Get the first ranking; sort the multiple applications in the order of the favorable rate of each application from high to low to obtain the second ranking; according to the first ranking and the second ranking from the multiple At least one application is selected as the target application.
  • each application is sorted according to the number of good reviews of each application in descending order, and the first sorting can be obtained, and each application is sorted according to the good frequency of each application in descending order to obtain
  • the second ranking for example, the number of reviews for application 1 is 100, 70 are positive, and the positive rate is 70%, the number of reviews for application 2 is 150, the positive number is 60, the positive rate is 40%, and the reviews for application 3 The number is 300, and there are 90 good reviews, and the positive rate is 30%. Sort according to the number of good reviews of each application.
  • the first ranking obtained is Application 3, Application 1, Application 2, and sorted according to the good frequency of each application
  • the second ranking obtained is application 1, application 2, application 3. Visible, more praise may be because more users commented, but it does not mean that users are really satisfied with this application.
  • the high praise rate may be because fewer users commented , It does not mean that users are really satisfied with this application.
  • multiple applications can be sorted according to the number of favorable comments to get the first ranking, and multiple applications can be sorted according to the good frequency to get the second ranking.
  • the first order and the second order select the target application from multiple applications, which is beneficial to improve the reliability and comprehensiveness of the target application selection.
  • the selecting at least one application from the multiple applications as the target application according to the first ranking and the second ranking includes: selecting from the multiple applications, The application with the smallest sum of the ranking in the first ranking and the ranking in the second ranking is the target application, or the ranking in the first ranking is greater than the second preset threshold, and the At least one application ranked higher than the third preset threshold in the second ranking is the target application.
  • the first ranking is application 3, application 1, application 2, and the second ranking is application 1, application 2, and application 3. If the application with the smallest sum of the first ranking and the second ranking is selected as If the target application is the target application, the target application is application 1. If the ranking in the first ranking is greater than the second preset threshold, such as the first ranking application, the ranking in the second ranking is greater than the third preset threshold, such as ranking first ,
  • the target applications are Application 1 and Application 3.
  • the target application when selecting the target application, you can select the application with the smallest between the ranking in the first ranking and the ranking in the second ranking, or select the ranking in the first ranking to be greater than the second preset threshold and In the second ranking, the applications ranked higher than the third preset threshold can make the selected target applications not only have more praise than other applications, but also have a higher frequency of goodness.
  • the method further includes: when it is detected that the electronic device starts the application store application, displaying on the homepage of the application store Display the target application and/or applications similar to the target application.
  • the server sends a push message of the target application to the electronic device to recommend the user to download the target application. It can also update the data on the homepage of the application store so that the electronic device can see the application when the application store application is started.
  • the target application displayed on the homepage of the store, or an application similar to the target application.
  • the push message of the target application only includes the download link and brief introduction information of the target application, and the target user can see more detailed introduction information of the target application in the application store.
  • the target application not only can the target application be pushed to the user through the electronic device, but the user can also view the target application on the homepage of the application store, so that more detailed information about the target application can be obtained, and the user can again choose whether to download the target application.
  • FIG. 2 is a schematic flowchart of an application push method provided by an embodiment of the present application, which is applied to a server. As shown in the figure, the application push method includes:
  • the server determines the application types of multiple applications downloaded from the application store by the electronic device, and determines the number of applications corresponding to each application type.
  • S202 The server determines a target application type with a user interest degree greater than a preset interest degree according to the number of applications of each application type.
  • S203 The server obtains multiple applications of the target application type in the application store, and obtains comment information of the multiple applications.
  • S204 The server determines a target application according to the review information of the multiple applications.
  • the server outputs a push message recommending downloading the target application through the electronic device held by the target user, the push message including the download link of the target application and introduction information.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • the application type of each application downloaded by the electronic device is determined first, and then the number of applications corresponding to each application type is determined, so that each application The number of types of applications is more accurate to obtain the target application types with higher interest of the target users, which is conducive to application push to users for the target application types.
  • FIG. 3 is a schematic flowchart of an application push method provided by an embodiment of the present application, which is applied to a server. As shown in the figure, the application push method includes:
  • the server determines the application types of multiple applications downloaded from the application store by the electronic device, and determines the number of applications corresponding to each application type.
  • the server determines a target application type with a user interest degree greater than a preset interest degree according to the number of applications of each application type.
  • S303 The server obtains multiple applications of the target application type in the application store, and obtains comment information of the multiple applications.
  • S304 The server determines multiple user comments for each of the multiple applications according to the review information of the multiple applications.
  • the server determines a keyword set of each application according to multiple user comments of each application, wherein the keywords in the keyword set are words in a preset vocabulary set, and each key The word corresponds to a user comment.
  • S306 The server determines the number of favorable comments and the favorable rate of each application according to the keyword set of each application.
  • S307 The server determines the target application according to the number of favorable comments and favorable rate of each application.
  • the server outputs a push message recommending downloading the target application through the electronic device held by the target user, the push message including the download link of the target application and introduction information.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • the application type of each application downloaded by the electronic device is determined first, and then the number of applications corresponding to each application type is determined, so that each application The number of types of applications is more accurate to obtain the target application types with higher interest of the target users, which is conducive to application push to users for the target application types.
  • users who download the application can comment or evaluate the application, and obtain a set of keywords for each application after obtaining multiple user reviews for each application in multiple applications.
  • the collection can quickly determine the number and frequency of good reviews for each application, and combine the user reviews of each application to select target applications that can be pushed and downloaded for the target users, which is conducive to helping target users download easy-to-use and suitable applications.
  • FIG. 4 is a schematic structural diagram of an electronic device 400 provided by an embodiment of the present application.
  • the electronic device 400 has one or Multiple application programs and operating systems.
  • the electronic device 400 includes a processor 410, a memory 420, a communication interface 430, and one or more programs 421, wherein the one or more programs 421 are stored in the In the memory 420 and configured to be executed by the processor 410, the one or more programs 421 include instructions for executing the following steps;
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • the instructions in the program are specifically used to perform the following operations: determining that the electronic device is downloaded from the application store And determine the number of applications corresponding to each application type; according to the number of applications of each application type, determine the target application type whose user interest is greater than the preset interest.
  • the instructions in the program are specifically used to perform the following operations: Comment information on each of the multiple applications Perform semantic analysis to obtain the characteristic information of the comment user; obtain the pre-stored characteristic information of the target user, and select the application whose matching degree between the characteristic information of the comment user and the characteristic information of the target user is higher than the first preset threshold.
  • Comment information on each of the multiple applications Perform semantic analysis to obtain the characteristic information of the comment user; obtain the pre-stored characteristic information of the target user, and select the application whose matching degree between the characteristic information of the comment user and the characteristic information of the target user is higher than the first preset threshold.
  • the target application is specifically used to perform the following operations: Comment information on each of the multiple applications Perform semantic analysis to obtain the characteristic information of the comment user; obtain the pre-stored characteristic information of the target user, and select the application whose matching degree between the characteristic information of the comment user and the characteristic information of the target user is higher than the first preset threshold.
  • the instructions in the program are specifically used to perform the following operations: determining the target application based on the review information of the multiple applications Multiple user comments for each of the multiple applications; determine the keyword set of each application according to the multiple user comments of each application, wherein the keywords in the keyword set are preset words
  • each keyword corresponds to a user comment
  • the number of favorable comments and the favorable rate of each application are determined according to the keyword set of each application
  • the number of favorable comments and the favorable comment of each application are determined Rate determines the target application.
  • the instructions in the program are specifically used to perform the following operations: detecting the Whether the keyword set of each application contains the first target vocabulary indicating user emotion; if so, determine whether the emotion expressed by the first target vocabulary is a positive emotion; if so, determine whether the user comment corresponding to the first target vocabulary is favorable , And determine the number of the first target vocabulary; determine the number of favorable comments and the favorable rate of each application according to the number of the first target vocabulary of each application.
  • the instructions in the program are specifically used to perform the following operations: detecting the Whether the keyword set of each application contains a second target vocabulary indicating user behavior; if so, determine whether the user will use the application again according to the user behavior indicated by the second target vocabulary; if so, determine that the second target vocabulary corresponds
  • the user comments of is favorable, and the number of the second target vocabulary is determined; the number of favorable comments and the favorable rate of each application are determined according to the number of the second target vocabulary of each application.
  • the instructions in the program are specifically used to perform the following operations: Sort the multiple applications in the most-to-less order to obtain the first ranking; sort the multiple applications in the order of the favorable ratings of each application from high to low to obtain the second ranking; The first ranking and the second ranking select at least one application from the plurality of applications as the target application.
  • the instructions in the program are specifically used to execute The following operation: among the multiple applications, the application with the smallest sum of the ranking in the first ranking and the ranking in the second ranking is selected as the target application, or, selecting the application in the first ranking
  • the ranking in the ranking is greater than the second preset threshold, and at least one application ranked greater than the third preset threshold in the second ranking is the target application.
  • the instructions in the program are specifically used to perform the following operations: when it is detected that the electronic device starts the application store application, The target application and/or applications similar to the target application are displayed on the homepage of the application store.
  • the electronic device includes hardware structures and/or software modules corresponding to each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.
  • the embodiments of the present application may divide the functional units of the electronic device according to the foregoing method examples.
  • each functional unit may be divided corresponding to each function, or two or more functions may be integrated into one control unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of this application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • FIG. 5 is a block diagram of the functional unit composition of the device 500 involved in an embodiment of the present application.
  • the application pushing device 500 is applied to a server, and the application pushing device 500 includes a processing unit 501 and a communication unit 502, wherein:
  • the processing unit 501 is configured to determine a target application type whose target user's interest degree is greater than a preset interest degree; and to obtain multiple applications in an application store whose application type is the target application type, and to obtain the multiple applications And used to determine the target application according to the comment information of the multiple applications; and used to output a push message recommending the user to download the target application through the communication unit 502, the push message including the target application Download link and introduction information.
  • the server first determines the target application type whose target user's interest degree is greater than the preset interest degree, and secondly, obtains multiple applications whose application type is the target application type in the application store, and obtains the The review information of multiple applications, and then determine the target application according to the review information of the multiple applications, and finally, output a push message recommending to download the target application through the electronic device held by the target user, the push message including The download link and introduction information of the target application.
  • the server can intelligently determine the target application type that the target user is interested in, and can determine the target application suitable for the target user according to the review information of multiple applications whose application type is the target application type, and thereby use the electronic device held by the target user Output push information for the target application. After seeing the push information, the target user can choose whether to download the target application. This improves the reliability of application push and helps increase the number of application downloads in the application store.
  • the processing unit 501 is specifically configured to: determine that the target electronic device held by the target user is from the application The application types of multiple applications downloaded by the store, and the number of applications corresponding to each application type is determined; and the target application type is used to determine the target application type whose user interest is greater than the preset interest according to the number of applications of each application type.
  • the processing unit 501 is specifically configured to: perform semantic analysis on the review information of each application in the multiple applications, Acquiring characteristic information of the reviewing user; and for acquiring the pre-stored characteristic information of the target user, and determining that the application whose matching degree between the characteristic information of the reviewing user and the characteristic information of the target user is higher than a first preset threshold is said Target application.
  • the processing unit 501 is specifically configured to: determine the target application according to the review information of the multiple applications Multiple user reviews for each application; and a keyword set for determining each application according to the multiple user reviews for each application, wherein the keywords in the keyword set are preset vocabulary sets Each keyword corresponds to a user comment; and used to determine the number of favorable comments and favorable rate of each application according to the keyword set of each application; The number of positive reviews and the positive rate determine the target application.
  • the processing unit 501 is specifically configured to: detect the number of favorable comments and the favorable rate of each application according to the keyword set of each application Whether the keyword set contains the first target vocabulary indicating the user’s emotion; and if it is, it is used to determine whether the emotion expressed by the first target vocabulary is a positive emotion; if it is, it is determined that the user comment corresponding to the first target vocabulary is favorable, And determining the number of the first target vocabulary; and determining the number of favorable comments and the favorable rate of each application according to the number of the first target vocabulary of each application.
  • the processing unit 501 is specifically configured to: detect the number of favorable comments and the favorable rate of each application according to the keyword set of each application Whether the keyword set contains a second target vocabulary indicating user behavior; and if so, determine whether the user will use the application again according to the user behavior indicated by the second target vocabulary; if so, determine the corresponding second target vocabulary
  • the user comments are favorable, and the number of the second target words is determined; and used to determine the number of favorable comments and the favorable rate of each application according to the number of second target words of each application.
  • the processing unit 501 is specifically configured to: according to the number of favorable comments of each application from more to less Sorting the multiple applications in order to obtain a first ranking; and for sorting the multiple applications in the order of the favorable ratings of each application from high to low to obtain the second ranking; and Select at least one application from the plurality of applications as the target application according to the first ranking and the second ranking.
  • the processing unit 501 is specifically configured to: Out of the plurality of applications, the application with the smallest sum of the ranking in the first ranking and the ranking in the second ranking is the target application, or, and used to select the application in the first ranking
  • the middle ranking is greater than the second preset threshold, and at least one application ranking greater than the third preset threshold in the second ranking is the target application.
  • the processing unit 501 is specifically configured to: when it is detected that the electronic device starts the application store, log in to the application store
  • the homepage of shows the target application and/or applications similar to the target application.
  • the electronic device may further include a storage unit 503, the processing unit 501 and the communication unit 502 may be a controller or a processor, and the storage unit 503 may be a memory.
  • An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method as recorded in the above method embodiment ,
  • the aforementioned computer includes a mobile terminal.
  • the embodiments of the present application also provide a computer program product.
  • the above-mentioned computer program product includes a non-transitory computer-readable storage medium storing a computer program.
  • the above-mentioned computer program is operable to cause a computer to execute any of the methods described in the above-mentioned method embodiments. Part or all of the steps of the method.
  • the computer program product may be a software installation package, and the above-mentioned computer includes a mobile terminal.
  • the disclosed device may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the above-mentioned units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored, or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.
  • the units described above as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each unit in each embodiment of the present application may be integrated into one control unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, A number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the foregoing methods of the various embodiments of the present application.
  • the aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other various media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: flash disk , Read-only memory (English: Read-Only Memory, abbreviated as: ROM), random access device (English: Random Access Memory, abbreviated as: RAM), magnetic disk or optical disc, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Stored Programmes (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

一种应用推送方法及相关装置，应用于服务器，该方法包括：确定目标用户兴趣度大于预设兴趣度的目标应用类型（S101）；获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息（S102）；根据所述多个应用的评论信息确定目标应用（S103）；通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息（S104）。该方法有利于为用户推荐适合用户使用的应用。

Description

应用推送方法及相关装置 技术领域
本申请涉及移动终端技术领域，具体涉及一种应用推送方法及相关装置。
背景技术
随着智能手机等移动终端的大量普及应用，智能手机能够支持的应用越来越多，功能越来越强大，智能手机向着多样化、个性化的方向发展，成为用户生活中不可缺少的电子用品。应用商店上架有多种类型的应用供用户选择，从而进行下载，但是应用商店不能够智能的根据用户已下载的应用进行统计学习，从而得到适合用户使用的应用并推荐给用户，或者推荐的应用不适合用户，从而导致应用商店的下载量得不到提升。
发明内容
本申请实施例提供了一种应用推送方法及相关装置，有利于为用户推荐适合用户使用的应用。
第一方面，本申请实施例提供一种应用推送方法，应用于服务器，所述方法包括：
确定目标用户兴趣度大于预设兴趣度的目标应用类型；
获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；
根据所述多个应用的评论信息确定目标应用；
通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
第二方面，本申请实施例提供一种应用推送装置，应用于服务器，所述应用推送装置包括处理单元和通信单元，其中，
所述处理单元，用于确定目标用户兴趣度大于预设兴趣度的目标应用类型；以及用于获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；以及用于根据所述多个应用的评论信息确定目标应用；以及用于通过所述通信单元输出推荐用户下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
第三方面，本申请实施例提供一种电子设备，包括控制器、存储器、通信接口以及一个或多个程序，其中，上述一个或多个程序被存储在上述存储器中，并且被配置由上述控制器执行，上述程序包括用于执行本申请实施例第一方面任一方法中的步骤的指令。
第四方面，本申请实施例提供了一种计算机可读存储介质，其中，上述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，上述计算机程序使得计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。
第五方面，本申请实施例提供了一种计算机程序产品，其中，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如本申请实施例第一方面任一方法中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述 多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1A是本申请实施例提供的一种电子设备的结构示意图；
图1B是本申请实施例提供的一种应用推送方法的流程示意图；
图2是本申请实施例提供的另一种应用推送方法的流程示意图；
图3是本申请实施例提供的另一种应用推送方法的流程示意图；
图4是本申请实施例提供的一种电子设备的结构示意图；
图5是本申请实施例提供的一种应用推送装置的功能单元组成框图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
电子设备可以包括各种具有无线通信功能的手持设备、车载设备、可穿戴设备(例如智能手表、智能手环、计步器等)、计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备(User Equipment，UE)，移动台(Mobile Station，MS)，终端设备(terminal device)等等。为方便描述，上面提到的设备统称为电子设备。
下面对本申请实施例进行详细介绍。
请参阅图1A，图1A是本申请实施例提供的一种电子设备100的结构示意图，所述电子设备100包括：壳体110、设置于所述壳体110内的电路板120、设置于所述壳体110上的触控显示屏130和摄像头140，所述电路板120上设置有处理器121和存储器122，存储器122与所述处理器121连接，所述处理器121连接所述触控显示屏130；其中，
所述触控显示屏130，用于显示所述目标应用的推送消息；
所述存储器122，用于存储所述目标应用的下载链接以及介绍信息；
所述处理器121，用于确定目标用户兴趣度大于预设兴趣度的目标应用类型；以及用于获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；以及用于根据所述多个应用的评论信息确定目标应用；以及用于通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
请参阅图1B，图1B是本申请实施例提供了一种应用推送方法的流程示意图，应用于服务器。如图所示，本应用推送方法包括：
S101，服务器确定目标用户兴趣度大于预设兴趣度的目标应用类型。
其中，服务器为应用商店对应的服务器，应用商店商家有各种类型的应用，服务器可以根据用户持有的目标电子设备的应用下载记录，或者用户在浏览应用商店时的足迹等信息，确定目标有应用比较感兴趣的目标应用类型，即用户兴趣度大于预设兴趣度的应用类型，目标应用类型可能为游戏应用类型，或者社交应用类型，或者视频应用类型等，目标应用类型可以包括多种应用类型。
S102，所述服务器获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息。
其中，服务器可以获取应用商店中，应用类型为目标应用类型的多个应用，多个应用的数目可以由用户预先设定，例如目标应用类型为游戏应用类型，多个应用可以是下载量前十的游戏应用，或者，评分最高的前十个游戏应用，或者，用户喜欢的某个游戏开发商开发的所有游戏应用。此外，还可以进一步获取这多个应用的评论信息。
S103，所述服务器根据所述多个应用的评论信息确定目标应用。
其中，服务器可以根据多个应用的评论信息，做语义分析，或者结合用户平时在使用应用商店时的所有记录，或者结合电子设备当前所处的网络环境，即流量环境或者WIFI环境等，从多个应用中确定出目标应用，从而可以针对目标应用向电子设备进行推送。
S104，所述服务器通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
其中，服务器将所述目标应用的推送消息发送给电子设备，并通过电子设备来输出显示下载目标应用的推送消息，持有电子设备的目标用户可以根据目标应用的下载链接以及介绍信息，确定是否需要下载目标应用，从而，实现对目标用户的应用推送。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所 述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
在一个可能的示例中，所述确定目标用户兴趣度大于预设兴趣度的目标应用类型，包括：确定所述电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量；根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
其中，在确定用户兴趣度大于预设兴趣度的目标应用类型是，服务器可以先确定电子设备从应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量，在根据每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型，例如，目标应用类型可以是多个应用类型中下载的应用数量最多的，或者是下载的频率最高的，例如，应用类型A对应有8个应用，应用类型B对应有5个应用，应用类型C对应有4个应用，可以把应用类型A作为目标应用类型，在检测到应用类型A的8个应用的下载时长，即当中第一个应用下载完成的时间到最后一个应用下载完成的时间之间的时间段，为4个月，应用类型B对应的下载时长为2个月，应用类型C的下载时长为2个月时，可以把应用类型B多为目标应用类型，并不是某个应用类型的应用下载的越多才表明用户对这个应用类型感兴趣。
可见，本示例中，在确定目标应用兴趣度大于预设兴趣度的目标应用类型时，先确定了电子设备下载的每个应用的应用类型，再确定每个应用类型对应的应用数量，从而可以根据每个应用类型的应用数量较准确的得到目标用户兴趣度较高的目标应用类型，有利于针对目标应用类型向用户进行应用推送。
在一个可能的示例中，所述根据所述多个应用的评论信息确定目标应用，包括：对所述多个应用中每个应用的评论信息进行语义分析，获取评论用户的特征信息；获取预存的所述目标用户的特征信息，并选取评论用户的特征信息和所述目标用户的特征信息匹配度高于第一预设阈值的应用为所述目标应用。
其中，多个应用中每个应用的评论信息都包括多天用户评论，对每个应用的评论信息进行语义解析，确定评论每个应用的特征信息，特征信息可是包括评论用户的年薪信息，职业信息，爱好信息等信息，例如，应用1对应的评论用户的特征信息为用户年龄段集中在15-18岁，应用2对应的评论用户的特征信息为用户年龄段集中在19-25岁，应用3对应的评论用户的特征信息为用户年龄段集中在26-30岁，此时可以获取预存的目标用户的特征信息，从而选取评论用户的特征信息和目标用户的特征信息匹配度最高的应用为目标应用，例如，目标用户为24岁，则选取应用2为目标应用。
可见，本示例中，对多个应用中每个应用的评论信息进行语义分析，可以确定每个应用的评论用户的特征信息，从而可以选取评论用户的特征信息和目标用户的特征信息的匹配度大于第一预设阈值的应用作为目标应用，由于评论用户和目标用户相似，容易产生共鸣，因此推送的目标应用更适合目标用户。
在一个可能的示例中，所述根据所述多个应用的评论信息确定目标应用，包括：根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论；根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论；所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率；根据所述每个应用的好评数量以及好评 率确定目标应用。
其中，在根据每个应用的评论信息从多个应用中确定出目标应用时，可以根据每个应用的多条用户评论得到一个针对每个应用的关键词集合，关键词集合中的词汇为预设词汇集合中的词汇，预设词汇集合可以由用户提前进行设定，或者，服务器提供一些词汇供用户进行选取后得到预设词汇集合，每个关键词对应一条用户评论，一条用户评论可以包括至少一个关键词。此外，还可以实现用户铜鼓搜索关键词来查找该关键词对应的应用。
其中，根据每个应用的关键词集合可以确定每个应用的好评数量以及好评率，某个应用对应的关键词集合中的关键词越多，代表该应用的好评越多，结合该应用的评论数量可以确定好评率，从而确定目标应用。
可见，本示例中，当某个应用被下载后下载该应用的用户可以对该应用进行评论或评价，获取多个应用中每个应用的多条用户评论后得到每个应用的一个关键词集合，根据关键词集合可以快速确定每个应用的好评数量以及好频率，结合每个应用的用户评论来为目标用户选取可以推送下载的目标应用，有利于帮助目标用户下载到好用合适的应用。
在一个可能的示例中，所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率，包括：检测所述每个应用的关键词集合中是否包含指示用户情感的第一目标词汇；若是，确定第一目标词汇表达的情感是否为积极的情感；若是，确定所述第一目标词汇对应的用户评论为好评，并确定所述第一目标词汇的数量；根据所述每个应用的第一目标词汇的数量确定所述每个应用的好评数量以及好评率。
其中，在根据每个应用的关键词集合确定每个应用的好评数量和好频率时，检测每个应用的关键词集合中是否包含指示用户情感的第一目标词汇，如喜欢，好用，难用，开心，讨厌，烦躁等可以指示用户在使用应用时的情感的词汇，如果有，则确定第一目标词汇表达的情感是否为积极的情感，如若是，则可以确定第一目标词汇对应的用户评论为好评，从而可以根据第一目标词汇的数量确定对应应用的好评数量，进而计算出好评率。
可见，本示例中，每个应用的关键词集合中可能会包含可以指示用户情感的词汇，从而可以确定用户在使用应用过程中的情感是否为积极地情感，如果是积极的情感，则可以表明积极情感对应的词汇为好评，根据用户的情感倾向迅速得到多条用户评论中的好评并确定好评数量，结合每个应用的好评数量和好频率，有利于确定出的目标应用适合用户使用。
在一个可能的示例中，所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率，包括：检测所述每个应用的关键词集合中是否包含指示用户行为的第二目标词汇；若是，根据所述第二目标词汇指示的用户行为确定用户是否会再次使用应用；若是，确定所述第二目标词汇对应的用户评论为好评，并确定所述第二目标词汇的数量；根据所述每个应用的第二目标词汇的数量确定所述每个应用的好评数量以及好评率。
其中，在根据每个应用的关键词集合确定每个应用的好评数量和好频率时，检测每个应用的关键词集合中是否包含指示用户行为的第二目标词汇，如反应灵敏，功能多，好操作，或者卡顿，点不动，等待时间长，弃坑，卸载等词汇，根据第二目标词汇指示的用户行为确定用户是否会再次是否应，如果是，则确定第二目标词汇对应的用户评论为好评，从而可以根据第二目标词汇的数量确定每个应用的好评数量以及好频率。
可见，本示例中，每个应用的关键词集合中可能会包含可以指示用户行为的词汇，从而可以确定用户在使用应用过程中的行为确定用户是否会再次使用该应用，如果会再次使用，则可以表明该词汇为好评，如果用户不会在使用该应用，则可以表明该词汇为差评。根据用户是否为继续使用某个应用来确定该应用的多条用户评论中的好评以及好评数量，结合每个应用的好评数量和好频率，有利于确定出的目标应用适合用户使用。
在一个可能的示例中，所述根据所述每个应用的好评数量以及好评率确定目标应用，包括按照所述每个应用的好评数量从多到少的顺序将所述多个应用进行排序，得到第一排序；按照所述每个应用的好评率从高到低的顺序将所述多个应用进行排序，得到第二排序；根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用。
其中，根据每个应用的好评数量从多到少的顺序将每个应用进行排序，可以得到第一排序，根据每个应用的好频率从高到低的顺序将每个应用进行排序，可以得到第二排序，例如，应用1的评论数量为100条，好评有70条，好评率为70％，应用2的评论数量为150条，好评有60条，好评率为40％，应用3的评论数量为300条，好评有90条，好评率为30％，按照每个应用的好评数量进行排序，得到的第一排序为应用3，应用1，应用2，按照每个应用的好频率进行排序，得到的第二排序为应用1，应用2，应用3，可见，好评多可能是因为评论的用户比较多，不能代表用户真的对这个应用满意，好评率高可能是因为评论的用户比较少，也不能代表用户真的对这个应用满意。
可见，本示例中，在确定每个应用的好评数量以及好评率之后，可以按照好评数量将多个应用进行排序得到第一排序，按照好频率将多个应用进行排序得到第二排序，结合第一排序和第二排序从多个应用中选取出目标应用，有利于提高目标应用选取的可靠性和全面性。
在一个可能的示例中，所述根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用，包括：选出所述多个应用中，在所述第一排序中的排名与在所述第二排序中的排名之和最小的应用为所述目标应用，或者，选取在所述第一排序中排名大于第二预设阈值，以及在所述第二排序中排名大于第三预设阈值的至少一个应用为所述目标应用。
其中，在第一排序为应用3，应用1，应用2，第二排序为应用1，应用2，应用3，如果选取在第一排序的排名和在第二排序的排名之和最小的应用为目标应用的话，则目标应用为应用1，如果选取在第一排序中排名大于第二预设阈值，例如排名第一的应用，在第二排序中排名大于第三预设阈值，例如排名第一的应用，则目标应用为应用1和应用3。
可见，本示例中，在选取目标应用时，可以选取在第一排序中的排名和第二排序中的排名之间最小的应用，或者，选取在第一排序中排名大于第二预设阈值和在第二排序中排名大于第三预设阈值的应用，从而可以使选取出来的目标应用相对于其他应用不仅好评较多，好频率也较高。
在一个可能的示例中，所述发送推荐用户下载所述目标应用的推送消息之后，所述方法还包括：在检测到所述电子设备启动所述应用商店应用时，在所述应用商店的首页显示所述目标应用和/或和所述目标应用相似的应用。
其中，在确定目标应用之后，服务器向电子设备发送目标应用的推送消息以推荐用户下载目标应用，还可以将应用商店的首页进行数据更新，使电子设备在启动应用商店应用时，可以看到应用商店首页显示的目标应用，或者和所述目标应用相似的应用。目标应用的推送消息仅包括目标应用的下载链接和简要的介绍信息，目标用户可以在应用商店看到目标应用更详细的介绍信息。
可见，本示例中，不仅可以通过电子设备向用户推送目标应用，还可以让用户在应用商店首页查看到目标应用，从而可以获取目标应用更详细的信息，用户可以再次选择是否需要下载目标应用。
与所述图1B所示的实施例一致的，请参阅图2，图2是本申请实施例提供的一种应用推送方法的流程示意图，应用于服务器。如图所示，本应用推送方法包括：
S201，所述服务器确定所述电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量。
S202，所述服务器根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
S203，所述服务器获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息。
S204，所述服务器根据所述多个应用的评论信息确定目标应用。
S205，所述服务器通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
此外，在确定目标应用兴趣度大于预设兴趣度的目标应用类型时，先确定了电子设备下载的每个应用的应用类型，再确定每个应用类型对应的应用数量，从而可以根据每个应用类型的应用数量较准确的得到目标用户兴趣度较高的目标应用类型，有利于针对目标应用类型向用户进行应用推送。
与所述图1B、图2所示的实施例一致的，请参阅图3，图3是本申请实施例提供的一种应用推送方法的流程示意图，应用于服务器。如图所示，本应用推送方法包括：
S301，所述服务器确定所述电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量。
S302，所述服务器根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
S303，所述服务器获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息。
S304，所述服务器根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论。
S305，所述服务器根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论。
S306，所述服务器所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率。
S307，所述服务器根据所述每个应用的好评数量以及好评率确定目标应用。
S308，所述服务器通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述 多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
此外，在确定目标应用兴趣度大于预设兴趣度的目标应用类型时，先确定了电子设备下载的每个应用的应用类型，再确定每个应用类型对应的应用数量，从而可以根据每个应用类型的应用数量较准确的得到目标用户兴趣度较高的目标应用类型，有利于针对目标应用类型向用户进行应用推送。
此外，当某个应用被下载后下载该应用的用户可以对该应用进行评论或评价，获取多个应用中每个应用的多条用户评论后得到每个应用的一个关键词集合，根据关键词集合可以快速确定每个应用的好评数量以及好频率，结合每个应用的用户评论来为目标用户选取可以推送下载的目标应用，有利于帮助目标用户下载到好用合适的应用。
与所述图1B、图2、图3所示的实施例一致的，请参阅图4，图4是本申请实施例提供的一种电子设备400的结构示意图，该电子设备400运行有一个或多个应用程序和操作系统，如图所示，该电子设备400包括处理器410、存储器420、通信接口430以及一个或多个程序421，其中，所述一个或多个程序421被存储在所述存储器420中，并且被配置由所述处理器410执行，所述一个或多个程序421包括用于执行以下步骤的指令；
确定目标用户兴趣度大于预设兴趣度的目标应用类型；
获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；
根据所述多个应用的评论信息确定目标应用；
通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
在一个可能的示例中，在所述确定目标用户兴趣度大于预设兴趣度的目标应用类型方面，所述程序中的指令具体用于执行以下操作：确定所述电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量；根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
在一个可能的示例中，在所述根据所述多个应用的评论信息确定目标应用方面，所述程序中的指令具体用于执行以下操作：对所述多个应用中每个应用的评论信息进行语义分析，获取评论用户的特征信息；获取预存的所述目标用户的特征信息，并选取评论用户的 特征信息和所述目标用户的特征信息匹配度高于第一预设阈值的应用为所述目标应用。
在一个可能的示例中，在所述根据所述多个应用的评论信息确定目标应用方面，所述程序中的指令具体用于执行以下操作：根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论；根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论；所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率；根据所述每个应用的好评数量以及好评率确定目标应用。
在一个可能的示例中，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述程序中的指令具体用于执行以下操作：检测所述每个应用的关键词集合中是否包含指示用户情感的第一目标词汇；若是，确定第一目标词汇表达的情感是否为积极的情感；若是，确定所述第一目标词汇对应的用户评论为好评，并确定所述第一目标词汇的数量；根据所述每个应用的第一目标词汇的数量确定所述每个应用的好评数量以及好评率。
在一个可能的示例中，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述程序中的指令具体用于执行以下操作：检测所述每个应用的关键词集合中是否包含指示用户行为的第二目标词汇；若是，根据所述第二目标词汇指示的用户行为确定用户是否会再次使用应用；若是，确定所述第二目标词汇对应的用户评论为好评，并确定所述第二目标词汇的数量；根据所述每个应用的第二目标词汇的数量确定所述每个应用的好评数量以及好评率。
在一个可能的示例中，在所述根据所述每个应用的好评数量以及好评率确定目标应用方面，所述程序中的指令具体用于执行以下操作：按照所述每个应用的好评数量从多到少的顺序将所述多个应用进行排序，得到第一排序；按照所述每个应用的好评率从高到低的顺序将所述多个应用进行排序，得到第二排序；根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用。
在一个可能的示例中，在所述根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用方面，所述程序中的指令具体用于执行以下操作：选出所述多个应用中，在所述第一排序中的排名与在所述第二排序中的排名之和最小的应用为所述目标应用，或者，选取在所述第一排序中排名大于第二预设阈值，以及在所述第二排序中排名大于第三预设阈值的至少一个应用为所述目标应用。
在一个可能的示例中，所述发送推荐用户下载所述目标应用的推送消息之后，所述程序中的指令具体用于执行以下操作：在检测到所述电子设备启动所述应用商店应用时，在所述应用商店的首页显示所述目标应用和/或和所述目标应用相似的应用。
上述主要从方法侧执行过程的角度对本申请实施例的方案进行了介绍。可以理解的是，电子设备为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对电子设备进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个控制单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。需要说明的是，本申请实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实 现时可以有另外的划分方式。
图5是本申请实施例中所涉及的装置500的功能单元组成框图。该应用推送装置500应用于服务器，应用推送装置500包括处理单元501和通信单元502，其中：
所述处理单元501，用于确定目标用户兴趣度大于预设兴趣度的目标应用类型；以及用于获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；以及用于根据所述多个应用的评论信息确定目标应用；以及用于通过所述通信单元502输出推荐用户下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
可以看出，本申请实施例中，服务器首先确定目标用户兴趣度大于预设兴趣度的目标应用类型，其次，获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息，然后，根据所述多个应用的评论信息确定目标应用，最后，通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。由于服务器可以智能确定出目标用户感兴趣的目标应用类型，并且可以根据应用类型为目标应用类型的多个应用的评论信息确定出适合目标用户的目标应用，从而通过目标用户持有的电子设备来输出针对目标应用的推送信息，目标用户在看到推送信息后可以选择是否下载目标应用，进而提高的应用推送的可靠性，有利于提高应用商店的应用下载量。
在一个可能的示例中，在所述确定目标用户兴趣度大于预设兴趣度的目标应用类型方面，所述处理单元501具体用于：确定所述目标用户持有的目标电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量；以及用于根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
在一个可能的示例中，在所述根据所述多个应用的评论信息确定目标应用方面，所述处理单元501具体用于：对所述多个应用中每个应用的评论信息进行语义分析，获取评论用户的特征信息；以及用于获取预存的所述目标用户的特征信息，并确定评论用户的特征信息和所述目标用户的特征信息匹配度高于第一预设阈值的应用为所述目标应用。
在一个可能的示例中，在所述根据所述多个应用的评论信息确定目标应用方面，所述处理单元501具体用于：根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论；以及用于根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论；以及用于所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率；以及用于根据所述每个应用的好评数量以及好评率确定目标应用。
在一个可能的示例中，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述处理单元501具体用于：检测所述每个应用的关键词集合中是否包含指示用户情感的第一目标词汇；以及用于若是，确定第一目标词汇表达的情感是否为积极的情感；若是，确定所述第一目标词汇对应的用户评论为好评，并确定所述第一目标词汇的数量；以及用于根据所述每个应用的第一目标词汇的数量确定所述每个应用的好评数量以及好评率。
在一个可能的示例中，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述处理单元501具体用于：检测所述每个应用的关键词集合中是否包含指示用户行为的第二目标词汇；以及用于若是，根据所述第二目标词汇指示的用户行为确定用户是否会再次使用应用；若是，确定所述第二目标词汇对应的用户评论为好评，并确定所述第二目标词汇的数量；以及用于根据所述每个应用的第二目标词汇的数量确定所述每个应用的好评数量以及好评率。
在一个可能的示例中，在所述根据所述每个应用的好评数量以及好评率确定目标应用方面，所述处理单元501具体用于：按照所述每个应用的好评数量从多到少的顺序将所述多个应用进行排序，得到第一排序；以及用于按照所述每个应用的好评率从高到低的顺序将所述多个应用进行排序，得到第二排序；以及用于根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用。
在一个可能的示例中，在所述根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用方面，所述处理单元501具体用于：选出所述多个应用中，在所述第一排序中的排名与在所述第二排序中的排名之和最小的应用为所述目标应用，或者，以及用于选取在所述第一排序中排名大于第二预设阈值，以及在所述第二排序中排名大于第三预设阈值的至少一个应用为所述目标应用。
在一个可能的示例中，所述发送推荐用户下载所述目标应用的推送消息之后，所述处理单元501具体用于：在检测到所述电子设备启动所述应用商店时，在所述应用商店的首页显示所述目标应用和/或和所述目标应用相似的应用。
其中，所述电子设备还可包括存储单元503，处理单元501和通信单元502可以是控制器或处理器，存储单元503可以是存储器。
本申请实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤，上述计算机包括移动终端。
本申请实施例还提供一种计算机程序产品，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括移动终端。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个控制单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本申请的技术方案本质上或者说 对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例上述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器(英文：Read-Only Memory，简称：ROM)、随机存取器(英文：Random Access Memory，简称：RAM)、磁盘或光盘等。
以上对本申请实施例进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种应用推送方法，其特征在于，应用于服务器，所述方法包括：
    确定目标用户兴趣度大于预设兴趣度的目标应用类型；
    获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；
    根据所述多个应用的评论信息确定目标应用；
    通过所述目标用户持有的电子设备输出推荐下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
  2. 根据权利要求1所述的方法，其特征在于，所述确定目标用户兴趣度大于预设兴趣度的目标应用类型，包括：
    确定所述电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量；
    根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
  3. 根据权利要求1或2所述的方法，其特征在于，所述根据所述多个应用的评论信息确定目标应用，包括：
    对所述多个应用中每个应用的评论信息进行语义分析，获取评论用户的特征信息；
    获取预存的所述目标用户的特征信息，并选取评论用户的特征信息和所述目标用户的特征信息匹配度高于第一预设阈值的应用为所述目标应用。
  4. 根据权利要求1或2所述的方法，其特征在于，所述根据所述多个应用的评论信息确定目标应用，包括：
    根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论；
    根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论；
    所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率；
    根据所述每个应用的好评数量以及好评率确定目标应用。
  5. 根据权利要求4所述的方法，其特征在于，所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率，包括：
    检测所述每个应用的关键词集合中是否包含指示用户情感的第一目标词汇；
    若是，确定第一目标词汇表达的情感是否为积极的情感；
    若是，确定所述第一目标词汇对应的用户评论为好评，并确定所述第一目标词汇的数量；
    根据所述每个应用的第一目标词汇的数量确定所述每个应用的好评数量以及好评率。
  6. 根据权利要求4所述的方法，其特征在于，所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率，包括：
    检测所述每个应用的关键词集合中是否包含指示用户行为的第二目标词汇；
    若是，根据所述第二目标词汇指示的用户行为确定用户是否会再次使用应用；
    若是，确定所述第二目标词汇对应的用户评论为好评，并确定所述第二目标词汇的数量；
    根据所述每个应用的第二目标词汇的数量确定所述每个应用的好评数量以及好评率。
  7. 根据权利要求4所述的方法，其特征在于，所述根据所述每个应用的好评数量以及好评率确定目标应用，包括
    按照所述每个应用的好评数量从多到少的顺序将所述多个应用进行排序，得到第一排序；
    按照所述每个应用的好评率从高到低的顺序将所述多个应用进行排序，得到第二排序；
    根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用。
  8. 根据权利要求7所述的方法，其特征在于，所述根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用，包括：
    选出所述多个应用中，在所述第一排序中的排名与在所述第二排序中的排名之和最小的应用为所述目标应用，或者，
    选取在所述第一排序中排名大于第二预设阈值，以及在所述第二排序中排名大于第三预设阈值的至少一个应用为所述目标应用。
  9. 根据权利要求1-8任一项所述的方法，其特征在于，所述发送推荐用户下载所述目标应用的推送消息之后，所述方法还包括：
    在检测到所述电子设备启动所述应用商店应用时，在所述应用商店的首页显示所述目标应用和/或和所述目标应用相似的应用。
  10. 一种应用推送装置，其特征在于，应用于服务器，所述应用推送装置包括处理单元和通信单元，其中，
    所述处理单元，用于确定目标用户兴趣度大于预设兴趣度的目标应用类型；以及用于获取应用商店中应用类型为所述目标应用类型的多个应用，并获取所述多个应用的评论信息；以及用于根据所述多个应用的评论信息确定目标应用；以及用于通过所述通信单元输出推荐用户下载所述目标应用的推送消息，所述推送消息包括所述目标应用的下载链接以及介绍信息。
  11. 根据权利要求10所述的应用推送装置，其特征在于，在所述确定目标用户兴趣度大于预设兴趣度的目标应用类型方面，所述处理单元具体用于：确定所述目标用户持有的目标电子设备从所述应用商店下载的多个应用的应用类型，并确定每个应用类型对应的应用数量；以及用于根据所述每个应用类型的应用数量，确定用户兴趣度大于预设兴趣度的目标应用类型。
  12. 根据权利要求10或11所述的应用推送装置，其特征在于，在所述根据所述多个应用的评论信息确定目标应用方面，所述处理单元具体用于：对所述多个应用中每个应用的评论信息进行语义分析，获取评论用户的特征信息；以及用于获取预存的所述目标用户的特征信息，并确定评论用户的特征信息和所述目标用户的特征信息匹配度高于第一预设阈值的应用为所述目标应用。
  13. 根据权利要求10或11所述的应用推送装置，其特征在于，在所述根据所述多个应用的评论信息确定目标应用方面，所述处理单元具体用于：根据所述多个应用的评论信息，确定所述多个应用中每个应用的多条用户评论；以及用于根据所述每个应用的多条用户评论确定所述每个应用的关键词集合，其中，所述关键词集合中的关键词为预设词汇集合中的词汇，每个关键词对应一条用户评论；以及用于所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率；以及用于根据所述每个应用的好评数量以及好评率确定目标应用。
  14. 根据权利要求13所述的应用推送装置，其特征在于，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述处理单元具体用于：检测所述每个应用的关键词集合中是否包含指示用户情感的第一目标词汇；以及用于若是，确定第一目标词汇表达的情感是否为积极的情感；
    若是，确定所述第一目标词汇对应的用户评论为好评，并确定所述第一目标词汇的数量；以及用于根据所述每个应用的第一目标词汇的数量确定所述每个应用的好评数量以及好评 率。
  15. 根据权利要求13所述的应用推送装置，其特征在于，在所述根据所述每个应用的关键词集合确定所述每个应用的好评数量以及好评率方面，所述处理单元具体用于：检测所述每个应用的关键词集合中是否包含指示用户行为的第二目标词汇；以及用于若是，根据所述第二目标词汇指示的用户行为确定用户是否会再次使用应用；若是，确定所述第二目标词汇对应的用户评论为好评，并确定所述第二目标词汇的数量；以及用于根据所述每个应用的第二目标词汇的数量确定所述每个应用的好评数量以及好评率。
  16. 根据权利要求13所述的应用推送装置，其特征在于，在所述根据所述每个应用的好评数量以及好评率确定目标应用方面，所述处理单元具体用于：按照所述每个应用的好评数量从多到少的顺序将所述多个应用进行排序，得到第一排序；以及用于按照所述每个应用的好评率从高到低的顺序将所述多个应用进行排序，得到第二排序；以及用于根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用。
  17. 根据权利要求16所述的应用推送装置，其特征在于，在所述根据所述第一排序和所述第二排序从所述多个应用中选取至少一个应用为所述目标应用方面，所述处理单元具体用于：选出所述多个应用中，在所述第一排序中的排名与在所述第二排序中的排名之和最小的应用为所述目标应用，或者，以及用于选取在所述第一排序中排名大于第二预设阈值，以及在所述第二排序中排名大于第三预设阈值的至少一个应用为所述目标应用。
  18. 根据权利要求10-17任一项所述的应用推送装置，其特征在于，所述发送推荐用户下载所述目标应用的推送消息之后，所述处理单元具体用于：在检测到所述电子设备启动所述应用商店时，在所述应用商店的首页显示所述目标应用和/或和所述目标应用相似的应用。
  19. 一种电子设备，其特征在于，包括处理器、存储器、通信接口，以及一个或多个程序，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行如权利要求1-9任一项所述的方法中的步骤的指令。
  20. 一种计算机可读存储介质，其特征在于，存储用于电子数据交换的计算机程序，其中，所述计算机程序使得计算机执行如权利要求1-9任一项所述的方法。
PCT/CN2019/098006 2019-07-26 2019-07-26 应用推送方法及相关装置 WO2021016760A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/098006 WO2021016760A1 (zh) 2019-07-26 2019-07-26 应用推送方法及相关装置
CN201980097278.6A CN113950678A (zh) 2019-07-26 2019-07-26 应用推送方法及相关装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/098006 WO2021016760A1 (zh) 2019-07-26 2019-07-26 应用推送方法及相关装置

Publications (1)

Publication Number Publication Date
WO2021016760A1 true WO2021016760A1 (zh) 2021-02-04

Family

ID=74229060

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/098006 WO2021016760A1 (zh) 2019-07-26 2019-07-26 应用推送方法及相关装置

Country Status (2)

Country Link
CN (1) CN113950678A (zh)
WO (1) WO2021016760A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113076402A (zh) * 2021-04-13 2021-07-06 上海华客信息科技有限公司 评论数据分析方法、系统、电子设备及存储介质
CN113177170A (zh) * 2021-04-12 2021-07-27 维沃移动通信有限公司 评论展示方法、装置及电子设备
CN114780842A (zh) * 2022-04-20 2022-07-22 北京字跳网络技术有限公司 一种数据处理方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104281622A (zh) * 2013-07-11 2015-01-14 华为技术有限公司 一种社交媒体中的信息推荐方法和装置
CN106708817A (zh) * 2015-07-17 2017-05-24 腾讯科技（深圳）有限公司 信息搜索方法及装置
CN106952129A (zh) * 2017-02-23 2017-07-14 广东小天才科技有限公司 一种应用商店的应用推荐方法及装置
CN107562847A (zh) * 2017-08-25 2018-01-09 广东欧珀移动通信有限公司 信息处理方法及相关产品

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8224713B2 (en) * 2006-07-28 2012-07-17 Visible World, Inc. Systems and methods for enhanced information visualization
CN105989107A (zh) * 2015-02-12 2016-10-05 广东欧珀移动通信有限公司 一种应用推荐方法及装置
CN109492160A (zh) * 2018-10-31 2019-03-19 北京字节跳动网络技术有限公司 用于推送信息的方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104281622A (zh) * 2013-07-11 2015-01-14 华为技术有限公司 一种社交媒体中的信息推荐方法和装置
CN106708817A (zh) * 2015-07-17 2017-05-24 腾讯科技（深圳）有限公司 信息搜索方法及装置
CN106952129A (zh) * 2017-02-23 2017-07-14 广东小天才科技有限公司 一种应用商店的应用推荐方法及装置
CN107562847A (zh) * 2017-08-25 2018-01-09 广东欧珀移动通信有限公司 信息处理方法及相关产品

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113177170A (zh) * 2021-04-12 2021-07-27 维沃移动通信有限公司 评论展示方法、装置及电子设备
CN113177170B (zh) * 2021-04-12 2023-05-23 维沃移动通信有限公司 评论展示方法、装置及电子设备
CN113076402A (zh) * 2021-04-13 2021-07-06 上海华客信息科技有限公司 评论数据分析方法、系统、电子设备及存储介质
CN114780842A (zh) * 2022-04-20 2022-07-22 北京字跳网络技术有限公司 一种数据处理方法、装置、设备及存储介质
CN114780842B (zh) * 2022-04-20 2022-12-13 北京字跳网络技术有限公司 一种数据处理方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN113950678A (zh) 2022-01-18

Similar Documents

Publication Publication Date Title
WO2021003673A1 (zh) 内容推送方法及相关产品
WO2021016760A1 (zh) 应用推送方法及相关装置
US20060059147A1 (en) System and method of adaptive personalization of search results for online dating services
CN104462262A (zh) 一种实现语音搜索的方法、装置和浏览器客户端
CN105335398A (zh) 一种服务推荐方法及终端
CN104142964A (zh) 信息匹配的方法及装置
US20170249934A1 (en) Electronic device and method for operating the same
CN108427761B (zh) 一种新闻事件处理的方法、终端、服务器及存储介质
US9843670B2 (en) Method and apparatus for setting color ring back tone and determining color ring back tone music
CN110442515B (zh) 应用测试方法、装置、设备及可读存储介质
CN103702297A (zh) 短信增强方法、装置及系统
CN108846030B (zh) 访问官方网站的方法、系统、电子设备及存储介质
CN103916436A (zh) 信息推送方法、装置、终端及服务器
CN111242709A (zh) 一种消息推送方法及其装置、设备、存储介质
CN109949172A (zh) 社交账号影响力评价方法、装置及存储介质
CN107547646B (zh) 应用程序推送方法、装置、终端及计算机可读存储介质
CN114860919A (zh) 一种话题推荐方法、装置、计算机设备及存储介质
CN108509582B (zh) 一种信息的回复方法、终端设备及计算机可读存储介质
CN113016169A (zh) 信息推送方法及相关产品
CN114357325A (zh) 内容搜索方法、装置、设备及介质
CN109584088B (zh) 产品信息的推送方法及装置
CN110765326A (zh) 推荐方法、装置、设备及计算机可读存储介质
KR20140007294A (ko) 콘텍스트 가중 및 인센티브들에 기초하여 폰북 연락처들을 소팅하기 위한 시스템 및 방법
CN110634024A (zh) 一种用户属性标记方法、装置、电子设备及存储介质
CN105677926A (zh) 一种本地搜索结果展示方法、装置及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19939764

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 260422)

122 Ep: pct application non-entry in european phase

Ref document number: 19939764

Country of ref document: EP

Kind code of ref document: A1