System and method for recommending applications based on historical usage
An application program recommending method may include acquiring current context information of the terminal, acquiring an amount of context information generated when the terminal runs a first application program, where the first application program refers to an application program stored in the terminal, determining a to-be-used recommending mechanism according to the amount of the context information generated when the terminal runs the first application program, and determining, according to the to-be-used recommending mechanism, a second application program corresponding to the current context information, where the second application program refers to a to-be-recommended application program; and displaying the second application program. In this way, accuracy of predicting an application program to be used by a user is improved. Moreover, when historical information of using an application program by the user is insufficient, a to-be-recommended application program can also be accurately determined.
1. An application program recommending method, comprising:
acquiring current context information of a terminal;
acquiring first context information generated when the terminal executes a first application program stored in the terminal;
extracting a context information characteristic value of the first application program from the first context information;
generating a use rule and a use model based on the first context information and the context information characteristic value using a machine learning method;
determining a recommending mechanism based on a quantity of times the first context information has been acquired;
determining, according to the recommending mechanism, a second application program corresponding to the current context information; and
displaying an indicator of the second application program on a display of the terminal, wherein the second application program is selected from a plurality of application programs installed on the terminal, and wherein the second application program is in an unlaunched state, the indicator selectable to launch the second application program,
wherein the recommending mechanism comprises at least one of the use rule and the use model, and wherein determining, according to the recommending mechanism, the second application program comprises:
determining the second application program further according to the use rule when the quantity of times the first context information has been collected is less than or equal to a first preset value;
determining the second application program further according to the use model when the quantity of times the first context information has been collected is greater than or equal to a second preset value; and
determining the second application program further according to the use rule and the use model when the quantity of times the first context information has been collected is greater than the first preset value and less than the second preset value,
the method further comprising:
acquiring feedback information of the second application program after displaying the second application program; and
updating the use rule and the use model based on the feedback information.
2. The method of claim 1 , wherein generating the use rule and the use model comprises:
determining, based on the context information characteristic value, a recommended priority for the second application program under a preset condition;
using the recommended priority as the use rule; and
generating the use model based on the context information characteristic value of the first application program using the machine training method.
3. The method of claim 1 , wherein the feedback information comprises use time and use duration.
4. A terminal, comprising:
a display; and
a processor in communication with the display, the processor configured to:
acquire current context information of the terminal;
acquire first context information generated when the terminal executes a first application program stored in the terminal;
extract a context information characteristic value of the first application program from the first context information;
generate a use rule and a use model based on the first context information and the context information characteristic value using a machine learning method;
determine a recommending mechanism based on a quantity of times the first context information has been acquired, wherein the recommending mechanism comprises at least one of a use rule and a use model;
determine a second application program according to the use rule and the current context information when the quantity of times the first context information has been collected is less than or equal to a first preset value;
determine the second application program according to the use model and the current context information when the quantity of times the first context information has been collected is greater than or equal to a second preset value; and
determine the second application program according to the use rule, the use model, and the current context information when the quantity of times the first context information has been collected is greater than the first preset value and less than the second preset value;
display an indicator of the second application program on the display, wherein the second application program is selected from a plurality of application programs installed on the terminal, and wherein the second application program is in an unlaunched state, the indicator selectable to launch the second application program;
acquire feedback information of the second application program after the displaying unit displayed the indicator of second application program; and update the use rule and the use model based on the feedback information.
5. The terminal of claim 4 , wherein the processor is further configured to:
determine, based on the context information characteristic value, a recommended priority for the second application program under a preset condition;
use the recommended priority as the use rule; and
generate the use model further based on the context information characteristic value of the first application program using the machine training method.
6. The terminal of claim 4 , wherein the feedback information comprises use time and use duration.
7. An application program recommending method, comprising:
acquiring current context information of a terminal;
acquiring first context information generated when the terminal executes a first application program stored in the terminal;
determining a recommending mechanism based on a quantity of times the first context information has been acquired;
determining, according to the recommending mechanism, a second application program corresponding to the current context information; and
displaying an indicator of the second application program on a display of the terminal, wherein the second application program is selected from a plurality of application programs installed on the terminal, and wherein the second application program is in an unlaunched state, the indicator selectable to launch the second application program,
wherein the recommending mechanism comprises at least one of a use rule and a use model, and wherein determining, according to the recommending mechanism, the second application program comprises:
determining the second application program further according to the use rule when the quantity of times the first context information has been collected is less than or equal to a first preset value;
determining the second application program further according to the use model when the quantity of times the first context information has been collected is greater than or equal to a second preset value; and
determining the second application program further according to the use rule and the use model when the quantity of times the first context information has been collected is greater than the first preset value and less than the second preset value,
the method further comprising:
acquiring the first context information prior to determining the recommending mechanism; and
generating the use rule and the use model based on the first context information,
wherein generating the use rule and the use model comprises:
extracting a context information characteristic value of the first application program from the first context information; and
generating the use rule and the use model further based on the context information characteristic value using a machine learning method.
8. The method of claim 7 , wherein generating the use rule and the use model comprises:
determining, based on the context information characteristic value, a recommended priority for the second application program under a preset condition;
using the recommended priority as the use rule; and
generating the use model based on the context information characteristic value of the first application program using a machine training method.
9. The method of claim 1 , further comprising:
acquiring feedback information of the second application program after displaying the second application program; and
updating the use rule and the use model based on the feedback information.
10. The method of claim 9 , wherein the feedback information comprises use time and use duration.