Abstract:
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.
Abstract:
A method for determining a target user, includes: for any target service, acquiring historical data of multiple behavior objects that belong to a same service type as the target service; establishing a correspondence between user identifiers of different users and behavior object identifiers of different behavior objects of the same type; based on multiple established correspondences, constructing a data model that includes a user identifier and a behavior object identifier; using a value update rule to obtain, by means of calculation, a value of a probability that a user corresponding to each user identifier becomes a target user of the target service; and further using the value of the probability to select a target user of the target service, which can not only determine a target user group in a relatively open manner, but also effectively improve accuracy of and efficiency in determining a target user.
Abstract:
The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.
Abstract:
The method includes: collecting historical operations of sample users for M items, and predicting a preference value of a target user for each of the M items according to historical operations of the sample users for each of the M items, collecting classification data of N to-be-recommended items, and classifying the N to-be-recommended items according to the classification data of the N to-be-recommended items, to obtain X themes, where each of the X themes includes at least one of the N to-be-recommended items, and the N to-be-recommended items are some or all of the M items; calculating a preference value of the target user for each of the X themes according to a preference value of the target user for a to-be-recommended item included in each of the X themes; and pushing a target theme to the target user.
Abstract:
The present invention provide a terminal device, including: at least one sensor, a data processing unit, a memory, a CPU, and a storage, where the sensor is configured to sense a corresponding measured object and generate corresponding sensing data; and the data processing unit is configured to collect the sensing data jointly with the CPU in a mutually complementary manner, store the collected sensing data in the memory, perform feature extraction on the sensing data stored in the memory, and store extracted feature data in the storage, where the mutually complementary manner refers to that, when one of the data processing unit and the CPU is in a working state, the other is in a dormant state. The terminal device provided by the embodiments of the present invention can improve a utilization rate of the CPU.
Abstract:
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.