Back to results
US 12,572,896 B2Granted
Processing a user task
AssigneeBeijing Zitiao Network Technology Co., Ltd.
InventorsLinlin Wang, Wenliang He
Life of this patent
Estimating the term…
Abstract
A method, apparatus, device, and medium for processing a user task are provided. In one method, a user input represented in a natural language is received from a user. The user input indicates a task to be executed. A task type of the task is determined based on the user input. In response to determining that the task type indicates an execution result of the task is unable to be obtained within a predetermined time period, a subsequent task of the task is created to provide the execution result of the task by a machine learning model when a triggering condition for the task is met. With exemplary implementations of the present disclosure, user tasks that cannot obtain the execution result of the task within a predetermined time period can be processed in a more flexible and efficient manner.
Claims19
A method for processing a user task, comprising:
- receiving a user input represented in a natural language format from a user during a first session between the user and a digital assistant, the user input indicating a task to be executed;
- determining a task type of the task and a first triggering condition for the task based on the user input;
- in response to determining that the task type indicates that an execution result of the task is unable to be obtained within a predetermined time period, creating a first subsequent task of the task, wherein the first subsequent task is executed by a machine learning model to provide the execution result of the task when the first triggering condition for the task is met;
- in accordance with that the first triggering condition is met, providing the execution result of the task to the user in the natural language format during a second session between the user and the digital assistant, the second session being different from the first session;
- in response to determining that a preset task corresponding to a predetermined future time point is activated, determining a second triggering condition for the preset task, the preset task being added to the digital assistant during creation of the digital assistant, the second triggering condition of the preset task indicating that an execution result of the preset task is to be provided at the predetermined future time point;
- and
- creating a second subsequent task of the preset task to provide the execution result of the preset task based on the machine learning model when the second triggering condition for the preset task is met.
4 more elements
An electronic device, comprising:
- at least one processing unit;
- and
- at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the electronic device to perform operations comprising:
- receiving a user input represented in a natural language format from a user during a first session between the user and a digital assistant, the user input indicating a task to be executed;
- determining a task type of the task and a first triggering condition for the task based on the user input;
- in response to determining that the task type indicates that an execution result of the task is unable to be obtained within a predetermined time period, creating a first subsequent task of the task, wherein the first subsequent task is executed by a machine learning model to provide the execution result of the task when the first triggering condition for the task is met;
- in accordance with that the first triggering condition is met, providing the execution result of the task to the user in the natural language format during a second session between the user and the digital assistant, the second session being different from the first session;
- in response to determining that a preset task corresponding to a predetermined future time point is activated, determining a second triggering condition for the preset task, the preset task being added to the digital assistant during creation of the digital assistant, the second triggering condition of the preset task indicating that an execution result of the preset task is to be provided at the predetermined future time point;
- and
- creating a second subsequent task of the preset task to provide the execution result of the preset task based on the machine learning model when the second triggering condition for the preset task is met.
7 more elements
A non-transitory computer readable storage medium having stored thereon a computer program which, when executed by one or more computers, causes the one or more computers to perform operations comprising:
- receiving a user input represented in a natural language format from a user during a first session between the user and a digital assistant, the user input indicating a task to be executed;
- determining a task type of the task and a first triggering condition for the task based on the user input;
- in response to determining that the task type indicates that an execution result of the task is unable to be obtained within a predetermined time period, creating a first subsequent task of the task, wherein the first subsequent task is executed by a machine learning model to provide the execution result of the task when the first triggering condition for the task is met;
- in accordance with that the first triggering condition is met, providing the execution result of the task to the user in the natural language format during a second session between the user and the digital assistant, the second session being different from the first session;
- in response to determining that a preset task corresponding to a predetermined future time point is activated, determining a second triggering condition for the preset task, the preset task being added to the digital assistant during creation of the digital assistant, the second triggering condition of the preset task indicating that an execution result of the preset task is to be provided at the predetermined future time point;
- and
- creating a second subsequent task of the preset task to provide the execution result of the preset task based on the machine learning model when the second triggering condition for the preset task is met.
4 more elements
Dependencies are inferred from the claim text.