Back to results
US 12,762,859 B2Granted
Electronic device and video clip extraction method thereof
AssigneeAcer Incorporated
InventorChia-Shang Yuan
Life of this patent
Estimating the term…
Abstract
An electronic device and a video clip extraction method thereof are disclosed. The method includes the following steps. Event information of multiple game events of a game application during a program execution period is obtained. The event information of the game events is converted into an input text. The input text is provided to a text classification model. A video clip is extracted from a recorded game video of the game application according to a classification category of the input text predicted by the text classification model.
Claims12
A video clip extraction method, comprising:
- obtaining event information of a plurality of game events of a game application during a program execution period;
- converting the event information of the game events into an input text, wherein an event sampling time window is utilized to retrieve the game events of an event sequence for conversion into the input text, and the game events comprise a first game event and a second game event;
- providing the input text comprising a first event identification of the first game event, a second event identification of the second game event and a first time interval between the first game event and the second game event to a text classification model;
- when the text classification model determines that the input text is a first classification category, determining timestamp information of a video clip according to an event occurrence time of one of the game events included in the event sequence corresponding to the input text;
- and
- extracting the video clip from the recorded game video according to the timestamp information,
- wherein the converting the event information of the game events into the input text comprises:
- calculating at least one time interval between the game events according to a plurality of event occurrence times of the game events, wherein calculating the at least one time interval comprising calculating the first time interval between a first event occurrence time of the first game event and a second event occurrence time of the second game event;
- and
- generating the input text for the text classification model by concatenating the at least one time interval and event identifications of the game events.
7 more elements
An electronic device, comprising:
- a storage device, recording a plurality of modules;
- a processor, coupled to the storage device, executing the module and configured to:
- obtain event information of a plurality of game events of a game application during a program execution period;
- convert the event information of the game events into an input text, wherein an event sampling time window is utilized to retrieve the game events of an event sequence for conversion into the input text, and the game events comprise a first game event and a second game event;
- provide the input text comprising a first event identification of the first game event, a second event identification of the second game event and a first time interval between the first game event and the second game event to a text classification model;
- when the text classification model determines that the input text is a first classification category, determine timestamp information of a video clip according to an event occurrence time of one of the game events included in the event sequence corresponding to the input text;
- and
- extract the video clip from the recorded game video according to the timestamp information,
- wherein the processor is further configured to:
- calculate at least one time interval between the game events according to a plurality of event occurrence times of the game events, wherein the processor is configured to calculate the first time interval between a first event occurrence time of the first game event and a second event occurrence time of the second game event;
- and
- generate the input text for the text classification model by concatenating the at least one time interval and event identifications of each of the game events.
9 more elements
Dependencies are inferred from the claim text.