Film and television resource matching method and device and smart television
A technology of video resources and matching methods, applied in electrical components, voice analysis, instruments, etc., can solve problems such as unmatched video, cumbersome operations, and lack of video classification functions, and achieve the effect of improving user experience and convenience
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] see figure 1 , is a schematic flowchart of a video resource matching method provided by an embodiment of the present disclosure. Such as figure 1 As shown, the video resource matching method mainly includes the following steps:
[0050] S101. Receive a voice command input by a user;
[0051] When users search for movies and TV, they only need to input specific instructions by voice. For example, directly say the preset voice wake-up name of the TV; or operate the voice key on the remote control, and then say a specific name. The smart TV conducts video search after performing relevant analysis based on the voice command.
[0052] Specifically, the voice instruction may also be voice content of at least one byte.
[0053] S102. Input the voice instruction into the voiceprint recognition model to identify the category of the user, where the category includes at least one of gender and age;
[0054] The voiceprint recognition model is pre-embedded in the smart TV. Wh...
Embodiment 2
[0087] see image 3 , is a specific implementation diagram of a video resource matching method provided by an embodiment of the present disclosure. Such as image 3 As shown, the specific steps of the method are as follows:
[0088] In this embodiment, the trained voiceprint recognition model is embedded into the TV terminal. When the user enters commands by voice, the TV end calls the voiceprint recognition model to identify the user's category. Then perform video resource matching, and intelligently recommend video resources corresponding to user categories according to user categories.
[0089] see Figure 4 , is a voiceprint recognition model training diagram of a video resource matching method provided by an embodiment of the present disclosure. Such as Figure 4 As shown, the specific process is as follows:
[0090] In the first stage, a large amount of speech information is collected through big data as training data, and the speech information is manually marked...
Embodiment 3
[0093] with the above figure 1 Corresponding to the method embodiment shown, see Figure 5 , is a block diagram of a video resource matching device provided in an embodiment of the present disclosure. Such as Figure 5 As shown, the video resource matching device 500 includes:
[0094] A receiving module 501, configured to receive voice instructions input by the user;
[0095] A recognition module 502, configured to input the voice instruction into a voiceprint recognition model to recognize the category of the user, wherein the category includes at least one of gender and age;
[0096] A display module 503, configured to display video and video resources matching the category of the user.
[0097] with the above figure 2 Corresponding to the method embodiment shown, see Figure 6 , is a block diagram of some modules of a video resource matching device provided in an embodiment of the present disclosure. Such as Figure 6 As shown, the video resource matching device 5...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More