Playing mode switching method and audio-video playing device thereof

Abstract

The invention provides a playing mode switching method and audio and video playing equipment thereof. The playing mode switching method comprises the following steps: the audio-video playing equipment establishes an index corresponding table of a plurality of preset keyword data and a plurality of playing modes, plays audio-video content, captures a frame image aiming at the audio-video content and generates inquiry information according to the frame image to inquire a network artificial intelligent model; the network artificial wisdom model returns the first keyword data to the audio and video playing device according to the inquiry information, and the audio and video playing device analyzes and compares the first keyword data with the index corresponding table to judge whether to execute playing mode switching operation or not so as to adjust audio and video playing parameter setting of the audio and video content.

Description

Technical Field

[0001] The present invention relates to a playback mode switching method and a video playback device thereof, and more particularly to a playback mode switching method and a video playback device thereof for analyzing and comparing a first keyword data returned by a network artificial intelligence model according to a frame image of the video content to determine whether to execute a playback mode switching operation. Background Art

[0002] Generally speaking, common audio and video playback devices (such as projectors, display screens, etc.) usually have audio and video parameter adjustment functions, so that users can adjust the audio and video content played by the audio and video playback device to the audio and video presentation effect that meets their own viewing needs, such as manually pressing the button group on the display screen to adjust the on-screen display function (On Screen Display, OSD), or adjusting it by software settings, etc. However, due to the large number of audio and video parameter options (such as brightness, contrast, clarity, color saturation, etc.), the audio and video parameter adjustment process of the audio and video playback device is often time-consuming and labor-intensive. Although there are currently audio and video playback devices with built-in different audio and video playback modes (such as theater mode, game mode, etc.) for switching, this method still requires users to switch manually, so the audio and video playback mode switching operation is still not simple and fast enough.

[0003] Therefore, it is necessary to design a novel playback mode switching method and an audio and video playback device thereof to overcome the above-mentioned defects. Summary of the invention

[0004] The object of the present invention is to provide a playback mode switching method and a video playback device thereof, which can analyze and compare the first keyword data returned by a network artificial intelligence model according to the frame image of the video content to determine whether to perform a playback mode switching operation.

[0005] To achieve the above-mentioned purpose, the present invention provides a playback mode switching method, comprising: establishing an index correspondence table of multiple preset keyword data and multiple playback modes through an audio and video playback device; playing audio and video content through the audio and video playback device; capturing at least one frame of image for the audio and video content through the audio and video playback device and generating at least one query information based on the at least one frame of image to query a network artificial intelligence model; returning first keyword data to the audio and video playback device through the network artificial intelligence model based on the at least one query information; and analyzing and comparing the first keyword data with the index correspondence table through the audio and video playback device to determine whether to perform a playback mode switching operation, so as to adjust the audio and video playback parameter settings of the audio and video content.

[0006] Preferably, the method further comprises: the audio and video playback device generates voice keyword data according to the voice input data; and the audio and video playback device analyzes and compares the voice keyword data with the index corresponding table to determine whether to execute the playback mode switching operation.

[0007] Preferably, when the audio and video playback device determines that the voice input data matches one of the preset keyword data, the audio and video playback device performs the playback mode switching operation according to the index correspondence table; or, when the audio and video playback device determines that the voice input data does not match any of the preset keyword data, the audio and video playback device queries the network artificial intelligence model with the at least one query information.

[0008] Preferably, the audio-visual playback device uses a translation service to convert the language corresponding to the at least one query information into a default language of the network artificial intelligence model.

[0009] Preferably, the method further comprises: the video and audio playback device transmits the index correspondence table to the network artificial intelligence model to assist the network artificial intelligence model in evolving.

[0010] Preferably, when the audio and video playback device determines that the first keyword data matches one of the preset keyword data, the audio and video playback device performs the playback mode switching operation according to the index correspondence table.

[0011] Preferably, the at least one query information queries the network artificial intelligence model in the form of a closed-ended multiple-choice question asking about the image type.

[0012] Preferably, when the audio and video playback device determines that the first keyword data does not match any preset keyword data, the audio and video playback device does not perform the playback mode switching operation, or the audio and video playback device queries the network artificial intelligence model in the form of a question about the image type based on the at least one frame of image, and the audio and video playback device establishes an index correspondence between the second keyword data and one of the playback modes in the index correspondence table based on the second keyword data returned by the network artificial intelligence model.

[0013] Preferably, the step of the video playback device playing the video content includes: the video playback device transmits the video content to the network artificial intelligence model for inquiry to determine whether the video content is protected by copyright or whether the playback URL of the video content is unsafe, so as to decide whether to play the video content.

[0014] Preferably, the video playback device determines whether the playback method of the video content is legal based on the content description information in the video content.

[0015] Preferably, the video playback device determines whether the video content contains restricted video content through the network artificial intelligence model.

[0016] Preferably, the first keyword data includes multiple keywords, and the audio and video playback device assigns a weight value to each keyword; when the audio and video playback device determines that the total weight value corresponding to the same keyword is greater than a threshold value, the audio and video playback device analyzes and compares the same keyword with the index correspondence table to determine whether to execute the playback mode switching operation.

[0017] The present invention also provides an audio-visual playback device with a playback mode switching function, which is connected to a network artificial intelligence model through a network. The audio-visual playback device includes: an audio-visual playback device, which is used to play audio-visual content; an audio-visual processing device, which is electrically connected to the audio-visual playback device, which is used to pre-establish an index correspondence table of multiple preset keyword data and multiple playback modes and to capture at least one frame of image for the audio-visual content and generate at least one query information based on the at least one frame of image; and a network transmission device, which is electrically connected to the audio-visual processing device, which is used to return the first keyword data generated by the network artificial intelligence model based on the at least one query information to the audio-visual processing device, so that the audio-visual processing device analyzes and compares the first keyword data with the index correspondence table to determine whether to control the audio-visual playback device to perform a playback mode switching operation, so as to adjust the audio-visual playback parameter settings of the audio-visual content.

[0018] Preferably, it also includes: a voice processing device, electrically connected to the audio and video processing device, for generating voice input data; wherein the audio and video processing device generates voice keyword data based on the voice input data, and the audio and video processing device analyzes and compares the voice keyword data with the index correspondence table to determine whether to control the audio and video playback device to perform the playback mode switching operation.

[0019] Preferably, when the audio and video processing device determines that the voice input data matches one of the preset keyword data, the audio and video processing device controls the audio and video playback device to perform the playback mode switching operation according to the index correspondence table; or, when the audio and video processing device determines that the voice input data does not match any of the preset keyword data, the audio and video playback device queries the network artificial intelligence model with the at least one query information.

[0020] Preferably, the video processing device uses a translation service to convert the language corresponding to the at least one query information into a default language of the network artificial intelligence model.

[0021] Preferably, the network transmission device transmits the index correspondence table to the network artificial intelligence model to assist the network artificial intelligence model in evolving.

[0022] Preferably, when the video processing device determines that the first keyword data matches one of the preset keyword data, the video processing device controls the video playback device to execute the playback mode switching operation according to the index correspondence table.

[0023] Preferably, the at least one query information queries the network artificial intelligence model in the form of a closed-ended multiple-choice question asking about the image type.

[0024] Preferably, when the audio and video processing device determines that the first keyword data does not match any preset keyword data, the audio and video playback device does not perform the playback mode switching operation, or the audio and video processing device inquires the network artificial intelligence model in the form of a question about the image type based on the at least one frame of image, and the audio and video processing device establishes an index correspondence between the second keyword data and one of the playback modes in the index correspondence table based on the second keyword data returned by the network artificial intelligence model.

[0025] Preferably, the video processing device determines whether the video content is protected by copyright or whether the playback URL of the video content is unsafe through the network artificial intelligence model to decide whether to play the video content.

[0026] Preferably, the video processing device determines whether the playing method of the video content is legal according to a content description information in the video content.

[0027] Preferably, the video processing device determines whether the video content contains restricted video content through the network artificial intelligence model.

[0028] Preferably, the first keyword data includes multiple keywords, and the audio and video processing device assigns a weight value to each keyword; when the audio and video processing device determines that the total weight value corresponding to the same keyword is greater than a threshold value, the audio and video processing device analyzes and compares the same keyword with the index correspondence table to determine whether to control the audio and video playback device to perform the playback mode switching operation.

[0029] Compared with the prior art, the embodiment of the present invention provides a playback mode switching method and an audio and video playback device thereof, which determines whether it is necessary to execute a playback mode switching operation of the audio and video playback device by analyzing and comparing the first keyword data and the index correspondence table returned by the network artificial intelligence model according to the frame image of the audio and video content, so as to achieve the effect that the audio and video playback device can automatically switch to the audio and video scene mode that meets the user's current viewing needs without the need for manual adjustment by the user. In this way, the present invention can effectively solve the problem of time-consuming and labor-intensive audio and video parameter adjustment process of the audio and video playback device mentioned in the prior art, thereby greatly improving the user's operating convenience in using the audio and video playback device and optimizing the user's viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 FIG. 4 is a functional block diagram of an audio and video playback device according to an embodiment of the present invention.

[0031] Figure 2 FIG. 4 is a flow chart of a playback mode switching method according to an embodiment of the present invention.

[0032] Figure 3 FIG. 4 is a flow chart of a method for analyzing video sources according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to provide a further understanding of the purpose, structure, features and functions of the present invention, the following detailed description is given in conjunction with the embodiments.

[0034] See also Figure 1 , which is a functional block diagram of an audio-visual playback device 10 proposed according to an embodiment of the present invention. The audio-visual playback device 10 can be a common multimedia audio-visual playback device (such as a digital light processing (DLP) projector, a smart LCD TV, etc., but not limited thereto) with an audio-visual playback function and a playback mode (such as a theater mode, a game mode, a movie mode, etc.) switching function, and can be connected to the network (wirelessly or wired) to a network artificial intelligence model 12 (such as a generative pre-trained transformer 4 (GPT-4), etc.), such as Figure 1 As shown, the video and audio playback device 10 includes a video and audio playback device 14 , a video and audio processing device 16 , and a network transmission device 18 .

[0035] The audio and video playback device 14 (such as an image projection lens, a liquid crystal display panel, etc.) can be used to play audio and video content (such as concert videos, electronic games, movies, etc.), and the audio and video processing device 16 can be a microprocessor (such as a central processing unit (CPU), a graphics processing unit (GPU), etc.) in the audio and video playback device 10 for performing image-related processing and is electrically connected to the audio and video playback device 14, so as to pre-establish an index correspondence table of preset keyword data and its corresponding playback mode, so as to perform subsequent keyword analysis and comparison operations, and the audio and video processing device 16 can capture frame images (such as concert pictures, game title images, movie opening pictures, etc.) of the audio and video content played by the audio and video playback device 14 for subsequent generation of query information. The network transmission device 18 can be a common network interface card (such as a wireless network card) used for network signal transmission and is electrically connected to the audio and video processing device 16. Thus, the network transmission device 18 can upload the query information to the network artificial intelligence model 12, and return the keyword data answered by the network artificial intelligence model 12 according to the query information to the audio and video processing device 16. In this way, the audio and video processing device 16 can determine whether to control the audio and video playback device 14 to perform the playback mode switching operation through the analysis and comparison of the keyword data returned by the network artificial intelligence model 12 and the above-mentioned pre-established index correspondence table, so as to adjust the audio and video playback parameter settings of the currently played audio and video content, so that the audio and video playback device 10 can automatically switch to the audio and video scene mode that meets the current viewing needs, so as to enhance the user's viewing experience.

[0036] Here, the process steps of the playback mode switching method provided by the present invention are described. Figure 1 as well as Figure 2 , Figure 2 2 is a flowchart of a playback mode switching method according to an embodiment of the present invention. The playback mode switching method of the present invention using the audio and video playback device 10 to perform a playback mode switching operation includes the following steps.

[0037] Step S20: the video processing device 16 pre-establishes a corresponding index table of a plurality of preset keyword data and a plurality of play modes;

[0038] Step S22: the video playback device 14 plays the video content;

[0039] Step S24: the video processing device 16 captures frame images for the video content and generates query information according to the frame images;

[0040] Step S26: the network transmission device 18 transmits query information to query the network artificial intelligence model 12, and the network artificial intelligence model 12 returns the first keyword data generated according to the query information to the video processing device 16;

[0041] Step S28: The video processing device 16 analyzes and compares the first keyword data with the index corresponding table to determine whether to control the video playback device 14 to perform a playback mode switching operation.

[0042] The following is a detailed description of the above steps. First, in order to provide an instant search function, in step S20, the audio-visual processing device 16 can pre-establish a plurality of preset keyword data and an index correspondence table of a plurality of play modes, so as to serve as a reference for subsequent play mode switching. For example, in the index correspondence table established by the audio-visual processing device 16, one of the preset keyword data may include a pianist (such as Yo-Yo Ma) and a piano performance, the corresponding index of which is a concert, and the play mode to which the audio-visual processing device 16 needs to be switched is a theater mode, or another preset keyword data may include a golf player (such as Tiger Woods) and a golf course, the corresponding index of which is a golf match, and the play mode to which the audio-visual processing device 16 needs to be switched is a golf mode. As for the index correspondence design for other preset keyword data and the play mode they point to, it can be referred to the above example and can be changed according to the actual play application of the audio-visual playback device 10, and will not be repeated here.

[0043] Next, in step S22, the user can control the audio-visual playback device 14 to play the audio-visual content that the user wants to watch, such as using a projector to project a concert video or a game screen. At this time, the audio-visual processing device 16 can capture at least one frame image (such as the first frame image, but not limited to this, it can also be other frame images or multiple frame images within a certain playback time segment) for the audio-visual content, and generate query information for querying the network artificial intelligence model 12 based on the captured frame image (step S24). More specifically, in this embodiment, in order to achieve the purpose of rapid query, the above query information can preferably be used to query the network artificial intelligence model 12 in the form of closed-ended multiple-choice questions about the image type (but not limited to this). For example, the audio-visual processing device 16 can combine the frame image captured by the audio-visual processing device 16 and the closed-ended multiple-choice questions composed of text (for example: this picture is (1) a concert (2) a landscape (3) a sports field (4) a golf course (5) none of the above) to generate the query information to be queried to the network artificial intelligence model 12. In this way, after the network transmission device 18 transmits the query information to query the network artificial intelligence model 12, the network artificial intelligence model 12 can generate corresponding first keyword data according to the query information and send it back to the video processing device 16 (step S26) for the subsequent keyword analysis and comparison by the video processing device 16. It should be noted that in the above process, the video playback device 10 can preferably adopt a real-time translation function (but not limited to this). For example, in this embodiment, the video processing device 16 can use a translation service (such as a translation application software or a real-time translation service provided by the network artificial intelligence model 12 itself) to convert the language corresponding to the query information (such as Chinese) into the default language of the network artificial intelligence model (such as English), so as to improve the accuracy of the query information, so that the network artificial intelligence model 12 can return a more accurate and reasonable answer. In addition, in practice, the audio-visual playback device 10 can pre-set the network artificial intelligence model 12 to the projector optics expert mode, or use the network transmission device 18 to actively transmit the above-mentioned index correspondence table to the network artificial intelligence model 12, so as to assist the network artificial intelligence model 12 to continue to evolve in the projector optics application field, so that the network artificial intelligence model 12 can provide more professional field-oriented answers.

[0044] After receiving the first keyword data returned by the network artificial intelligence model 12, the audio and video processing device 16 can analyze and compare the first keyword data returned by the network artificial intelligence model 12 and the index correspondence table pre-established by the audio and video processing device 16 (step S28), for example, using a program syntax analysis method (parsing) to perform analysis and comparison (but not limited to this, and the relevant description of the program syntax analysis method is common in the prior art and will not be repeated here), so as to determine whether there is preset keyword data in the index correspondence table that can match the first keyword data, so as to serve as a reference for whether to control the audio and video playback device 14 to perform a playback mode switching operation.

[0045] In the above process, when the audio and video processing device 16 determines that the first keyword data matches one of the preset keyword data, for example, the network artificial intelligence model 12 returns the first keyword data corresponding to "(1) concert" and the audio and video processing device 16 determines that it matches the concert index in the index correspondence table, the audio and video processing device 16 can control the audio and video playback device 14 to perform a playback mode switching operation, that is, according to the index correspondence between the concert and the theater mode established in the index correspondence table, the current image playback mode of the audio and video playback device 14 is switched to the theater mode, so as to control the audio and video playback device 14 to adjust the audio and video playback parameter settings for the audio and video content (for example, enhancing the bass effect or increasing the image brightness and contrast, but not limited to this). In this way, the audio and video playback device 10 can automatically switch to the audio and video scene mode that meets the user's current viewing needs without the user's manual adjustment, thereby effectively improving the user's viewing experience. On the contrary, when the audio and video processing device 16 determines that the first keyword data does not match any preset keyword data, for example, the network artificial intelligence model 12 returns the first keyword data corresponding to "(5) None of the above" and the audio and video processing device 16 determines that it cannot correspond to any index correspondence in the index correspondence table, then the audio and video playback device 16 does not perform the playback mode switching operation, thereby improving the execution efficiency of the audio and video playback device 10 in switching the playback mode.

[0046] It should be noted that, in the case where the above keywords do not match, the audio and video processing device 16 can also continue to perform batch inquiries to the network artificial intelligence model 12 so as to subsequently establish a new index correspondence in the index correspondence table, wherein the audio and video processing device 16 can preferably continue to perform batch inquiries to the network artificial intelligence model 12 in the form of a question asking the image type (for example: What is this picture?) (but not limited to this). In this way, after the network transmission device 18 transmits the above query information to the network artificial intelligence model 12, the network artificial intelligence model 12 can generate corresponding second keyword data according to the query information, and the audio and video processing device 16 can establish a new index correspondence between the second keyword data and one of the playback modes in the above index correspondence table according to the second keyword data. For example, if the second keyword data returned by the network artificial intelligence model 12 is "scenery", the audio and video processing device 16 can additionally establish a new index correspondence between scenery and high brightness mode in the index correspondence table, thereby further expanding the functionality of the audio and video playback device 10 in switching the playback mode.

[0047] Compared to the prior art, the present invention determines whether it is necessary to execute a playback mode switching operation of the audio and video playback device by analyzing and comparing the first keyword data and the index correspondence table returned by the network artificial intelligence model according to the frame image of the audio and video content, so as to achieve the effect that the audio and video playback device can automatically switch to the audio and video scene mode that meets the user's current viewing needs without the user's manual adjustment. In this way, the present invention can effectively solve the problem of time-consuming and labor-intensive audio and video parameter adjustment process of the audio and video playback device mentioned in the prior art, thereby greatly improving the user's operating convenience in using the audio and video playback device and optimizing the user's viewing experience.

[0048] In practical applications, the audio and video playback device 10 can also provide a voice inquiry function, such as Figure 1As shown, the audio and video playback device 10 may further include a voice processing device 20, which may be a voice recognition device commonly used in voice input / output applications (its related description is common in the prior art and will not be repeated here) and is electrically connected to the audio and video processing device 16 to be used to deploy voice services on the audio and video playback device 10. Thereby, the voice processing device 20 can generate corresponding voice input data according to the voice message sent by the user, and the audio and video processing device 16 can generate corresponding voice keyword data according to the above voice input data, and then analyze and compare the voice keyword data and the index corresponding table to determine whether there is preset keyword data in the index corresponding table that can match the voice keyword data, so as to serve as a reference for whether to control the audio and video playback device 14 to perform a playback mode switching operation. For example, if the voice input data generated by the voice processing device 20 according to the user's voice input operation is "I am watching Yo-Yo Ma playing the piano", the voice keyword data generated by the audio-visual processing device 16 may include Yo-Yo Ma and piano performance. In this way, after analysis and comparison, the audio-visual processing device 16 can determine that the above-mentioned voice keyword data matches the concert index in the index correspondence table, and control the audio-visual playback device 14 to perform the playback mode switching operation accordingly, that is, according to the index correspondence relationship between the concert and the theater mode established in the index correspondence table, the current video playback mode of the audio-visual playback device 14 is switched to the theater mode. On the contrary, if the above-mentioned voice input data does not match any of the preset keyword data, the audio-visual processing device 16 will execute the aforementioned step of inquiring the network artificial intelligence model 12, and the relevant description can be referred to the above-mentioned embodiment by analogy, and will not be repeated here.

[0049] It is worth mentioning that in order to ensure the validity and legality of the source of the audio and video content played by the audio and video playback device 10, the present invention can also adopt the following Figure 3 The video source analysis method shown is used to pre-determine whether to play the above-mentioned audio and video content. First, before executing step S22, Figure 3 It can be seen that the video processing device 16 can upload relevant information of the video content (such as frame images or playback URLs) to the network artificial intelligence model 12 for inquiry, so as to pre-determine whether the video content to be played is protected by copyright or whether the playback URL of the video content is unsafe (step S30), so as to decide whether to play the video content.

[0050] In the above process, if the audio-visual processing device 16 determines that the audio-visual content is not protected by copyright or the playback URL of the audio-visual content is a safe URL based on the answer returned by the network artificial intelligence model 12, the audio-visual processing device 16 can execute step S32 to use the network artificial intelligence model 12 to determine whether the audio-visual content is restricted audio-visual content (for example, 18+ videos that are not suitable for children to watch). At this time, if the audio-visual content contains restricted audio-visual content, the audio-visual playback device 14 can choose not to play the audio-visual content (step S34). On the contrary, if the audio-visual content does not contain restricted audio-visual content, the audio-visual processing device 16 can execute step S22 to complete the subsequent playback mode switching step, thereby achieving the purpose of controlling the audio-visual playback content.

[0051] On the other hand, if the video processing device 16 determines that the playback URL of the video content is an unsafe URL (such as a fraudulent URL or a pseudo streaming video phishing link) based on the answer returned by the network artificial intelligence model 12, the video processing device 16 does not play the video content (step S34); in addition, if the video processing device 16 determines that the video content is protected by copyright (such as streaming video, movies, TV series, animation, etc.) based on the answer returned by the network artificial intelligence model 12, the video processing device 16 can continue to execute step S36 to determine whether the playback method of the video content is legal. For example, the video processing device 16 can determine whether the playback method of the video content is legal based on the content description information of the video content, such as through a high definition multimedia interface (High Definition Multimedia Interface). The auxiliary information (such as InfoFrame) obtained by the HDMI transmission line is used to determine whether the audio and video content is played with the officially authorized playback software (or hardware). If so, step S32 is executed, if not, step S34 is executed. The relevant description can be referred to the above description and will not be repeated here.

[0052] In addition, the present invention may further adopt a keyword weight allocation design. For example, the audio and video processing device 16 may capture multiple frame images (such as multiple frame images within a certain playback time segment, but not limited to this) for the audio and video content to batch query the network artificial intelligence model 12, and the network artificial intelligence model 12 may return keywords (such as concerts, advertisements, etc.) to the audio and video processing device 16 one by one for each query. At this time, the audio and video processing device 16 may assign a corresponding weight value to each keyword. Thereby, when the audio and video processing device 16 determines that the total weight value corresponding to the same keyword (such as concert) is greater than a preset threshold value, the audio and video processing device 16 may analyze and compare the same keyword and the index corresponding table as a reference for whether to subsequently control the audio and video playback device 14 to perform a playback mode switching operation. In this way, the network artificial intelligence model 12 can be effectively prevented from providing an incorrect answer, thereby further improving the execution accuracy of the playback mode switching method of the present invention.

[0053] In summary, the present invention provides a playback mode switching method and an audio-visual playback device thereof. The audio-visual playback device includes an audio-visual playback device, an audio-visual processing device, and a network transmission device. The audio-visual playback device is used to play audio-visual content; the audio-visual processing device is electrically connected to the audio-visual playback device, and is used to pre-establish a plurality of preset keyword data and an index correspondence table of a plurality of playback modes, and to capture at least one frame of image for the audio-visual content and generate at least one query information based on the at least one frame of image; the network transmission device is electrically connected to the audio-visual processing device, and is used to return the first keyword data generated by the network artificial intelligence model according to the at least one query information to the audio-visual processing device, so that the audio-visual processing device analyzes and compares the first keyword data with the index correspondence table to determine whether to control the audio-visual playback device to perform a playback mode switching operation, so as to adjust the audio-visual playback parameter settings of the audio-visual content. In this way, it is possible to effectively avoid the network artificial intelligence model from providing an erroneous answer, thereby further improving the execution accuracy of the playback mode switching method of the present invention.

[0054] Although the present invention is described in conjunction with the accompanying drawings, the embodiments disclosed in the drawings are intended to exemplify the preferred embodiments of the present invention and should not be construed as limiting the present invention. In order to clearly describe the required components, the proportions in the schematic drawings do not represent the proportional relationship of the actual components.

[0055] The present invention has been described by the above-mentioned relevant embodiments, however, the above-mentioned embodiments are only examples for implementing the present invention. It must be pointed out that the disclosed embodiments do not limit the scope of the present invention. On the contrary, changes and modifications made without departing from the spirit and scope of the present invention are all within the scope of patent protection of the present invention.

Claims

1. A method for switching a playback mode, characterized in that: include: Establishing an index correspondence table between a plurality of preset keyword data and a plurality of play modes through an audio and video play device; Playing the audio and video content through the audio and video playback device; Capturing at least one frame of image from the video content through the video playback device and generating at least one query information according to the at least one frame of image to query the network artificial intelligence model; Returning first keyword data to the video playback device according to the at least one query information through the network artificial intelligence model; as well as The audio-visual playback device analyzes and compares the first keyword data with the index corresponding table to determine whether to perform a playback mode switching operation, so as to adjust the audio-visual playback parameter settings of the audio-visual content.

2. The playback mode switching method according to claim 1, characterized in that: Also includes: The audio-visual playback device generates voice keyword data according to the voice input data; and The audio-visual playback device analyzes and compares the voice keyword data with the index corresponding table to determine whether to execute the playback mode switching operation.

3. The playback mode switching method according to claim 2, wherein: When the audio-visual playback device determines that the voice input data matches one of the preset keyword data, the audio-visual playback device performs the playback mode switching operation according to the index correspondence table; Alternatively, when the audio-visual playback device determines that the voice input data does not match any preset keyword data, the audio-visual playback device queries the network artificial intelligence model with the at least one query information.

4. The playback mode switching method according to claim 1, wherein: The audio-visual playback device uses a translation service to convert the language corresponding to the at least one query information into a default language of the network artificial intelligence model.

5. The playback mode switching method according to claim 1, characterized in that: Also includes: The video and audio playback device transmits the index correspondence table to the network artificial intelligence model to assist the network artificial intelligence model in evolving.

6. The playback mode switching method according to claim 1, wherein: When the audio-visual playback device determines that the first keyword data matches one of the preset keyword data, the audio-visual playback device performs the playback mode switching operation according to the index correspondence table.

7. The playback mode switching method according to claim 1, wherein: The at least one query information queries the network artificial intelligence model in the form of a closed-ended multiple-choice question asking about the image type.

8. The playback mode switching method according to claim 1, wherein: When the audio-visual playback device determines that the first keyword data does not match any preset keyword data, the audio-visual playback device does not perform the playback mode switching operation, or the audio-visual playback device queries the network artificial intelligence model in the form of a question about the image type based on the at least one frame of image, and the audio-visual playback device establishes an index correspondence between the second keyword data and one of the playback modes in the index correspondence table based on the second keyword data returned by the network artificial intelligence model.

9. The playback mode switching method according to claim 1, wherein: The steps of playing the audio and video content by the audio and video playback device include: The video playback device transmits the video content to the network artificial intelligence model for query to determine whether the video content is protected by copyright or whether the playback URL of the video content is unsafe, so as to decide whether to play the video content.

10. The playback mode switching method according to claim 9, characterized in that: The video playback device determines whether the playback method of the video content is legal according to the content description information in the video content.

11. The playback mode switching method according to claim 9, characterized in that: The video playback device determines whether the video content contains restricted video content through the network artificial intelligence model.

12. The playback mode switching method according to claim 1, wherein: The first keyword data includes multiple keywords, and the audio and video playback device assigns a weight value to each keyword; when the audio and video playback device determines that the total weight value corresponding to the same keyword is greater than a threshold value, the audio and video playback device analyzes and compares the same keyword with the index correspondence table to determine whether to execute the playback mode switching operation.

13. An audio and video playback device with a playback mode switching function, wherein the network is connected to a network artificial intelligence model, characterized in that: The audio and video playback device includes: Audio and video playback device, used to play audio and video content; An audio-visual processing device, electrically connected to the audio-visual playback device, for pre-establishing an index correspondence table of a plurality of preset keyword data and a plurality of playback modes, and for capturing at least one frame of image for the audio-visual content and generating at least one query information according to the at least one frame of image; as well as A network transmission device is electrically connected to the audio and video processing device, and is used to transmit the first keyword data generated by the network artificial intelligence model according to the at least one query information back to the audio and video processing device, so that the audio and video processing device analyzes and compares the first keyword data with the index correspondence table to determine whether to control the audio and video playback device to perform a playback mode switching operation to adjust the audio and video playback parameter settings of the audio and video content.

14. The video and audio playback device according to claim 13, characterized in that: Also includes: A voice processing device, electrically connected to the audio and video processing device, for generating voice input data; The audio-visual processing device generates voice keyword data according to the voice input data, and analyzes and compares the voice keyword data with the index corresponding table to determine whether to control the audio-visual playback device to perform the playback mode switching operation.

15. The video and audio playback device according to claim 14, characterized in that: When the audio and video processing device determines that the voice input data matches one of the preset keyword data, the audio and video processing device controls the audio and video playback device to perform the playback mode switching operation according to the index correspondence table; Alternatively, when the audio and video processing device determines that the voice input data does not match any preset keyword data, the audio and video playback device queries the network artificial intelligence model with the at least one query information.

16. The video and audio playback device according to claim 13, characterized in that: The video and audio processing device uses a translation service to convert the language corresponding to the at least one query information into a default language of the network artificial intelligence model.

17. The video and audio playback device according to claim 13, characterized in that: The network transmission device transmits the index correspondence table to the network artificial intelligence model to assist the network artificial intelligence model in evolving.

18. The video and audio playback device according to claim 13, characterized in that: When the video processing device determines that the first keyword data matches one of the preset keyword data, the video processing device controls the video playback device to perform the playback mode switching operation according to the index correspondence table.

19. The video and audio playback device according to claim 13, characterized in that: The at least one query information queries the network artificial intelligence model in the form of a closed-ended multiple-choice question asking about the image type.

20. The video and audio playback device as claimed in claim 13, characterized in that: When the audio and video processing device determines that the first keyword data does not match any preset keyword data, the audio and video playback device does not perform the playback mode switching operation, or the audio and video processing device inquires the network artificial intelligence model in the form of a question about the image type based on the at least one frame of image, and the audio and video processing device establishes an index correspondence between the second keyword data and one of the playback modes in the index correspondence table based on the second keyword data returned by the network artificial intelligence model.

21. The video and audio playback device according to claim 13, characterized in that: The video processing device determines whether the video content is protected by copyright or whether the playback URL of the video content is unsafe through the network artificial intelligence model to decide whether to play the video content.

22. The video and audio playback device according to claim 21, characterized in that: The video processing device determines whether the playing method of the video content is legal according to a content description information in the video content.

23. The video and audio playback device according to claim 21, characterized in that: The video processing device determines whether the video content contains restricted video content through the network artificial intelligence model.

24. The video and audio playback device according to claim 13, characterized in that: The first keyword data includes multiple keywords, and the audio and video processing device assigns a weight value to each keyword; when the audio and video processing device determines that the total weight value corresponding to the same keyword is greater than a threshold value, the audio and video processing device analyzes and compares the same keyword with the index correspondence table to determine whether to control the audio and video playback device to perform the playback mode switching operation.

Images