Multimedia playing control method and system

Abstract

The invention provides a multimedia playing control method and system, and the method comprises the following steps: obtaining an environment picture through a shooting unit, and obtaining a recognition scene through the environment picture; equipment type codes and equipment signal intensities of a plurality of external equipment in a preset range are collected, the external equipment comprises a Bluetooth sound box and a Bluetooth earphone, and equipment to be connected is selected from the external equipment based on the recognition scene, the equipment type codes and the equipment signal intensities; and switching the playing of the audio stream from the sound outlet hole to the to-be-connected device. Environment pictures are obtained through the shooting unit, identification of use scenes is completed, according to different use scenes, automatic scanning is carried out, different external devices are selected to be connected, dual-channel stereo output is achieved through the external devices, and experience deficiency caused by playing defects of a sound outlet hole is eliminated; through intelligent audio stream playing control, a user does not need to manually operate equipment switching, and the immersion of use is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of audio control, and in particular to a multimedia playback control method and system. Background Art

[0002] Augmented Reality (AR) technology combines the real world with virtual information based on real-time computer computing and multi-sensor fusion. By simulating and reproducing human senses such as vision, hearing, smell, and touch, and overlaying virtual information on real-world information, it provides an experience that transcends the real world.

[0003] AR glasses are devices that utilize augmented reality technology. They seamlessly overlay virtual information with the real world, providing an immersive experience. To use them, they connect to a mobile device, such as a smartphone. Users can access information and enjoy a variety of virtual visual effects anytime, anywhere, without the need for a screen. The display principle of AR glasses is to seamlessly blend virtual space with real scenes through a "layering" process, allowing users to simultaneously see both the real world and virtual content.

[0004] Existing AR glasses usually have sound holes on the temples. After connecting to terminal devices such as mobile phones, audio is played through the sound holes. However, the sound holes set on the temples have low sound and are easily affected by the external environment, affecting the user experience. Summary of the Invention

[0005] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a multimedia playback control method and system, which aims to solve the technical problem in the existing technology that AR glasses play audio through the sound holes on the temples, the sound is relatively small, and is easily affected by the external environment, affecting the user experience.

[0006] To achieve the above objectives, in a first aspect, embodiments of the present application provide a multimedia playback control method for controlling the audio output of AR glasses, wherein the AR glasses are provided with a sound pickup microphone and a camera unit, and the temples of the AR glasses are provided with sound outlets for playing audio streams. The multimedia playback control method comprises the following steps:

[0007] Acquire an environmental image through the shooting unit, and acquire a recognition scene through the environmental image;

[0008] Collecting device type codes and device signal strengths of multiple external devices within a preset range, the external devices including a Bluetooth speaker and a Bluetooth headset, and selecting a device to be connected from the multiple external devices based on the recognition scenario, the device type codes, and the device signal strengths;

[0009] The playback of the audio stream is switched from the sound outlet to the connected device.

[0010] Furthermore, the step of obtaining the recognition scene through the environment picture includes:

[0011] Converting the environment image from the RGB space to the YUV space to obtain a converted image, and performing histogram equalization processing on the converted image to obtain a stand-by image;

[0012] Based on the feature extraction model, image features are extracted from the stand-by image, and attribution scores of the image features under different scene types are obtained. The highest score is selected from several attribution scores, and the scene type corresponding to the highest score is selected as the recognition scene.

[0013] Furthermore, the formula for obtaining the attribution score is:

[0014]

[0015] Among them, P c represents the attribution score corresponding to the c-th scene type, α i represents the weight of the i-th boundary vector, y i represents the label value of the i-th boundary vector, T i represents the i-th boundary vector, T represents the image feature, β c represents the bias term corresponding to the c-th scene type, K(·) represents the Gaussian kernel function, N c represents the total number of boundary vectors corresponding to the c-th scene type.

[0016] Furthermore, the step of selecting a device to be connected from the plurality of external devices based on the identification scenario, the device type code, and the device signal strength includes:

[0017] Determining the device type of the external device by using the device type code to assign a basic score to the external device, and assigning dynamic type weights to different device types by using the recognition scenario;

[0018] Normalizing the signal strength of the device to obtain a normalized strength value;

[0019] A final score corresponding to the external device is obtained through the basic score, the dynamic type weight and the normalized strength value, and the external device corresponding to the highest final score is selected as the device to be connected.

[0020] Furthermore, the calculation formula for the final score is:

[0021] F′ j =qj *F j +(1-q j -wq j )*Q j +wq j *C j ,

[0022] Among them, F′ j represents the final score corresponding to the jth external device, q j represents the dynamic type weight of the device type corresponding to the jth external device, F j represents the basic score corresponding to the jth external device, wq j represents the previous connection weight corresponding to the j-th external device, Q j represents the normalized intensity value corresponding to the jth external device, C j Indicates the number of previous connections of the j-th external device.

[0023] Furthermore, the step of switching the playback of the audio stream from the sound outlet to the connected device includes:

[0024] Taking the time point of selecting the device to be connected as the starting time point, and selecting a conversion time period based on the starting time point;

[0025] intercepting a segment audio stream and a remaining audio stream from the audio stream based on the conversion time period, and transmitting the segment audio stream and the remaining audio stream to the waiting device;

[0026] An adjustment coefficient is constructed by the start time and the conversion time period, and the paragraph audio stream in the sound outlet and the paragraph audio stream in the connected device are synchronously adjusted by the adjustment coefficient. After the playback of the paragraph audio stream is completed, the remaining audio stream is played through the external device.

[0027] Furthermore, the formula for obtaining the adjustment coefficient is:

[0028]

[0029] Among them, e(t) represents the adjustment coefficient at time t, and t∈t pe , t0 represents the starting time point, and t0∈t pe , t pe Indicates the conversion time period.

[0030] Furthermore, after the step of switching the playback of the audio stream from the sound outlet to the connected device, the method further includes:

[0031] When the device to be connected is a Bluetooth headset, an external environment signal is obtained through the sound pickup microphone, a noise type is obtained based on the external environment signal, and the play mode of the Bluetooth headset is switched according to the noise type.

[0032] Furthermore, the noise type includes steady-state noise and transient noise, the playback mode includes a transparent mode and a noise reduction mode, and the step of obtaining the noise type based on the external environmental signal and switching the playback mode of the Bluetooth headset according to the noise type includes:

[0033] Acquire a frequency spectrum characteristic of the external environmental signal, and acquire low-frequency energy, intermediate-frequency energy, and high-frequency energy corresponding to the external environmental signal based on the frequency spectrum characteristic;

[0034] Determining a noise type based on the low-frequency energy, the intermediate-frequency energy, the high-frequency energy, and a Gaussian mixture model;

[0035] When the noise type is steady-state noise, the Bluetooth headset is switched to a noise reduction mode.

[0036] In a second aspect, an embodiment of the present application provides a multimedia playback control system, which is applied to the multimedia playback control method described in the first aspect above, and the system includes:

[0037] An acquisition module, configured to acquire an environmental image through the shooting unit, and to acquire a recognition scene through the environmental image;

[0038] a collection module, configured to collect device type codes and device signal strengths of a plurality of external devices within a preset range, the external devices including Bluetooth speakers and Bluetooth headsets, and select a device to be connected from the plurality of external devices based on the recognition scenario, the device type codes, and the device signal strengths;

[0039] The switching module is used to switch the playing of the audio stream from the sound outlet to the connected device.

[0040] In a third aspect, an embodiment of the present application provides a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the multimedia playback control method as described in the first aspect above is implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the multimedia playback control method as described in the first aspect above is implemented.

[0042] Compared with the prior art, the beneficial effects of the present invention are: the environmental picture is obtained by the shooting unit, the usage scenario is identified, and according to different usage scenarios, different external devices are automatically scanned and selected for connection, and the connection of the external device is completed according to different external scenes, thereby avoiding the influence of the external environment on audio playback, and realizing dual-channel stereo output through the external device, eliminating the lack of experience caused by the sound outlet, such as low volume; through intelligent audio stream playback control, there is no need for users to manually switch devices, thereby improving the immersive feeling of use; by splitting the audio stream and performing dual dynamic adjustment between the sound outlet and the external device through the adjustment coefficient, audio termination or explosion between audio stream playback switching is avoided; by obtaining the noise type and automatically completing the mode switching of the Bluetooth headset, the intelligence level of playback control is further improved, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 Flowchart of the multimedia playback control method in the first embodiment of the present invention;

[0044] Figure 2 This is a structural block diagram of a multimedia playback control system in a second embodiment of the present invention;

[0045] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0046] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0047] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0049] See also Figure 1 The first embodiment of the present invention provides a multimedia playback control method for controlling the audio output of AR glasses. The AR glasses are provided with a sound pickup microphone and a camera unit, and the temples of the AR glasses are provided with sound outlets for playing audio streams. The multimedia playback control method includes the following steps:

[0050] S10: Acquire an environment picture through the shooting unit, and acquire a recognition scene through the environment picture;

[0051] The step S10 includes:

[0052] S110: Converting the environment image from the RGB space to the YUV space to obtain a converted image, and performing histogram equalization processing on the converted image to obtain a standby image;

[0053] Color space conversion and histogram equalization processing have been widely used and will not be described in detail here. By performing the histogram equalization processing, the dynamic range of the environment image can be expanded and the contrast can be enhanced to ensure that more accurate image features can be extracted later.

[0054] S120: extracting image features from the to-be-used image based on a feature extraction model, obtaining attribution scores of the image features under different scene types, selecting a highest score from a plurality of attribution scores, and selecting the scene type corresponding to the highest score as the recognition scene;

[0055] In this embodiment, the feature extraction model is MobileNetV3, and the formula for obtaining the attribution score is:

[0056]

[0057] Among them, P c represents the attribution score corresponding to the c-th scene type, α i represents the weight of the i-th boundary vector, y i represents the label value of the i-th boundary vector, T i represents the i-th boundary vector, T represents the image feature, β c represents the bias term corresponding to the c-th scene type, K(·) represents the Gaussian kernel function, N cRepresents the total number of boundary vectors corresponding to the c-th scene type. It should be noted that the boundary vector is obtained by comparing the historical images corresponding to two different scene types. Assuming that there are two scene types, office and shopping mall, the boundary vector is the feature of high complexity in the office scene and the optical flow feature of high crowd density in the shopping mall scene. As the number of scene types increases, the number of boundary vectors also increases. When obtaining the attribution score of the office scene, it is necessary to extract the boundary vector between the office scene and all other scene types to obtain the attribution score.

[0058] S20: collecting device type codes and device signal strengths of a plurality of external devices within a preset range, the external devices including a Bluetooth speaker and a Bluetooth headset, and selecting a device to be connected from the plurality of external devices based on the recognition scenario, the device type codes, and the device signal strengths;

[0059] In some embodiments, the external device also includes a device capable of playing audio streams, such as a car speaker.

[0060] The step S20 includes:

[0061] S210: Determine the device type of the external device by using the device type code to assign a basic score to the external device, and assign dynamic type weights to different device types by using the recognition scenario;

[0062] The basic score of the Bluetooth headset is greater than the basic score of the Bluetooth speaker. In this embodiment, the basic score of the Bluetooth headset is 1, and the basic score of the Bluetooth speaker is 0.3. By setting the corresponding basic scores, the access priority of the Bluetooth headset is increased.

[0063] S220: Normalizing the device signal strength to obtain a normalized strength value;

[0064] S230: Obtaining a final score corresponding to the external device based on the basic score, the dynamic type weight, and the normalized strength value, and selecting the external device corresponding to the highest final score as the device to be connected;

[0065] The calculation formula for the final score is:

[0066] F′ j =q j *F j +(1-q j -wq j )*Q j +wq j *C j ,

[0067] Among them, F′ j represents the final score corresponding to the jth external device, q j represents the dynamic type weight of the device type corresponding to the jth external device, F j represents the basic score corresponding to the jth external device, wq j represents the previous connection weight corresponding to the j-th external device, Q j represents the normalized intensity value corresponding to the jth external device, C j Represents the number of previous connections of the jth external device. As the same external device is connected multiple times, the probability of determining the connection the next time it is connected will also increase.

[0068] S30: Switching the playback of the audio stream from the sound outlet to the connected device;

[0069] The step S30 includes:

[0070] S310: Taking the time point of selecting the device to be connected as the starting time point, selecting a conversion time period based on the starting time point;

[0071] In this embodiment, the conversion time period is 100 ms.

[0072] S320: intercepting a segment audio stream and a remaining audio stream from the audio stream based on the conversion time period, and transmitting the segment audio stream and the remaining audio stream to the connected device;

[0073] S330: constructing an adjustment coefficient based on the start time and the conversion time period, synchronously adjusting the segment audio stream in the sound outlet and the segment audio stream in the connected device based on the adjustment coefficient, and after the playback of the segment audio stream is completed, playing the remaining audio stream through the external device;

[0074] The formula for obtaining the adjustment coefficient is:

[0075]

[0076] Among them, e(t) represents the adjustment coefficient at time t, and t∈t pe , t0 represents the starting time point, and t0∈t pe , t pe Indicates the conversion time period.

[0077] It should be noted that after the transmission is completed, the sound outlet and the external device play the audio stream of the segment synchronously. The playing rules of the sound outlet are:

[0078] B p (t) = D L (t)*(1-e(t)),

[0079] Among them, B p (t) represents the audio stream played by the sound hole at time t, D L (t) represents the audio stream of the segment at time t;

[0080] The playback rules for external devices are as follows:

[0081] B w (t) = D L (t)*e(t),

[0082] Among them, B w (t) represents the audio stream played by the external device at time t.

[0083] Preferably, the method further comprises:

[0084] S40: When the connected device is a Bluetooth headset, obtaining an external environment signal through the sound pickup microphone, obtaining a noise type based on the external environment signal, and switching a play mode of the Bluetooth headset according to the noise type;

[0085] The noise types include steady-state noise (such as air conditioning sound) and transient noise (such as door knocking), and the playback modes include transparent mode and noise reduction mode.

[0086] The step S40 includes:

[0087] S410: Acquire frequency spectrum characteristics of the external environmental signal, and acquire low-frequency energy, medium-frequency energy, and high-frequency energy corresponding to the external environmental signal based on the frequency spectrum characteristics;

[0088] Specifically, the external environmental signal is windowed to obtain a signal to be processed, and the signal to be processed is Fourier transformed to obtain the spectral features. The low-frequency energy, the mid-frequency energy, and the high-frequency energy are obtained by using the spectral features in a low-frequency band (20 Hz to 300 Hz), a mid-frequency band (30 Hz to 3 kHz), and a high-frequency band (3 kHz to 20 kHz).

[0089] S420: Determine a noise type based on the low-frequency energy, the intermediate-frequency energy, the high-frequency energy, and a Gaussian mixture model;

[0090] The low-frequency energy, the intermediate-frequency energy, and the high-frequency energy are substituted into the Gaussian mixture model for analysis to clarify the probability of this portion of energy under different noise types, and then the noise type with a higher probability is selected.

[0091] S430: When the noise type is steady-state noise, switch the Bluetooth headset to a noise reduction mode.

[0092] The environmental picture is obtained by the shooting unit, and the usage scenario is identified. According to different usage scenarios, different external devices are automatically scanned and selected for connection. The connection of the external device is completed according to different external scenes, avoiding the influence of the external environment on the audio playback. The dual-channel stereo output is achieved through the external device, eliminating the lack of experience caused by the sound outlet, such as low volume; through intelligent audio stream playback control, there is no need for users to manually switch devices, thereby improving the immersive feeling of use; by dividing the audio stream and performing dual dynamic adjustment between the sound outlet and the external device through the adjustment coefficient, audio termination or explosion between audio stream playback switching is avoided; by obtaining the noise type and automatically completing the mode switching of the Bluetooth headset, the intelligence of the playback control is further improved, and the user experience is improved.

[0093] See also Figure 2 The second embodiment of the present invention provides a multimedia playback control system, which is applied to the multimedia playback control method described in the above embodiment. Details that have been described will not be repeated here. As used below, the terms "module," "unit," "subunit," etc. may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0094] The system comprises:

[0095] An acquisition module 10 is configured to acquire an environment image through the shooting unit and to obtain a recognition scene through the environment image;

[0096] The acquisition module 10 includes:

[0097] The first unit is configured to convert the environment image from the RGB space to the YUV space to obtain a converted image, and perform histogram equalization processing on the converted image to obtain a stand-by image;

[0098] a second unit configured to extract image features from the to-be-used image based on a feature extraction model, obtain attribution scores of the image features under different scene types, select a highest score from a plurality of attribution scores, and select the scene type corresponding to the highest score as the recognition scene;

[0099] a collection module 20 for collecting device type codes and device signal strengths of a plurality of external devices within a preset range, the external devices including Bluetooth speakers and Bluetooth headsets, and selecting a device to be connected from the plurality of external devices based on the recognition scenario, the device type codes, and the device signal strengths;

[0100] The acquisition module 20 includes:

[0101] a third unit, configured to determine the device type of the external device according to the device type code, assign a basic score to the external device, and assign dynamic type weights to different device types according to the recognition scenario;

[0102] A fourth unit is configured to perform normalization processing on the device signal strength to obtain a normalized strength value;

[0103] A fifth unit is configured to obtain a final score corresponding to the external device based on the basic score, the dynamic type weight, and the normalized strength value, and select the external device corresponding to the highest final score as the device to be connected;

[0104] A switching module 30 is used to switch the playback of the audio stream from the sound outlet to the connected device;

[0105] The switching module 30 includes:

[0106] A sixth unit is configured to use the time point when the to-be-connected device is selected as the starting time point and select a conversion time period based on the starting time point;

[0107] A seventh unit is configured to intercept a segment audio stream and a remaining audio stream from the audio stream based on the conversion time period, and transmit the segment audio stream and the remaining audio stream to the connected device;

[0108] an eighth unit, configured to construct an adjustment coefficient based on the start time and the conversion time period, synchronously adjust the segment audio stream in the sound outlet and the segment audio stream in the connected device based on the adjustment coefficient, and after completing the playback of the segment audio stream, play the remaining audio stream through the external device;

[0109] Preferably, the system further comprises:

[0110] an adjustment module 40 for, when the connected device is a Bluetooth headset, obtaining an external environment signal through the sound pickup microphone, obtaining a noise type based on the external environment signal, and switching a playback mode of the Bluetooth headset according to the noise type;

[0111] The adjustment module 40 includes:

[0112] A ninth unit is configured to obtain a spectrum characteristic of the external environmental signal, and obtain low-frequency energy, intermediate-frequency energy, and high-frequency energy corresponding to the external environmental signal based on the spectrum characteristic;

[0113] a tenth unit, configured to determine a noise type based on the low-frequency energy, the intermediate-frequency energy, the high-frequency energy, and a Gaussian mixture model;

[0114] The eleventh unit is configured to switch the Bluetooth headset to a noise reduction mode when the noise type is steady-state noise.

[0115] The present invention also provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the multimedia playback control method as described in the above technical solution when executing the computer program.

[0116] The present invention also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the multimedia playback control method described in the above technical solution is implemented.

[0117] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0118] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A multimedia playback control method for controlling the audio output of AR glasses, wherein the AR glasses are provided with a pickup microphone and a camera unit, and the temples of the AR glasses are provided with sound outlets for playing audio streams, characterized in that: The multimedia playback control method comprises the following steps: Acquire an environmental image through the shooting unit, and acquire a recognition scene through the environmental image; Collecting device type codes and device signal strengths of multiple external devices within a preset range, the external devices including a Bluetooth speaker and a Bluetooth headset, and selecting a device to be connected from the multiple external devices based on the recognition scenario, the device type codes, and the device signal strengths; The playback of the audio stream is switched from the sound outlet to the connected device.

2. The multimedia playback control method according to claim 1, wherein: The step of obtaining the recognition scene through the environment image includes: Converting the environment image from the RGB space to the YUV space to obtain a converted image, and performing histogram equalization processing on the converted image to obtain a stand-by image; Image features are extracted from the stand-by image based on a feature extraction model, attribution scores of the image features under different scene types are obtained, the highest score is selected from a number of attribution scores, and the scene type corresponding to the highest score is selected as the recognition scene.

3. The multimedia playback control method according to claim 2, wherein: The formula for obtaining the attribution score is: Among them, P c represents the attribution score corresponding to the c-th scene type, α i represents the weight of the i-th boundary vector, y i represents the label value of the i-th boundary vector, T i represents the i-th boundary vector, T represents the image feature, β c represents the bias term corresponding to the c-th scene type, K(·) represents the Gaussian kernel function, N c represents the total number of boundary vectors corresponding to the c-th scene type.

4. The multimedia playback control method according to claim 1, wherein: The step of selecting a device to be connected from the plurality of external devices based on the identification scenario, the device type code, and the device signal strength includes: Determining the device type of the external device by using the device type code to assign a basic score to the external device, and assigning dynamic type weights to different device types by using the recognition scenario; Normalizing the signal strength of the device to obtain a normalized strength value; A final score corresponding to the external device is obtained through the basic score, the dynamic type weight and the normalized strength value, and the external device corresponding to the highest final score is selected as the device to be connected.

5. The multimedia playback control method according to claim 4, characterized in that: The calculation formula for the final score is: F′ j =q j *F j +(1-q j -wq j )*Q j +wq j *C j , Among them, F′ j represents the final score corresponding to the jth external device, q j represents the dynamic type weight of the device type corresponding to the jth external device, F j represents the basic score corresponding to the jth external device, wq j represents the previous connection weight corresponding to the j-th external device, Q j represents the normalized intensity value corresponding to the jth external device, C j Indicates the number of previous connections of the j-th external device.

6. The multimedia playback control method according to claim 1, wherein: The step of switching the playback of the audio stream from the sound outlet to the connected device includes: Taking the time point of selecting the device to be connected as the starting time point, and selecting a conversion time period based on the starting time point; intercepting a segment audio stream and a remaining audio stream from the audio stream based on the conversion time period, and transmitting the segment audio stream and the remaining audio stream to the waiting device; An adjustment coefficient is constructed by the start time and the conversion time period, and the paragraph audio stream in the sound outlet and the paragraph audio stream in the connected device are synchronously adjusted by the adjustment coefficient. After the playback of the paragraph audio stream is completed, the remaining audio stream is played through the external device.

7. The multimedia playback control method according to claim 6, characterized in that: The formula for obtaining the adjustment coefficient is: Among them, e(t) represents the adjustment coefficient at time t, and t∈t pe , t0 represents the starting time point, and t 0∈ t pe , t pe Indicates the conversion time period.

8. The multimedia playback control method according to claim 1, wherein: After the step of switching the playback of the audio stream from the sound outlet to the connected device, the method further includes: When the device to be connected is a Bluetooth headset, an external environment signal is obtained through the sound pickup microphone, a noise type is obtained based on the external environment signal, and the play mode of the Bluetooth headset is switched according to the noise type.

9. The multimedia playback control method according to claim 8, characterized in that: The noise type includes steady-state noise and transient noise, the playback mode includes a transparent mode and a noise reduction mode, and the steps of obtaining the noise type based on the external environment signal and switching the playback mode of the Bluetooth headset according to the noise type include: Acquire a frequency spectrum characteristic of the external environmental signal, and acquire low-frequency energy, intermediate-frequency energy, and high-frequency energy corresponding to the external environmental signal based on the frequency spectrum characteristic; Determining a noise type based on the low-frequency energy, the intermediate-frequency energy, the high-frequency energy, and a Gaussian mixture model; When the noise type is steady-state noise, the Bluetooth headset is switched to a noise reduction mode.

10. A multimedia playback control system, applied to the multimedia playback control method according to any one of claims 1 to 9, characterized in that: The system comprises: An acquisition module, configured to acquire an environmental image through the shooting unit, and to acquire a recognition scene through the environmental image; a collection module, configured to collect device type codes and device signal strengths of a plurality of external devices within a preset range, the external devices including Bluetooth speakers and Bluetooth headsets, and select a device to be connected from the plurality of external devices based on the recognition scenario, the device type codes, and the device signal strengths; The switching module is used to switch the playing of the audio stream from the sound outlet to the connected device.

Images