Parameter adjustment methods, devices, electronic equipment, and computer-readable storage media

Abstract

This application discloses a parameter adjustment method, apparatus, electronic device, and computer-readable storage medium, belonging to the field of multimedia technology. The method includes: acquiring multimodal information and auxiliary decision-making information of a target device; inputting the multimodal information into a prediction model, and outputting predicted network parameters of the target device through the prediction model; and adjusting the parameters of the multimedia data of the target device based on the predicted network parameters and the auxiliary decision-making information. Thus, by inputting multimodal information into the prediction model, a forward-looking judgment of network parameters can be achieved. Simultaneously, by comprehensively considering the auxiliary decision-making information based on the predicted network parameters, intelligent and precise control of multimedia data parameters can be achieved, thereby significantly improving the robustness, adaptability, and user experience satisfaction of multimedia services in complex network environments.

Description

Technical Field

[0001] This application relates to the field of multimedia technology, specifically to a parameter adjustment method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] Existing adaptive bitrate streaming technologies mainly rely on real-time monitoring of the current network bandwidth to dynamically adjust the video resolution and bitrate to ensure smooth playback.

[0003] However, the above adjustment methods are lagging, which may still cause stuttering during sudden network congestion. Furthermore, the adjustment strategies are relatively simple and fixed, usually with the sole goal of maintaining smoothness, making it difficult to achieve precise and intelligent adjustment of video parameters, thus resulting in a poor user experience. Summary of the Invention

[0004] This application provides a parameter adjustment method, apparatus, electronic device, and computer-readable storage medium, which can achieve precise and intelligent adjustment of multimedia data parameters and improve the user experience.

[0005] In a first aspect, embodiments of this application provide a parameter adjustment method, including: Acquire multimodal information and decision support information of the target device; The multimodal information is input into the prediction model, and the prediction model outputs the prediction network parameters of the target device. Based on the predicted network parameters and the auxiliary decision-making information, the multimedia data of the target device is adjusted.

[0006] In one embodiment, adjusting the parameters of the multimedia data of the target device based on the prediction network parameters and the auxiliary decision information includes: Based on the predicted network parameters, determine the initial setting parameters; Based on the auxiliary decision-making information, the initial setting parameters are corrected to obtain the target setting parameters; Based on the target setting parameters, the multimedia data of the target device is adjusted.

[0007] In one embodiment, the predicted network parameters include predicted bandwidth; The step of determining the initial setting parameters based on the predicted network parameters includes: The ratio of the predicted bandwidth to the preset bandwidth threshold is determined as the scaling factor; Based on the scaling factor, the default setting parameters are adjusted to obtain the initial setting parameters.

[0008] In one embodiment, the auxiliary decision-making information includes one or more of user playback preference information, usage scenario information, and local network characteristic information of the user's location; the initial setting parameters include one or more of initial resolution, initial frame rate, initial bitrate, and initial HDR parameters; the target setting parameters include one or more of target resolution, target frame rate, target bitrate, and target HDR parameters. The step of correcting the initial setting parameters based on the auxiliary decision-making information to obtain the target setting parameters includes: Based on the user playback preference information, determine the first resolution adjustment range, the first frame rate adjustment range, the first bitrate adjustment range, and the first HDR parameter adjustment range; and / or, Based on the aforementioned usage scenario information, determine the second resolution adjustment range, the second frame rate adjustment range, the second bitrate adjustment range, and the second HDR parameter adjustment range; and / or, Based on the regional network characteristic information, the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range are determined. Based on the first resolution adjustment range and / or the second resolution adjustment range and / or the third resolution adjustment range, the initial resolution is corrected to obtain the target resolution; and / or, Based on the first frame rate adjustment magnitude and / or the second frame rate adjustment magnitude and / or the third frame rate adjustment magnitude, the initial frame rate is corrected to obtain the target frame rate; and / or, Based on the first bitrate adjustment range and / or the second bitrate adjustment range and / or the third bitrate adjustment range, the initial bitrate is corrected to obtain the target bitrate; Based on the adjustment range of the first HDR parameter and / or the adjustment range of the second HDR parameter and / or the adjustment range of the third HDR parameter, the initial HDR parameter is corrected to obtain the target HDR parameter.

[0009] In one embodiment, determining the first resolution adjustment range, the first frame rate adjustment range, the first bitrate adjustment range, and the first HDR parameter adjustment range based on the user playback preference information includes: When the user playback preference information indicates that picture quality is prioritized, the first resolution adjustment range is determined as a first resolution increase, the first frame rate adjustment range is determined as a first frame rate decrease, the first bit rate adjustment range is determined as a first bit rate decrease, and the first HDR parameter adjustment range is determined as a first HDR parameter increase. When the user playback preference information indicates that smoothness is prioritized, the first resolution adjustment range is determined to be the first resolution reduction range, the first frame rate adjustment range is determined to be the first frame rate increase range, and the first HDR parameter adjustment range is determined to be the first HDR parameter reduction range.

[0010] In one embodiment, determining the second resolution adjustment range, the second frame rate adjustment range, the second bitrate adjustment range, and the second HDR parameter adjustment range based on the usage scenario information includes: When the usage scenario information characterizes an indoor scene, the second resolution adjustment range is determined as the second resolution increase, and the second HDR parameter adjustment range is determined as the second HDR parameter increase; When the usage scenario information represents an outdoor scene, the second frame rate adjustment range is determined as the second frame rate reduction range, and the second bit rate adjustment range is determined as the second bit rate reduction range; When the usage scenario information represents a mobile scenario, the second resolution adjustment range is determined as the second resolution reduction range, and the second bitrate adjustment range is determined as the third bitrate reduction range.

[0011] In one embodiment, determining the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range based on the regional network characteristic information includes: When the regional network characteristic information characterizes the first type of network region, the third resolution adjustment range is determined as the third resolution increase, and the third HDR parameter adjustment range is determined as the third HDR parameter increase; When the regional network characteristic information characterizes the second type of network region, the third frame rate adjustment magnitude is determined as the third frame rate reduction magnitude, and the third bit rate adjustment magnitude is determined as the fourth bit rate reduction magnitude.

[0012] Secondly, embodiments of this application provide a parameter adjustment device, the device comprising: The information acquisition module is used to acquire multimodal information and decision support information of the target device; The parameter prediction module is used to input the multimodal information into the prediction model and output the predicted network parameters of the target device through the prediction model. The parameter adjustment module is used to adjust the parameters of the multimedia data of the target device based on the prediction network parameters and the auxiliary decision information.

[0013] In one embodiment, the parameter adjustment module includes: The initial parameter determination submodule is used to determine the initial setting parameters based on the prediction network parameters; The target parameter determination submodule is used to correct the initial setting parameters based on the auxiliary decision information to obtain the target setting parameters; The parameter adjustment submodule is used to adjust the parameters of the multimedia data of the target device based on the target setting parameters.

[0014] In one embodiment, the predicted network parameters include the predicted bandwidth; the initial parameter determination submodule includes: A coefficient determination unit is used to determine the ratio of the predicted bandwidth to the preset bandwidth threshold as a scaling factor; The default parameter adjustment unit is used to adjust the default setting parameters based on the scaling factor to obtain the initial setting parameters.

[0015] In one embodiment, the auxiliary decision-making information includes one or more of user playback preference information, usage scenario information, and local network characteristic information of the user's location; the initial setting parameters include one or more of initial resolution, initial frame rate, initial bitrate, and initial HDR parameters; the target setting parameters include one or more of target resolution, target frame rate, target bitrate, and target HDR parameters; the target parameter determination submodule includes: The first amplitude determination unit is used to determine the first resolution adjustment amplitude, the first frame rate adjustment amplitude, the first bit rate adjustment amplitude, and the first HDR parameter adjustment amplitude based on the user playback preference information. The second amplitude determination unit is used to determine the second resolution adjustment amplitude, the second frame rate adjustment amplitude, the second bit rate adjustment amplitude, and the second HDR parameter adjustment amplitude based on the usage scenario information. The third amplitude determination unit is used to determine the third resolution adjustment amplitude, the third frame rate adjustment amplitude, the third bit rate adjustment amplitude, and the third HDR parameter adjustment amplitude based on the regional network characteristic information. The first parameter correction unit is used to correct the initial resolution based on the first resolution adjustment range and / or the second resolution adjustment range and / or the third resolution adjustment range to obtain the target resolution. The second parameter correction unit is used to correct the initial frame rate based on the first frame rate adjustment magnitude and / or the second frame rate adjustment magnitude and / or the third frame rate adjustment magnitude to obtain the target frame rate. The third parameter correction unit is used to correct the initial bitrate based on the first bitrate adjustment range and / or the second bitrate adjustment range and / or the third bitrate adjustment range to obtain the target bitrate. The fourth parameter correction unit is used to correct the initial HDR parameters based on the adjustment range of the first HDR parameter and / or the adjustment range of the second HDR parameter and / or the adjustment range of the third HDR parameter to obtain the target HDR parameters.

[0016] In one embodiment, the first amplitude determination unit includes: The first amplitude determination subunit is used to determine the first resolution adjustment amplitude as a first resolution increase, the first frame rate adjustment amplitude as a first frame rate decrease, the first bit rate adjustment amplitude as a first bit rate decrease, and the first HDR parameter adjustment amplitude as a first HDR parameter increase when the user playback preference information indicates that picture quality is prioritized. The second amplitude determination subunit is used to determine, when the user playback preference information indicates smoothness priority, the first resolution adjustment amplitude is determined as a first resolution reduction amplitude, the first frame rate adjustment amplitude is determined as a first frame rate increase amplitude, and the first HDR parameter adjustment amplitude is determined as a first HDR parameter reduction amplitude.

[0017] In one embodiment, the second amplitude determining unit includes: The third amplitude determination subunit is used to determine the second resolution adjustment amplitude as the second resolution increase and the second HDR parameter adjustment amplitude as the second HDR parameter increase when the usage scenario information characterizes the indoor scene. The fourth amplitude determination subunit is used to determine the second frame rate adjustment amplitude as the second frame rate reduction amplitude and the second bit rate adjustment amplitude as the second bit rate reduction amplitude when the usage scenario information represents an outdoor scene. The fifth amplitude determination subunit is used to determine the second resolution adjustment amplitude as the second resolution reduction amplitude and the second bitrate adjustment amplitude as the third bitrate reduction amplitude when the usage scenario information represents the mobile scenario.

[0018] In one embodiment, the third amplitude determination unit includes: The sixth amplitude determination subunit is used to determine the third resolution adjustment amplitude as the third resolution increase and the third HDR parameter adjustment amplitude as the third HDR parameter increase when the regional network characteristic information characterizes the first type of network region. The seventh amplitude determination subunit is used to determine the third frame rate adjustment amplitude as the third frame rate reduction amplitude and the third bit rate adjustment amplitude as the fourth bit rate reduction amplitude when the regional network characteristic information characterizes the second type of network region.

[0019] Thirdly, embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps in the parameter adjustment method described above.

[0020] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the parameter adjustment method described above.

[0021] Fifthly, embodiments of this application also provide a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described in the embodiments of this application.

[0022] In summary, the embodiments of this application can acquire multimodal information and auxiliary decision-making information of the target device, input the multimodal information into a prediction model, output the predicted network parameters of the target device through the prediction model, and then adjust the parameters of the multimedia data of the target device based on the predicted network parameters and auxiliary decision-making information. Thus, by inputting multimodal information into the prediction model, a forward-looking judgment of network parameters can be achieved. Simultaneously, by comprehensively considering auxiliary decision-making information based on the predicted network parameters, intelligent and precise control of multimedia data parameters can be achieved, thereby significantly improving the robustness, adaptability, and user experience satisfaction of multimedia services in complex network environments. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of a parameter adjustment method provided in an embodiment of this application; Figure 2 This is a schematic flowchart illustrating a specific embodiment of adjusting multimedia data parameters provided in this application; Figure 3 This is a schematic flowchart illustrating a specific embodiment of determining initial setting parameters provided in this application; Figure 4This is a schematic flowchart of a specific embodiment of the modification of initial setting parameters provided in this application; Figure 5 This is a schematic diagram of the structure of a parameter adjustment device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0026] It's important to note that in fields like video streaming, video conferencing, and live online broadcasting, adaptive bitrate streaming technology is one of the core technologies for ensuring a good user experience. Its typical workflow is as follows: the client continuously monitors current network availability, latency, packet loss rate, and other metrics, and based on preset threshold mapping rules, selects and switches between media files of different quality levels (corresponding to different resolutions and bitrates) pre-stored on the server to play the stream most suitable for the current network conditions. For example, when a bandwidth decrease is detected, it automatically switches to a lower bitrate and lower resolution video stream to avoid buffering; when bandwidth recovers, it gradually switches back to a higher resolution version.

[0027] The inventors of this application have discovered that although this technology is widely used, its inherent technical paradigm has several shortcomings: 1. Passive response and lack of prediction: It relies entirely on real-time or recent historical network conditions for decision-making, which is a "post-event remedy." It lacks the ability to predict rapid, periodic, or trend-based changes in network conditions, making it difficult to make forward-looking parameter adjustments before network deterioration, leading to fluctuations in user experience. 2. Rigid strategy and lack of personalization: The adjustment logic is usually a pre-set fixed algorithm, with "no lag" as the primary or only optimization goal, making it difficult to distinguish and meet the personalized needs of users. 3. Single optimization dimension: The core variables of traditional solutions are resolution and bitrate, while lacking dynamic and coordinated adjustment mechanisms for frame rate (affecting motion smoothness) and HDR (High Dynamic Range) parameters (affecting color and contrast), which also significantly affect subjective experience. For example, on high refresh rate devices, the frame rate is not fully utilized to improve smoothness; or on HDR display devices, the transmission of HDR parameters is not prioritized.

[0028] Therefore, how to construct a solution that can proactively predict network changes and integrate multi-dimensional auxiliary decision-making information for intelligent and personalized dynamic parameter adjustment has become a key technical issue in improving the quality of multimedia services.

[0029] To address the current challenge of achieving precise and intelligent adjustment of multimedia data parameters, this application aims to provide a parameter adjustment method. This method acquires multimodal information and auxiliary decision-making information from the target device, inputs the multimodal information into a prediction model, and outputs predicted network parameters for the target device. Based on these predicted network parameters and auxiliary decision-making information, the method can adjust the multimedia data parameters of the target device. Thus, by inputting multimodal information into the prediction model, it enables forward-looking judgment of network parameters. Furthermore, by comprehensively considering auxiliary decision-making information based on the predicted network parameters, it achieves intelligent and precise control of multimedia data parameters, thereby significantly improving the robustness, adaptability, and user experience satisfaction of multimedia services in complex network environments.

[0030] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the priority of the embodiments.

[0031] Figure 1 The illustration shows a schematic flowchart of a parameter adjustment method according to an embodiment of this application. The execution subject of this parameter adjustment method can be a parameter adjustment device, which can be integrated into any electronic device with data processing, network communication, and program execution functions. The electronic device can be a server or a terminal, etc.

[0032] The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, network acceleration services (Content Delivery Network, CDN), as well as big data and artificial intelligence platforms.

[0033] The terminal can be a mobile phone, tablet computer, laptop computer, desktop computer, smart home device, wearable smart device, or in-vehicle computer, but is not limited to these. The terminal and server can be connected directly or indirectly through wired or wireless communication, which is not limited herein.

[0034] In this embodiment, the description will be from the perspective of a parameter adjustment device, which can be integrated into a server or terminal. To facilitate the explanation of the parameter adjustment method of this application, the following will describe the parameter adjustment device integrated into the target device in detail, that is, the target device will be used as the execution subject for detailed explanation.

[0035] Reference Figure 1 The diagram shows a flowchart of a parameter adjustment method according to this application. The method may specifically include steps S101 to S103, as follows: S101: Acquire multimodal information and decision support information of the target device.

[0036] In this embodiment, the target device refers to a terminal device that is receiving, decoding, rendering, or playing multimedia data, such as a smartphone, tablet computer, smart TV, or personal computer.

[0037] In this embodiment, multimodal information refers to diverse data collected from the target device and its operating environment, which is used to characterize the current operating state of the target device. Specifically, multimodal information includes at least two of the following content types: network status data, user behavior data, device performance data, and multimedia data.

[0038] In this embodiment, network status data is used to characterize the real-time performance indicators of the target device's current network connection. Specifically, network status data may include one or more of the following: current network bandwidth, latency, and packet loss rate. This network status data can be collected through operating system APIs (Application Programming Interfaces) or network probes. Bandwidth represents the currently available downlink bandwidth (in Mbps), a key indicator determining the upper limit of video bitrate; latency represents the round-trip time (RTT, in milliseconds) of network data packets, affecting the interactive experience and buffering decisions; and packet loss rate represents the percentage (%) of data packets lost within a specific time period, reflecting network stability and reliability.

[0039] In this embodiment, user behavior data is used to characterize user behavior patterns during interaction with current multimedia data. Specifically, user behavior data may include one or more of the following: multimedia data usage duration, interaction frequency, and historical usage preferences. This user behavior data can be obtained through application layer logs and interaction event monitoring. Usage duration represents the duration of playback of the current multimedia data, used to determine user engagement; interaction frequency represents the number of times the user performs operations such as play, pause, fast forward, and rewind per unit of time, reflecting user activity and their need to control the content's pace; historical usage preferences represent biased conclusions drawn from the analysis of the user's long-term viewing history, such as a preference for high frame rate sports events or a preference for high-resolution movies.

[0040] In this embodiment, device performance data is used to characterize the real-time resource load and capacity constraints of the target device. Specifically, device performance data may include one or more of the following: CPU (processor) load, GPU (graphics processor) load, memory usage, and battery status. This device performance data can be obtained through system monitoring tools. CPU load and GPU load refer to the current utilization rate (%) of the processor and graphics processor, respectively, directly affecting the smoothness of high-definition video decoding; memory usage indicates the current available memory size, and insufficient resources may cause application lag or termination; battery status includes the remaining battery percentage and whether it is charging, etc. Low battery levels may trigger power-saving strategies to limit performance and extend battery life.

[0041] In this embodiment, the content type of multimedia data refers to the semantic category of the multimedia data. Content types can be obtained through video metadata, content identifiers, or lightweight real-time analytics (such as scene detection). For example, they can be categorized as "live sports" (sensitive to frame rate), "movies / TV series" (sensitive to resolution and HDR), "video conferencing" (sensitive to low latency), and "animation" (potentially requiring lower bitrate).

[0042] In this embodiment, by fusing information from at least two modalities, the target device can obtain a more comprehensive and accurate device status, providing an effective data foundation for the accurate prediction of network parameters.

[0043] In this embodiment, the auxiliary decision-making information is contextual information used to guide parameter adjustments. Specifically, this auxiliary decision-making information may include one or more of the following: user playback preference information, usage scenario information, and local network characteristic information of the user's location.

[0044] In this embodiment, user playback preference information is used to characterize the user's preference for the playback effect of multimedia data. This user playback preference information can be the playback mode selected by the user through the application settings interface. For example, user playback preference information can include picture quality priority, smoothness priority, etc.

[0045] In this embodiment, the usage scenario information is used to characterize the environmental category of the target device. This usage scenario information can be identified based on GPS signal strength, Wi-Fi connection status, accelerometer and light sensor data. For example, the usage scenario information may specifically include indoor scene, outdoor scene, mobile scene, etc.

[0046] In this embodiment, regional network characteristic information is used to characterize the overall network performance of the user's location. For example, the user's location may specifically include a first type of network area and a second type of network area. The first type of network area is used to characterize areas with high network performance, and the second type of network area is used to characterize areas with low network performance. For example, the first type of network area refers to an area where 5G coverage is greater than a first threshold and average bandwidth is greater than a second threshold, and the second type of network area refers to an area where 5G coverage is less than or equal to the first threshold or average bandwidth is less than or equal to the second threshold.

[0047] S102: Input multimodal information into the prediction model, and output the prediction network parameters of the target device through the prediction model.

[0048] In this embodiment, the prediction model can specifically employ a deep learning model for processing multivariate time series data, such as a Transformer model or a Long Short-Term Memory network. The model input of the prediction model can be represented as follows: , where X t Represents multimodal information, B t Indicates bandwidth, L t P indicates a delay. loss U represents the packet loss rate. t D represents a user behavior data vector. t This represents a vector of device performance data. The model output of the prediction model is predicted network parameters, which can specifically represent predicted bandwidth, predicted latency, predicted packet loss rate, etc. These predicted network parameters can specifically represent network parameters for the next n seconds, where n is an integer greater than or equal to 1. For example, these predicted network parameters can be represented as [ , ,..., ].

[0049] In this embodiment, the prediction model can be trained using a training dataset, where the sample data includes multimodal information of the samples and the corresponding sample labels. For example, the prediction model can be trained as follows: input the multimodal information of the samples into an initial model to obtain the predicted values ​​output by the initial model; calculate the loss function value by applying a preset loss function to the predicted values ​​and the sample labels corresponding to the multimodal information; update the model parameters of the initial model based on the loss function value until the training cutoff condition is met, thus obtaining the prediction model. In this way, the prediction model can fully explore the correlation patterns between multimodal information and prediction network parameters. For example, the prediction model can learn that when "GPU load starts to increase" and "the content type is a high bitrate movie," even if the current bandwidth is stable, the risk of network processing capacity decreasing due to device overheating and frequency throttling will increase in the future; or, when "user interaction frequency suddenly decreases," it may indicate that the network is about to enter a stable viewing period.

[0050] In this embodiment, the loss function can be a mean squared error loss function or an L2 loss function, etc. For example, the following mean squared error loss function can be used to calculate the loss function value by calculating the sample labels corresponding to the predicted value and the multimodal information of the sample: (1); Where L represents the loss function value, This represents the predicted value corresponding to the i-th time step. Let represent the sample label corresponding to the i-th time step, and n represent the number of samples.

[0051] In this embodiment, the prediction model performs collaborative reasoning by comprehensively considering information such as network status data, user behavior data, device performance data, and the content type of multimedia data. This makes the output predicted network parameters no longer just simple inferences from network status data, but a comprehensive prediction that takes into account device load, user habits, and content characteristics. As a result, the prediction results are more accurate and reliable, especially for changes in network experience indirectly caused by factors on the device side or user behavior side.

[0052] S103: Based on the predicted network parameters and auxiliary decision-making information, adjust the parameters of the multimedia data of the target device.

[0053] In this embodiment, multimedia data may include one or more of video data, audio data, and image data. Specifically, parameters for video data may include resolution, bitrate, frame rate, and HDR parameters; parameters for audio data may include bitrate, sampling rate, bit depth, number of channels, and encoding format; and parameters for image data may include resolution, compression quality, and image format.

[0054] It's important to note that bitrate refers to the amount of data transmitted per second in a video stream, usually measured in kbps (kilobits per second) or Mbps (megabits per second). A higher bitrate results in better video quality, but also requires more network bandwidth. Resolution refers to the number of pixels in a video frame, typically expressed as width x height (e.g., 1920 x 1080, or 1080p for short). Higher resolution results in a clearer image, but also requires more network bandwidth. Frame rate refers to the number of frames displayed per second in a video, usually measured in fps (frames per second). A higher frame rate results in smoother playback. HDR is a video technology that enhances detail and color reproduction by increasing the range of brightness and contrast.

[0055] In this implementation, after obtaining the auxiliary decision-making information and the prediction network parameters output by the prediction model, the feasible parameter range can be determined first by using the prediction network parameters as a hard constraint. For example, if the prediction bandwidth is 3Mbps, then all parameter combinations with bitrate requirements exceeding 3Mbps are excluded. Then, the auxiliary decision-making information is used as the optimization objective to find the optimal solution in the feasible solution space. For example, when user playback preference information is the primary consideration, if the user prioritizes image quality, then while meeting the prediction bandwidth requirements, priority is given to improving resolution and HDR effects, and a moderate reduction in frame rate is acceptable. Simultaneously, fine-tuning is performed based on usage scenario information. For example, in mobile scenarios, more bandwidth margin can be reserved to cope with prediction errors, thereby moderately reducing resolution and bitrate.

[0056] In this embodiment, by integrating multimodal information including network status data, user behavior data, device performance data, and content type, the usage status of the target device can be comprehensively perceived. Then, a predictive model can be used to extract more accurate and reliable predicted network parameters. Finally, based on the predicted network parameters, by comprehensively considering auxiliary decision-making information, intelligent and precise control of multimedia data parameters can be achieved. This not only avoids lag more proactively, but also accurately meets the personalized experience needs of users in complex and ever-changing environments, significantly improving the intelligence level of multimedia services and user satisfaction.

[0057] In one feasible implementation, refer to Figure 2 The steps for adjusting the parameters of the multimedia data of the target device based on predicted network parameters and auxiliary decision-making information may specifically include steps S201 to S203, as follows: S201: Determine the initial setup parameters based on the predicted network parameters.

[0058] In this embodiment, after obtaining the prediction network parameters output by the prediction model, the target device can determine the initial setting parameters corresponding to the prediction network parameters based on the preset correspondence between the prediction network parameters and the initial setting parameters. The correspondence between the prediction network parameters and the initial setting parameters can be stored in the target device's memory using a mapping table.

[0059] In this embodiment, taking the predicted network parameters as the predicted bandwidth and the initial setting parameters as the video parameters as an example, the mapping table can be established offline through extensive experiments and analysis. It defines the minimum guaranteed bandwidth required for different levels of video parameter combinations (such as 1080p@30fps with HDR, 720p@60fps without HDR). In the specific implementation, firstly, the mapping table is searched for at least one parameter combination whose bandwidth is not higher than the predicted bandwidth. Then, the target combination is selected from at least one parameter combination as the initial setting parameters. For example, if the predicted bandwidth is 2.5Mbps, the mapping table shows that 1080p@30fps requires 2.8Mbps, while 720p@30fps only requires 1.5Mbps. Therefore, 720p@30fps can be selected as the initial resolution and frame rate, and an initial bitrate slightly lower than the predicted bandwidth (such as 2.0Mbps) can be assigned to it to reserve a safety margin.

[0060] In this embodiment, by finding the initial setting parameters corresponding to the predicted network parameters, the technical feasibility of the initial setting parameters can be ensured. That is, it can be effectively guaranteed that under the predicted network conditions in the future, the transmission of multimedia data with these initial setting parameters will not be interrupted due to insufficient bandwidth, and a safe and stable starting point is provided for subsequent precise optimization.

[0061] S202: Based on auxiliary decision-making information, the initial setting parameters are corrected to obtain the target setting parameters.

[0062] In this embodiment, correcting the initial setting parameters refers to adjusting, lowering, or keeping the initial setting parameters unchanged. Target setting parameters refer to the specific parameter values ​​used for actual adjustment of multimedia data after correction by auxiliary decision information, such as target resolution, target bitrate, target frame rate, target HDR parameters, etc.

[0063] In this embodiment, the target device has a pre-built correction rule library corresponding to various auxiliary decision-making information. These correction rules define the direction and magnitude of adjustment to each initial setting parameter under different auxiliary decision-making information. For example: Rule A: If the user's playback preference is quality priority, a correction instruction of {resolution: +1 level, HDR: enabled or +1} is generated. Rule B: If the usage scenario is a mobile scene, a correction instruction of {bitrate: -20%} is generated. Rule C: If the regional network characteristic is a second-type network region, a correction instruction of {bitrate: -20%, frame rate: -20%} is generated.

[0064] In this embodiment, the target device integrates all applicable correction rules, for example, by performing weight calculations on all satisfied correction rules, thereby generating correction amounts corresponding to each initial setting parameter, and finally correcting the initial setting parameters based on these correction amounts to obtain the target setting parameters.

[0065] S203: Adjust the parameters of the multimedia data of the target device based on the target setting parameters.

[0066] In this embodiment, after determining the target setting parameters, the target device encapsulates these parameters into a parameter configuration instruction that can be recognized by the multimedia client or encoder. This allows the multimedia client or encoder to encode the multimedia data according to the target setting parameters based on the parameter configuration instruction. For example, when the multimedia data is video data, a parameter configuration instruction containing the target setting parameters can be sent to a local or remote video encoder, causing it to encode the video according to the new target setting parameters.

[0067] In this embodiment, the initial setting parameters that are technically stable and feasible are first determined by using the predictive network parameters. Then, auxiliary decision information is introduced to finely optimize the initial setting parameters in a personalized manner, so that the final target setting parameters can more flexibly adapt to complex user needs and diverse application scenarios, thereby greatly improving the user experience.

[0068] In one feasible implementation, refer to Figure 3 The predicted network parameters may include the predicted bandwidth; the step of determining the initial setting parameters based on the predicted network parameters may specifically include steps S301~S302, as follows: S301: The ratio of the predicted bandwidth to the preset bandwidth threshold is determined as the scaling factor.

[0069] In this embodiment, the preset bandwidth threshold refers to the baseline bandwidth that matches the current default settings. The preset bandwidth threshold is used to characterize the minimum bandwidth required for smooth playback at standard picture quality. This preset bandwidth threshold can be a fixed value or a value dynamically calculated based on the default settings, for example, obtained by looking up a mapping table between preset default settings and preset bandwidth thresholds.

[0070] In this implementation, the scaling factor reflects the degree to which the predicted network conditions meet the requirements of the default parameters. If the scaling factor > 1, it indicates that the predicted bandwidth is higher than the default requirement, the network conditions are relaxed, and there is room to improve image quality; if the scaling factor ≈ 1, it indicates that the predicted bandwidth basically meets the default requirement, and the network conditions are matched; if the scaling factor < 1, it indicates that the predicted bandwidth is lower than the default requirement, the network conditions are strained, and the image quality needs to be reduced.

[0071] S302: Adjust the default settings parameters based on the scaling factor to obtain the initial settings parameters.

[0072] In this embodiment, the default setting parameters refer to the set of multimedia parameters that serve as the scaling reference point. The default setting parameters characterize the image quality level that the target device expects to use under default network conditions. For example, for video data, the default setting parameters may include one or more of the following: default resolution, default frame rate, default bitrate, and default HDR parameters; the initial setting parameters include one or more of the following: initial resolution, initial frame rate, initial bitrate, and initial HDR parameters. For example, the default setting parameters can be set to: {resolution: 1080p, frame rate: 30fps, bitrate: 3.0Mbps, HDR: On}.

[0073] In practical implementation, scaling factors can be used to perform multiplication or exponential operations on numerical or graded parameters in the default parameters. For non-numerical parameters (such as HDR on / off), switching may be performed based on the range in which the coefficient falls.

[0074] In this embodiment, for the default bitrate in the default settings parameters, since the bitrate is usually linearly related to the bandwidth requirement, its adjustment formula can be: Initial bitrate = Default bitrate × min(S, S_max). Where S represents the scaling factor, S represents the maximum scaling factor (e.g., 1.5), and min(S, S_max) is used to limit excessive scaling.

[0075] In this implementation, for the default resolution in the default settings parameters, the resolution level (e.g., 720p, 1080p) typically has a non-linear relationship with the bitrate (e.g., a squared relationship). Therefore, the adjustment logic can be: predefine a list of resolution levels and their corresponding typical bitrate requirement ratios. Based on the bitrate ratio range that the scaling factor S falls into, select the corresponding resolution level as the initial resolution. For example, if S≥1.2, 1080p can be selected; if 0.8≤S<1.2, 720p can be selected; if S<0.8, 480p can be selected.

[0076] In this embodiment, the default frame rate in the default settings parameters is adjusted in a logic similar to that of the resolution, and different levels such as 30fps, 24fps, or 15fps can be selected based on the range of the S value.

[0077] In this embodiment, a threshold can be set for the default HDR parameter in the default settings. When S is higher than the threshold (e.g., S > 1.1), HDR is included in the initial parameters; otherwise, HDR is turned off to save bandwidth.

[0078] In this embodiment, by determining the ratio of the predicted bandwidth to the preset bandwidth threshold as the scaling factor, adaptive adjustment of the default setting parameters can be achieved, providing accurate and reliable data support for subsequent parameter correction.

[0079] In one feasible implementation, the auxiliary decision-making information may specifically include one or more of the following: user playback preference information, usage scenario information, and local network characteristic information of the user's location; initial setting parameters may include one or more of the following: initial resolution, initial frame rate, initial bitrate, and initial HDR parameters; target setting parameters may include one or more of the following: target resolution, target frame rate, target bitrate, and target HDR parameters. (Refer to...) Figure 4 The step of correcting the initial setting parameters based on auxiliary decision-making information to obtain the target setting parameters may specifically include steps S401 to S407, as follows: S401: Based on user playback preference information, determine the first resolution adjustment range, the first frame rate adjustment range, the first bit rate adjustment range, and the first HDR parameter adjustment range.

[0080] In this implementation, the adjustment magnitude is used to characterize the relative change in the initial setting parameters. This adjustment magnitude can be an absolute value (e.g., increasing resolution by one level, bitrate by 200kbps), a relative percentage (e.g., decreasing frame rate by 20%), or a directional instruction (e.g., HDR parameter "increase" indicates enabling or enhancing, "decrease" indicates disabling or weakening). The magnitude value can be positive (increase), negative (decrease), or zero (unchanged).

[0081] In this embodiment, user playback preference information is used to characterize the user's preference for the playback effect of multimedia data. Specifically, user playback preference information may include a picture quality priority mode, a smoothness priority mode, etc. Different user playback preference information can correspond to different adjustments to the first resolution, first frame rate, first bitrate, and first HDR parameters.

[0082] In this embodiment, the step of determining the first resolution adjustment range, the first frame rate adjustment range, the first bitrate adjustment range, and the first HDR parameter adjustment range based on user playback preference information may specifically include: when the user playback preference information indicates priority for image quality, determining the first resolution adjustment range as a first resolution increase, the first frame rate adjustment range as a first frame rate decrease, the first bitrate adjustment range as a first bitrate decrease, and the first HDR parameter adjustment range as a first HDR parameter increase; when the user playback preference information indicates priority for smoothness, determining the first resolution adjustment range as a first resolution decrease, the first frame rate adjustment range as a first frame rate increase, and the first HDR parameter adjustment range as a first HDR parameter decrease.

[0083] In this implementation, image quality priority is used to represent the user's preference for a clearer, more detailed, and more colorful visual image, with a higher tolerance for a slight decrease in motion smoothness.

[0084] In this implementation, the first resolution increase is a positive adjustment signal. For example, it is recommended to increase the resolution by one level (e.g., from 720p to 1080p) based on the initial resolution, or it is recommended to select the highest resolution level allowed by the current network conditions from the available resolution levels.

[0085] In this implementation, the first frame rate reduction is a negative adjustment signal. For example, it may be suggested to reduce the frame rate by one level (e.g., from 60fps to 30fps) or by a percentage (e.g., a 25% reduction). The saved bitrate resources will be reallocated to the increased resolution.

[0086] In this implementation, the first bitrate reduction is a negative or conservative adjustment instruction. In quality-priority mode, the total bitrate requirement may increase due to the resolution increase. Therefore, the first bitrate reduction indicates adopting a relatively low bitrate value relative to the native bitrate matched to the increased resolution. For example, if the resolution increases from 720p to 1080p, the theoretically required bitrate should increase by about 1.5 times. However, it needs to be reduced from 1.5 times, for example, by only 1.2 times, with the remaining bandwidth used to ensure HDR or as a buffer. Alternatively, a small reduction can be made from the initial bitrate to allow the encoder to use a more efficient encoding algorithm when increasing the resolution, thereby reducing the initial bitrate.

[0087] In this embodiment, the increase in the first HDR parameter is a positive adjustment signal. For example, it can be used to switch from a non-HDR mode to an HDR mode, or to enhance the data quality of HDR (such as increasing peak brightness or expanding the color gamut).

[0088] In this implementation, image quality is prioritized to represent the user's preference for smooth, uninterrupted video footage with no buffering or stuttering, while the pursuit of the highest definition and color depth is secondary.

[0089] In this implementation, the first resolution reduction is a negative adjustment signal. For example, it is recommended to actively reduce the resolution by one level (e.g., from 1080p to 720p) based on the initial resolution to pre-release a large amount of bandwidth.

[0090] In this implementation, the first frame rate increase is a positive adjustment signal. For example, it is recommended to increase the frame rate by one level (e.g., from 30fps to 60fps) based on the initial frame rate, or to select the highest frame rate level supported by the current network conditions.

[0091] In this embodiment, the reduction in the first HDR parameter is a negative adjustment signal. For example, turning off HDR mode or weakening the metadata effect of HDR (such as reducing peak brightness or narrowing the color gamut).

[0092] In this implementation, by setting corresponding parameter adjustment strategies for the two core user preferences of prioritizing image quality and smoothness, the abstract user intent can be accurately translated into executable system instructions. This allows limited network resources to be concentrated on the experience dimensions that users care about most, providing users with a playback experience that better meets their subjective expectations, and greatly improving the personalization of the service and user satisfaction.

[0093] S402: Based on usage scenario information, determine the second resolution adjustment range, the second frame rate adjustment range, the second bit rate adjustment range, and the second HDR parameter adjustment range.

[0094] In this embodiment, the usage scenario information is used to characterize the environmental category of the target device. This usage scenario information can specifically include indoor scenes, outdoor scenes, mobile scenes, etc. Different usage scenario information can correspond to different adjustments in the second resolution, second frame rate, second bitrate, and second HDR parameters.

[0095] In this embodiment, the step of determining the second resolution adjustment range, the second frame rate adjustment range, the second bit rate adjustment range, and the second HDR parameter adjustment range based on usage scenario information may specifically include: when using the usage scenario information to represent an indoor scene, determining the second resolution adjustment range as a second resolution increase and the second HDR parameter adjustment range as a second HDR parameter increase; when using the usage scenario information to represent an outdoor scene, determining the second frame rate adjustment range as a second frame rate decrease and the second bit rate adjustment range as a second bit rate decrease; when using the usage scenario information to represent a mobile scene, determining the second resolution adjustment range as a second resolution decrease and the second bit rate adjustment range as a third bit rate decrease. S403: Based on the regional network characteristic information, determine the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range.

[0096] In this embodiment, the target device can integrate data from light sensors, accelerometers / gyroscopes, Wi-Fi connection status, and GPS, and apply classification algorithms (such as decision trees or simple rules) to determine the usage scenario information. For example, when dim lighting, a stationary device, and a Wi-Fi connection are detected, the scenario can be determined to be indoors.

[0097] In this embodiment, the indoor scene refers to a fixed indoor location such as a home or office where the ambient light is relatively controllable and stable, the network connection is mostly Wi-Fi, which is relatively reliable, and the user's viewing distance is relatively close and their attention is focused.

[0098] In this embodiment, the second resolution increase in indoor scenes refers to selecting or maintaining a higher resolution level based on the initial parameters. The reasons for this adjustment are: a stable network and power environment indoors reduces the risk of frequent adjustments and lag; the closer viewing distance makes the human eye perceive the resolution improvement more clearly; and users are relatively focused and have higher requirements for image detail. The second HDR parameter increase in indoor scenes refers to enabling or enhancing the HDR effect. The reasons for this adjustment are: indoor ambient light is usually moderate or dim, meeting the optimal viewing conditions for HDR content, fully leveraging its high contrast and wide color gamut advantages, and significantly improving visual immersion.

[0099] In this embodiment, an outdoor scenario refers to a user who is stationary or moving slowly outdoors (such as a park bench or an outdoor cafe), where the ambient light is strong and variable (direct sunlight or reflected sunlight), and the network connection may be a cellular network with generally poor signal stability.

[0100] In this embodiment, the second frame rate reduction in outdoor scenarios refers to a moderate reduction in the frame rate based on the initial parameters. This adjustment is made because: under strong ambient light, screen reflections are severe, reducing the human eye's ability to perceive dynamic details in the image, and sensitivity to stuttering may also be relatively reduced due to environmental interference. The second bitrate reduction in outdoor scenarios refers to adopting a more conservative bitrate strategy. This adjustment is made because: outdoor cellular networks typically have higher latency and volatility compared to indoor Wi-Fi; reducing the bitrate allows for more buffer space for network fluctuations, while also reducing user data consumption, addressing practical concerns for outdoor use.

[0101] In this embodiment, the mobile scenario refers to a scenario where the user is running or moving quickly in a vehicle, and the network faces frequent base station switching or signal attenuation. This is the most unstable and unpredictable scenario in terms of network conditions.

[0102] In this embodiment, the second resolution reduction in mobile scenarios refers to actively and significantly reducing the resolution. The reason for this adjustment is that a significant reduction in the amount of data per frame is needed to cope with the extremely high risk of network fluctuations, and in a jittery environment, the human eye has difficulty focusing on high-definition details; therefore, reducing the resolution has a relatively small impact on the subjective experience. The third bitrate reduction in mobile scenarios can be greater than the second bitrate reduction in outdoor scenarios, referring to adopting a more aggressive bitrate reduction strategy than in outdoor scenarios. The reason for this adjustment is that network jitter is extremely severe during movement, requiring a larger bandwidth safety margin to absorb sudden packet loss and latency spikes.

[0103] In this implementation, by pre-setting differentiated parameter adjustment strategies based on the characteristics of different usage scenarios and user needs, the video streaming service can achieve environmental adaptive adjustment. In indoor scenarios, priority is given to improving picture quality and immersion to meet users' demand for high-quality viewing; in outdoor scenarios, the focus shifts to ensuring stability and conserving resources to cope with the challenges of ambient light and cellular networks; in mobile scenarios, an extremely robust strategy is adopted to prioritize ensuring playback continuity. This significantly improves the service's contextual awareness and overall user satisfaction.

[0104] S403: Based on the regional network characteristic information, determine the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range.

[0105] In this embodiment, regional network characteristic information is used to characterize the overall network performance of the user's location. Specifically, the user's location may include a first type of network region and a second type of network region, where the first type of network region characterizes regions with high network performance, and the second type of network region characterizes regions with low network performance. Different regional network characteristic information can correspond to different adjustments in the third resolution, third frame rate, third bitrate, and third HDR parameters.

[0106] In this embodiment, the determination of the third resolution adjustment magnitude, the third frame rate adjustment magnitude, the third bit rate adjustment magnitude, and the third HDR parameter adjustment magnitude based on the regional network characteristic information includes: when the regional network characteristic information represents a first type of network region, the third resolution adjustment magnitude is determined as a third resolution increase, and the third HDR parameter adjustment magnitude is determined as a third HDR parameter increase; when the regional network characteristic information represents a second type of network region, the third frame rate adjustment magnitude is determined as a third frame rate decrease, and the third bit rate adjustment magnitude is determined as a fourth bit rate decrease.

[0107] In this embodiment, regional network characteristic information refers to the assessment information of the network infrastructure capabilities of a region obtained by querying the background database through the geographical location information of user equipment. This regional network characteristic information can be generated based on long-term, large-scale measurement data (such as average bandwidth, 5G / fiber coverage, and network stability indicators).

[0108] In this embodiment, the first type of network area refers to regions classified as having well-developed network infrastructure, high average available bandwidth, and low and stable network latency. Examples include core areas of central cities, key 5G trial zones, or countries / regions with high fiber optic penetration rates.

[0109] In this embodiment, the third resolution increase corresponding to the first type of network region refers to adopting a higher resolution based on the initial resolution. The reason for this adjustment is that the overall network carrying capacity of the first type of network region is strong, and providing users with higher-definition video has a high success rate and stability expected, meeting the high-quality image requirements of users in this region. The third HDR parameter increase corresponding to the first type of network region refers to enabling or enhancing the HDR effect. The reason for this adjustment is that the high-bandwidth, low-latency network environment can easily handle the additional data overhead of HDR video streams, making it possible and providing high-end visual features (HDR) in this region with a good user experience.

[0110] In this embodiment, the second type of network area refers to regions classified as having relatively weak network infrastructure, low average available bandwidth, and high network volatility. Examples include remote areas, parts of developing countries, or the periphery of signal coverage.

[0111] In this embodiment, the third frame rate reduction corresponding to the second type of network area refers to using a lower frame rate level based on the initial frame rate. The reason for this adjustment is that in bandwidth-constrained areas, reducing the frame rate is one of the most direct and effective methods to reduce data volume, immediately alleviating bandwidth pressure. Furthermore, compared to completely unplayable content or frequent buffering, a stable video stream with a slightly lower frame rate is acceptable and practical. The fourth bitrate reduction corresponding to the second type of network area refers to adopting a more conservative bitrate strategy, which can be greater than the third bitrate reduction. The reason for this adjustment is that in low-performance areas, network bandwidth is a hard bottleneck. Using a lower encoding bitrate means using stronger compression to ensure that the video stream can be continuously transmitted in the typically narrow bandwidth channels of that area.

[0112] In this embodiment, by setting corresponding parameter adjustment strategies for network regions with different network performance, the regional automatic adjustment of video streaming services can be realized. This enables streaming services to intelligently adapt to the objective phenomenon of uneven development of network infrastructure in different regions of the world. This not only significantly improves the overall user satisfaction and inclusiveness of global services, but also achieves more intelligent and efficient allocation of network resources.

[0113] S404: Based on the first resolution adjustment range and / or the second resolution adjustment range and / or the third resolution adjustment range, the initial resolution is corrected to obtain the target resolution.

[0114] In this embodiment, a first weight can be set for the first resolution adjustment range, a second weight can be set for the second resolution adjustment range, and a third weight can be set for the third resolution adjustment range. Then, the first resolution adjustment range, the second resolution adjustment range, and the third resolution adjustment range are weighted and summed using the first weight, the second weight, and the third weight to obtain the target resolution adjustment range. Finally, the initial resolution is corrected using the target resolution adjustment range to obtain the target resolution.

[0115] In this embodiment, the first weight, the second weight, and the third weight can be set according to actual needs. For example, the first weight corresponding to user playback preference information is the highest, the second weight corresponding to usage scenario information is the next highest, and the third weight corresponding to regional network characteristic information is the lowest.

[0116] In this implementation, when different strategies adjust the same parameter in opposite directions (e.g., a user prioritizes image quality and requests a higher resolution, but a "mobile scene" strategy suggests lowering the resolution to ensure smoothness), a conflict resolution mechanism can be used. For example, when using weighted summation, positive and negative magnitudes will cancel each other out, and the final result is determined by the weights; or, the adjustment magnitude with the highest weight can be used directly.

[0117] S405: Based on the first frame rate adjustment range and / or the second frame rate adjustment range and / or the third frame rate adjustment range, the initial frame rate is corrected to obtain the target frame rate.

[0118] In this implementation, a fourth weight can be assigned to the first frame rate adjustment magnitude, a fifth weight to the second frame rate adjustment magnitude, and a sixth weight to the third frame rate adjustment magnitude. Then, the first, second, and third frame rate adjustment magnitudes are weighted and summed using the fourth, fifth, and sixth weights to obtain the target frame rate adjustment magnitude. Finally, the initial frame rate is corrected using the target frame rate adjustment magnitude to obtain the target frame rate.

[0119] In this embodiment, the fourth, fifth, and sixth weights can be set according to actual needs. For example, the fourth weight corresponding to user playback preference information is the highest, the fifth weight corresponding to usage scenario information is the second highest, and the sixth weight corresponding to regional network characteristic information is the lowest.

[0120] S406: Based on the first bitrate adjustment range and / or the second bitrate adjustment range and / or the third bitrate adjustment range, the initial bitrate is corrected to obtain the target bitrate.

[0121] In this implementation, a fourth weight can be assigned to the first frame rate adjustment magnitude, a fifth weight to the second frame rate adjustment magnitude, and a sixth weight to the third frame rate adjustment magnitude. Then, the first, second, and third frame rate adjustment magnitudes are weighted and summed using the fourth, fifth, and sixth weights to obtain the target frame rate adjustment magnitude. Finally, the initial frame rate is corrected using the target frame rate adjustment magnitude to obtain the target frame rate.

[0122] In this embodiment, the fourth, fifth, and sixth weights can be set according to actual needs. For example, the fourth weight corresponding to user playback preference information is the highest, the fifth weight corresponding to usage scenario information is the second highest, and the sixth weight corresponding to regional network characteristic information is the lowest.

[0123] S407: Based on the adjustment range of the first HDR parameter and / or the adjustment range of the second HDR parameter and / or the adjustment range of the third HDR parameter, the initial HDR parameter is corrected to obtain the target HDR parameter.

[0124] In this embodiment, a seventh weight can be assigned to the adjustment range of the first HDR parameter, an eighth weight to the adjustment range of the second HDR parameter, and a ninth weight to the adjustment range of the third HDR parameter. Then, the adjustment ranges of the first, second, and third HDR parameters are weighted and summed using the seventh, eighth, and ninth weights to obtain the target HDR parameter adjustment range. Finally, the initial HDR parameters are corrected using the target HDR parameter adjustment range to obtain the target HDR parameter.

[0125] In this embodiment, the seventh, eighth, and ninth weights can be set according to actual needs. For example, the seventh weight corresponding to user playback preference information is the highest, the eighth weight corresponding to usage scenario information is the second highest, and the ninth weight corresponding to regional network characteristic information is the lowest.

[0126] In this embodiment, after obtaining the target adjustment range, for numerical parameters (such as bitrate and frame rate), the target adjustment range can be corrected by addition or multiplication operations on the initial parameters; for level parameters (such as resolution and HDR parameters), the adjustment range can correspond to the number of levels that jump up or down.

[0127] In this implementation, by setting corresponding adjustment strategies based on user playback preferences, usage scenarios, and the local network characteristics of the user's location, and then scientifically integrating these strategies, precise and intelligent corrections can be made to multi-dimensional parameters, including resolution, bitrate, frame rate, and HDR parameters. This significantly improves the intelligence and personalization of parameter adjustment decisions, enabling more accurate responses to user intent and adaptation to complex environments.

[0128] To facilitate better implementation of the parameter adjustment method of this application, this application also provides a parameter adjustment device based on the above-described parameter adjustment method. The meanings of the terms used are the same as in the parameter adjustment method described above, and specific implementation details can be found in the description of the method embodiments.

[0129] Based on the same inventive concept, and referring to Figure 5 This application provides a parameter adjustment device 500, which includes: Information acquisition module 501 is used to acquire multimodal information and decision support information of the target device; The parameter prediction module 502 is used to input multimodal information into the prediction model and output the predicted network parameters of the target device through the prediction model. The parameter adjustment module 503 is used to adjust the parameters of the multimedia data of the target device based on the predicted network parameters and auxiliary decision-making information.

[0130] In one embodiment, the parameter adjustment module 503 includes: The initial parameter determination submodule is used to determine the initial setting parameters based on the predicted network parameters; The target parameter determination submodule is used to correct the initial setting parameters based on auxiliary decision-making information to obtain the target setting parameters; The parameter adjustment submodule is used to adjust the parameters of the multimedia data of the target device based on the target settings.

[0131] In one embodiment, the predicted network parameters include the predicted bandwidth; the initial parameter determination submodule includes: The coefficient determination unit is used to determine the ratio of the predicted bandwidth to the preset bandwidth threshold as the scaling factor; The default parameter adjustment unit is used to adjust the default setting parameters based on the scaling factor to obtain the initial setting parameters.

[0132] In one embodiment, the auxiliary decision-making information includes one or more of user playback preference information, usage scenario information, and local network characteristic information of the user's location; the initial setting parameters include one or more of initial resolution, initial frame rate, initial bitrate, and initial HDR parameters; the target setting parameters include one or more of target resolution, target frame rate, target bitrate, and target HDR parameters; the target parameter determination submodule includes: The first amplitude determination unit is used to determine the first resolution adjustment amplitude, the first frame rate adjustment amplitude, the first bit rate adjustment amplitude, and the first HDR parameter adjustment amplitude based on user playback preference information. The second amplitude determination unit is used to determine the second resolution adjustment amplitude, the second frame rate adjustment amplitude, the second bit rate adjustment amplitude, and the second HDR parameter adjustment amplitude based on the usage scenario information. The third amplitude determination unit is used to determine the third resolution adjustment amplitude, the third frame rate adjustment amplitude, the third bit rate adjustment amplitude, and the third HDR parameter adjustment amplitude based on the regional network characteristic information. The first parameter correction unit is used to correct the initial resolution based on the first resolution adjustment range and / or the second resolution adjustment range and / or the third resolution adjustment range to obtain the target resolution; The second parameter correction unit is used to correct the initial frame rate based on the first frame rate adjustment range and / or the second frame rate adjustment range and / or the third frame rate adjustment range to obtain the target frame rate. The third parameter correction unit is used to correct the initial bit rate based on the first bit rate adjustment magnitude and / or the second bit rate adjustment magnitude and / or the third bit rate adjustment magnitude to obtain the target bit rate. The fourth parameter correction unit is used to correct the initial HDR parameters based on the adjustment range of the first HDR parameter and / or the adjustment range of the second HDR parameter and / or the adjustment range of the third HDR parameter to obtain the target HDR parameters.

[0133] In one embodiment, the first amplitude determination unit includes: The first amplitude determination subunit is used to determine the first resolution adjustment amplitude as a first resolution increase, the first frame rate adjustment amplitude as a first frame rate decrease, the first bit rate adjustment amplitude as a first bit rate decrease, and the first HDR parameter adjustment amplitude as a first HDR parameter increase when the user playback preference information indicates that picture quality is prioritized. The second amplitude determination subunit is used to determine, when the user playback preference information indicates smoothness priority, the first resolution adjustment amplitude is determined as the first resolution reduction amplitude, the first frame rate adjustment amplitude is determined as the first frame rate increase amplitude, and the first HDR parameter adjustment amplitude is determined as the first HDR parameter reduction amplitude.

[0134] In one embodiment, the second amplitude determination unit includes: The third amplitude determination subunit is used to determine the second resolution adjustment amplitude as the second resolution increase and the second HDR parameter adjustment amplitude as the second HDR parameter increase when using scene information to characterize indoor scenes. The fourth amplitude determination subunit is used to determine the second frame rate reduction amplitude and the second bit rate reduction amplitude when using scene information to characterize an outdoor scene. The fifth amplitude determination subunit is used to determine the second resolution adjustment amplitude as the second resolution reduction amplitude and the second bitrate adjustment amplitude as the third bitrate reduction amplitude when using scene information to represent a mobile scene.

[0135] In one embodiment, the third amplitude determination unit includes: The sixth amplitude determination subunit is used to determine the third resolution adjustment amplitude as the third resolution increase and the third HDR parameter adjustment amplitude as the third HDR parameter increase when characterizing the first type of network region with regional network characteristic information. The seventh amplitude determination subunit is used to determine the third frame rate adjustment amplitude as the third frame rate reduction amplitude and the third bit rate adjustment amplitude as the fourth bit rate reduction amplitude when characterizing the second type of network region with regional network characteristic information.

[0136] By employing the technical solution of this application embodiment, and integrating multimodal information including network status data, user behavior data, device performance data, and content type, the usage status of the target device can be comprehensively perceived. Then, a predictive model can be used to extract more accurate and reliable predicted network parameters. Finally, based on the predicted network parameters, and by comprehensively considering auxiliary decision-making information, intelligent and precise control of multimedia data parameters can be achieved. This not only avoids lag more proactively, but also accurately meets the personalized experience needs of users in complex and ever-changing environments, significantly improving the intelligence level of multimedia services and user satisfaction.

[0137] Specific limitations regarding the parameter adjustment device 500 can be found in the limitations regarding the parameter adjustment method described above, and will not be repeated here. Each module in the parameter adjustment device 500 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0138] In addition, this application also provides an electronic device, such as Figure 6 As shown, it illustrates the structural diagram of the electronic device involved in this application, specifically: The electronic device may include components such as a processor 601 with one or more processing cores and a memory 602 with one or more computer-readable storage media. Those skilled in the art will understand that... Figure 6 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 601 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 602, and by calling data stored in the memory 602, thereby providing overall monitoring of the electronic device. Optionally, the processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 601.

[0139] The memory 602 can be used to store software programs and modules. The processor 601 executes various functional applications and data processing by running the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.

[0140] In one feasible implementation, the electronic device further includes a power supply 603 that supplies power to the various components. Preferably, the power supply 603 can be logically connected to the processor 601 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 603 may also include one or more DC or AC power supplies, recharging systems, power equipment debugging circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0141] In one feasible implementation, the electronic device may further include an input unit 604, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0142] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 601 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 602 according to the following instructions, and the processor 601 runs the applications stored in the memory 602, thereby implementing the steps in any of the parameter adjustment methods provided in the embodiments of this application.

[0143] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one feasible implementation, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the methods described in any embodiment of this application.

[0145] In one feasible implementation, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the methods described in any embodiment of this application.

[0146] In one feasible implementation, a computer program product is also proposed, comprising a computer program or instructions that, when executed by a processor, implement the methods described in any embodiment of this application.

[0147] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0148] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0149] Therefore, this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor to execute the steps in any of the parameter adjustment methods provided in this application.

[0150] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0151] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0152] Since the instructions stored in the computer-readable storage medium can execute the steps of any parameter adjustment method provided in this application, the beneficial effects that any parameter adjustment method provided in this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0153] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the element.

[0154] The foregoing has provided a detailed description of a parameter adjustment method, apparatus, electronic device, and computer-readable storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A parameter adjustment method, characterized in that, The method includes: Acquire multimodal information and decision support information of the target device; The multimodal information is input into the prediction model, and the prediction model outputs the prediction network parameters of the target device. Based on the predicted network parameters and the auxiliary decision-making information, the multimedia data of the target device is adjusted.

2. The parameter adjustment method according to claim 1, characterized in that, The step of adjusting the parameters of the multimedia data of the target device based on the prediction network parameters and the auxiliary decision information includes: Based on the predicted network parameters, determine the initial setting parameters; Based on the auxiliary decision-making information, the initial setting parameters are corrected to obtain the target setting parameters; Based on the target setting parameters, the multimedia data of the target device is adjusted.

3. The parameter adjustment method according to claim 2, characterized in that, The predicted network parameters include the predicted bandwidth; The step of determining the initial setting parameters based on the predicted network parameters includes: The ratio of the predicted bandwidth to the preset bandwidth threshold is determined as the scaling factor; Based on the scaling factor, the default setting parameters are adjusted to obtain the initial setting parameters.

4. The parameter adjustment method according to claim 2, characterized in that, The auxiliary decision-making information includes one or more of the following: user playback preference information, usage scenario information, and regional network characteristic information of the user's location; the initial setting parameters include one or more of the following: initial resolution, initial frame rate, initial bitrate, and initial HDR parameters; the target setting parameters include one or more of the following: target resolution, target frame rate, target bitrate, and target HDR parameters. The step of correcting the initial setting parameters based on the auxiliary decision-making information to obtain the target setting parameters includes: Based on the user playback preference information, determine the first resolution adjustment range, the first frame rate adjustment range, the first bitrate adjustment range, and the first HDR parameter adjustment range; and / or, Based on the aforementioned usage scenario information, determine the second resolution adjustment range, the second frame rate adjustment range, the second bitrate adjustment range, and the second HDR parameter adjustment range; and / or, Based on the regional network characteristic information, the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range are determined. Based on the first resolution adjustment range and / or the second resolution adjustment range and / or the third resolution adjustment range, the initial resolution is corrected to obtain the target resolution; and / or, Based on the first frame rate adjustment magnitude and / or the second frame rate adjustment magnitude and / or the third frame rate adjustment magnitude, the initial frame rate is corrected to obtain the target frame rate; and / or, Based on the first bitrate adjustment range and / or the second bitrate adjustment range and / or the third bitrate adjustment range, the initial bitrate is corrected to obtain the target bitrate; Based on the adjustment range of the first HDR parameter and / or the adjustment range of the second HDR parameter and / or the adjustment range of the third HDR parameter, the initial HDR parameter is corrected to obtain the target HDR parameter.

5. The parameter adjustment method according to claim 4, characterized in that, The step of determining the first resolution adjustment range, the first frame rate adjustment range, the first bitrate adjustment range, and the first HDR parameter adjustment range based on the user playback preference information includes: When the user playback preference information indicates that picture quality is prioritized, the first resolution adjustment range is determined as a first resolution increase, the first frame rate adjustment range is determined as a first frame rate decrease, the first bit rate adjustment range is determined as a first bit rate decrease, and the first HDR parameter adjustment range is determined as a first HDR parameter increase. When the user playback preference information indicates that smoothness is prioritized, the first resolution adjustment range is determined to be the first resolution reduction range, the first frame rate adjustment range is determined to be the first frame rate increase range, and the first HDR parameter adjustment range is determined to be the first HDR parameter reduction range.

6. The parameter adjustment method according to claim 4, characterized in that, The step of determining the second resolution adjustment range, the second frame rate adjustment range, the second bit rate adjustment range, and the second HDR parameter adjustment range based on the usage scenario information includes: When the usage scenario information characterizes an indoor scene, the second resolution adjustment range is determined as the second resolution increase, and the second HDR parameter adjustment range is determined as the second HDR parameter increase; When the usage scenario information represents an outdoor scene, the second frame rate adjustment range is determined as the second frame rate reduction range, and the second bit rate adjustment range is determined as the second bit rate reduction range; When the usage scenario information represents a mobile scenario, the second resolution adjustment range is determined as the second resolution reduction range, and the second bitrate adjustment range is determined as the third bitrate reduction range.

7. The parameter adjustment method according to claim 4, characterized in that, The step of determining the third resolution adjustment range, the third frame rate adjustment range, the third bit rate adjustment range, and the third HDR parameter adjustment range based on the regional network characteristic information includes: When the regional network characteristic information characterizes the first type of network region, the third resolution adjustment range is determined as the third resolution increase, and the third HDR parameter adjustment range is determined as the third HDR parameter increase; When the regional network characteristic information characterizes the second type of network region, the third frame rate adjustment magnitude is determined as the third frame rate reduction magnitude, and the third bit rate adjustment magnitude is determined as the fourth bit rate reduction magnitude.

8. A parameter adjustment device, characterized in that, The device includes: The information acquisition module is used to acquire multimodal information and decision support information of the target device; The parameter prediction module is used to input the multimodal information into the prediction model and output the predicted network parameters of the target device through the prediction model. The parameter adjustment module is used to adjust the parameters of the multimedia data of the target device based on the prediction network parameters and the auxiliary decision information.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the parameter adjustment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the parameter adjustment method as described in any one of claims 1 to 7.

Images