Wireless communication power adjustment method and device, electronic equipment, cloud and medium

Abstract

The invention provides a wireless communication power adjustment method and device, electronic equipment, a cloud end and a medium. The method comprises the following steps: determining that the electronic equipment works in a preset working scene of wireless communication, and obtaining stability data of the wireless communication; the stability data is uploaded by system bottom layer communication or acquired by a user interface; and adjusting the transmitting power of the electronic equipment according to the stability data. According to the embodiment, the transmitting power of the electronic equipment in the preset working scene is adjusted through the stable data, the transmitting power can be matched with the preset working scene, the phenomenon of unstable data transmission can be relieved or avoided, the data transmission quality is kept, and the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, and in particular, to a wireless communication power adjustment method and device, an electronic device, a cloud server, and a medium. BACKGROUND

[0002] Electronic devices usually use dynamic power adjustment technology to ensure audio transmission quality and optimize user experience. Existing dynamic power adjustment methods rely on a preset parameter adjustment table to determine the parameter data of the electronic device and query the parameter adjustment table to obtain a recommended power level. The scheme of querying the parameter adjustment table in related technologies performs well in static or slowly changing environments.

[0003] However, when the use environment changes rapidly, such as in a station with a large number of people, inside a high-speed moving train, or in an indoor place with serious signal interference, the scheme of related technologies will have a parameter lag problem, resulting in audio transmission noise and stuttering, and affecting the user's audio experience. SUMMARY

[0004] The present disclosure provides a wireless communication power adjustment method, device, electronic device, cloud server, and medium to solve the above technical problems.

[0005] According to a first aspect of the present disclosure, a wireless communication power adjustment method is provided, comprising:

[0006] determining that an electronic device is operating in a preset working scenario of wireless communication, and obtaining stability data of the wireless communication; the stability data is obtained from a system bottom layer communication or a user interface;

[0007] adjusting the transmission power of the electronic device according to the stability data.

[0008] In an embodiment, the preset working scenario includes a high-speed data communication scenario and / or a scenario fast switching scenario.

[0009] In an embodiment, the stability data includes at least one of the following: packet delay time, packet error rate, RSSI value, and retransmission count.

[0010] In an embodiment, adjusting the transmission power of the electronic device according to the stability data comprises:

[0011] determining a recommended level of the transmission power of the electronic device according to the stability data; the recommended level is obtained from a pre-configured power recommendation model or a user interface;

[0012] adjusting the transmission power of the wireless communication of the electronic device to the recommended level.

[0013] In an embodiment, after adjusting the transmission power of the electronic device according to the stability data, the method further comprises:

[0014] obtaining a communication state of the wireless communication; the communication state comprises a stable state;

[0015] determining that the communication state is the stable state, and obtaining a first preset parameter after the electronic device is adjusted to the recommended level;

[0016] uploading the first preset parameter to the cloud; the first preset parameter is configured to train model parameters of the power recommendation model in the cloud.

[0017] In an embodiment, the method further comprises:

[0018] determining that the communication state is an unstable state, and displaying an adjustment pop-up window; the adjustment pop-up window is configured to obtain a second recommended level of the transmission power;

[0019] determining that the second recommended level is obtained, and adjusting the transmission power of the electronic device to the second recommended level;

[0020] obtaining a second preset parameter after the transmission power is adjusted to the second recommended level;

[0021] uploading the second preset parameter to the cloud; the second preset parameter is configured to train model parameters of the power recommendation model in the cloud.

[0022] In an embodiment, the first preset parameter comprises at least one of the following: a first recommended level, a packet error rate, an RSSI value, and a retransmission count; and the second preset parameter comprises at least one of the following: a second recommended level, a packet error rate, an RSSI value, a retransmission count, and spatial position data.

[0023] In an embodiment, the method further comprises:

[0024] obtaining a target model parameter of the power recommendation model;

[0025] updating the model parameters of the power recommendation model to the target model parameter.

[0026] In an embodiment, the electronic device obtains the target model parameter through an OTA mode, and updates the model parameters of the power recommendation model to the target model parameter in a silent mode.

[0027] According to a second aspect of the present disclosure, a power recommendation model training method is provided, the method comprising:

[0028] obtaining a preset parameter uploaded by an electronic device; the preset parameter comprises a first preset parameter and / or a second preset parameter;

[0029] training the power recommendation model according to the preset parameter to obtain a trained power recommendation model; and model parameters of the power recommendation model are configured as target model parameters and pushed to the electronic device.

[0030] In an embodiment, the method further comprises:

[0031] determining that a push condition is met, and pushing the model parameters of the power recommendation model as the target model parameters to the electronic device.

[0032] In an embodiment, the push condition comprises one of the following: the power recommendation model is trained each time, a time interval from a last push reaches a preset length of time, and an update request sent by the electronic device is received.

[0033] In an embodiment, the cloud pushes the target model parameters through an OTA mode.

[0034] According to a third aspect of the present disclosure, a wireless communication power adjustment apparatus is provided, and the apparatus comprises:

[0035] a stability data acquisition module configured to determine that an electronic device works in a preset working scenario of wireless communication, and acquire stability data of the wireless communication; the stability data is acquired from a system bottom layer communication or a user interface;

[0036] a transmission power adjustment module configured to adjust transmission power of the electronic device according to the stability data.

[0037] In an embodiment, the preset working scenario comprises a high-speed data communication scenario and / or a scenario fast switching scenario.

[0038] In an embodiment, the stability data comprises at least one of the following: a data packet delay time, a packet error rate, an RSSI value, and a retransmission count.

[0039] In an embodiment, the transmission power adjustment module comprises:

[0040] a recommendation level determination sub-module configured to determine a recommendation level of the transmission power of the electronic device according to the stability data; the recommendation level is obtained from a preconfigured power recommendation model inference or a user interface;

[0041] a transmission power adjustment sub-module configured to adjust the transmission power of the wireless communication of the electronic device to the recommendation level.

[0042] In an embodiment, the apparatus further comprises:

[0043] The communication state acquisition module is configured to acquire a communication state of the wireless communication; the communication state comprises a stable state.

[0044] The first parameter acquisition module is configured to determine that the communication state is the stable state, and acquire a first preset parameter after the electronic device is adjusted to the recommended level.

[0045] The first parameter uploading module is configured to upload the first preset parameter to a cloud; the first preset parameter is configured to train a model parameter of the power recommendation model in the cloud.

[0046] In an embodiment, the device further comprises:

[0047] The adjustment popup window display module is configured to determine that the communication state is an unstable state, and display an adjustment popup window; the adjustment popup window is configured to acquire a second recommended level of the transmission power.

[0048] The second level adjustment module is configured to determine that the second recommended level is acquired, and adjust the transmission power of the electronic device to the second recommended level.

[0049] The second parameter acquisition module is configured to acquire a second preset parameter after the transmission power is adjusted to the second recommended level.

[0050] The second parameter uploading module is configured to upload the second preset parameter to a cloud; the second preset parameter is configured to train a model parameter of the power recommendation model in the cloud.

[0051] In an embodiment, the first preset parameter comprises at least one of the following: a first recommended level, a packet error rate, an RSSI value, and a retransmission count; and the second preset parameter comprises at least one of the following: a second recommended level, a packet error rate, an RSSI value, a retransmission count, and spatial position data.

[0052] In an embodiment, the device further comprises:

[0053] The target parameter acquisition module is configured to acquire a target model parameter of the power recommendation model.

[0054] The target parameter updating module is configured to update the model parameter of the power recommendation model to the target model parameter.

[0055] In an embodiment, the electronic device acquires the target model parameter through an OTA mode; and updates the model parameter of the power recommendation model to the target model parameter in a silent mode.

[0056] According to a fourth aspect of the present disclosure, a power recommendation model training device is provided, the device comprising:

[0057] The preset parameter acquisition module is configured to acquire preset parameters uploaded by the electronic device, wherein the preset parameters comprise first preset parameters and / or second preset parameters.

[0058] The recommendation model training module is configured to train a power recommendation model according to the preset parameters, to obtain a trained power recommendation model, wherein model parameters of the power recommendation model are configured as target model parameters and pushed to the electronic device.

[0059] In an embodiment, the apparatus further comprises:

[0060] The model parameter pushing module is configured to determine that a pushing condition is met, and push the model parameters of the power recommendation model as the target model parameters to the electronic device.

[0061] In an embodiment, the pushing condition comprises one of the following: the power recommendation model is trained each time, a time interval from the last pushing reaches a preset length, and an update request sent by the electronic device is received.

[0062] In an embodiment, the cloud pushes the target model parameters through an OTA mode.

[0063] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising a processor and a memory.

[0064] The memory is configured to store a computer program executable by the processor.

[0065] The processor is configured to execute the computer program in the memory to implement the method according to any one of the first aspect.

[0066] According to a sixth aspect of the present disclosure, a cloud is provided, comprising a processor and a memory.

[0067] The memory is configured to store a computer program executable by the processor.

[0068] The processor is configured to execute the computer program in the memory to implement the method according to any one of the second aspect.

[0069] According to a seventh aspect of the present disclosure, a non-transitory computer readable storage medium is provided, which, when the executable computer program in the storage medium is executed by a processor, can implement the method according to any one of the first aspect or the second aspect.

[0070] The technical solution provided by the embodiments of the present disclosure can include the following beneficial effects:

[0071] The wireless communication power adjustment method provided in this embodiment includes: determining a preset operating scenario for wireless communication of an electronic device; acquiring stability data of the wireless communication; the stability data being uploaded from the underlying system communication layer or acquired by the user interface; and adjusting the transmission power of the electronic device based on the stability data. Thus, this embodiment adjusts the transmission power of the electronic device in a preset operating scenario using stability data, ensuring that the transmission power matches the preset operating scenario, mitigating or avoiding unstable data transmission, maintaining data transmission quality, and improving user experience.

[0072] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0073] Figure 1 This is a schematic diagram illustrating the scene switching when an electronic device and a playback device are connected via Bluetooth, according to an embodiment of this disclosure.

[0074] Figure 2 This is an architectural diagram of an electronic device according to an embodiment of the present disclosure.

[0075] Figure 3 This is a flowchart of a wireless communication power adjustment method according to an embodiment of the present disclosure.

[0076] Figure 4 This is a flowchart of another wireless communication power adjustment method according to an embodiment of the present disclosure.

[0077] Figure 5 This is a flowchart of another wireless communication power adjustment method according to an embodiment of the present disclosure.

[0078] Figure 6 This is a flowchart of a power recommendation model training method according to an embodiment of the present disclosure.

[0079] Figure 7 This is a block diagram of a wireless communication power adjustment device according to an embodiment of the present disclosure.

[0080] Figure 8 This is a block diagram of a power recommendation model training device according to an embodiment of the present disclosure.

[0081] Figure 9 This is a block diagram of an electronic device according to an embodiment of the present disclosure. Detailed Implementation

[0082] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses consistent with some aspects of this disclosure as detailed in the appended claims.

[0083] To address the aforementioned technical problems, this disclosure provides a wireless communication power adjustment method, apparatus, electronic device, cloud platform, and medium. The electronic device may include devices with wireless communication capabilities, such as smartphones, tablets, or smart wearable devices. The wireless communication may include Bluetooth, WiFi, etc. In subsequent embodiments, examples using Bluetooth communication are used to describe the solutions of various embodiments, but this does not constitute a limitation on the solutions disclosed herein.

[0084] In one embodiment, the electronic device can communicate with a wireless communication device. Taking a Bluetooth playback device as an example, see [link to relevant documentation]. Figure 1 Electronic device 11 can establish a Bluetooth link with playback device 12, such as Bluetooth headset, and transmit control commands and audio data through the Bluetooth link. In one example, electronic device 11 can transmit high-bandwidth data such as high-definition audio with playback device 12 via Bluetooth. Furthermore, electronic device 11 can switch from a low-interference source scenario 13 to a high-interference source scenario 14. The Bluetooth link between electronic device 11 and playback device 12 may experience changes in link transmission quality due to a sudden increase in interference sources, potentially leading to audio stuttering or increased latency.

[0085] See Figure 2 The architecture diagram of the electronic device may include a self-recovery and data monitoring module 21, a large model inference module 22, and a power adjustable module 23. The self-recovery and data monitoring module 21 includes a terminal self-recovery and adjustment submodule 211, a user self-recovery and adjustment submodule 212, and an information acquisition submodule 213.

[0086] The self-recovery and data monitoring module 21 is responsible for monitoring current environmental interference data, for example,

[0087] The self-recovery and data monitoring module 21 can determine the preset working scenario of the electronic device in wireless communication. The preset working scenario may include, but is not limited to, high-speed data communication and scene switching. High-speed data communication may include, but is not limited to, audio data transmission, video viewing, and voice calls. Scene switching may include, but is not limited to, taking transportation (such as subways and high-speed trains) and switching between closed and open scenes (such as moving between buildings, entering and exiting tunnels, and entering and exiting basements). The preset working scenario can be set according to the specific scenario and is not limited here.

[0088] When the electronic device is determined to be operating in a preset wireless communication scenario, the self-recovery and data monitoring module 21 can acquire stability data of the wireless communication. This stability data is determined based on the type of wireless communication. For example, in Bluetooth communication, the stability data may include packet delay time, packet error rate, etc.; in WiFi communication, the stability data may include packet error rate, RSSI value, retransmission count, etc. This stability data can be obtained from the underlying system communication of the electronic device, or by displaying a user interface on the electronic device during wireless communication and obtaining user input data through the user interface.

[0089] The self-recovery and data monitoring module 21 can determine a second preset parameter of the electronic device based on the stability data. The second preset parameter is used to determine the transmission power of the electronic device.

[0090] In one embodiment, taking high-speed Bluetooth data transmission as an example, the terminal self-recovery and adjustment submodule 211 can acquire each Bluetooth audio transmission packet in the high-speed data transmission scenario of Bluetooth transmission, i.e., the aforementioned preset working scenario, and then acquire the interval time between two adjacent Bluetooth audio transmission packets. Then, the terminal self-recovery and adjustment submodule 211 can compare the aforementioned interval time with a preset interval threshold to obtain the relationship between the interval time and the preset interval threshold. The preset interval threshold can be set according to the audio encoding method. For example, in high-definition Bluetooth audio, the Bluetooth audio transmission packets of the audio encoding method are larger, and the preset interval threshold can be larger, such as 100ms. That is, the preset interval threshold can be set according to the specific Bluetooth audio scenario, and the corresponding scheme falls within the protection scope of this disclosure.

[0091] When the size relationship indicates that the above interval time is greater than the preset interval threshold, the terminal self-recovery and adjustment submodule 211 can obtain the second preset parameter and send the second preset parameter to the large model inference module 22.

[0092] When the size relationship indicates that the above interval time is less than or equal to the preset interval threshold, the terminal self-recovery and adjustment submodule 211 can obtain the second preset parameter and send the second preset parameter to the large model inference module 22.

[0093] It should be noted that the second preset parameter includes at least one of the following: packet error rate, RSSI value, retransmission count, and spatial location data. Among these,

[0094] Packet Error Rate (PER) is a metric for measuring data transmission quality in wireless communication systems. It represents the ratio of erroneous data packets received to the total number of data packets within a given time period. PER is a crucial parameter for evaluating the performance of a communication system, directly impacting the reliability of data transmission.

[0095] The Received Signal Strength Indicator (RSSI) value is a metric for measuring the strength of a received wireless signal, measured in decibels per milliwatt (dBm). It reflects the power level of the wireless signal at the receiving end. RSSI does not directly reflect communication reliability or data transmission rate, but it is an important parameter for evaluating wireless signal coverage and quality.

[0096] Retransmission count refers to the number of times a data packet is retransmitted by the sender when it fails to reach the receiver due to errors, loss, or other reasons during data communication. Retransmission is a mechanism to ensure reliable data transmission.

[0097] Spatial location data refers to the coordinates of an electronic device in a world coordinate system, such as GPS data. This spatial location data is used to pinpoint the location of the electronic device, such as a subway station, basement, or stadium, thus determining the usage scenario of the electronic device. This spatial location data is particularly helpful in identifying interference sources and transmission power levels within the usage scenario of the electronic device.

[0098] In this embodiment, the second preset parameters are selected as packet error rate, RSSI value, retransmission count and spatial location data, which restore the usage scenario of the electronic device from multiple dimensions, and help improve the accuracy of subsequent inference of the transmission power level.

[0099] In one embodiment, the user self-recovery and adjustment submodule 212 can acquire each Bluetooth audio transmission packet and the interval time between two adjacent Bluetooth audio transmission packets, i.e., the data packet delay time. Then, the user self-recovery and adjustment submodule 212 can compare the aforementioned interval time with a preset interval threshold to obtain the relationship between the interval time and the preset interval threshold. In one example, the user self-recovery and adjustment submodule 212 can share the determined relationship with the terminal self-recovery and adjustment submodule 211; that is, either submodule determines the relationship, and both can share the relationship.

[0100] When the interval indicated by the magnitude relationship exceeds a preset interval threshold, the user self-recovery and adjustment submodule 212 can provide the user with a self-recovery interface for manually adjusting the power level, allowing the user to actively adjust the parameters. Specifically, the electronic device can display an adjustment pop-up window, which includes power level adjustment controls, such as a slider indicating the power level or an input box allowing the user to enter the power level. When the user enters the power level in the adjustment pop-up window, the electronic device can obtain the transmission power level, i.e., the second recommended level. Finally, the user self-recovery and adjustment submodule 212 can send the second recommended level to the power adjustable module 23, which then adjusts the electronic device's transmission power level to the second recommended level.

[0101] In one embodiment, the information acquisition submodule 213 can acquire the spatial location data (GPS data) and transmission power level of the electronic device after adjusting the transmission power level. Then, the information acquisition submodule 213 can upload the second preset parameter and the transmission power level (including the aforementioned first recommended level or second recommended level) as the first preset parameter to the cloud.

[0102] In one embodiment, a power recommendation model is pre-set within the large model inference module 22. The input data for the power recommendation model is the aforementioned second preset parameter, and its output data is the inferred transmission power level. This power recommendation model can be implemented using a deep learning model, which can be at least one of recurrent neural networks (RNNs), convolutional neural networks (CNNs), long short-term memory networks (LSTMs), generative adversarial networks (GANs), deep residual networks (ResNets), and Transformers. In one example, the power recommendation model can be implemented using an RNN network.

[0103] In this embodiment, after detecting the input data, namely the second preset parameter, the power recommendation model can determine the transmission power level based on the second preset parameter, and output the transmission power level, namely the first recommended level, and transmit it to the power adjustable module 23. The power adjustable module 23 can adjust its own power according to the first recommended level, thereby adjusting the interval time of Bluetooth audio transmission packets. That is, by determining whether Bluetooth data packets are delayed through the data packet transmission delay time interval, it can alleviate or avoid the phenomenon of audio transmission noise or stuttering, and maintain audio transmission quality. In other words, this embodiment adjusts the transmission power of the electronic device in a preset working scenario by stabilizing the data, so that the transmission power can match the preset working scenario, which can alleviate or avoid the phenomenon of unstable data transmission, maintain data transmission quality, and improve user experience.

[0104] In one embodiment, a power recommendation model is pre-set on the cloud side, and the power recommendation model on the cloud side and the power recommendation model on the electronic device side are implemented using the same model. Considering the low computing power resources of the electronic device, in this embodiment, given that the power recommendation model on the cloud side is determined, the power recommendation model on the electronic device side is implemented using its lightweight model. The input data for both are the aforementioned stability data, such as spatial location data, packet error rate, RSSI (Received Signal Strength Indicator) value, and retransmission count. The output data for both is the transmit power level. After training, the power recommendation model on the cloud side can deploy its model parameters to the electronic device, which can then be used as the target model parameters for the power recommendation model on the electronic device side.

[0105] In this embodiment, the training process of the power recommendation model on the cloud side may include:

[0106] First, obtain personalized training data.

[0107] The cloud can store pre-trained power recommendation models. These pre-trained power recommendation models can be trained using general training data, which can obtain several sets of first preset parameters for different scenarios. Then, the power recommendation model can be pre-trained using the general training data to obtain the aforementioned power recommendation model.

[0108] The cloud can obtain the first preset parameters uploaded by the electronic device and store them in a designated location, such as local storage or a storage server. Before using the first preset parameters as training data, the cloud can filter them. For example, the cloud can obtain the first preset parameters and then reconstruct the usage scenario of the electronic device (which preset working scenario) based on the parameters within the first preset parameters; deduce the transmission power level of this usage scenario; then compare the deduced transmission power level with the transmission power level uploaded by the electronic device; when the two transmission power levels are equal or close (e.g., differing by one or two levels, which can be adjusted), the first preset parameter is determined to be usable as training data and a first label (e.g., 1) can be set. When the two transmission power levels differ significantly (e.g., more than two levels), the first preset parameter cannot be used as training data and a second label (e.g., 0) can be set.

[0109] It should be noted that the process of filtering the first preset parameters can be done manually. For example, the cloud side can display each set of first preset parameters, then display the derived transmission power level and the transmission power level uploaded by the electronic device, and display the first feedback control and the second feedback control. The first feedback control is used to receive feedback indicating that the two transmission power levels are equal or similar, and the second feedback control is used to receive feedback indicating that the two transmission power levels differ significantly.

[0110] Thus, by filtering the first preset parameters in this embodiment, the first preset parameters can be matched with the preset working scenario, ensuring the accuracy of the training data and ultimately improving the accuracy of the power recommendation model in predicting the transmission power.

[0111] Second, train a pre-trained power recommendation model.

[0112] The cloud can train a power recommendation model using at least one set of first preset parameters as training data. When the training termination conditions are met (such as the number of training iterations exceeding a preset threshold, the error being less than or equal to a preset error threshold, or the gradient value being less than or equal to a preset gradient value threshold), the trained power recommendation model is obtained.

[0113] After training the recommended power model, the cloud can send a model parameter deployment request to the electronic device. The electronic device can respond to this request, download the target model parameters, and update its local power recommendation parameters, thus updating the power recommendation model. In one example, the electronic device can obtain the target model parameters via OTA (Over-The-Air) and silently update the power recommendation model's parameters to the target model parameters. This silent approach refers to an installation mode that requires no user interaction. The electronic device system can update the power recommendation model's parameters to the target model parameters after obtaining them, even without using the power recommendation model. This minimizes the impact of the update process on the user while ensuring the power recommendation model increasingly matches the user's usage scenario.

[0114] Based on the aforementioned electronic device, this disclosure also provides a wireless communication power adjustment method, see [link to relevant documentation]. Figure 3 This includes steps 31 and 32:

[0115] In step 31, the electronic device is determined to be operating in a preset working scenario of wireless communication, and the stability data of the wireless communication is obtained; the stability data is uploaded by the underlying system communication or obtained by the user interface.

[0116] In this step, the electronic device can acquire the working scenario of the electronic device under wireless communication and determine whether the working scenario is a preset working scenario. The preset working scenario may include, but is not limited to, scenarios such as high-speed data communication and rapid scene switching. High-speed data communication may include, but is not limited to, audio data transmission, video viewing scenarios, and voice calls. Rapid scene switching may include, but is not limited to, scenarios such as riding transportation (e.g., subway, high-speed rail) and switching between closed and open scenarios (e.g., moving between buildings, entering and exiting tunnels, entering and exiting basements). The preset working scenario can be set according to the specific scenario and is not limited here.

[0117] In this step, given that the electronic device is operating in a preset wireless communication scenario, the electronic device can acquire stability data for wireless communication.

[0118] The stability data mentioned above is determined based on the type of wireless communication. For example, in Bluetooth communication, the stability data might include packet latency, packet error rate, etc.; in WiFi communication, the stability data might include packet error rate, RSSI value, retransmission count, etc. This stability data can be obtained from the underlying system communication of the electronic device, or by obtaining user input data through the user interface displayed on the electronic device during wireless communication.

[0119] In step 32, the transmission power of the electronic device is adjusted based on the stability data.

[0120] In this step, the electronic device can determine a recommended level of its transmission power based on the stability data; the recommended level is obtained by reasoning from a pre-configured power recommendation model or by the user interface.

[0121] In one example, the electronic device can acquire the communication status of wireless communication, including a stable state. The electronic device can then determine that the communication status is stable. In this case, the electronic device can send a first preset parameter to a local power recommendation model. The power recommendation model can output a recommendation level based on the first preset parameter, and the power adjustable module 23 can adjust the transmission power of the wireless communication to the recommended level, thus achieving transmission power adjustment.

[0122] In this example, the electronic device can obtain the first preset parameters after adjusting the electronic device to the recommended level, and then upload the first preset parameters to the cloud. It is understood that the aforementioned first preset parameters are configured as model parameters for training the power recommendation model in the cloud, in order to obtain the target model parameters (used to update the local power recommendation model).

[0123] In one example, the electronic device can acquire the communication status of the wireless communication, including an unstable state. Then, if the communication status is determined to be unstable, the electronic device can display an adjustment pop-up. This adjustment pop-up is configured to acquire a second recommended level of transmit power. Subsequently, if the second recommended level is determined to be acquired, the electronic device can adjust the transmit power of the wireless communication to the second recommended level.

[0124] In this embodiment, the electronic device can acquire second preset parameters after the transmit power is adjusted to the second recommended level. Then, the electronic device can upload the second preset parameters to the cloud. These second preset parameters are configured as model parameters for training the power recommendation model in the cloud, and their function is the same as that of the first preset parameters described above.

[0125] In this way, by adjusting the transmission power of the electronic device in the preset working scenario through stable data, this embodiment can match the transmission power with the preset working scenario, which can alleviate or avoid the phenomenon of unstable data transmission, maintain data transmission quality, and improve user experience.

[0126] A wireless communication power adjustment method is described using Bluetooth communication as an example. (See [link to relevant documentation]). Figure 4 This includes steps 41 to 43:

[0127] In step 41, the interval between two adjacent Bluetooth audio transmission packets is obtained.

[0128] In this step, the electronic device can send Bluetooth audio transmission packets to the playback device and record the transmission time of each Bluetooth audio transmission packet; the interval between two adjacent Bluetooth audio transmission packets can be obtained by combining the transmission times of two adjacent Bluetooth audio transmission packets. Alternatively, the electronic device can receive a feedback message returned by the playback device, which includes the reception time of the received Bluetooth audio transmission packets; then, the interval between two adjacent Bluetooth audio transmission packets can be obtained by combining the reception times of two adjacent Bluetooth audio transmission packets. Those skilled in the art can calculate the interval between Bluetooth audio transmission packets according to specific scenarios, and the corresponding solutions fall within the protection scope of this disclosure.

[0129] In step 42, the recommended level of the electronic device's transmission power is adjusted according to the interval time and the preset interval threshold; the recommended level is obtained by reasoning from a pre-configured power recommendation model.

[0130] In this step, the electronic device stores a preset interval threshold. Please refer to the above description for instructions on how to set this preset interval threshold.

[0131] In this step, the electronic device can adjust its transmission power level according to the above interval time and the preset interval threshold.

[0132] First, the electronic device can determine the relationship between the interval between two Bluetooth audio transmission packets and the aforementioned preset interval threshold. For example, the relationship can indicate that the interval is less than or equal to the preset interval threshold, or it can indicate that the interval is greater than the preset interval threshold.

[0133] It should be noted that the size relationship indicates that when the interval time is greater than the above-mentioned preset interval threshold, the playback device may experience problems such as stuttering / noise when playing audio.

[0134] It is understood that the electronic device can acquire a second preset parameter of the electronic device according to a set period. The method of acquiring the second preset parameter can be found in the above embodiments, and will not be repeated here.

[0135] In one example, the transmit power level of the electronic device includes a first recommended level. When the magnitude relationship indicates that the interval time is less than or equal to a preset interval threshold, the electronic device can input the first preset parameter into the power recommendation model. The model parameters of this power recommendation model are deployed based on the target model parameters of the power recommendation model on the cloud side. This power recommendation model can infer the transmit power level based on the first preset parameter, hereinafter referred to as the first recommended level. At this time, the electronic device can adjust its transmit power according to the first recommended level.

[0136] In one example, the power level of the electronic device's transmission power includes a second recommended level. When the interval between magnitudes exceeds a preset interval threshold, the electronic device can display an adjustment pop-up window. The user can input the recommended transmission power level in this pop-up window, thus obtaining the second recommended transmission power level. At this time, the electronic device can adjust its transmission power according to the second recommended level. In other words, the power level of the electronic device's transmission power includes the second recommended level.

[0137] In step 43, the first preset parameters after the electronic device is adjusted to the recommended level are obtained, and the first preset parameters are configured as model parameters for training the power recommendation model.

[0138] In this step, after successfully adjusting the transmission power, the electronic device can obtain the first preset parameters after the transmission power adjustment. When the interval time (indicated by the magnitude relationship) is less than or equal to a preset interval threshold (i.e., no audio stuttering occurs), the transmission power adopts the first recommended level. In this case, the first preset parameters include the second preset parameters and the first recommended level. When the interval time (indicated by the magnitude relationship) is greater than the preset interval threshold (i.e., audio stuttering occurs), the transmission power adopts the second recommended level. In this case, the first preset parameters include the second preset parameters and the second recommended level. Then, the electronic device can upload the above first preset parameters to the cloud. The cloud can filter the above first preset parameters and use them as training data. That is, the above first preset parameters are configured as model parameters for the power adjustment recommendation model.

[0139] In one example, the power recommendation model can output a predicted scenario in addition to the power recommendation level. This predicted scenario includes either stuttering or no stuttering. For example, two stuttering prediction thresholds can be preset in the range of 0-1, such as 0.3 and 0.8. Then, the output recommended power level can be divided into three categories: Category 1, 0-0.3, indicates that the first recommendation level output by the power recommendation model is a valid value that can be used directly. In this case, the model parameters of the power recommendation model perfectly match the usage scenario. Category 2, 0.3-0.8, indicates that the first recommendation level output by the power recommendation model is a valid value that can be used directly. In this case, the model parameters of the power recommendation model match the usage scenario but there is room for improvement. Category 3, 0.8-1, indicates that the first recommendation level output by the power recommendation model is unusable. In this case, the model parameters of the power recommendation model do not match the usage scenario, and the electronic device generates a pop-up window for the user to input a second recommendation level. Based on the above, in this example, the first preset parameters obtained from the second and third categories can be uploaded to the cloud. This allows us to obtain the user's personalized first preset parameters to train the power recommendation model, improve the matching degree between the power recommendation model and the user's usage scenario, and reduce the amount of data uploaded by electronic devices.

[0140] Considering that the cloud-based power recommendation model is trained and updated with model parameters according to a preset period, in one example, the electronic device obtains the target model parameters of the power recommendation model. For example, the electronic device can request model parameters from the cloud at a set period, which can be greater than or equal to the preset training period of the cloud model, thereby ensuring that each request obtains the latest target model parameters. In another example, the cloud can send a training completion notification or a model parameter deployment request to the electronic device after the power recommendation model training is completed. Then, after receiving the notification or deployment request, the electronic device interacts with the cloud to obtain the target model parameters. Those skilled in the art can choose an appropriate scheme to obtain the target model parameters according to the specific scenario, and the corresponding scheme falls within the protection scope of this disclosure. Then, the electronic device can update the model parameters of the local power recommendation model to the aforementioned target model parameters.

[0141] Based on the Bluetooth power adjustment method provided in this disclosure, the working process of the electronic device is described, combined with... Figure 5 and Figure 3 ,include:

[0142] In step 51, the terminal self-recovery and adjustment submodule of the electronic device can collect the second preset parameter, and then input the second preset parameter into the large model inference module to obtain the first recommended level output by the large model inference module. Then, the large model inference module can transmit the first recommended level to the power adjustable module, which adjusts the transmission power of the electronic device. At this time, the first recommended level and the second preset parameter constitute the first preset parameter.

[0143] In step 52, the electronic device can determine whether there is a stutter in the Bluetooth audio, that is, based on the interval between two adjacent Bluetooth audio transmission packets and a preset interval threshold.

[0144] In step 53, if there is no stuttering in the Bluetooth audio, proceed to step 56.

[0145] In step 54, if Bluetooth audio stutters, proceed to step 55.

[0146] In step 55, the terminal self-recovery and adjustment submodule of the electronic device can extract the self-recovery interface, i.e., display the adjustment pop-up window, to obtain the second recommended level input by the user; and transmit the second recommended level to the power adjustable module, which adjusts the transmission power of the electronic device. At this time, the second recommended level and the second preset parameter constitute the first preset parameter.

[0147] In step 56, the information acquisition submodule of the electronic device can upload the first preset parameters to the cloud and return to step 51. After the first preset parameters are uploaded to the cloud, the power recommendation model on the cloud side can be trained to obtain the target model parameters used by the power recommendation model on the electronic device side.

[0148] In this embodiment, the target model parameters trained in the cloud are used to configure the local power recommendation model, which can make the inference transmit power level more compatible with the usage scenario and solve the problem of parameter lag in dynamic power adjustment in Bluetooth audio transmission scenarios. The link quality of Bluetooth audio transmission is monitored in real time, and self-repair is performed when audio stuttering is detected, thereby improving the user experience.

[0149] Based on the aforementioned electronic device, this disclosure also provides a power recommendation model training method, see [link to relevant documentation]. Figure 6 The method includes steps 61 and 62.

[0150] In step 61, preset parameters uploaded by the electronic device are obtained; the preset parameters include a first preset parameter and / or a second preset parameter.

[0151] In this step, the cloud maintains a communication connection with the electronic device. After obtaining the first preset parameter and / or the second preset parameter, the electronic device can upload it to the cloud. The cloud can then obtain the aforementioned first preset parameter and / or second preset parameter.

[0152] In this step, after obtaining the preset parameters, the cloud can store these preset parameters in a designated location, such as local storage or a storage server. Before using these preset parameters to train the cloud's power recommendation model, the cloud can determine whether the preset parameters can be used as training data. That is, the cloud can filter the preset parameters. The specific filtering process can be found above and will not be repeated here.

[0153] In step 62, a power recommendation model is trained according to the preset parameters to obtain a trained power recommendation model; the model parameters of the power recommendation model are configured to be pushed to the electronic device as target model parameters.

[0154] In this step, after determining the training data, the cloud can train the power recommendation model based on all or part of the selected training data, i.e., all or part of the preset parameters mentioned above. Please refer to the above content for the training process, so as to obtain the completed power recommendation model and the target model parameters of the power recommendation model.

[0155] In one embodiment, the cloud stores preset push conditions, which include one of the following: the power recommendation model completes training each time, the time interval since the last push reaches a preset duration, and an update request is received from an electronic device.

[0156] Taking the completion of power recommendation training as an example, after each training iteration, the target model parameters of the power recommendation model are updated compared to the model parameters of the power recommendation model within the electronic device, and are more closely matched to the user's preset working scenario. In this case, the cloud can determine that the push conditions are met and push the target model parameters to the electronic device via OTA (Over-The-Air). In this way, the cloud and the power recommendation model within the electronic device can maintain synchronization of the target model parameters, thereby ensuring the stability of wireless communication under the preset working scenario and guaranteeing data transmission efficiency.

[0157] Taking a preset time interval since the last push as an example, this preset time interval can be a calendar day, a calendar week, a calendar month, etc. After determining that the preset time interval has elapsed, the cloud pushes the target model parameters to the electronic device via OTA (Over-The-Air). In this way, by setting a preset time interval, sufficient training data can be obtained through a sufficient number of preset working scenarios, ensuring the accuracy of the cloud-trained power recommendation model. The power recommendation models in the cloud and on the electronic device can be better matched with the preset working scenarios, avoiding the impact of a few scenarios on the model, thereby ensuring the stability of wireless communication under the preset working scenarios and guaranteeing data transmission efficiency.

[0158] Based on the wireless communication power adjustment method provided in the embodiments of this disclosure, the embodiments of this disclosure also provide a wireless communication power adjustment device, see [link to relevant documentation]. Figure 7 The device includes:

[0159] The stability data acquisition module 71 is used to determine the preset working scenario of the electronic device operating in wireless communication and acquire the stability data of the wireless communication; the stability data is uploaded from the underlying system communication or obtained from the user interface;

[0160] The transmit power adjustment module 72 is used to adjust the transmit power of the electronic device according to the stability data.

[0161] In one embodiment, the preset working scenario includes a high-speed data communication scenario and / or a scenario with rapid switching between scenarios.

[0162] In one embodiment, the stability data includes at least one of the following: packet delay time, packet error rate, RSSI value, and retransmission count.

[0163] In one embodiment, the transmit power adjustment module includes:

[0164] The recommendation level determination submodule is used to determine the recommended level of the electronic device's transmit power based on the stability data; the recommendation level is obtained by reasoning from a pre-configured power recommendation model or by the user interface;

[0165] The transmit power adjustment submodule is used to adjust the transmit power of the electronic device's wireless communication to the recommended level.

[0166] In one embodiment, the device further includes:

[0167] A communication status acquisition module is used to acquire the communication status of the wireless communication; the communication status includes a stable state.

[0168] The first parameter acquisition module is used to determine that the communication state is a stable state and acquire the first preset parameters after the electronic device is adjusted to the recommended level.

[0169] The first parameter upload module is used to upload the first preset parameter to the cloud; the first preset parameter is configured as the model parameter for training the cloud-based power recommendation model.

[0170] In one embodiment, the device further includes:

[0171] An adjustment pop-up display module is used to determine that the communication status is unstable and display an adjustment pop-up; the adjustment pop-up is configured to obtain a second recommended level of the transmission power.

[0172] The second-level adjustment module is used to determine that the second recommended level has been obtained, and then adjust the transmission power of the electronic device to the second recommended level;

[0173] The second parameter acquisition module is used to acquire the second preset parameters after the transmission power is adjusted to the second recommended level;

[0174] The second parameter upload module is used to upload the second preset parameter to the cloud; the second preset parameter is configured as the model parameter for training the power recommendation model in the cloud.

[0175] In one embodiment, the first preset parameter includes at least one of the following: a first recommendation level, packet error rate, RSSI value, and retransmission count; the second preset parameter includes at least one of the following: a second recommendation level, packet error rate, RSSI value, retransmission count, and spatial location data.

[0176] In one embodiment, the device further includes:

[0177] The target parameter acquisition module is used to acquire the target model parameters of the power recommendation model.

[0178] The target parameter update module is used to update the model parameters of the power recommendation model to the target model parameters.

[0179] In one embodiment, the electronic device acquires the target model parameters via OTA and silently updates the model parameters of the power recommendation model to the target model parameters.

[0180] It should be noted that the solutions of the device embodiments of this disclosure have been described when describing the method embodiments, and can be found in the content of the above embodiments, which will not be repeated here.

[0181] Based on the power recommendation model training method provided in this disclosure, this disclosure also provides a power recommendation model training apparatus, see [link to relevant documentation]. Figure 8 The device includes:

[0182] The preset parameter acquisition module 81 is used to acquire preset parameters uploaded by the electronic device; the preset parameters include a first preset parameter and / or a second preset parameter;

[0183] The recommendation model training module 82 is used to train a power recommendation model according to the preset parameters to obtain a trained power recommendation model; the model parameters of the power recommendation model are configured to be pushed to the electronic device as target model parameters.

[0184] In one embodiment, the device further includes:

[0185] The model parameter push module is used to determine whether the push conditions are met and push the model parameters of the power recommendation model as target model parameters to the electronic device.

[0186] In one embodiment, the push conditions include one of the following: the power recommendation model completes training each time, the time interval since the last push reaches a preset duration, and an update request is received from an electronic device.

[0187] In one embodiment, the target model parameters are pushed to the cloud via OTA.

[0188] It should be noted that the solutions of the device embodiments of this disclosure have been described when describing the method embodiments, and can be found in the content of the above embodiments, which will not be repeated here.

[0189] Figure 9 This is a block diagram illustrating an electronic device according to an exemplary embodiment. For example, the electronic device 11 may be a smartphone, computer, digital broadcasting terminal, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0190] Reference Figure 9The electronic device 11 may include one or more of the following components: processing component 902, memory 904, power supply component 906, multimedia component 908, audio component 910, input / output (I / O) interface 912, sensor component 914, communication component 916, and image acquisition component 918.

[0191] Processing component 902 typically controls the overall operation of electronic device 11, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 902 may include one or more processors 920 to execute computer programs. Furthermore, processing component 902 may include one or more modules to facilitate interaction between processing component 902 and other components. For example, processing component 902 may include a multimedia module to facilitate interaction between multimedia component 908 and processing component 902.

[0192] Memory 904 is configured to store various types of data to support the operation of electronic device 11. Examples of such data include computer programs for any application or method operating on electronic device 11, contact data, phone book data, messages, pictures, videos, etc. Memory 904 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0193] Power supply component 906 provides power to various components of electronic device 11. Power supply component 906 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 11. Power supply component 906 may include a power chip, and a controller may communicate with the power chip to control the power chip to turn on or off switching devices, thereby enabling or disabling battery power to the motherboard circuitry.

[0194] Multimedia component 908 includes a screen that provides an output interface between electronic device 11 and target object. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input information from the target object. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation.

[0195] Audio component 910 is configured to output and / or input audio file information. For example, audio component 910 includes a microphone (MIC) configured to receive external audio file information when electronic device 11 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio file information may be further stored in memory 904 or transmitted via communication component 916. In some embodiments, audio component 910 also includes a speaker for outputting audio file information.

[0196] I / O interface 912 provides an interface between processing component 902 and peripheral interface modules, such as keyboards, click wheels, buttons, etc.

[0197] Sensor assembly 914 includes one or more sensors for providing state assessments of various aspects of electronic device 11. For example, sensor assembly 914 can detect the on / off state of electronic device 11, the relative positioning of components (e.g., the display screen and keypad of electronic device 11), changes in position of electronic device 11 or a component, the presence or absence of contact between a target object and electronic device 11, the orientation or acceleration / deceleration of electronic device 11, and temperature changes of electronic device 11. In this example, sensor assembly 914 may include a magnetic sensor, a gyroscope, and a magnetic field sensor, wherein the magnetic field sensor includes at least one of the following: a Hall sensor, a thin-film magnetoresistive sensor, and a magnetic fluid accelerometer.

[0198] Communication component 916 is configured to facilitate wired or wireless communication between electronic device 11 and other devices. Electronic device 11 can access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G, 5G, or combinations thereof. In one exemplary embodiment, communication component 916 receives broadcast information or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 916 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0199] In an exemplary embodiment, the electronic device 11 may be implemented by one or more application-specific integrated circuits (ASICs), digital information processors (DSPs), digital information processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, or other electronic components.

[0200] In an exemplary embodiment, an electronic device is also provided, comprising:

[0201] Memory and processor;

[0202] The memory is used to store computer programs that can be executed by the processor;

[0203] The processor is used to execute the computer program in the memory to implement the method as described above.

[0204] In an exemplary embodiment, a cloud platform is also provided, including:

[0205] Memory and processor;

[0206] The memory is used to store computer programs that can be executed by the processor;

[0207] The processor is used to execute the computer program in the memory to implement the method as described above.

[0208] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as a memory 904 including instructions, wherein the executable computer program described above can be executed by a processor. The readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0209] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This disclosure is intended to cover any variations, uses, or adaptations that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0210] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for adjusting wireless communication power, characterized in that, include: Determine the preset operating scenario of the electronic device in wireless communication, and obtain the stability data of the wireless communication; The stability data is uploaded from the system's underlying communication or obtained from the user interface; The transmission power of the electronic device is adjusted based on the stability data.

2. The method according to claim 1, characterized in that, The preset working scenarios include high-speed data communication scenarios and / or scenarios with rapid switching.

3. The method according to claim 1, characterized in that, The stability data includes at least one of the following: packet delay time, packet error rate, RSSI value, and retransmission count.

4. The method according to claim 1, characterized in that, Adjusting the transmission power of the electronic device based on the stability data includes: A recommended level for the transmit power of the electronic device is determined based on the stability data; the recommended level is obtained by reasoning from a pre-configured power recommendation model or by the user interface. Adjust the wireless transmission power of the electronic device to the recommended level.

5. The method according to claim 4, characterized in that, After adjusting the transmission power of the electronic device based on the stability data, the method further includes: Obtain the communication status of the wireless communication; the communication status includes a stable state; Determine that the communication state is stable, and obtain the first preset parameters after the electronic device is adjusted to the recommended level; The first preset parameters are uploaded to the cloud; the first preset parameters are configured as model parameters for training the cloud-based power recommendation model.

6. The method according to claim 5, characterized in that, The method further includes: If the communication state is determined to be unstable, an adjustment pop-up window is displayed; the adjustment pop-up window is configured to obtain a second recommended level of the transmission power. If the second recommended level is obtained, the transmission power of the electronic device is adjusted to the second recommended level; Obtain the second preset parameters after the transmit power is adjusted to the second recommended level; The second preset parameter is uploaded to the cloud; the second preset parameter is configured as the model parameter for training the power recommendation model in the cloud.

7. The method according to claim 6, characterized in that, The first preset parameter includes at least one of the following: first recommendation level, packet error rate, RSSI value, and retransmission count; the second preset parameter includes at least one of the following: second recommendation level, packet error rate, RSSI value, retransmission count, and spatial location data.

8. The method according to any one of claims 5 to 7, characterized in that, The method further includes: Obtain the target model parameters of the power recommendation model; Update the model parameters of the power recommendation model to the target model parameters.

9. The method according to claim 8, characterized in that, The electronic device acquires the target model parameters via OTA and silently updates the model parameters of the power recommendation model to the target model parameters.

10. A power recommendation model training method, characterized in that, The method includes: Obtain preset parameters uploaded by the electronic device; the preset parameters include a first preset parameter and / or a second preset parameter; A power recommendation model is trained according to the preset parameters to obtain a completed power recommendation model; the model parameters of the power recommendation model are configured to be pushed to the electronic device as target model parameters.

11. The method according to claim 10, characterized in that, The method further includes: Once the push conditions are met, the model parameters of the power recommendation model are pushed to the electronic device as the target model parameters.

12. The method according to claim 11, characterized in that, The push conditions include one of the following: the power recommendation model completes training each time, the time interval between the last push and the previous push reaches a preset duration, and an update request is received from an electronic device.

13. The method according to claim 10, characterized in that, The target model parameters are pushed to the cloud via OTA.

14. A wireless communication power adjustment device, characterized in that, The device includes: The stability data acquisition module is used to determine the preset working scenario of the electronic device operating in wireless communication and acquire the stability data of the wireless communication; the stability data is uploaded from the underlying system communication or obtained from the user interface; A transmit power adjustment module is used to adjust the transmit power of the electronic device based on the stability data.

15. The apparatus according to claim 14, characterized in that, The preset working scenarios include high-speed data communication scenarios and / or scenarios with rapid switching.

16. The apparatus according to claim 14, characterized in that, The transmit power adjustment module includes: The recommendation level determination submodule is used to determine the recommended level of the electronic device's transmit power based on the stability data; the recommendation level is obtained by reasoning from a pre-configured power recommendation model or by the user interface; The transmit power adjustment submodule is used to adjust the transmit power of the electronic device's wireless communication to the recommended level.

17. The apparatus according to claim 16, characterized in that, The device further includes: A communication status acquisition module is used to acquire the communication status of the wireless communication; the communication status includes a stable state. The first parameter acquisition module is used to determine that the communication state is a stable state and acquire the first preset parameters after the electronic device is adjusted to the recommended level. The first parameter upload module is used to upload the first preset parameter to the cloud; the first preset parameter is configured as the model parameter for training the cloud-based power recommendation model.

18. The apparatus according to claim 17, characterized in that, The device further includes: An adjustment pop-up display module is used to determine that the communication status is unstable and display an adjustment pop-up; the adjustment pop-up is configured to obtain a second recommended level of the transmission power. The second-level adjustment module is used to determine that the second recommended level has been obtained, and then adjust the transmission power of the electronic device to the second recommended level; The second parameter acquisition module is used to acquire the second preset parameters after the transmission power is adjusted to the second recommended level; The second parameter upload module is used to upload the second preset parameter to the cloud; the second preset parameter is configured as the model parameter for training the power recommendation model in the cloud.

19. A power recommendation model training device, characterized in that, The device includes: A preset parameter acquisition module is used to acquire preset parameters uploaded by an electronic device; the preset parameters include a first preset parameter and / or a second preset parameter; The recommendation model training module is used to train a power recommendation model according to the preset parameters to obtain a trained power recommendation model; the model parameters of the power recommendation model are configured to be pushed to the electronic device as target model parameters.

20. An electronic device, characterized in that, Including processor and memory; The memory is used to store computer programs that can be executed by the processor; The processor is configured to execute a computer program in the memory to implement the method as described in any one of claims 1 to 9.

21. A cloud computing platform, characterized in that, Including processor and memory; The memory is used to store computer programs that can be executed by the processor; The processor is configured to execute a computer program in the memory to implement the method as described in any one of claims 10 to 13.

22. A non-transitory computer-readable storage medium, characterized in that, When the executable computer program in the storage medium is executed by a processor, it can implement the method as described in any one of claims 1 to 9, 10 to 13.

Images