Gain Adjustment Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a gain adjustment method, apparatus, computer device, and storage medium. The method includes: obtaining a signal to be adjusted; determining a first gain value based on the power of the signal to be adjusted; inputting the signal to be adjusted into a gain determination model to obtain a second gain value, where the gain determination model is obtained through deep learning training; and obtaining a target gain value based on the first gain value and the second gain value. In the above gain adjustment method, apparatus, computer device, and storage medium, by combining the gain predicted by the deep learning model and the gain adjusted by traditional power detection, and determining the final gain value according to the gain values obtained by the two methods, it can respond to the change of the signal in a timely manner, provide an appropriate gain, and ensure the stability of the signal.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a gain adjustment method, apparatus, computer device, and storage medium. Background Art

[0002] Traditional signal gain technologies do not have the ability to predict power. Generally, the gain of a signal is adjusted at a constant rate based on experience. When the signal has a large amplitude change and a fast change speed, more lag time is required to adjust to an appropriate gain.

[0003] Existing technologies perform gain adjustment by means of fast attenuation and slow release. However, the attenuation speed or release speed of this method is a constant value designed based on experience, and may not be able to respond to signal changes in a timely manner in an actual system. Summary of the Invention

[0004] Based on this, it is necessary to provide a gain adjustment method, apparatus, computer device, and storage medium for the above technical problems.

[0005] In a first aspect, this application provides a gain adjustment method. The method includes:

[0006] Obtain a signal to be adjusted;

[0007] Determine a first gain value based on the power of the signal to be adjusted;

[0008] Input the signal to be adjusted into a gain determination model trained by deep learning to obtain a second gain value, where the second gain value is a predicted gain value for the next moment;

[0009] Obtain a target gain value based on the first gain value and the second gain value.

[0010] In one embodiment, obtaining the target gain value based on the first gain value and the second gain value includes:

[0011] Obtain an accuracy evaluation result for the previous moment, where the accuracy evaluation result is determined based on the second gain value and a standard gain value for the previous moment;

[0012] If the accuracy evaluation result meets a preset threshold, use the second gain value as the target gain value;

[0013] If the accuracy evaluation result does not meet the preset threshold, use the first gain value as the target gain value.

[0014] In one embodiment, obtaining the accuracy evaluation result for the previous moment includes:

[0015] Use the first gain value at the current moment as the standard gain value;

[0016] Determine the accuracy score based on the deviation degree between the second gain value at the previous moment and the standard gain value.

[0017] In one embodiment, after obtaining the target gain value based on the first gain value and the second gain value, the following steps are further included:

[0018] Update the model parameters of the gain determination model based on the accuracy evaluation result

[0019] In one embodiment, after obtaining the accuracy evaluation result at the previous moment, the following steps are further included:

[0020] If the accuracy evaluation result meets the reset threshold, restore the gain determination model to the initial model.

[0021] In one embodiment, the step of determining the first gain value based on the power of the signal to be adjusted includes:

[0022] Compare the power of the signal to be adjusted with the preset power;

[0023] Determine the first gain value based on the comparison result.

[0024] In one embodiment, before inputting the signal to be adjusted into the gain determination model to obtain the second gain value, the following steps are further included:

[0025] Obtain an initial model, where the initial model is a long short-term memory network;

[0026] Use the reference signal and the reference gain value as a training set to train the initial model to obtain the gain determination model.

[0027] In a second aspect, the present application further provides a gain adjustment device. The device includes:

[0028] An acquisition module, configured to acquire a signal to be adjusted;

[0029] A first determination module, configured to determine a first gain value based on the power of the signal to be adjusted;

[0030] A second determination module, configured to input the signal to be adjusted into a gain determination model to obtain a second gain value, where the gain determination model is obtained through deep learning training;

[0031] A gain determination module, configured to obtain a target gain value based on the first gain value and the second gain value.

[0032] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain a signal to be adjusted;

[0034] Determine a first gain value based on the power of the signal to be adjusted;

[0035] Input the signal to be adjusted into a gain determination model obtained through deep learning training to obtain a second gain value, where the second gain value is a predicted gain value for the next moment;

[0036] Obtain a target gain value based on the first gain value and the second gain value.

[0037] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0038] Obtain a signal to be adjusted;

[0039] Determine a first gain value based on the power of the signal to be adjusted;

[0040] Input the signal to be adjusted into a gain determination model obtained through deep learning training to obtain a second gain value, where the second gain value is a predicted gain value for the next moment;

[0041] Obtain a target gain value based on the first gain value and the second gain value.

[0042] For the above gain adjustment method, device, computer device, and storage medium, by obtaining a signal to be adjusted; determining a first gain value based on the power of the signal to be adjusted; inputting the signal to be adjusted into a gain determination model to obtain a second gain value, where the gain determination model is obtained through deep learning training; and obtaining a target gain value based on the first gain value and the second gain value, the predicted gain of the deep learning model and the traditional power detection adjustment gain are combined, and the final gain value is determined according to the gain values obtained by the two methods, which can respond to signal changes in a timely manner, provide an appropriate gain, and ensure signal stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is an application environment diagram of the gain adjustment method in an embodiment of the present application;

[0044] Figure 2 It is a flowchart of the gain adjustment method in an embodiment of the present application;

[0045] Figure 3Schematic diagram of the prediction principle of the long short - term memory network in an embodiment of the present application;

[0046] Figure 4 Structural block diagram of the gain determination model of the gain adjustment method in an embodiment of the present application;

[0047] Figure 5 Structural block diagram of the gain adjustment system in an embodiment of the present application;

[0048] Figure 6 Structural block diagram of the gain adjustment device in an embodiment of the present application;

[0049] Figure 7 Internal structure diagram of a computer device in an embodiment of the present application. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0051] The gain adjustment method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 In the figure, the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in - vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head - mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0052] In one embodiment, as shown in Figure 2 In the figure, a gain adjustment method is provided, including the following steps:

[0053] Step S201, obtain the signal to be adjusted.

[0054] It can be understood that the signal to be adjusted is the currently acquired real - time signal. At this time, the amplitude of the signal changes, and it is necessary to adjust the gain of the signal according to the signal situation to ensure the stability of the signal output.

[0055] Step S202, determine a first gain value based on the power of the signal to be adjusted.

[0056] Exemplarily, the determination method of the first gain value is a traditional gain control method, that is, based on the current power value of the signal, the corresponding gain value is judged, and the signal is amplified. However, when the signal changes greatly and rapidly, if the gain value is determined only when the signal is acquired and then the signal is amplified, at this time, the signal has maintained the current power for a period of time, and the signals in the previous period have not been properly amplified, or the signal power will change again at the next moment, and the currently determined gain value cannot adapt to the signal at the next moment, which easily leads to unstable signal output and distortion.

[0057] Step S203: Input the signal to be adjusted into a gain determination model trained by deep learning to obtain a second gain value, where the second gain value is the predicted gain value for the next moment.

[0058] Exemplarily, the gain determination model is trained to be used to determine the predicted gain value for the next moment based on the signal at the current moment. It can be understood that the initial model of the deep learning model here can adopt an existing neural network model, and no specific limitation is made here.

[0059] Step S204: Obtain a target gain value based on the first gain value and the second gain value.

[0060] It can be understood that after obtaining two gain values through two methods, comparison can be carried out, and a more appropriate gain value can be determined as the final gain value. Exemplarily, the matching degrees of the two gain values with the actual requirements can be respectively judged, and a more matching gain value can be selected to amplify the signal to be adjusted.

[0061] The above gain adjustment method combines the predicted gain of the deep learning model and the traditional power detection and adjustment gain by obtaining the signal to be adjusted; determining the first gain value based on the power of the signal to be adjusted; inputting the signal to be adjusted into the gain determination model to obtain the second gain value, where the gain determination model is trained by deep learning; and obtaining the target gain value based on the first gain value and the second gain value, and determining the final gain value according to the gain values obtained by the two methods. It can respond to the change of the signal in time, provide appropriate gain, meet the requirements of high precision and convergence speed through the prediction of the future signal situation, and ensure the stability of the signal.

[0062] In one embodiment, the obtaining the target gain value based on the first gain value and the second gain value includes:

[0063] Step 1: Obtain the accuracy evaluation result of the previous moment, where the accuracy evaluation result is determined based on the second gain value and the standard gain value of the previous moment;

[0064] Step 2, if the accuracy evaluation result meets the preset threshold, then use the second gain value as the target gain value;

[0065] Step 3, if the accuracy evaluation result does not meet the preset threshold, then use the first gain value as the target gain value.

[0066] In this embodiment, the accuracy evaluation result at the previous moment is used to determine whether to use the first gain value or the second gain value as the target gain value. Exemplarily, the accuracy evaluation result can be an accuracy score.

[0067] It can be understood that by comparing the second gain value at the previous moment with the standard gain value to determine the accuracy evaluation result, it is actually comparing the power value corresponding to the second gain value at the previous moment with the actually observed power value, where the actually observed power value is the output power actually required by the signal. If the accuracy evaluation result meets the preset threshold, it means that the second gain value at the previous moment matches the actually observed gain value, and the second gain value can meet the actual requirements, so the second gain value is still used as the final output gain value at this moment; if the accuracy evaluation result does not meet the preset threshold, it means that the second gain value at the previous moment deviates from the actually observed gain value and cannot meet the signal gain adjustment requirement, so the first gain value obtained by the traditional method is used as the final output gain value at this moment.

[0068] In the above embodiment, the evaluation result of the second gain value at the previous moment is used as a reference standard to determine whether the second gain value can meet the signal gain requirement, and when the second gain value cannot meet the requirement, the first gain value is used as the final output gain, avoiding signal distortion when the second gain value deviates from the actual requirement, and effectively ensuring the accuracy of signal gain and the stability of the system.

[0069] In other embodiments, the basis for selecting the first gain value or the second gain value as the target gain value can also be the matching degree between the first gain value and the actual requirement, or by comparing the evaluation scores of the first gain value and the second gain value, and selecting the one with the higher evaluation score as the target gain value; in addition, the target gain value can also be determined by weighted summation of the first gain value and the second gain value, etc., comprehensively considering the two gain values. It can be understood that the specific method of determining the target gain value according to the first gain value and the second gain value can be determined by the user according to actual requirements, and will not be elaborated here.

[0070] In one of the embodiments, the obtaining of the accuracy evaluation result at the previous moment includes:

[0071] Step 1, use the first gain value at the current moment as the standard gain value;

[0072] Step 2, determine an accuracy score based on the deviation degree between the second gain value at the previous moment and the standard gain value.

[0073] It can be understood that the first gain value lags behind the signal to be adjusted at the current moment and can only meet the signal gain requirements before the current moment. Therefore, the first gain value at the current moment corresponds to the actually observed gain value at the previous moment, that is, the standard gain value at the previous moment.

[0074] In other embodiments, the accuracy evaluation result can also be in other forms, such as an accuracy level, which is not specifically limited here.

[0075] In the above embodiments, by using the lag of the traditional gain control method and taking the first gain value at the current moment as the standard gain value at the previous moment, the actual requirements of the signal gain at the previous moment can be accurately reflected, making the accuracy evaluation result more reliable.

[0076] In one of the embodiments, the determining the accuracy score based on the deviation degree between the second gain value at the previous moment and the standard gain value includes:

[0077] Score according to the inverse proportional function of the difference between the power corresponding to the second gain value at the previous moment and the power corresponding to the standard gain value. The closer they are, the higher the score.

[0078] It can be understood that in other embodiments, other calculation methods can be used to determine the accuracy score, as long as it can reflect the deviation degree between the second gain value at the previous moment and the standard gain value, which is not specifically limited here.

[0079] In one of the embodiments, after obtaining the target gain value based on the first gain value and the second gain value, the following further includes:

[0080] Step 1, update the model parameters of the gain determination model based on the accuracy evaluation result.

[0081] It can be understood that the accuracy evaluation result can reflect the deviation between the output result of the gain determination model and the actual requirements. Based on this deviation, reinforcement learning is performed on the gain determination model to update the model parameters. During real-time operation, the weight can be updated according to the prediction situation to adapt to other unconsidered problems in online operation, which can effectively improve the accuracy of the output result of the gain determination model.

[0082] In one of the embodiments, after obtaining the accuracy evaluation result at the previous moment, the following further includes:

[0083] Step 1, if the accuracy evaluation result meets the reset threshold, restore the gain determination model to the initial model.

[0084] It is understandable that if the accuracy evaluation result meets the reset threshold, it indicates that the gain value output by the gain determination model deviates far from the gain value actually required, indicating that the current gain determination model has reached a singularity point and cannot provide accurate predictions. Therefore, the gain determination model is reset and retrained. At the same time, before the gain determination model is retrained, the first gain value is used as the target gain value for the final output. Among them, the reset threshold can be set by the user according to actual needs and is not specifically limited here.

[0085] In another embodiment, the gain determination model can also be reset when the accuracy evaluation result is less than the preset threshold multiple times. Specifically, both here and the threshold can be set by the user according to actual needs and are not specifically limited here.

[0086] In the above embodiment, when it is determined that the prediction result of the gain determination model is inaccurate, the gain determination model is reset, and the first gain value is used as the target gain value for the final output, degenerating to the traditional gain control method to avoid the problem of network locking, protecting the system, and making the signal output more stable.

[0087] In another embodiment, the determining the first gain value based on the power of the signal to be adjusted includes:

[0088] Step 1, comparing the power of the signal to be adjusted with the preset power;

[0089] Step 2, determining the first gain value based on the comparison result.

[0090] It is understandable that the traditional gain control method is used to determine the first gain value, that is, according to the power of the current real-time signal and the preset power, it is judged whether the power of the current signal is too large or too small, and the degree of being too large or too small, and the corresponding gain value is output according to the degree of being too large or too small to adjust the signal power value.

[0091] In another embodiment, before inputting the signal to be adjusted into the gain determination model to obtain the second gain value, it further includes:

[0092] Step 1, obtaining an initial model, where the initial model is a long short-term memory network;

[0093] Step 2, training the initial model with the reference signal and the reference gain value as the training set to obtain the gain determination model.

[0094] It can be understood that the reference signal is the signal information obtained based on historical data, and the reference gain value is obtained based on historical data, which is the gain value actually required for the corresponding reference signal at the next moment. The reference signal and the reference gain value are used as the training set to train the initial model, and through parameter update and iteration until the convergence requirement is met, the gain determination model is obtained.

[0095] Long Short-Term Memory (LSTM) is a type of recurrent neural network, which is specifically designed to solve the long-term dependence problem existing in general Recurrent Neural Networks (RNNs). LSTM adds control of memory and forgetting on the basis of RNN, and can provide better prediction for long sequences.

[0096] In the above embodiment, the long short-term memory network is used for training to obtain the gain determination model, which can comprehensively consider the signal amplitude change situation before the current moment to make a prediction of the signal amplitude at the next moment, so as to determine the gain value, with better prediction effect and more accurate result.

[0097] In other embodiments, the gain determination model can also be a model composed of a combination of a neural network and a gain adjuster. Among them, the neural network is used to receive signal input and output the signal power at the next moment, and the gain adjuster is used to determine the required gain value according to the signal power at the next moment and output it.

[0098] Please refer to Figure 3 , Figure 3 , which is a schematic diagram of the prediction principle of the long short-term memory network according to an embodiment of the present application. It can be understood that the long short-term memory network makes a prediction of the maximum amplitude of the future signal based on the signal amplitude change situation at the current moment and before the current moment, that is, historical information.

[0099] Please refer to Figure 4 , Figure 4 , which is a structural block diagram of the gain determination model of the gain adjustment method according to an embodiment of the present application. Exemplarily, the A-layer network is a long short-term memory network, and the B-layer network is a fully connected network. Specifically, A1 to An are recurrent networks with memory, and B1 to Bn are networks without memory. The A1 layer and the B1 layer are directly connected, and finally, after summing through C0, the prediction output is obtained. The input-output relationship between the A-layer network and the B-layer network is as follows:

[0100]

[0101]

[0102] b t = σ(W r · [y t-1 , xr )

[0103] a t = σ(W z ·[y t-1 , x r )

[0104] where x t is the input of An, and y t is the output of An as y t , W is the model parameter weight, σ is the hyperparameter, and is the user-defined prediction bias weight.

[0105] The input-output relationship between the B-layer network and the C-layer network is as follows:

[0106] m t = A T n t + c

[0107] where m t is the input of Bn, and n t is the output of C0, A T is used to perform matrix rank transformation on the input of C0 and reduce the data dimension to obtain the output data with the expected dimension, and c is the model parameter.

[0108] It can be understood that the output of the neural network is finally a prediction of the signal power, which is between -1 and 1, used to reflect the change degree of the signal power, and is mapped from -1 to 1 to the true gain through the gain adjuster.

[0109] Please refer to Figure 5 , Figure 5 which is the structural block diagram of the gain adjustment system according to an embodiment of the present application.

[0110] In this embodiment, the gain adjustment system includes a long short-term memory network, a gain adjustment module B, a power detection module, a gain adjustment module A, a scoring module, a gain output module, and a gain control module. Among them, the long short-term memory network is used to provide a predicted value of the signal amplitude according to the signal input. The gain adjustment module B is used to output the gain B at the next moment according to the predicted value of the signal amplitude. The power detection module is a traditional detection module used to detect the amplitude of the current signal power. The gain adjustment module A is a traditional gain control used to output a gain according to the current signal amplitude. The scoring module is used to score through the outputs of the gain adjustment module A and the gain adjustment module B, and the current signal amplitude, and judge which of the outputs of the gain adjustment module A and the gain adjustment module B is better, that is, better meets the signal adjustment requirements, and then gives a higher score, and uses it as the final gain output, which is transmitted to the gain control module through the gain output module. The gain control module is used to perform gain on the signal input signal according to the final gain output to obtain the output signal.

[0111] Exemplarily, the entire system can be abstracted into an input-output black box, and the overall function is to add an appropriate gain to the signal input and then give it to the signal output. First, the input signal passes through the gain calculator, which will calculate a currently required gain. This gain is output to the gain control module to control the gain of the current signal and output it. Inside the gain calculator, the signal is divided into two streams. The power detection module and the power adjustment module A are traditional gain controllers, and the long short-term memory network and the gain adjustment module B are a power prediction model. Both output their respective determined gain values, and are scored in the scoring module, and a combined gain is given to the gain output module. At the same time, the result is also returned to the long short-term memory network for reinforcement learning to optimize the result.

[0112] In this embodiment, the input-output relationship of the gain adjustment module B is specifically as follows:

[0113] z(g) = k * g

[0114]

[0115] Among them, the input of the gain adjustment module B is g, the output of the gain adjustment module B is f(g), and k is set according to the parameters related to the maximum output amplitude of the hardware system.

[0116] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be based on the same inventive concept as other steps or steps or stages in other steps. Embodiments of the present application also provide a gain adjustment device for implementing the above-described gain adjustment method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the gain adjustment device provided below can refer to the limitations on the gain adjustment method in the above text, and will not be elaborated here.

[0117] In one embodiment, as Figure 6 shown, a gain adjustment device is provided, including: an acquisition module 610, a first determination module 620, a second determination module 630, and a gain determination module 640, where:

[0118] The acquisition module 610 is used to acquire the signal to be adjusted.

[0119] The first determination module 620 is used to determine a first gain value based on the power of the signal to be adjusted.

[0120] The first determination module 620 is further used to:

[0121] Compare the power of the signal to be adjusted with a preset power;

[0122] Determine the first gain value based on the comparison result.

[0123] The second determination module 630 is used to input the signal to be adjusted into a gain determination model to obtain a second gain value, and the gain determination model is obtained through deep learning training.

[0124] The gain determination module 640 is used to obtain a target gain value based on the first gain value and the second gain value.

[0125] The gain determination module 640 is further used to:

[0126] Obtain the accuracy evaluation result at the previous moment, and the accuracy evaluation result is determined based on the second gain value and the standard gain value at the previous moment;

[0127] If the accuracy evaluation result meets the preset threshold, use the second gain value as the target gain value;

[0128] If the accuracy evaluation result does not meet the preset threshold, use the first gain value as the target gain value.

[0129] The gain determination module 640 is further configured to:

[0130] Use the first gain value at the current moment as the standard gain value;

[0131] Determine an accuracy score based on the deviation degree between the second gain value at the previous moment and the standard gain value.

[0132] The gain adjustment device further includes: an update module.

[0133] The update module is configured to update the model parameters of the gain determination model based on the accuracy evaluation result.

[0134] The gain adjustment device further includes: a reset module.

[0135] The reset module is configured to restore the gain determination model to the initial model if the accuracy evaluation result meets the reset threshold.

[0136] The gain adjustment device further includes: a training module.

[0137] The training module is configured to:

[0138] Obtain an initial model, where the initial model is a long short-term memory network;

[0139] Use the reference signal and the reference gain value as a training set to train the initial model to obtain the gain determination model.

[0140] Each module in the above gain adjustment device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0141] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 7As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a gain adjustment method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0142] Those skilled in the art can understand that Figure 7 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0143] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0144] Obtain the signal to be adjusted;

[0145] Determine a first gain value based on the power of the signal to be adjusted;

[0146] Input the signal to be adjusted into a gain determination model obtained through deep learning training to obtain a second gain value, where the second gain value is the predicted gain value for the next moment;

[0147] Obtain a target gain value based on the first gain value and the second gain value.

[0148] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0149] Obtain the signal to be adjusted;

[0150] Determine a first gain value based on the power of the signal to be adjusted;

[0151] Input the signal to be adjusted into a gain determination model obtained through deep learning training to obtain a second gain value, where the second gain value is the predicted gain value for the next moment;

[0152] Obtain a target gain value based on the first gain value and the second gain value.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0154] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium provided in the various embodiments of the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random-access memories (ReRAM), magnetoresistive random-access memories (MRAM), ferroelectric random-access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memories (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments of the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments of the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0155] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0156] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A gain adjustment method, characterized in that The method includes: Obtaining an adjustment - to - be signal; Determining a first gain value based on the power of the adjustment - to - be signal; Inputting the adjustment - to - be signal into a gain determination model obtained through deep - learning training to obtain a second gain value, where the second gain value is a predicted gain value for the next moment; Obtaining a target gain value based on the first gain value and the second gain value; The obtaining the target gain value based on the first gain value and the second gain value includes: Obtaining an accuracy evaluation result of the previous moment, where the accuracy evaluation result is determined based on the second gain value of the previous moment and a standard gain value; If the accuracy evaluation result meets a preset threshold, then using the second gain value as the target gain value; If the accuracy evaluation result does not meet the preset threshold, then using the first gain value as the target gain value.

2. The method according to claim 1, wherein The obtaining the accuracy evaluation result of the previous moment includes: Using the first gain value of the current moment as the standard gain value; Determining an accuracy score based on the deviation degree between the second gain value of the previous moment and the standard gain value.

3. The method according to claim 1, wherein After obtaining the target gain value based on the first gain value and the second gain value, it further includes: Updating the model parameters of the gain determination model based on the accuracy evaluation result.

4. The method according to claim 1, characterized in that, After obtaining the accuracy evaluation result of the previous moment, it further includes: If the accuracy evaluation result meets a reset threshold, then restoring the gain determination model to the initial model.

5. The method according to claim 1, characterized in that The determining the first gain value based on the power of the adjustment - to - be signal includes: Comparing the power of the adjustment - to - be signal with a preset power; Determining the first gain value based on the comparison result.

6. The method according to claim 1, characterized in that, Before inputting the adjustment - to - be signal into the gain determination model to obtain the second gain value, it further includes: Obtaining an initial model, where the initial model is a long short - term memory network; Training the initial model with a reference signal and a reference gain value as a training set to obtain the gain determination model.

7. A gain adjustment device, characterized in that The device includes: An obtaining module, configured to obtain an adjustment - to - be signal; A first determination module, configured to determine a first gain value based on the power of the adjustment - to - be signal; A second determination module, configured to input the adjustment - to - be signal into a gain determination model to obtain a second gain value, where the gain determination model is obtained through deep - learning training; A gain determination module, configured to obtain a target gain value based on the first gain value and the second gain value; The gain determination module is further configured to obtain an accuracy evaluation result of the previous moment. If the accuracy evaluation result meets a preset threshold, then using the second gain value as the target gain value. If the accuracy evaluation result does not meet the preset threshold, then using the first gain value as the target gain value; the accuracy evaluation result is determined based on the second gain value of the previous moment and a standard gain value.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.

Images