Automatic frequency modulation method, device and equipment of wireless microphone, medium and product

Abstract

The embodiment of the invention discloses an automatic frequency modulation method and device for a wireless microphone, equipment, a medium and a product. Comprising the following steps: acquiring to-be-processed data, and determining a to-be-input vector corresponding to the to-be-processed data; performing vector analysis on the to-be-input vector based on a pre-constructed string frequency prediction model to obtain a string frequency interference result corresponding to the to-be-adjusted wireless microphone; determining an optimal frequency modulation strategy corresponding to the to-be-adjusted wireless microphone based on the to-be-processed data, the string frequency interference result and a reinforcement learning algorithm; and adjusting the current microphone transmitting power of the wireless microphone to be adjusted to the target microphone transmitting power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy. According to the invention, automatic frequency modulation is carried out on the wireless microphone based on the optimal frequency modulation strategy corresponding to the wireless microphone, the influence of crosstalk interference on the wireless microphone is reduced, and the effect of poor information transmission quality in the use process of the wireless microphone is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of wireless microphone control, and in particular to an automatic frequency modulation method, device, equipment, medium and product of a wireless microphone. Background Art

[0002] In today's conference sound reinforcement systems, as the use of wireless microphones becomes more and more popular, the problem of crosstalk has attracted more and more attention.

[0003] At present, anti-interference technology is usually used to solve the cross-frequency problem in the use of wireless microphones, such as filtering, signal shielding or digital encryption technology. However, when the wireless microphone is located in a complex and changeable wireless signal environment with multiple strong interference sources, the information transmission quality of the wireless microphone will still be affected by the cross-frequency interference problem.

[0004] In order to solve the above problems, it is necessary to improve the automatic frequency modulation method of the wireless microphone. Summary of the invention

[0005] The embodiments of the present invention provide a method, device, equipment, medium and product for automatically tuning the frequency of a wireless microphone to solve the problem that the prior art relies on simple signal monitoring or fixed regular microphone frequencies to tune the frequency of a wireless microphone and is difficult to cope with a complex and changeable wireless signal environment, resulting in crosstalk interference during the use of the wireless microphone.

[0006] In a first aspect, an embodiment of the present invention provides an automatic frequency tuning method for a wireless microphone, comprising:

[0007] Acquire data to be processed, and determine a vector to be input corresponding to the data to be processed; wherein the data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to the wireless microphone to be adjusted;

[0008] Performing vector analysis on the input vector based on a pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk interference result is interference or no interference;

[0009] Determine an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm;

[0010] Based on the optimal frequency modulation strategy, the current microphone transmission power of the wireless microphone to be adjusted is adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy.

[0011] In a second aspect, an embodiment of the present invention further provides an automatic frequency tuning device for a wireless microphone, comprising:

[0012] A vector determination module, used to obtain data to be processed and determine a vector to be input corresponding to the data to be processed; wherein the data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to a wireless microphone to be adjusted;

[0013] An interference result determination module, used for performing vector analysis on the input vector based on a pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk interference result is interference or no interference;

[0014] A strategy determination module, used to determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm;

[0015] The microphone frequency modulation module is used to adjust the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0017] one or more processors;

[0018] A storage device for storing one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the automatic frequency tuning method for a wireless microphone described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the automatic frequency tuning method for a wireless microphone as described in any embodiment of the present invention.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the automatic frequency tuning method for a wireless microphone as described in any embodiment of the present invention.

[0022] The embodiments of the present invention provide an automatic frequency modulation method, device, electronic device and storage medium for a wireless microphone, which obtains data to be processed and determines a vector to be input corresponding to the data to be processed; performs vector analysis on the vector to be input based on a pre-constructed crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; determines an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and a reinforcement learning algorithm; and adjusts the current microphone transmission power of the wireless microphone to be adjusted to a target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy. In this technical solution, the wireless signal parameters and microphone parameters of the wireless microphone are analyzed by a pre-built crosstalk prediction model to obtain the crosstalk interference results corresponding to the wireless microphone at each data collection moment. Further, the reinforcement learning algorithm is combined on the basis of the wireless signal parameters and microphone parameters, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined according to the environmental state and model output of the reinforcement learning algorithm, and then the current microphone transmission power of the wireless microphone is automatically and dynamically adjusted based on the smooth transition technology until it is adjusted to the target microphone transmission power, so as to ensure that the wireless microphone will not have audio interruption problems during the frequency modulation process, and reduce the impact of the crosstalk interference problem on the wireless microphone. The problem that the wireless microphone is difficult to cope with the complex and changeable wireless signal environment when the wireless microphone is frequency modulated by simple signal monitoring or fixed regular microphone frequency in the prior art is solved, resulting in the problem of crosstalk interference in the use of the wireless microphone, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined in the complex and changeable wireless signal environment, and the wireless microphone is automatically frequency modulated based on the optimal frequency modulation strategy, so as to reduce the impact of crosstalk interference on the wireless microphone and improve the effect of poor information transmission quality during the use of the wireless microphone. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts. In the drawings:

[0024] Figure 1 is a flow chart of an automatic frequency modulation method for a wireless microphone provided in an embodiment of the present invention;

[0025] Figure 2 is a flow chart of an automatic frequency tuning method for a wireless microphone provided in an embodiment of the present invention;

[0026] Figure 3 is a flowchart of a specific example of an automatic frequency tuning method for a wireless microphone provided in an embodiment of the present invention;

[0027] Figure 4 It is a structural schematic diagram of an automatic frequency modulation device for a wireless microphone provided in an embodiment of the present invention;

[0028] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0030] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0031] Among them, the acquisition, storage, use and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, some existing solutions in the industry such as certain software, components or models may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0033] Embodiment 1

[0034] Figure 1This is a flowchart of an automatic frequency tuning method for a wireless microphone provided in an embodiment of the present invention. This embodiment can be applied to obtain wireless signal parameters and microphone parameters during the use of a wireless microphone, and perform crosstalk interference prediction on the wireless signal parameters and microphone parameters based on a pre-built crosstalk prediction model to obtain crosstalk interference results. Further, the wireless signal parameters, microphone parameters and crosstalk interference results are combined with a reinforcement learning method to determine the optimal frequency tuning strategy corresponding to the wireless microphone, so as to adjust the microphone transmission power of the wireless microphone to the target microphone transmission power based on the optimal frequency tuning strategy. The method of this embodiment can be executed by an automatic frequency tuning device for a wireless microphone, which can be implemented in hardware and / or software. The method specifically includes the following steps:

[0035] S110, obtaining data to be processed, and determining a vector to be input corresponding to the data to be processed.

[0036] The data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to the wireless microphone to be adjusted. The wireless microphone to be adjusted refers to a wireless microphone in a conference sound reinforcement system, which can usually be used in conference scenes or performance scenes. The input vector refers to a vector obtained after vectorizing the data to be processed, which is used to characterize the parameter information of the wireless microphone to be adjusted in a vectorized form.

[0037] The wireless signal parameters refer to the wireless signal emitted by the wireless microphone to be adjusted, for example, the wireless signal parameters include signal strength, frequency distribution information parameters, interference source information parameters during wireless signal transmission, etc. The microphone parameters include the signal quality of the wireless microphone to be adjusted, such as signal-to-noise ratio, distortion and bit error rate, microphone transmission power, and the current frequency of the wireless microphone to be adjusted.

[0038] Taking conference scenarios as an example, in existing conference sound reinforcement systems, as the use of wireless microphones becomes more and more popular, the problem of microphone crosstalk has attracted more and more attention. The so-called crosstalk problem refers to the interference, confusion or abnormality of the sound of the wireless microphone due to the reception of signals from other wireless microphones or wireless devices during the use of the wireless microphone. For example, when there are multiple strong interference sources and their frequency range is wide or changes frequently, it may be difficult to effectively eliminate all interference by relying solely on fixed frequency selection or simple filtering, resulting in the sound signal still being affected, and problems such as crosstalk affecting the quality of conference sound reinforcement.

[0039] Based on this, this technical solution processes the wireless signal of the wireless microphone during use and determines the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted, so as to reduce the interference of the crosstalk problem on the user's auditory experience by frequency adjustment of the wireless microphone to be adjusted, thereby ensuring that the user can easily capture key information when listening to conference information and improving the information transmission quality of the wireless microphone.

[0040] Specifically, wireless signal parameters and microphone parameters are collected at at least one data collection moment during the use of the wireless microphone to be adjusted, so as to obtain an input vector corresponding to the data to be processed by vectorizing the collected data, and then vector analysis and processing are performed on the input vector to determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted, thereby ensuring the voice transmission quality during the use of the wireless microphone to be adjusted.

[0041] Optionally, determining the input vector corresponding to the data to be processed includes: before acquiring the data to be processed, performing data normalization on the data to be processed at each data collection moment after data cleaning; and generating the input vector from the data to be processed after the data normalization in chronological order.

[0042] Specifically, before vectorizing the data to be processed, it is necessary to first perform data processing on the data to be processed to eliminate obvious abnormal data in the data to be processed, so as to ensure the data quality of the data to be processed.

[0043] Exemplarily, the data of the wireless microphone to be adjusted during use is generally numerical data. Based on this, when performing data cleaning, it is possible to check whether there are data points in the data to be processed that are obviously deviated from the normal numerical range, such as a data point where a signal data strength value is much higher than / or lower than a preset data range. If so, the abnormal data point is removed. At the same time, data deletion can be performed on duplicate data points in the data to be processed.

[0044] On this basis, the data to be processed after data cleaning is further normalized to generate a vector to be input based on the normalized data.

[0045] Exemplarily, taking the wireless signal strength data in the data to be processed as an example, it is normalized to the interval [0,1]. Specifically, the minimum data signal strength value can be mapped to 0 and the strongest data signal strength value can be mapped to 1 through linear transformation, and the remaining data signal strength values ​​can be mapped and processed in proportion. Similarly, for other data to be processed that need to be normalized, such as the frequency distribution information of the wireless signal, the signal-to-noise ratio, distortion, bit error rate, microphone transmission power, and microphone frequency in the microphone parameters, the same data mapping method can also be used for data normalization.

[0046] Furthermore, the data to be processed at at least one data collection moment are arranged in chronological order, and the normalized data information is used as a vector value to generate a vector to be input.

[0047] Specifically, taking the data to be processed including signal strength, frequency distribution information parameters, microphone transmission power, and the current frequency of the wireless microphone to be adjusted as an example, after data cleaning and data normalization, the data corresponding to a certain data collection moment can be represented by [0.5, 0.6, 0.4, 0.5], and it is used as the vector information corresponding to the data collection moment to generate the corresponding input vector according to the time sequence corresponding to the data collection moment. Among them, the input vector may include the corresponding vector information at one or more data collection moments.

[0048] S120: Perform vector analysis on the input vector based on the pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted.

[0049] The crosstalk prediction model is a combination model based on the LSTM model and the SVM model. The crosstalk interference result is set to have interference or no interference.

[0050] The LSTM model is used to extract vector features from the input vector to obtain the vector to be used, and the SVM model is used to perform vector analysis and classification on the vector to be used output by the LSTM model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted.

[0051] Specifically, the input vector is input into a pre-built crosstalk prediction model, and the input vector is analyzed and processed based on the crosstalk prediction model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted. Optionally, the input vector is vector analyzed based on the pre-built crosstalk prediction model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted, including: inputting the input vector into an LSTM model for feature extraction to obtain a vector to be used; inputting the vector to be used into an SVM model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted.

[0052] S130: Determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm.

[0053] Among them, the reinforcement learning algorithm is mainly a deep learning algorithm that guides the learning object on how to make decisions at each step and what actions to take to achieve a specific purpose or maximize benefits. The optimal frequency modulation strategy includes the most suitable microphone transmission power and current frequency corresponding to the wireless microphone to be adjusted.

[0054] In this technical solution, based on the data to be processed and the results of crosstalk interference, data analysis is performed in combination with a reinforcement learning algorithm, and the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted can be obtained, and then the transmission power and usage frequency of the wireless microphone to be adjusted can be adjusted based on the optimal frequency modulation strategy to reduce the impact of crosstalk interference on the signal quality of the wireless microphone to be adjusted.

[0055] Among them, the microphone parameters include the current usage frequency and microphone transmission power corresponding to the microphone to be adjusted. The so-called action space refers to the set of valid actions in a given environment, and the action space usually includes two types, one is a discrete action space, and the other is a continuous action space. In this technical solution, only the discrete action space is taken as an example. The discrete action space is usually composed of a limited number of execution actions, generally including all available control instructions in a specific task. For example, in this technical solution, the action space includes specific execution actions of switching different usage frequencies of the microphone to be adjusted and the microphone transmission power to different levels.

[0056] Optionally, based on the data to be processed, the crosstalk interference results and the reinforcement learning algorithm, the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted is determined, including: defining the environmental state of the reinforcement learning algorithm based on the wireless signal parameters, microphone parameters and crosstalk interference results at the current data collection time; defining the action space of the reinforcement learning algorithm according to the microphone parameters; determining the reward value corresponding to the current specific execution action of the wireless microphone to be adjusted based on the environmental state, action space and the reward function in the reinforcement learning algorithm; and optimizing the current frequency modulation strategy of the wireless microphone to be adjusted based on the reward value to obtain the optimal frequency modulation strategy.

[0057] In a specific example, the data to be processed of the wireless microphone to be adjusted at at least one data collection moment and the crosstalk interference result outputted based on the crosstalk prediction model are received, so as to define the environment state of reinforcement learning based on the data to be processed and the crosstalk interference result. The data to be processed includes the wireless signal parameters and microphone parameters of the wireless microphone to be adjusted, and the wireless signal parameters may include signal strength, frequency distribution information parameters, and interference source information parameters during wireless signal transmission. The microphone parameters include the signal quality of the wireless microphone to be adjusted, such as signal-to-noise ratio, distortion and bit error rate, microphone transmission power, and the current use frequency of the wireless microphone to be adjusted.

[0058] Further, the action space of the reinforcement learning algorithm is defined according to the microphone parameters. Specifically, the action space of the reinforcement learning is defined as specific execution actions such as switching different microphone frequencies and microphone transmission power to different levels. Further, the reward function is defined according to the microphone parameters of the wireless microphone to be adjusted, wherein the influencing factor index for determining the reward function may include the signal-to-noise ratio, signal strength, distortion, crosstalk interference information, energy consumption index, and stability index during the use of the wireless microphone to be adjusted. Specifically, the reward function R can be expressed by the following formula:

[0059] R=w1×SNR+w2×sig+w3×D+w4×C+w5×E+w6×sta

[0060] Among them, w1 represents the weight corresponding to the signal-to-noise ratio, w2 represents the weight corresponding to the signal strength, w3 represents the weight corresponding to the distortion, w4 represents the weight corresponding to the crosstalk interference information, w5 represents the weight corresponding to the energy consumption index of the wireless microphone to be adjusted, w6 represents the weight corresponding to the stability index of the wireless microphone to be adjusted, SNR represents signal-to-noise ratio, sig represents signal strength, D represents distortion, C represents crosstalk interference information, E represents the energy consumption index of the wireless microphone to be adjusted, and sta represents the stability index of the wireless microphone to be adjusted.

[0061] On this basis, a specific execution action is randomly selected from the action space as the starting action, and a greedy algorithm is used for balanced exploration. The selected starting action is executed and the new environmental state generated after the execution of the starting action is observed in real time. The reward value of each specific execution action in the action space after execution is calculated according to the set reward function.

[0062] On this basis, considering the impact of each specific action in the action space on the state of the environment, risk penalties or reward items can be added when updating the reward value Q. For example, if a specific action may bring a greater risk, a certain penalty will be given in the update of the reward value Q. Specifically, the Q value can be updated by the following formula:

[0063] Q(s,a)=Q(s,a)+α*(R+γ*max(Q(s',a'))-Q(s,a))-risk_factor(a)

[0064] Among them, Q(s,a) represents the reward value of taking action a in state s, which represents the estimate of the long-term expected cumulative reward for the specific execution action taken under the environment state; α represents the learning rate; r represents the immediate reward obtained after executing action a; γ represents the discount factor, which is used to measure the importance of future rewards; max(Q(s',a')) represents the Q value of the action with the largest Q value among all possible actions a' in the new state s', which represents the expected reward estimate for the best future action; risk_factor(a): the risk factor of action a.

[0065] On this basis, the reward value Q is continuously updated until the reward value Q reaches stability, and the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted is output.

[0066] S140: Based on the optimal frequency modulation strategy, adjust the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy.

[0067] The target microphone transmission power may refer to the microphone transmission power corresponding to the wireless microphone to be adjusted in the optimal frequency modulation strategy.

[0068] In practical applications, the microphone transmission power and microphone use power of the wireless microphone to be adjusted are the main factors affecting the information transmission quality of the wireless microphone. Therefore, the frequency modulation strategy corresponding to the wireless microphone to be adjusted mainly includes the microphone transmission power and the microphone use frequency. The so-called optimal frequency modulation strategy can be understood as a frequency modulation strategy that includes the microphone transmission power and the microphone use frequency used when the wireless microphone to be adjusted is at the optimal information transmission quality.

[0069] It should be noted that when adjusting the wireless microphone to be adjusted, the microphone usage frequency can be adjusted to the microphone usage frequency in the optimal frequency modulation strategy by manual or automatic adjustment, for example, the usage frequency of the wireless microphone to be adjusted is adjusted from FM.88Hz to FM.95Hz. When adjusting the microphone transmission power of the wireless microphone to be adjusted, it is necessary to consider whether the wireless microphone audio will be interrupted during the adjustment process.

[0070] Therefore, in the actual process of frequency modulation of the wireless microphone to be adjusted, the adjustment of the microphone transmission power is particularly important. Optionally, based on the optimal frequency modulation strategy, the current microphone transmission power of the wireless microphone to be adjusted is adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy, including: sending the optimal frequency modulation strategy to the wireless microphone to be adjusted, and determining the target microphone transmission power corresponding to the wireless microphone to be adjusted in the optimal frequency modulation strategy; based on the dynamic power adjustment algorithm, the current microphone transmission power of the microphone to be adjusted is adjusted to the target microphone transmission power.

[0071] Specifically, after determining the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted, the strategy is sent to the wireless microphone to be adjusted, so that the control unit in the wireless microphone to be adjusted adjusts the microphone transmission power of the wireless microphone to be adjusted according to the strategy.

[0072] Exemplarily, the microphone transmit power currently used by the wireless microphone to be adjusted is adjusted through a dynamic power adjustment algorithm, and each adjustment increases or decreases a smaller power increase amount △P until the current microphone transmit power is adjusted to the target microphone transmit power. Under the premise of real-time monitoring of the signal quality and interference of the wireless microphone to be adjusted, it is ensured that the wireless microphone to be adjusted will not have audio interruption problems during the adjustment of the microphone transmit power.

[0073] The embodiments of the present invention provide an automatic frequency modulation method, device, electronic device and storage medium for a wireless microphone, which obtains data to be processed and determines a vector to be input corresponding to the data to be processed; performs vector analysis on the vector to be input based on a pre-constructed crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; determines an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and a reinforcement learning algorithm; and adjusts the current microphone transmission power of the wireless microphone to be adjusted to a target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy. In this technical solution, the wireless signal parameters and microphone parameters of the wireless microphone are analyzed by a pre-built crosstalk prediction model to obtain the crosstalk interference results corresponding to the wireless microphone at each data collection moment. Further, the reinforcement learning algorithm is combined on the basis of the wireless signal parameters and microphone parameters, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined according to the environmental state and model output of the reinforcement learning algorithm, and then the current microphone transmission power of the wireless microphone is automatically and dynamically adjusted based on the smooth transition technology until it is adjusted to the target microphone transmission power, so as to ensure that the wireless microphone will not have audio interruption problems during the frequency modulation process, and reduce the impact of the crosstalk interference problem on the wireless microphone. The problem that the wireless microphone is difficult to cope with the complex and changeable wireless signal environment when the wireless microphone is frequency modulated by simple signal monitoring or fixed regular microphone frequency in the prior art is solved, resulting in the problem of crosstalk interference in the use of the wireless microphone, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined in the complex and changeable wireless signal environment, and the wireless microphone is automatically frequency modulated based on the optimal frequency modulation strategy, so as to reduce the impact of crosstalk interference on the wireless microphone and improve the effect of poor information transmission quality during the use of the wireless microphone.

[0074] Embodiment 2

[0075] Figure 2The flowchart of the automatic frequency tuning method of a wireless microphone provided in an embodiment of the present invention. The embodiment of the present invention further optimizes the above embodiment on the basis of the above embodiment, and the embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the automatic frequency tuning method of a wireless microphone provided in an embodiment of the present invention may include the following steps:

[0076] S210: Build a frequency prediction model.

[0077] Optionally, before obtaining the data to be processed, it is necessary to pre-build a string frequency prediction model to perform vector analysis on the input vector corresponding to the data to be processed based on the string frequency prediction model. Specifically, when building the string frequency prediction model, it includes: obtaining historical data to be processed at least one historical data collection moment, and performing data annotation on each historical data to be processed to obtain a data annotation result; inputting each historical data to be processed into the model to be trained, and predicting the string frequency interference result for each historical data to be processed based on the model to be trained to obtain a string frequency interference prediction result; adjusting the model parameters of the model to be trained according to the data annotation result and the string frequency interference prediction result to obtain a string frequency prediction model, and performing vector analysis on the input vector corresponding to the data to be processed based on the string frequency prediction model to obtain a string frequency interference result corresponding to the wireless microphone to be adjusted.

[0078] The historical data to be processed refers to the data to be processed for model training of the frequency prediction model. For example, the historical data to be processed may be the wireless signal parameters and microphone parameters of the wireless microphone in the past week. The data is labeled as interference or no interference. The model to be trained is the initial frequency prediction model without parameter adjustment. The frequency interference prediction result can be understood as the analysis result obtained after frequency analysis of the historical data to be processed based on the frequency prediction model.

[0079] In practical applications, since the historical data to be processed is the data corresponding to the historical data collection time, it is known whether there is crosstalk interference in the historical data to be processed corresponding to each historical data collection time. Based on this, the historical data to be processed at all historical data collection times can be pre-labeled.

[0080] Furthermore, before inputting the historical data to be processed into the model to be trained, it is necessary to perform data cleaning and data normalization on the historical data to be processed, generate corresponding historical vectors for the historical data to be processed in the chronological order of the historical data collection time, and perform model training on the model to be trained based on at least one historical vector, and output the crosstalk interference prediction results corresponding to each historical vector.

[0081] On this basis, the data annotation results of each historical data to be processed and the crosstalk interference prediction results corresponding to each historical data to be processed based on the output of the model to be trained are compared to determine whether the prediction results of the model to be trained are accurate. For example, for the historical data to be processed 1, the corresponding data annotation result is no interference, and the crosstalk interference prediction result obtained after vector analysis of the historical vector corresponding to the historical data to be processed 1 based on the model to be trained is no interference, which indicates that the prediction result of the model to be trained for the historical data to be processed 1 is accurate; on the contrary, if the crosstalk interference prediction result output by the model to be trained is interference, it indicates that the prediction result for the historical data to be processed 1 fails. The historical vectors corresponding to a large number of historical data to be processed are analyzed and predicted by the model to be trained, and the model parameters of the model to be trained are adjusted according to the output results of each model to increase the model accuracy of the model to be trained. For example, when the accuracy of the model to be trained is higher than the preset accuracy, it indicates that the model accuracy of the model to be trained meets the model training requirements, and the model to be trained after parameter adjustment is used as the crosstalk prediction model in actual use.

[0082] S220: Obtain data to be processed, and determine a vector to be input corresponding to the data to be processed.

[0083] S230: Perform vector analysis on the input vector based on the pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted.

[0084] S240: Determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm.

[0085] S250: Based on the optimal frequency modulation strategy, adjust the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy.

[0086] In a specific example, Figure 3 As shown, before the frequency of the wireless microphone to be adjusted is modulated, the technical solution needs to pre-build a crosstalk prediction model to process the data to be processed during the use of the wireless microphone to be adjusted based on the model. Specifically, the historical data to be processed of the wireless microphone to be adjusted is obtained, such as the historical data to be processed includes the wireless signal parameters of the wireless microphone to be adjusted and the conference sound reinforcement system related data (i.e., microphone parameters), and the historical data to be processed is pre-processed. The pre-processing includes data cleaning, data normalization processing and data labeling processing.

[0087] Furthermore, each historical data to be processed after normalization is vectorized in chronological order to obtain a historical vector corresponding to each historical data to be processed, and the historical vector is input into a string frequency prediction model (the string frequency prediction model here is a model to be trained without parameter adjustment). Wherein, the string frequency prediction model is based on a combination model of an LSTM model and an SVM model. The historical vector is feature extracted by the LSTM model to output a feature vector, and the feature vector is input into the SVM model for string frequency interference prediction to obtain a string frequency interference prediction result corresponding to each historical data to be processed, and the model to be trained is trained based on the data annotation results corresponding to each historical data to be processed and the string frequency interference prediction results, until the accuracy of the model to be trained reaches the preset accuracy, and the model to be trained is used as the string frequency prediction model in actual use.

[0088] On this basis, the data to be processed of the wireless microphone to be adjusted is obtained, and the data to be processed is preprocessed and vectorized to obtain the input vector corresponding to the data to be processed. The input vector is input into the constructed crosstalk prediction model to obtain the crosstalk interference result corresponding to each data to be processed based on the crosstalk prediction model.

[0089] Furthermore, the environment state, action space and reward function of the reinforcement learning algorithm are defined based on the data to be processed and the crosstalk interference results. A specific execution action is randomly selected from the action space as the starting action, and a greedy algorithm is used for balanced exploration. The selected starting action is executed and the new environment state generated after the execution of the starting action is observed in real time. The reward value of each specific execution action in the action space after execution is calculated according to the set reward function. Considering the impact of each specific execution action in the action space on the environment state, a risk penalty or reward item can be added when updating the reward value Q, so as to determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted according to the update of the reward value Q.

[0090] The optimal frequency modulation strategy is sent to the control unit of the wireless microphone to be adjusted, so that the control unit adjusts the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power according to the target microphone transmission power in the optimal frequency modulation strategy.

[0091] The embodiments of the present invention provide an automatic frequency modulation method, device, electronic device and storage medium for a wireless microphone, which obtains data to be processed and determines a vector to be input corresponding to the data to be processed; performs vector analysis on the vector to be input based on a pre-constructed crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; determines an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and a reinforcement learning algorithm; and adjusts the current microphone transmission power of the wireless microphone to be adjusted to a target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy. In this technical solution, the wireless signal parameters and microphone parameters of the wireless microphone are analyzed by a pre-built crosstalk prediction model to obtain the crosstalk interference results corresponding to the wireless microphone at each data collection moment. Further, the reinforcement learning algorithm is combined on the basis of the wireless signal parameters and microphone parameters, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined according to the environmental state and model output of the reinforcement learning algorithm, and then the current microphone transmission power of the wireless microphone is automatically and dynamically adjusted based on the smooth transition technology until it is adjusted to the target microphone transmission power, so as to ensure that the wireless microphone will not have audio interruption problems during the frequency modulation process, and reduce the impact of the crosstalk interference problem on the wireless microphone. The problem that the wireless microphone is difficult to cope with the complex and changeable wireless signal environment when the wireless microphone is frequency modulated by simple signal monitoring or fixed regular microphone frequency in the prior art is solved, resulting in the problem of crosstalk interference in the use of the wireless microphone, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined in the complex and changeable wireless signal environment, and the wireless microphone is automatically frequency modulated based on the optimal frequency modulation strategy, so as to reduce the impact of crosstalk interference on the wireless microphone and improve the effect of poor information transmission quality during the use of the wireless microphone.

[0092] Embodiment 3

[0093] Figure 4 1 is a schematic diagram of the structure of an automatic frequency tuning device for a wireless microphone provided in an embodiment of the present invention. The device can be implemented by software and / or hardware and is generally integrated on any electronic device with network communication function, including but not limited to: servers, computers, personal digital assistants and other devices. Figure 4 As shown, the automatic frequency tuning device for a wireless microphone provided in this embodiment may include: a vector determination module 310 , an interference result determination module 320 , a strategy determination module 330 and a microphone frequency tuning module 340 .

[0094] The vector determination module 310 is used to obtain the data to be processed and determine the input vector corresponding to the data to be processed; wherein the data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to the wireless microphone to be adjusted;

[0095] The interference result determination module 320 is used to perform vector analysis on the input vector based on the pre-built crosstalk prediction model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk interference result is interference or no interference;

[0096] A strategy determination module 330, for determining an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm;

[0097] The microphone frequency modulation module 340 is used to adjust the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy.

[0098] The embodiments of the present invention provide an automatic frequency modulation method, device, electronic device and storage medium for a wireless microphone, which obtains data to be processed and determines a vector to be input corresponding to the data to be processed; performs vector analysis on the vector to be input based on a pre-constructed crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; determines an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and a reinforcement learning algorithm; and adjusts the current microphone transmission power of the wireless microphone to be adjusted to a target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy. In this technical solution, the wireless signal parameters and microphone parameters of the wireless microphone are analyzed by a pre-built crosstalk prediction model to obtain the crosstalk interference results corresponding to the wireless microphone at each data collection moment. Further, the reinforcement learning algorithm is combined on the basis of the wireless signal parameters and microphone parameters, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined according to the environmental state and model output of the reinforcement learning algorithm, and then the current microphone transmission power of the wireless microphone is automatically and dynamically adjusted based on the smooth transition technology until it is adjusted to the target microphone transmission power, so as to ensure that the wireless microphone will not have audio interruption problems during the frequency modulation process, and reduce the impact of the crosstalk interference problem on the wireless microphone. The problem that the wireless microphone is difficult to cope with the complex and changeable wireless signal environment when the wireless microphone is frequency modulated by simple signal monitoring or fixed regular microphone frequency in the prior art is solved, resulting in the problem of crosstalk interference in the use of the wireless microphone, and the optimal frequency modulation strategy corresponding to the wireless microphone is determined in the complex and changeable wireless signal environment, and the wireless microphone is automatically frequency modulated based on the optimal frequency modulation strategy, so as to reduce the impact of crosstalk interference on the wireless microphone and improve the effect of poor information transmission quality during the use of the wireless microphone.

[0099] On the basis of the above embodiment, optionally, the automatic frequency tuning device of the wireless microphone further includes: a data labeling module, which is used to obtain historical data to be processed at least one historical data collection moment, and to label each historical data to be processed to obtain a data labeling result; wherein the data labeling result is interference or no interference;

[0100] A prediction result determination module is used to input each historical data to be processed into a model to be trained, and predict the crosstalk interference result of each historical data to be processed based on the model to be trained to obtain a crosstalk interference prediction result; wherein the model to be trained is an initial crosstalk prediction model without parameter adjustment;

[0101] The interference result determination module is used to adjust the model parameters of the training model according to the data labeling results and the crosstalk interference prediction results to obtain the crosstalk prediction model, and to perform vector analysis on the input vector corresponding to the processed data based on the crosstalk prediction model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted.

[0102] On the basis of the above embodiment, optionally, the vector determination module includes: a normalization unit, which is used to perform data normalization processing on each group of data to be processed after data cleaning is performed on the data to be processed at each data collection moment;

[0103] The vector generating unit is used to generate the input vectors according to the time sequence from the data to be processed after the data normalization processing.

[0104] On the basis of the above embodiment, optionally, the interference result determination module includes: a to-be-used vector determination unit, configured to input the to-be-input vector into the LSTM model for feature extraction to obtain the to-be-used vector;

[0105] The crosstalk interference result determination unit is used to input the vector to be used into the SVM model to obtain the crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk prediction model is a combined model based on the LSTM model and the SVM model.

[0106] On the basis of the above embodiment, optionally, the strategy determination module includes: an environment state determination unit, which is used to define the environment state of the reinforcement learning algorithm based on the wireless signal parameters, microphone parameters and crosstalk interference results at the current data collection moment; wherein the microphone parameters include the current use frequency and microphone transmission power corresponding to the microphone to be adjusted;

[0107] An action space determination unit, used to define an action space of a reinforcement learning algorithm according to microphone parameters; wherein the action space includes specific execution actions of switching different usage frequencies of the microphone to be adjusted and microphone transmission power to different levels;

[0108] A reward value determination unit, used to determine a reward value corresponding to a specific execution action of the wireless microphone to be adjusted based on the environment state, the action space and the reward function in the reinforcement learning algorithm;

[0109] The strategy determination unit is used to optimize the current frequency modulation strategy of the wireless microphone to be adjusted based on the reward value to obtain the optimal frequency modulation strategy.

[0110] On the basis of the above embodiment, optionally, the microphone frequency modulation module includes: a power determination unit, which is used to send the optimal frequency modulation strategy to the wireless microphone to be adjusted, and determine the target microphone transmission power corresponding to the wireless microphone to be adjusted in the optimal frequency modulation strategy;

[0111] The microphone frequency modulation unit is used to adjust the current microphone transmission power of the microphone to be adjusted to the target microphone transmission power based on a dynamic power adjustment algorithm.

[0112] The automatic frequency tuning device for a wireless microphone provided in an embodiment of the present invention can execute the automatic frequency tuning method for a wireless microphone provided in any embodiment of the present invention described above, and has the corresponding functions and beneficial effects of executing the automatic frequency tuning method for a wireless microphone. For detailed processes, please refer to the relevant operations of the automatic frequency tuning method for a wireless microphone in the aforementioned embodiments.

[0113] Embodiment 4

[0114] Figure 5 1 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0115] like Figure 5As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0117] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the automatic frequency tuning method of a wireless microphone.

[0118] In some embodiments, the automatic frequency tuning method of the wireless microphone may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the automatic frequency tuning method of the wireless microphone described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the automatic frequency tuning method of the wireless microphone in any other appropriate manner (e.g., by means of firmware).

[0119] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0121] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0124] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0125] Embodiment 5

[0126] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the automatic frequency tuning method for a wireless microphone provided in any embodiment of the present application.

[0127] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0128] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic frequency modulation of a wireless microphone, characterized in that: The method comprises: Acquire data to be processed, and determine a vector to be input corresponding to the data to be processed; wherein the data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to the wireless microphone to be adjusted; Performing vector analysis on the input vector based on a pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk interference result is interference or no interference; Determine an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm; Based on the optimal frequency modulation strategy, the current microphone transmission power of the wireless microphone to be adjusted is adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy.

2. The method according to claim 1, characterized in that Before obtaining the data to be processed, the method further includes: Obtaining historical data to be processed at least at a historical data collection moment, and performing data annotation on each historical data to be processed to obtain a data annotation result; wherein the data annotation result is interference or no interference; Input each historical data to be processed into the model to be trained, and predict the crosstalk interference result of each historical data to be processed based on the model to be trained to obtain a crosstalk interference prediction result; wherein the model to be trained is an initial crosstalk prediction model without parameter adjustment; The model parameters of the model to be trained are adjusted according to the data labeling results and the cross-frequency interference prediction results to obtain a cross-frequency prediction model, and vector analysis is performed on the input vector corresponding to the data to be processed based on the cross-frequency prediction model to obtain the cross-frequency interference result corresponding to the wireless microphone to be adjusted.

3. The method according to claim 1, characterized in that The determining of the input vector corresponding to the data to be processed includes: After cleaning the data to be processed at each data collection moment, normalize each group of data to be processed; The data to be processed after data normalization is generated into input vectors in chronological order.

4. The method according to claim 1, characterized in that: The crosstalk prediction model is a combined model based on the LSTM model and the SVM model. The crosstalk prediction model based on the pre-built model performs vector analysis on the input vector to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted, including: Inputting the vector to be input into the LSTM model for feature extraction to obtain a vector to be used; The vector to be used is input into the SVM model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted.

5. The method according to claim 1, characterized in that The determining, based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm, an optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted includes: Defining the environmental state of the reinforcement learning algorithm based on the wireless signal parameters, microphone parameters and the crosstalk interference results at the current data collection moment; wherein the microphone parameters include the current use frequency and microphone transmission power corresponding to the microphone to be adjusted; Defining the action space of the reinforcement learning algorithm according to the microphone parameters; wherein the action space includes specific execution actions of switching different usage frequencies of the microphone to be adjusted and the microphone transmission power to different levels; Determine a reward value corresponding to a specific execution action currently performed by the wireless microphone to be adjusted based on the environmental state, the action space and a reward function in the reinforcement learning algorithm; The current frequency modulation strategy of the wireless microphone to be adjusted is optimized based on the reward value to obtain an optimal frequency modulation strategy.

6. The method according to claim 1, characterized in that The step of adjusting the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy includes: Sending the optimal frequency modulation strategy to the wireless microphone to be adjusted, and determining the target microphone transmission power corresponding to the wireless microphone to be adjusted in the optimal frequency modulation strategy; Based on a dynamic power adjustment algorithm, the current microphone transmission power of the microphone to be adjusted is adjusted to the target microphone transmission power.

7. An automatic frequency modulation device for a wireless microphone, characterized in that: The device comprises: A vector determination module, used to obtain data to be processed and determine a vector to be input corresponding to the data to be processed; wherein the data to be processed includes at least one wireless signal parameter at a data collection moment and a microphone parameter corresponding to a wireless microphone to be adjusted; An interference result determination module, used for performing vector analysis on the input vector based on a pre-built crosstalk prediction model to obtain a crosstalk interference result corresponding to the wireless microphone to be adjusted; wherein the crosstalk interference result is interference or no interference; A strategy determination module, used to determine the optimal frequency modulation strategy corresponding to the wireless microphone to be adjusted based on the data to be processed, the crosstalk interference result and the reinforcement learning algorithm; The microphone frequency modulation module is used to adjust the current microphone transmission power of the wireless microphone to be adjusted to the target microphone transmission power corresponding to the optimal frequency modulation strategy based on the optimal frequency modulation strategy.

8. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the automatic frequency tuning method for a wireless microphone as described in any one of claims 1-6.

9. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to execute the automatic frequency tuning method for a wireless microphone as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the automatic frequency tuning method of a wireless microphone according to any one of claims 1 to 6.

Images