Bluetooth-based electroencephalogram signal processing method and system

Abstract

The invention discloses an electroencephalogram signal processing method and system based on Bluetooth, and the method comprises the steps: obtaining historical channel data and a labeling result of an electroencephalogram signal channel of a user, and building a pre-training model and a recognition model; deploying the pre-training model to a plurality of participants, and issuing historical channel data to the participants, so that the participants train the pre-training model based on local data of the participants, and a trained pre-training model is obtained; identifying the historical channel data based on the trained pre-training model at the participant to obtain an identification result; receiving an identification result uploaded by each participant, comparing the identification result with the labeling result, and determining a comparison result; and determining a training participant of the recognition model based on a comparison result, and training the recognition model based on local data of the training participant so as to deploy the trained recognition model to a recognition terminal of the user.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for processing electroencephalogram (EEG) signals based on Bluetooth. Background Art

[0002] Brain diseases are prone to sudden onset and difficult to detect in time. For example, epilepsy is a serious neurological disease. EEG signals, as an important tool for recording brain activity, are widely used in the detection of brain diseases.

[0003] Existing solutions usually adopt a general recognition model to identify the patient's EEG signals. It is impossible to train the model and identify it specifically based on the user's historical data, resulting in low recognition accuracy. Summary of the invention

[0004] The present invention provides an EEG signal processing method and system based on Bluetooth, which can train a model specifically according to the user's historical EEG data, and deploy the trained recognition model to the user's recognition terminal, so as to obtain and recognize the user's EEG signal based on Bluetooth communication, thereby improving the recognition accuracy.

[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0006] In the first aspect, the present application provides a Bluetooth-based EEG signal processing method, the method comprising: obtaining historical channel data of a user's EEG signal channel and the labeling results corresponding to the historical channel data, and establishing a pre-trained model and a recognition model; deploying the pre-trained model to multiple participants, and issuing the historical channel data to each participant, so that the participant trains the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant recognizes the historical channel data based on the trained pre-trained model to obtain a recognition result; receiving the recognition results uploaded by each participant, and comparing the recognition results with the labeling results to determine the comparison results; determining the training participant of the recognition model based on the comparison results, and training the recognition model based on the local data of the training participant, so that the trained recognition model is deployed to the user's recognition terminal, the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and performs recognition based on the trained recognition model.

[0007] Preferably, the sending of historical channel data to each participant includes: generating a target random number, and processing the historical channel data based on the target random number; adding a data identifier to the processed historical channel data; sending the processed historical channel data carrying the data identifier to each participant, so that the trained pre-trained model can restore the processed historical channel data based on the data identifier for identification.

[0008] Preferably, the generating of a target random number and processing the historical channel data based on the target random number; adding a data identifier to the processed historical channel data includes: generating a random number seed and a random batch, and generating a target random number based on the random batch and the random number seed; processing the historical channel data based on the target random number, and adding a data identifier to the processed historical channel data, the data identifier including the random batch; wherein the pre-trained model sent to the participant carries a random number seed to generate a target random number based on the random number seed and the random batch in the data identifier, so as to restore the historical channel data.

[0009] Preferably, the method of adding a data identifier to the processed historical channel data includes: generating a random difference amount for the target participant, generating a data identifier based on the random batch and the random difference amount, and adding a data identifier to the processed historical channel data; wherein the pre-trained model sent to the participant carries a random number seed and a random difference amount, so as to restore the random batch based on the data identifier and the random difference amount, and then generate a target random number based on the random number seed and the random batch to restore the historical channel data.

[0010] Preferably, the method further includes: receiving a trained pre-trained model uploaded by a participant; inputting historical channel data into the trained pre-trained model for recognition to obtain a center recognition result, and comparing the center recognition result with the labeling result to determine the comparison result.

[0011] Preferably, the method further includes: determining a numerical range corresponding to the historical channel data based on the historical channel data and the annotation results corresponding to the historical channel data; and generating extended channel data as the historical channel data based on the numerical range and the historical channel data.

[0012] Preferably, the training of the recognition model based on the local data of the training participants includes: deploying the recognition model to the training participants, and training the recognition model based on the local data of the training participants to obtain local parameters of the recognition model; receiving the local parameters of each training participant, and performing a global analysis to obtain global parameters; determining the parameter update information of each training participant based on the global parameters and sending it to each training participant to update the recognition model of the training participant for the next round of training until a trained recognition model is determined.

[0013] In the second aspect, the present application provides a Bluetooth-based EEG signal processing system, which includes: a historical data acquisition module, which is used to obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-trained model and a recognition model; a training model deployment module, which is used to deploy the pre-trained model to multiple participants, and send the historical channel data to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; a comparison result acquisition module, which is used to receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; a recognition model training module, which is used to determine the training participant of the recognition model based on the comparison result, and train the recognition model based on the local data of the training participant, so that the trained recognition model can be deployed to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and performs recognition based on the trained recognition model.

[0014] In a third aspect, the present application provides an electronic device comprising: a memory and at least one processor; the memory is used to store computer-executable instructions; the at least one processor is used to execute the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0016] This application can be applied in scenarios based on EEG signal recognition, for example, the user's EEG signal can be obtained through Bluetooth, and input into the trained recognition model for recognition processing to determine the user's status. This solution can select the data of the corresponding participants for model training based on the user's historical channel data, and deploy the trained model to the user's recognition terminal to perform EEG signal recognition. Specifically, this solution can obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-training model and a recognition model; the model size and complexity of the pre-training model are smaller than the size of the recognition model, and the pre-training model and the recognition model are both based on the user's EEG channel data for recognition to determine the user's status. The existing solution is to use a large number of participants' data for model training, but in this scenario, a large amount of irrelevant data will be mixed, resulting in problems such as excessive model parameters. This solution uses pre-training models to deploy to each participant, and screens the training participants of the recognition model according to the pre-training models trained by each participant, which can reduce the amount of training data and ensure recognition quality. Specifically, the pre-trained model can be deployed to multiple participants, and the historical channel data can be sent to each participant, so that the participant can train the pre-trained model based on the local data of the participant to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; determine the training participant of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participant, so that the trained recognition model can be deployed to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and recognizes based on the trained recognition model. Compared with the solution of adopting a general model, this solution can use the user's historical channel data to select data that is more suitable for the user for model training, and deploy the trained recognition model to the user's recognition terminal, so as to obtain the user's EEG signal based on Bluetooth communication and recognize it more accurately, thereby improving the recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0018] Figure 1 It is a flowchart of a method for processing EEG signals based on Bluetooth according to an embodiment of the present application;

[0019] Figure 2 It is a structural diagram of a Bluetooth-based EEG signal processing system according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] This application can be applied in scenarios based on EEG signal recognition, for example, the user's EEG signal can be obtained through Bluetooth, and input into the trained recognition model for recognition processing to determine the user's status. This solution can select the data of the corresponding participants for model training based on the user's historical channel data, and deploy the trained model to the user's recognition terminal to perform EEG signal recognition. Specifically, this solution can obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-training model and a recognition model; the model size and complexity of the pre-training model are smaller than the size of the recognition model, and the pre-training model and the recognition model are both based on the user's EEG channel data for recognition to determine the user's status. The existing solution is to use a large number of participants' data for model training, but in this scenario, a large amount of irrelevant data will be mixed, resulting in problems such as excessive model parameters. This solution uses pre-training models to deploy to each participant, and screens the training participants of the recognition model according to the pre-training models trained by each participant, which can reduce the amount of training data and ensure recognition quality. Specifically, the pre-trained model can be deployed to multiple participants, and the historical channel data can be sent to each participant, so that the participant can train the pre-trained model based on the local data of the participant to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; determine the training participant of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participant, so that the trained recognition model can be deployed to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and recognizes based on the trained recognition model. Compared with the solution of adopting a general model, this solution can use the user's historical channel data to select data that is more suitable for the user for model training, and deploy the trained recognition model to the user's recognition terminal, so as to obtain the user's EEG signal based on Bluetooth communication and recognize it more accurately, thereby improving the recognition accuracy.

[0022] Specifically, the present application embodiment provides a method for processing electroencephalogram signals based on Bluetooth, such as Figure 1 As shown, the method includes:

[0023] Step 102: Obtain historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-training model and a recognition model.

[0024] Step 104: deploy the pre-trained model to multiple participants, and send historical channel data to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant can identify the historical channel data based on the trained pre-trained model to obtain an identification result.

[0025] Step 106: Receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results.

[0026] Step 108: determine the training participants of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participants, so as to deploy the trained recognition model to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and performs recognition based on the trained recognition model.

[0027] This application can be applied in scenarios based on EEG signal recognition. For example, the user's EEG signal can be obtained through Bluetooth, and input into a trained recognition model for recognition processing to determine the user's status. This solution can select the data of the corresponding participants for model training based on the user's historical channel data, and deploy the trained model to the user's recognition terminal to perform EEG signal recognition. Specifically, this solution can obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-trained model and a recognition model. This solution uses the pre-trained model to deploy to each participant, and screens the training participants of the recognition model according to the pre-trained model trained by each participant, which can reduce the amount of training data and ensure recognition quality. Specifically, the pre-trained model can be deployed to multiple participants, and historical channel data can be sent to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; determine the training participant of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participant, so that the trained recognition model can be deployed to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and performs recognition based on the trained recognition model.

[0028] If the historical channel data is directly sent to each participant in plain text, each participant will obtain the plain text data, which may cause privacy leakage. Therefore, this solution can add random numbers to the historical channel data and configure the corresponding restoration processing for the pre-trained model. The pre-trained model can remove the random number before processing the data and identify it based on the restored data. Specifically, as an optional embodiment, the sending of historical channel data to each participant includes: generating a target random number, and processing the historical channel data based on the target random number; adding a data identifier to the processed historical channel data; sending the processed historical channel data carrying the data identifier to each participant, so that the trained pre-trained model can restore the processed historical channel data based on the data identifier and then identify it.

[0029] In this solution, multiple batches can be set for historical channel data, and each batch corresponds to a different random number. The random numbers of multiple batches can be generated based on the same random number seed. By generating different random numbers from different batches to process the data, the security of the data can be improved. Correspondingly, the random number seed can be added to the pre-trained model to restore the data in the pre-trained model. Specifically, as an optional embodiment, the target random number is generated, and the historical channel data is processed based on the target random number; a data identifier is added to the processed historical channel data, including: generating a random number seed and a random batch, and generating a target random number based on the random batch and the random number seed; the historical channel data is processed based on the target random number, and a data identifier is added to the processed historical channel data, and the data identifier includes a random batch; wherein the pre-trained model sent to the participant carries a random number seed to generate a target random number based on the random number seed and the random batch in the data identifier to restore the historical channel data.

[0030] For different participants, this solution can generate random difference amounts for random batches so that the data identifiers of the same data for different participants are different. When performing random batch restoration, the random batch can be restored based on the random number seed and random difference amount carried by the pre-trained model to generate a corresponding random number to restore the data. Specifically, as an optional embodiment, the data identifier is added to the processed historical channel data, including: generating a random difference amount for the target participant, generating a data identifier based on the random batch and the random difference amount, and adding a data identifier to the processed historical channel data; wherein the pre-trained model sent to the participant carries a random number seed and a random difference amount, so that after restoring the random batch based on the data identifier and the random difference amount, a target random number is generated based on the random number seed and the random batch to restore the historical channel data.

[0031] In addition to deploying historical channel data to participating parties for identification, this solution can also receive the trained pre-trained models uploaded by participating parties on the server side and perform identification. For untrusted participating parties, this solution can use the server side to complete the evaluation of the pre-trained model to determine whether to use the data of this participating party for training. Specifically, as an optional embodiment, the method further includes: receiving the trained pre-trained model uploaded by the participating party; inputting the historical channel data into the trained pre-trained model for identification to obtain a central identification result, and comparing the central identification result with the annotation result to determine the comparison result. This solution can also fluctuate the historical channel data within a numerical range to expand the data for identifying and evaluating a larger amount of data. Specifically, as an optional embodiment, the method further includes: determining the numerical range corresponding to the historical channel data according to the historical channel data and the annotation result corresponding to the historical channel data; generating augmented channel data as the historical channel data according to the numerical range and the historical channel data.

[0032] After screening out a small number of training participating parties from multiple participating parties, this solution can adopt the method of federated learning to train the identification model to protect the data security and model security of all parties. Specifically, as an optional embodiment, training the identification model based on the local data of the training participating parties includes: deploying the identification model to the training participating parties and training the identification model based on the local data of the training participating parties to obtain the local parameters of the identification model; receiving the local parameters of each training participating party and performing global analysis to obtain global parameters; determining the parameter update information of each training participating party according to the global parameters and sending it to each training participating party to update the identification model of the training participating party for the next round of training until the trained identification model is determined.

[0033] Based on the above embodiments, an embodiment of the present application further provides a brain-computer signal processing system based on Bluetooth, as Figure 2 shown, the system includes:

[0034] A historical data acquisition module 202, configured to acquire historical channel data of the brain-computer signal channels of the user and the annotation results corresponding to the historical channel data, and establish a pre-trained model and an identification model.

[0035] A training model deployment module 204, configured to deploy the pre-trained model to multiple participating parties and send the historical channel data to each participating party, so that the participating party trains the pre-trained model based on the local data of the participating party to obtain a trained pre-trained model; and the participating party performs identification on the historical channel data based on the trained pre-trained model to obtain an identification result.

[0036] The comparison result acquisition module 206 is used to receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results.

[0037] The recognition model training module 208 is used to determine the training participants of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participants, so as to deploy the trained recognition model to the user's recognition terminal. The recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth and performs recognition based on the trained recognition model.

[0038] The implementation of the embodiment of the present application is similar to the implementation of the embodiment of the method described above. The specific implementation can refer to the specific implementation of the method described above, which will not be repeated here.

[0039] This application can be applied in scenarios based on EEG signal recognition. For example, the user's EEG signal can be obtained through Bluetooth, and input into a trained recognition model for recognition processing to determine the user's status. This solution can select the data of the corresponding participants for model training based on the user's historical channel data, and deploy the trained model to the user's recognition terminal to perform EEG signal recognition. Specifically, this solution can obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-trained model and a recognition model. This solution uses the pre-trained model to deploy to each participant, and screens the training participants of the recognition model according to the pre-trained model trained by each participant, which can reduce the amount of training data and ensure recognition quality. Specifically, the pre-trained model can be deployed to multiple participants, and historical channel data can be sent to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; determine the training participant of the recognition model based on the comparison results, and train the recognition model based on the local data of the training participant, so that the trained recognition model can be deployed to the user's recognition terminal, and the recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth, and performs recognition based on the trained recognition model.

[0040] Based on the above embodiments, the present application also provides an electronic device, comprising: a memory and at least one processor; the memory is used to store computer execution instructions; the at least one processor is used to execute the computer execution instructions stored in the memory, so that the at least one processor executes the method described in the above embodiments.

[0041] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, each process of the above-mentioned data processing method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0042] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0043] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0044] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0046] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0047] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0048] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0049] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0050] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0051] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for processing electroencephalogram signals based on Bluetooth, characterized in that: The method comprises: Obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and establish a pre-training model and a recognition model; Deploy the pre-trained model to multiple participants, and send historical channel data to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and recognize the historical channel data based on the trained pre-trained model to obtain a recognition result. Receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; Based on the comparison results, the training participants of the recognition model are determined, and the recognition model is trained based on the local data of the training participants, so that the trained recognition model is deployed to the user's recognition terminal. The recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth and performs recognition based on the trained recognition model.

2. The method according to claim 1, characterized in that The sending of historical channel data to each participant includes: Generate a target random number, and process the historical channel data based on the target random number; add a data identifier to the processed historical channel data; The processed historical channel data carrying the data identifier is sent to each participant, so that the trained pre-trained model can restore the processed historical channel data based on the data identifier and then perform identification.

3. The method according to claim 2, characterized in that The target random number is generated, and the historical channel data is processed based on the target random number; Add data identifiers to the processed historical channel data, including: Generate a random number seed and a random batch, and generate a target random number based on the random batch and the random number seed; The historical channel data is processed based on the target random number, and a data identifier is added to the processed historical channel data, wherein the data identifier includes a random batch; wherein the pre-trained model sent to the participant carries a random number seed to generate a target random number based on the random number seed and the random batch in the data identifier to restore the historical channel data.

4. The method according to claim 3, characterized in that: The step of adding a data identifier to the processed historical channel data includes: Generate a random difference for the target participant, generate a data identifier based on the random batch and the random difference, and add a data identifier to the processed historical channel data; wherein the pre-trained model sent to the participant carries a random number seed and a random difference, and after restoring the random batch based on the data identifier and the random difference, generates a target random number based on the random number seed and the random batch to restore the historical channel data.

5. The method according to claim 1, characterized in that The method further comprises: Receive the trained pre-trained model uploaded by the participants; The historical channel data is input into the trained pre-trained model for recognition to obtain the center recognition result, and the center recognition result is compared with the labeling result to determine the comparison result.

6. The method according to claim 5, characterized in that The method further comprises: Determine the numerical range corresponding to the historical channel data according to the historical channel data and the annotation results corresponding to the historical channel data; Based on the numerical range and the historical channel data, the expanded channel data is generated as the historical channel data.

7. The method according to claim 1, characterized in that The method of training the recognition model based on the local data of the training participants includes: Deploy the recognition model to the training participant, and train the recognition model based on the local data of the training participant to obtain local parameters of the recognition model; Receive local parameters of each training participant and perform global analysis to obtain global parameters; The parameter update information of each training participant is determined based on the global parameters and sent to each training participant to update the recognition model of the training participant for the next round of training until a trained recognition model is determined.

8. A Bluetooth-based EEG signal processing system, characterized in that: The system comprises: A historical data acquisition module is used to obtain the historical channel data of the user's EEG signal channel and the annotation results corresponding to the historical channel data, and to establish a pre-training model and a recognition model; The training model deployment module is used to deploy the pre-trained model to multiple participants and send historical channel data to each participant, so that the participant can train the pre-trained model based on the participant's local data to obtain a trained pre-trained model; and the participant can recognize the historical channel data based on the trained pre-trained model to obtain a recognition result; The comparison result acquisition module is used to receive the recognition results uploaded by each participant, and compare the recognition results with the annotation results to determine the comparison results; The recognition model training module is used to determine the training participants of the recognition model based on the comparison results, and to train the recognition model based on the local data of the training participants, so as to deploy the trained recognition model to the user's recognition terminal. The recognition terminal receives the channel data of the user's EEG signal channel via Bluetooth and performs recognition based on the trained recognition model.

9. An electronic device, characterized in that: include: memory and at least one processor; The memory is used to store computer-executable instructions; The at least one processor is configured to execute computer-executable instructions stored in the memory, so that the at least one processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images