Real-time Processing Method and System for Electroencephalogram Signals Based on Vagus Nerve Stimulation

Abstract

The present invention discloses a real-time processing method and system for electroencephalogram signals based on vagus nerve stimulation. The method includes: obtaining first-channel data of an electroencephalogram signal channel of a target user, and identifying the first-channel data according to a pre-trained recognition model to determine the status information of the target user; when it is determined that the target user has an abnormality according to the status information of the target user, determining a corresponding diagnosis and treatment strategy, where the diagnosis and treatment strategy includes stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period; applying a stimulation current according to the diagnosis and treatment strategy for stimulation, and obtaining second-channel data of the electroencephalogram signal channel of the target user during the stimulation period; performing user status analysis according to the second-channel data and the pre-trained recognition model to determine the diagnosis and treatment strategy for the next stimulation period. This solution can analyze and diagnose the electroencephalogram signals of users.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and more particularly to a real-time processing method and system for electroencephalogram (EEG) signals based on vagus nerve stimulation (VNS). Background Art

[0002] Brain diseases are difficult to detect and prone to sudden onset. For example, epilepsy is a serious neurological disease, and different types of epilepsy may correspond to different brain regions, with seizure manifestations being complex and diverse. As an important tool for recording brain activities, EEG signals are widely used in the detection of brain diseases.

[0003] Existing solutions usually monitor for abnormalities after obtaining EEG signals, and issue alerts if abnormalities occur, but do not form a diagnosis and treatment plan for the corresponding diseases. Summary of the Invention

[0004] The present invention provides a real-time processing method and system for EEG signals based on VNS, which can analyze and diagnose a user's EEG signals, and continuously diagnose based on the changes generated by the diagnosis and treatment.

[0005] To solve the above technical problems, the present invention is implemented as follows:

[0006] In a first aspect, the present application provides a real-time processing method for EEG signals based on VNS, the method comprising: obtaining first channel data of an EEG signal channel of a target user, and identifying the first channel data based on a pre-trained recognition model to determine the status information of the target user; when it is determined that the target user has an abnormality based on the status information of the target user, determining a corresponding diagnosis and treatment strategy, the diagnosis and treatment strategy including stimulation current information based on VNS, the stimulation current information including the magnitude of the stimulation current and the stimulation period; applying a stimulation current according to the diagnosis and treatment strategy for stimulation, and obtaining second channel data of the EEG signal channel of the target user during the stimulation period; analyzing the user status based on the second channel data and the pre-trained recognition model to determine the diagnosis and treatment strategy for the next stimulation period.

[0007] Preferably, the recognition model is obtained by training based on training data, and the method further includes a step of determining the training data: obtaining historical channel data of an EEG channel of a target user, and after performing data conversion on the historical channel data, obtaining first intermediate data; matching the first intermediate data with second intermediate data of multiple data providers to determine target intermediate data in the second intermediate data that matches the first intermediate data, the second intermediate data being obtained after data conversion of historical channel data of relevant users of the target user of the data provider; extracting the historical channel data corresponding to the target intermediate data to determine the training data for training the recognition model.

[0008] Preferably, the data conversion is used to divide the historical channel data into corresponding levels according to the corresponding level division rules, and replace them with corresponding numbers; after the data conversion of the historical channel data, the first intermediate data is obtained, including: sending the level division rules to the user side, and the level division rules include four groups of interval information to divide the historical channel data into four levels, and the four levels include the first level, the second level, the third level and the fourth level, and the first level, the second level, the third level and the fourth level are replaced by the numbers 0, 1, 2, and 3; the user side divides the historical channel data of the target user according to the level division rules and converts them into corresponding numbers to form the first intermediate data, which is uploaded to the server for analysis.

[0009] Preferably, the steps for the data provider to obtain the second intermediate data after data conversion of the historical channel data include: sending the level division rules to the data provider; the data provider divides the historical channel data of the relevant users of the target user locally according to the level division rules and converts them into corresponding numbers to form the second intermediate data, which is uploaded to the server for analysis.

[0010] Preferably, the steps for determining the relevant users of the target user include: statistically analyzing according to the first intermediate data of the target user to determine the data volume of each level of the target user in the level division rules as the first statistic; obtaining the data volume of each level of all users of each data provider in the level division rules as the second statistic; determining the difference between the first statistic and the second statistic, and screening out the relevant users of the target user from all users according to the difference threshold.

[0011] Preferably, the steps for determining the second statistic include: sending the screening division rules to the data provider, and the screening division rules include at least eight groups of interval information to divide the historical channel data into eight levels, and each group of interval information in the level division rules includes at least two groups of interval information of the screening division rules; the data provider divides the historical channel data of all users locally into the corresponding levels according to the screening division rules and counts the data volume corresponding to each level; receiving the data volume of each level corresponding to the screening division rules, and determining the data volume of each level in the level division rules according to the data volume of each level in the screening division rules to determine the second statistic.

[0012] Preferably, the extraction of the historical channel data corresponding to the target intermediate data to determine the training data includes: setting up a sandbox environment and obtaining the historical channel data corresponding to the target intermediate data in the sandbox environment; in the sandbox environment, performing similarity matching on the historical channel data of the target user and the historical channel data corresponding to the target intermediate data to determine the training data.

[0013] In a second aspect, the present application provides a real-time electroencephalogram (EEG) signal processing system based on vagus nerve stimulation. The system includes: a first data acquisition module configured to acquire first channel data of an EEG signal channel of a target user, and identify the state information of the target user by identifying the first channel data based on a pre-trained recognition model; a diagnosis and treatment strategy acquisition module configured to determine a corresponding diagnosis and treatment strategy when it is determined that the target user has an abnormality based on the state information of the target user. The diagnosis and treatment strategy includes stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period; a second data acquisition module configured to apply a stimulation current according to the diagnosis and treatment strategy and acquire second channel data of the EEG signal channel of the target user during the stimulation period; a second data analysis module configured to analyze the user state based on the second channel data and the pre-trained recognition model, and determine the diagnosis and treatment strategy for the next stimulation period.

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

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method as described in the first aspect is implemented.

[0016] The present application can be applied to the scenario of managing diseases of patients based on EEG signals. A personalized recognition model of the user can be pre-trained to identify the channel data of the user's EEG signal channel, and whether the user has an abnormality can be identified according to the channel data to form a diagnosis and treatment plan. The diagnosis and treatment strategy for the next stage can be adjusted according to whether the user's disease gradually improves or worsens after diagnosis and treatment, so as to treat the user. Specifically, this solution can acquire the historical data of the user, match similar users based on the historical data of the user, and then use the data of the user and related users to train the recognition model. After that, the first channel data of the user's EEG signal channel can be collected, and the first channel data can be identified based on the pre-trained recognition model to determine the state information of the user; when it is determined that the target user has an abnormality based on the state information of the target user, a corresponding diagnosis and treatment strategy is determined. The diagnosis and treatment strategy includes stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period; then, a stimulation current is applied according to the diagnosis and treatment strategy, and the second channel data of the EEG signal channel of the target user during the stimulation period is acquired; the user state is analyzed based on the second channel data and the pre-trained recognition model, and the diagnosis and treatment strategy for the next stimulation period is determined to form a continuous treatment for the user. Brief Description of the Drawings

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

[0018] Figure 1 is a schematic flowchart of real-time processing of electroencephalogram (EEG) signals based on vagus nerve stimulation in an embodiment of the present application;

[0019] Figure 2 is a schematic structural diagram of a real-time processing system of electroencephalogram (EEG) signals based on vagus nerve stimulation in an embodiment of the present application. Detailed Embodiments

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] The present application can be applied to the scenario of managing the diseases of patients based on electroencephalogram (EEG) signals. A personalized recognition model can be pre-trained for the user to recognize the channel data of the user's electroencephalogram signal channels, and whether the user has an abnormality can be recognized according to the channel data to form a diagnosis and treatment plan. Then, according to whether the user's disease gradually improves or worsens after diagnosis and treatment, the diagnosis and treatment strategy for the next stage can be adjusted, so as to treat the user. This solution provides a real-time processing system of electroencephalogram (EEG) signals based on vagus nerve stimulation. The system involves the user side, the data provider side, and the server side. The user side can provide historical data to the server side. The server side interacts with the data provider side based on the historical data to obtain users similar to the user side, so as to form training data and train the recognition model. Then, the server side deploys the recognition model to the user side to recognize the electroencephalogram signal of the user and perform corresponding diagnosis and treatment. Among them, the training data can include the signal data of multiple electroencephalogram signal channels and corresponding annotations (such as whether there is an abnormality and the corresponding disease). And the server side can match corresponding diagnosis and treatment strategies for the recognition results of the recognition model.

[0022] Specifically, this solution can obtain the historical data of the user, match similar users based on the historical data of the user, and then use the data of the user and related users to train an identification model. After that, it can collect the first-channel data of the user's electroencephalogram (EEG) signal channels, and identify the first-channel data according to the pre-trained identification model to determine the status information of the user. When it is determined that the target user has an abnormality based on the status information of the target user, a corresponding diagnosis and treatment strategy is determined. The diagnosis and treatment strategy includes the stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period. Then, a stimulation current is applied according to the diagnosis and treatment strategy, and the second-channel data of the target user's EEG signal channels during the stimulation period is obtained. The user status is analyzed based on the second-channel data and the pre-trained identification model to determine the diagnosis and treatment strategy for the next stimulation period, so as to form a continuous treatment for the user.

[0023] Specifically, the embodiment of the present application provides a real-time EEG signal processing method based on vagus nerve stimulation, as Figure 1 shown, the method includes:

[0024] Step 102: Obtain the first-channel data of the EEG signal channels of the target user, and identify the first-channel data according to the pre-trained identification model to determine the status information of the target user.

[0025] Step 104: When it is determined that the target user has an abnormality based on the status information of the target user, determine a corresponding diagnosis and treatment strategy. The diagnosis and treatment strategy includes the stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period.

[0026] Step 106: Apply a stimulation current according to the diagnosis and treatment strategy, and obtain the second-channel data of the EEG signal channels of the target user during the stimulation period.

[0027] Step 108: Analyze the user status based on the second-channel data and the pre-trained identification model to determine the diagnosis and treatment strategy for the next stimulation period.

[0028] This application can be applied to the scenario of managing patients' diseases based on electroencephalogram (EEG) signals. A personalized recognition model can be pre-trained to recognize the channel data of the user's EEG signal channels, and determine whether the user has an abnormality according to the channel data, form a diagnosis and treatment plan, and adjust the diagnosis and treatment strategy for the next stage according to whether the user's disease gradually improves or worsens after treatment, so as to treat the user. Specifically, this solution can obtain the user's historical data, match similar users based on the user's historical data, and then use the data of the user and related users to train the recognition model. After that, the first channel data of the user's EEG signal channels can be collected, and the first channel data can be recognized based on the pre-trained recognition model to determine the user's status information; when it is determined that the target user has an abnormality based on the status information of the target user, a corresponding diagnosis and treatment strategy is determined, and the diagnosis and treatment strategy includes the stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period; then, the stimulation current is applied according to the diagnosis and treatment strategy, and the second channel data of the target user's EEG signal channels during the stimulation period is obtained; the user status is analyzed based on the second channel data and the pre-trained recognition model to determine the diagnosis and treatment strategy for the next stimulation period, so as to form a continuous treatment for the user.

[0029] This solution can obtain the user's historical data, match similar users based on the user's historical data, and then use the data of the user and related users to train the recognition model. Compared with the solution of directly deploying a large model, the model deployed in this solution has fewer model parameters and is a recognition model suitable for the user's disease. The model in this solution can adopt a neural network model. Among them, in order to protect the data of the user and the data provider, this solution can perform data conversion before matching to determine the data of related users associated with the target user for training. Specifically, as an optional embodiment, the recognition model is obtained after being trained based on training data, and the method further includes the step of determining the training data: obtaining the historical channel data of the target user's EEG channels, and performing data conversion on the historical channel data to obtain the first intermediate data; matching the first intermediate data with the second intermediate data of multiple data providers to determine the target intermediate data that matches the first intermediate data, and the second intermediate data is obtained after being converted from the historical channel data of the related users of the target user of the data provider; extracting the historical channel data corresponding to the target intermediate data to determine the training data for training the recognition model.

[0030] Historical data is arranged in chronological order. This solution can classify each piece of historical data (historical channel data) of (both the user and the data provider) into corresponding levels, convert them into numbers, and form a digital string. Then, by simply matching whether the digital strings are the same or similar, it can be determined whether the user's historical data is similar to the data of the users of the data provider, and thus filter out the data that can be used for model training. Specifically, as an optional embodiment, the data conversion is used to classify the historical channel data into corresponding levels according to the corresponding level classification rules and replace them with corresponding numbers; after the data conversion of the historical channel data, the first intermediate data is obtained, including: sending the level classification rules to the user side. The level classification rules include four groups of interval information to classify the historical channel data into four levels. The four levels include the first level, the second level, the third level, and the fourth level, which are replaced by the numbers 0, 1, 2, and 3 respectively; the user side classifies the historical channel data of the target user according to the level classification rules and converts it into corresponding numbers to form the first intermediate data, which is uploaded to the server for analysis. As an optional embodiment, the steps for the data provider to obtain the second intermediate data after data conversion of the historical channel data include: sending the level classification rules to the data provider; the data provider classifies the historical channel data of the relevant users of the local target user according to the level classification rules and converts it into corresponding numbers to form the second intermediate data, which is uploaded to the server for analysis. By dividing the data into numbers from 0 to 3, two bytes can be used to transmit the data, and the amount of interactive data is small.

[0031] In addition, some data of the data provider is quite different from the user's data. To filter out this part of the data, this solution can count the data volume of each level in the digital string, such as counting the respective quantities corresponding to the numbers 0, 1, 2, and 3. Then analyze whether the quantity of the user is close to the quantity of the data of the data provider, and thus remove the data of the data provider that is quite different from the user's data. Specifically, as an optional embodiment, the steps to determine the relevant users of the target user include: performing statistics based on the first intermediate data of the target user to determine the data volume of each level of the target user in the level classification rules as the first statistic; obtaining the data volume of each level of all users of each data provider in the level classification rules as the second statistic; determining the difference between the first statistic and the second statistic, and determining and filtering out the relevant users of the target user from all users according to the difference threshold. The steps to determine the relevant users are completed before obtaining the second intermediate data.

[0032] In the statistical stage, this solution can divide the data of the data provider into more levels. Then, when matching other level division rules subsequently, the statistic can be directly obtained through the method of data combination. For example, if the level division rule is 0 - 3, it can be further divided into 8 levels (such as levels 4 - 11). As the screening division rule, level 0 corresponds to levels 4 and 5. Then, the data provider uploads the data volumes of 8 levels, and the server can combine the 8 levels to obtain the data volumes corresponding to 4 levels for matching. Specifically, as an optional embodiment, the steps of determining the second statistic include: sending the screening division rule to the data provider, where the screening division rule includes at least eight groups of interval information to divide the historical channel data into eight levels, and each group of interval information in the level division rule includes at least two groups of interval information of the screening division rule; the data provider divides the historical channel data of all local users into corresponding levels according to the screening division rule and counts the data volumes corresponding to each level; receiving the data volumes of each level corresponding to the screening division rule, and determining the data volumes of each level in the level division rule based on the data volumes of each level in the screening division rule to determine the second statistic.

[0033] After determining the target intermediate data corresponding to the user while protecting the data privacy of all parties, the original data can be obtained and matched in a sandbox. The sandbox is a secure environment that is not affected by the outside, thus ensuring data security. Specifically, as an optional embodiment, the extracting the historical channel data corresponding to the target intermediate data to determine the training data includes: setting up a sandbox environment and obtaining the historical channel data corresponding to the target intermediate data within the sandbox environment; within the sandbox environment, performing similarity matching on the historical channel data of the target user and the historical channel data corresponding to the target intermediate data to determine the training data.

[0034] Based on the above embodiments, an embodiment of the present application further provides a real-time electroencephalogram signal processing system based on vagus nerve stimulation, as Figure 2 shown, the system includes:

[0035] A first data acquisition module 202, configured to acquire the first channel data of the electroencephalogram signal channel of the target user and identify the status information of the target user according to a pre-trained recognition model.

[0036] A diagnosis and treatment strategy acquisition module 204, configured to determine a corresponding diagnosis and treatment strategy when it is determined that the target user has an abnormality according to the status information of the target user. The diagnosis and treatment strategy includes stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude and stimulation period of the stimulation current.

[0037] The second data acquisition module 206 is configured to apply a stimulation current according to a diagnosis and treatment strategy, and acquire second-channel data of the electroencephalogram signal channels of the target user during the stimulation period.

[0038] The second data analysis module 208 is configured to perform user state analysis based on the second-channel data and a pre-trained recognition model, and determine the diagnosis and treatment strategy for the next stimulation period.

[0039] The implementation manner of the embodiment of the present application is similar to that of the above method embodiment. The specific implementation manner can refer to the specific implementation manner of the above method, and will not be elaborated here.

[0040] The present application can be applied to the scenario of managing the diseases of patients based on electroencephalogram signals. A user-specific recognition model can be pre-trained to recognize the channel data of the user's electroencephalogram signal channels, and whether the user has an abnormality can be recognized according to the channel data to form a diagnosis and treatment plan. Then, according to whether the user's disease condition gradually improves or worsens after diagnosis and treatment, the diagnosis and treatment strategy for the next stage can be adjusted, so as to treat the user. Specifically, this solution can obtain the historical data of the user, match similar users based on the historical data of the user, and then use the data of the user and related users to train the recognition model. After that, the first-channel data of the electroencephalogram signal channels of the user can be collected, and the first-channel data can be recognized based on the pre-trained recognition model to determine the status information of the user. When it is determined that the target user has an abnormality based on the status information of the target user, the corresponding diagnosis and treatment strategy is determined. The diagnosis and treatment strategy includes the stimulation current information based on the vagus nerve stimulation technique, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period. Then, a stimulation current is applied according to the diagnosis and treatment strategy, and the second-channel data of the electroencephalogram signal channels of the target user during the stimulation period is acquired. User state analysis is performed based on the second-channel data and the pre-trained recognition model to determine the diagnosis and treatment strategy for the next stimulation period, so as to form a continuous treatment for the user.

[0041] Based on the above embodiments, the present application further provides an electronic device, including: 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 as described in the above embodiments.

[0042] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the above-described data processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0043] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.

[0044] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0045] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0046] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1The steps for the functions specified in one or more boxes.

[0047] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0048] 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.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A real-time EEG signal processing system based on vagus nerve stimulation, characterized in that: The real-time processing system for EEG signals based on vagus nerve stimulation comprises: A first data acquisition module is used to acquire first channel data of an EEG signal channel of a target user, and recognize the first channel data according to a pre-trained recognition model to determine the state information of the target user; A diagnosis and treatment strategy acquisition module, used to determine a corresponding diagnosis and treatment strategy when it is determined that the target user has an abnormality according to the state information of the target user, wherein the diagnosis and treatment strategy includes stimulation current information based on vagus nerve stimulation, and the stimulation current information includes the magnitude of the stimulation current and the stimulation period; The second data acquisition module is used to stimulate the target user by using the stimulation current according to the diagnosis and treatment strategy, and to obtain the second channel data of the EEG signal channel of the target user during the stimulation period; The second data analysis module is used to analyze the user status based on the second channel data and the pre-trained recognition model to determine the diagnosis and treatment strategy for the next stimulation period. The recognition model is obtained after training based on training data, and the real-time EEG signal processing system based on vagus nerve stimulation further determines the training data, including: Acquire historical channel data of the target user's EEG channel, and perform data conversion on the historical channel data to obtain first intermediate data; Matching the first intermediate data with the second intermediate data of multiple data providers, determining target intermediate data in the second intermediate data that matches the first intermediate data, the second intermediate data being obtained by converting the historical channel data of the relevant users of the target user of the data provider; Extract the historical channel data corresponding to the target intermediate data to determine the training data to train the recognition model, The data conversion is used to classify the historical channel data into corresponding levels according to corresponding level classification rules, and replace them with corresponding numbers; after the historical channel data is converted, the first intermediate data is obtained, including: Sending the level division rules to the user, the level division rules include four groups of interval information, so as to divide the historical channel data into four levels, the four levels include the first level, the second level, the third level and the fourth level, the first level, the second level, the third level and the fourth level are represented by the numbers 0, 1, 2, 3; The user side classifies the historical channel data of the target user according to the class classification rules and converts them into corresponding numbers to form the first intermediate data, which is then uploaded to the server side for analysis.

2. The real-time EEG signal processing system based on vagus nerve stimulation according to claim 1, characterized in that: After the data provider performs data conversion on the historical channel data, the second intermediate data is obtained, including: Sending grading rules to data providers; The data provider classifies the historical channel data of the local target user's related users according to the classification rules, and converts them into corresponding numbers to form the second intermediate data, which is then uploaded to the server for analysis.

3. The real-time EEG signal processing system based on vagus nerve stimulation according to claim 2, characterized in that: Identify relevant users of the target user, including: Performing statistics based on the first intermediate data of the target user to determine the data volume of each level of the target user in the level classification rule as the first statistical amount; Obtaining the data volume of all users of each data provider at each level in the level classification rule as a second statistic; The difference between the first statistic and the second statistic is determined, and users related to the target user are screened out from all users according to a difference threshold.

4. The real-time EEG signal processing system based on vagus nerve stimulation according to claim 3, characterized in that: Determine a second statistic, including: Sending a screening and division rule to a data provider, the screening and division rule including at least eight groups of interval information to divide the historical channel data into eight levels, each group of interval information in the level division rule including at least two groups of interval information of the screening and division rule; The data provider divides the historical channel data of all local users into corresponding levels according to the screening and division rules, and counts the data volume corresponding to each level; The data amount of each level corresponding to the screening and classification rule is received, and the data amount of each level in the classification rule is determined according to the data amount of each level in the screening and classification rule to determine the second statistic.

5. The real-time EEG signal processing system based on vagus nerve stimulation according to claim 4, characterized in that: The extracting historical channel data corresponding to the target intermediate data to determine the training data includes: Set up a sandbox environment and obtain historical channel data corresponding to the target intermediate data in the sandbox environment; In the sandbox environment, the historical channel data of the target user and the historical channel data corresponding to the target intermediate data are similarly matched to determine the training data.

Images