Upper computer system for brain-computer interface equipment

Abstract

The invention discloses an upper computer system for brain-computer interface equipment, which has the advantages of high real-time performance, friendly user interface, good expandability, high privacy and security, personalized customization, striking alarm prompt, data distribution to a cloud server and the like, and can better meet the requirements of users. According to the technical scheme, data transmitted by an implantable brain-computer interface device is obtained through a Bluetooth wireless communication module, the transmitted customized data format is analyzed and then converted into protobuf format data, the protobuf format data is encrypted through an AES algorithm and then transmitted to a data center module, the data center module distributes the transmitted data, and the data center module transmits the encrypted data to the implantable brain-computer interface device. Neural signal data are transmitted to the neural signal processing module, neural signals and other data are transmitted to the doctor control end module for data visualization and data storage, the data are uploaded to the server, and an alarm is given for sensor data.

Description

Technical Field

[0001] The present invention relates to the field of brain computer interface (BCI) technology, and in particular to a host computer system for collecting, processing and analyzing brain nerve signals and controlling external devices. Background Art

[0002] With the rapid development of science and technology, brain-computer interface (BCI) technology has become an important bridge connecting the human brain and external devices. The core of BCI technology is to collect brain nerve signals and process these signals through specific algorithms to ultimately control external devices. This technology has shown great application potential in many fields such as medical rehabilitation, human-computer interaction, and virtual reality.

[0003] In the existing BCI system, the host computer system plays a vital role. It is responsible for receiving, processing and analyzing the signals from the BCI device, and converting the user's intention into control commands to achieve control of external devices. However, despite the progress made in BCI technology, the existing host computer system still has some limitations, which restrict the application and development of BCI technology.

[0004] First, the real-time performance of existing systems is insufficient. Some systems have delays when processing EEG signals, which affects the user experience and control accuracy, especially in application scenarios with high real-time requirements, such as game control and mechanical exoskeleton control. Secondly, the user interface is not friendly. Some operating interfaces are complex and inconvenient to operate. Users need to undergo special training to use them proficiently, which limits their promotion and application. In addition, the scalability of existing systems is poor, and it is difficult to adapt to different types of EEG acquisition equipment and control tasks. Custom development is required for different application scenarios, which increases development costs and maintenance difficulties. Privacy and security are also problems faced by existing systems. With the popularization of BCI technology, data security and user privacy protection have become urgent issues to be solved. Existing systems have security risks in the process of data transmission and storage. Furthermore, the data is stored in a single disk. Existing systems generally store data on local disks and do not transmit it to cloud servers. The alarm prompts are not eye-catching and detailed, and users tend to ignore error and warning messages. Finally, there is no encryption during data transmission and storage, which increases the risk of data leakage. Summary of the invention

[0005] A brief summary of one or more aspects is given below to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceived aspects, and is neither intended to identify the key or critical elements of all aspects nor to define the scope of any or all aspects. Its only purpose is to give some concepts of one or more aspects in a simplified form as a prelude to a more detailed description that will be given later.

[0006] The purpose of the present invention is to solve the above-mentioned problems and provide a host computer system for brain-computer interface devices, which has the advantages of high real-time performance, user-friendly interface, good scalability, high privacy and security, personalized customization, eye-catching alarm prompts, and data storage on cloud servers, which can better meet the needs of users.

[0007] The technical solution of the present invention is as follows: The present invention discloses a host computer system for a brain-computer interface device, including a user login module, a device connection module, a data center module, a signal processing module, a device management module, a signal monitoring module, and a clinical management module, wherein:

[0008] User login module, used for the management of the security permissions of the host computer system;

[0009] Device connection module, used for wireless communication, custom message format parsing, protobuf structure data conversion and data encryption and decryption;

[0010] Data center module, used to realize complex communication requirements between modules;

[0011] Signal processing module for neural signal monitoring and decoding of brain-computer interface devices;

[0012] A device management module is used to control the implantable brain-computer interface device and visualize the sensor data inside the brain-computer interface device. The device management module transmits control instruction data to the data center module;

[0013] Signal monitoring module, used to display the neural activity signals of the cerebral cortex or deep structures in real time;

[0014] The clinical management module is used to view, add and modify patient information and bind patient and device information.

[0015] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the device connection module is configured to perform the following processing: first, the device connection module scans the Bluetooth device, and after finding the Bluetooth device name, it connects to the Bluetooth device and establishes wireless communication to receive and send data. The received data is in a custom message data format, and the received data is parsed accordingly according to the rules, wherein the received data includes neural signal data, impedance data, and sensor data. The parsed data is converted into protobuf structure data and then encrypted with the AES algorithm. Finally, the encrypted protobuf structure data is transmitted to the data center module, wherein the communication method between the device connection module and the data center module is an inter-process named pipe method.

[0016] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the data center module corresponds to the cross-process communication scenario, and uses named pipes, and corresponds to the cross-device communication scenario, and uses TCP. All independent modules establish a fixed named pipe with the data center module. At the same time, a TCP pipe is established between the data center module of the doctor-side software and the data center module of the patient-side software. No named pipe or TCP pipe connection will be established between all modules. The data center module acts as the central scheduling and distribution function of the data to realize the complex communication requirements between modules, and the data center module is programmed in the rust language.

[0017] According to one embodiment of the host computer system for a brain-computer interface device of the present invention, the signal processing module is configured to perform the following processing: ensuring the validity of the data by continuously monitoring the quality of neural signals of each channel; the monitoring process further includes: comparing the average firing rate of the channel over a period of time with historical data of a known normal proportion range, and automatically triggering an alarm prompt if it is detected that the firing rate of one or some channels exceeds the preset normal proportion range.

[0018] According to one embodiment of the host computer system for brain-computer interface devices of the present invention, the signal processing module also integrates a real-time neural decoding model training and deployment system, which works closely with the brain control calibration program on the patient side. During the first use or regular calibration, data of a series of standardized tasks completed by the user are collected and preprocessed. The preprocessed collected data is used to train a personalized decoding model based on an artificial neural network, Kalman filter or hidden Markov model. During the model training process, the collected data is used to adjust the model parameters, and the prediction error is minimized by the back propagation algorithm and the gradient descent optimization method. After the model training is completed, it is verified on the verification set. After verification, it is deployed in actual applications to realize real-time decoding of the user's brain signals and convert them into corresponding computer instructions.

[0019] According to an embodiment of the host computer system for brain-computer interface devices of the present invention, the device management module is configured to perform the following processing: the information displayed by the internal sensors of the brain-computer interface device includes waveform display of head-end device ambient temperature, head-end device ambient humidity, chest-end device ambient temperature, chest-end device ambient humidity, chest-end battery power, real-time label display of head-end device ambient temperature, head-end device ambient humidity, chest-end device ambient temperature, chest-end device ambient humidity, chest-end battery power, chest-end battery life, and chest-end battery charging status; the device management module displays or hides the corresponding waveform graph by clicking on the legend on the display interface, and displays the coordinate values ​​of the X and Y axes in real time when the cursor moves on the waveform line on the drawing interface, and sets the display amplitude to change the Y-axis display coordinate range; the device control functions in the device management module include device startup, device shutdown, electrode group selection, electrode group switching, neuron discharge output, impedance measurement, and internal emergency shutdown alarm of the device. Query and modify the alarm threshold parameters. Set the head-end device temperature, head-end device humidity, chest-end device temperature, chest-end device humidity and chest-end battery power thresholds by clicking the corresponding buttons, selection boxes and input boxes. Complete the alarm threshold parameter setting function after clicking the Set Alarm Threshold Parameters button; the single-channel selection page on the display interface of the device management module has multiple options. Click one of the buttons to complete the switching of the single channel. On the filter coefficient query and setting page, click the Query Filter Parameters button to return the current filter parameters to be displayed in the text box below. Set the corresponding values ​​of different filters in the text box to complete the filter coefficient setting. On the neuron discharge threshold query and setting page, first select the channel number, and then click the Query Neuron Discharge Threshold button. It will return to the current channel number under the multiple channel threshold parameters displayed in the text box below. Complete the neuron discharge threshold setting function by selecting the channel number and modifying the corresponding thresholds of multiple channels.

[0020] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the host computer system further includes:

[0021] The impedance query module is used to measure the impedance information of the electrodes in the current device and to plot the single-day historical impedance information within a given threshold in the form of a graph.

[0022] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the host computer system further includes:

[0023] Physiological parameter module, used to visualize intracranial oxygen partial pressure and intracranial temperature data.

[0024] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the host computer system further includes:

[0025] The file interaction module is used to upload local data files to the remote server, and query and download remote server files.

[0026] According to an embodiment of the host computer system for a brain-computer interface device of the present invention, the host computer system further includes:

[0027] The alarm prompt module is used to issue an alarm and prompt when the sensor parameters exceed the threshold.

[0028] Compared with the prior art, the present invention has the following beneficial effects: the present invention obtains the data transmitted by the implantable brain-computer interface device through the Bluetooth wireless communication module, parses the transmitted custom data format, converts it into protobuf format data, and then encrypts the protobuf format data with the AES algorithm, and then transmits it to the data center module. The data center distributes the incoming data, transmits the neural signal data to the neural signal processing module, transmits the neural signal and other data to the doctor control end module for data visualization, saves the data on the disk, uploads the data to the server, and alarms the sensor data. Overall, compared with the traditional technology, the advantages are: wireless communication, high real-time performance, user-friendly interface, good architecture scalability, high privacy and security, personalized customization, eye-catching alarms and prompts, and data is stored on the cloud server, which can better meet the needs of users. It is not only suitable for the field of medical rehabilitation, such as helping paralyzed patients to move the cursor with brain control, but also widely used in human-computer interaction, virtual reality, education and training, military science and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above features and advantages of the present invention can be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or features may have the same or similar reference numerals.

[0030] Figure 1A and 1B A schematic diagram of an embodiment of a host computer system for a brain-computer interface device of the present invention is shown.

[0031] Figure 2 Shows Figure 1A A schematic diagram of the operation flow of the device connection module in the system embodiment shown.

[0032] Figure 3A Shows Figure 1A A schematic diagram of a demonstration example of the main interface of the device management module in the system embodiment shown.

[0033] Figure 3B Shows Figure 1AA schematic diagram of a demonstration example of a device control page and a channel selection page of a device management module in the system embodiment shown.

[0034] Figure 3C Shows Figure 1A The diagram is a schematic diagram of demonstration examples of filter setting and query page and threshold setting and query page of the device management module in the system embodiment shown.

[0035] Figure 4A Shows Figure 1A A schematic diagram of a demonstration example of a clinical information management page of a clinical management module in the illustrated system embodiment.

[0036] Figure 4B Shows Figure 1A The schematic diagram of the demonstration example of adding and modifying patient information in the clinical management module in the system embodiment shown.

[0037] Figure 5 Shows Figure 1A A schematic diagram of an example of electrode impedance measurement and statistical demonstration of the impedance query module in the system embodiment is shown.

[0038] Figure 6 Shows Figure 1A A schematic diagram of a demonstration example of file interaction of a file interaction module in the system embodiment shown. DETAILED DESCRIPTION

[0039] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. Note that the aspects described below in conjunction with the accompanying drawings and specific embodiments are only exemplary and should not be construed as limiting the scope of protection of the present invention in any way.

[0040] Figure 1A and 1B The principle of an embodiment of the host computer system for a brain-computer interface device of the present invention is shown. Figure 1A and 1B The system of this embodiment includes the following modules: user login module, device connection module, data center module, signal processing module, device management module, clinical management module, physiological parameter module, impedance query module, file interaction module, signal monitoring module, and alarm prompt module.

[0041] The user login module is used for the management of the security permissions of the host computer system. Furthermore, the user login module is configured to perform the following processing: when the user logs in, an interface is provided for the user to input the user name and password, and an interface is provided for the user to input the content displayed in the verification code box. The content displayed in the verification code is composed of 5 characters composed of numbers and uppercase and lowercase English letters. The difference in uppercase and lowercase letters can be ignored when entering. The verification code is time-limited and is valid within 5 minutes of being generated. Click the verification code refresh button to reload the verification code. When the user enters the wrong user name, password and verification code, different message boxes will pop up to prompt.

[0042] The user login module uses scientific permission authentication design to ensure the security of the system, improve the user login experience, prevent illegal access, and lay a solid foundation for the security, stability and user management of the entire host computer system.

[0043] The device connection module is used for wireless communication, custom message format parsing, protobuf structure data conversion and data encryption and decryption. For further information, refer to Figure 2 As shown, the device connection module is configured to perform the following processing: First, the device connection module scans the Bluetooth device, connects the Bluetooth device after finding the Bluetooth device name, and establishes wireless communication. At this time, data can be received and sent. The received data is in a custom message data format. The received data is parsed accordingly according to the rules. These data include neural signal data, impedance data, sensor data, etc. After converting the parsed data into protobuf structure data, protobuf is a data serialization protocol developed by Google that can efficiently store and transmit structured data. Its advantage lies in the high efficiency and compactness of its binary format, which is particularly suitable for network communication and data storage. In the specific conversion process, first define the data structure corresponding to the received data in protobuf, including field type and field number; then map the parsed data to the data structure defined by protobuf to ensure that the corresponding relationship of the data is correct; then use the serialization tool provided by the protobuf library to convert the mapped data structure into the binary format of protobuf. Finally, the AES (Advanced Encryption Standard) algorithm is used for encryption, and the key length is selected as 256 bits. Finally, the encrypted protobuf structure data is transmitted to the data center module. The communication method between the device connection module and the data center module is the inter-process named pipe method. Named pipe is an inter-process communication mechanism that allows different processes to transmit data through a named pipe. This communication method is relatively safe because it limits the scope of data transmission, and only authorized processes can access this named pipe.

[0044] The device connection module achieves efficient and reliable data collection, analysis and transmission through wireless communication and data security processing, providing a solid technical foundation for subsequent data analysis, processing and display. At the same time, through high-security and standardized design, it improves the system's adaptability and user data protection capabilities.

[0045] The data center module is used to realize the complex communication requirements between modules. Furthermore, the data center module is configured to perform the following processing: the data center module corresponds to the cross-process communication scenario, using named pipes, and corresponds to the cross-device communication scenario, using TCP. All independent modules establish a fixed named pipe with the data center module. At the same time, the data center module of the doctor-side software establishes a TCP pipe with the data center module of the patient-side software (across devices), and no named pipe or TCP pipe connection is established between all modules. Finally, the data center module acts as the central scheduling and distribution function of the data to realize the complex communication requirements between modules.

[0046] The data center module is programmed in Rust language, which has high concurrency and real-time performance. Rust language effectively prevents data competition and other common concurrency errors through its ownership and borrowing mechanisms, thereby improving the concurrency performance of the data center module. This mechanism ensures that at any time, the data can only have one mutable reference or multiple immutable references, avoiding race conditions caused by multiple threads modifying the same data at the same time. Rust's asynchronous programming model (async / await) enables the data center module to handle a large number of concurrent I / O operations without blocking threads, which is particularly important for brain-computer interface application scenarios that require real-time response. Asynchronous programming allows threads to be released to handle other tasks while waiting for I / O operations to complete, thereby improving the overall response speed and throughput. The communication scheme of the present invention significantly optimizes the utilization of communication resources through the introduction of the data center module, reduces the complexity and operating overhead of the system, and improves the stability, security and scalability of the system. In the brain-computer interface application scenario of multiple modules and multiple devices, the scheme provides strong technical support for efficient and reliable cross-process and cross-device data communication.

[0047] The signal processing module is used for neural signal monitoring and decoding of brain-computer interface devices. Furthermore, the signal processing module is configured to perform the following processing: first, the validity of the data is ensured by continuously monitoring the quality of neural signals of each channel (i.e., receiving all channels of the implanted brain-computer interface device). Specifically, the system will compare the average firing rate of the channel over a period of time with the historical data of the known normal ratio range. If the firing rate of one or some channels is detected to exceed the preset normal ratio range, the system will automatically trigger an alarm prompt to remind the operator to pay attention to possible signal quality problems. In addition, the signal processing module also integrates a real-time neural decoding model training and deployment system that can work closely with the brain control calibration program on the patient side. During initial use or regular calibration, the user needs to complete a series of standardized tasks, such as controlling the cursor movement on the screen through mental imagination, simulating mouse clicks, and other operations. The data of these tasks will be collected and preprocessed, such as denoising, normalization, filtering, etc., to improve data quality and reduce the complexity of model training. The preprocessed collected data is used to train a personalized decoding model based on artificial neural network, Kalman filter or hidden Markov model. The definition of the model structure includes selecting the appropriate network layer, number of neurons, activation function, etc. During the model training process, the collected data is used to adjust the model parameters to minimize the prediction error, which is usually achieved through the back propagation algorithm and gradient descent optimization method. In the training process, the data is divided into training set, validation set and test set, where the training set is used for model learning, the validation set is used to adjust the hyperparameters, and the test set is used to evaluate the model performance. Once the model training is completed, the model needs to be verified on the validation set to evaluate its generalization ability. After passing the verification, it is deployed in actual applications to achieve real-time decoding of the user's brain signals and convert them into corresponding computer instructions, such as moving the mouse, clicking, double-clicking, etc., so that the user can efficiently control the computer interface with only thinking. The data center module transmits the neural signal data to the signal processing module. The communication method between them is the named pipe method between processes, and the communication data format is protobuf.

[0048] The signal processing module achieves real-time conversion of brain signals to computer instructions through efficient signal quality monitoring and accurate decoding model training. This not only improves the reliability and availability of the brain-computer interface system, but also provides users with an innovative and efficient human-computer interaction method, which has important application value in the fields of medical rehabilitation, assistive technology and human-computer collaboration.

[0049] The device management module is used to control the implantable brain-computer interface device and visualize the sensor data inside the brain-computer interface device. Furthermore, the device management module is configured to perform the following processing: the information displayed by the internal sensors of the brain-computer interface device includes waveform display of the head-end device ambient temperature, the head-end device ambient humidity, the chest-end device ambient temperature, the chest-end device ambient humidity, and the chest-end battery power, and also includes real-time label display of the head-end device ambient temperature, the head-end device ambient humidity, the chest-end device ambient temperature, the chest-end device ambient humidity, the chest-end battery power, the chest-end battery life, and the chest-end battery charging status. Figures 3A-3C As shown, by clicking on the legend, the corresponding waveform can be displayed or hidden. When the cursor moves on the waveform line in the drawing interface, the coordinate values ​​of the X and Y axes will be displayed in real time. By setting the display amplitude, the Y axis display coordinate range can be changed. The device control functions in the device management module include device startup, device shutdown, electrode group selection, electrode group switching, Spike (neuron discharge) output, impedance measurement, and query and modification of the device internal emergency shutdown alarm threshold parameter. By clicking on the corresponding buttons, selection boxes and input boxes, the head-end device temperature, head-end device humidity, chest-end device temperature, chest-end device humidity and chest-end battery power thresholds can be set. Among them, the input range of the head-end and chest-end device temperature is -40 to 125, the input range of the head-end and chest-end device humidity is 0 to 100, and the input range of the battery power lower limit is 0 to 100. If the input value exceeds the above range, the input is invalid. After clicking the Set Alarm Threshold Parameters button, the alarm threshold parameter setting function can be completed. There are 256 options in the single channel selection page, ranging from 0 to 255. Clicking one of the buttons will switch the single channel. On the filter coefficient query and setting page, click the query filter parameter button, and the current filter parameters will be returned and displayed in the text box below. After setting the corresponding values ​​of filter 1 (Filter1), Filter2, Filter3, Filter4, Filter5, Filter6, Filter7, and Filter8, click the set filter parameter button to complete the filter coefficient setting. The input box range of Filter1 to Filter8 is limited to decimal integers -2048 to 2047. If it exceeds this range, the input is invalid. On the spike threshold query and setting page, first select the 8 channel sequence number (0 to 31), and then click the query spike threshold button, and the 8 channel threshold parameters under the current 8 channel sequence number will be returned and displayed in the text box below. The 8 channel sequence number means that only 8 channels of spike thresholds are set each time, ranging from 0 to 31, corresponding to channels 0 to 255. After selecting the 8 channel numbers, modify the thresholds corresponding to the 8 channels, and then click the Set Spike Threshold button to complete the Spike threshold setting function. The device management module transmits control command data to the data center module.

[0050] The device management module provides real-time monitoring and visualization of device sensor data, refined device control, security assurance, personalized parameter configuration, data recording and analysis.

[0051] The clinical management module is used to view, add and modify patient information and bind patient and device information. Further, the clinical management module performs the following processing: The clinical information management interface is as follows: Figure 4A , 4B As shown, the left side of the upper half of the interface is the patient information table, and the upper right side is the patient details page, which is used to display the detailed information of a single patient. The lower right side of the interface is the patient information operation button group, including add, modify, refresh / return list buttons. The left side of the lower half of the interface is the implanted brain-computer interface device information display, status query and display, and the right side is the patient and device information binding input box and binding button. The patient information table on the left side of the upper half of the interface displays the patient information of the hospital to which the current doctor belongs, including 4 items: scientific research number, age, gender, and enrollment time. There is a vertical scroll bar on the right side of the patient information table. Drag the scroll bar to scroll the contents in the table. If the patient bound to the device connected to the current program exists in this patient information table, the patient information will be displayed in red. The patient details page on the upper right side of the upper half of the interface displays detailed information about a single patient, including research number, age, gender, enrollment time, handedness, and medical history. Handedness usually refers to the hand that a person mainly uses in daily life, that is, the "dominant hand". Most people are right-handed, that is, they are used to using their right hand to do most fine movements and tasks (such as writing, eating, etc.), and their left hand is used as a supporting hand. On the contrary, some people are left-handed and mainly use their left hand. Click on any item in the above patient information table to display the detailed information of the corresponding patient in the patient details page. When the patient information is not displayed in the patient information table or any item is not selected, the patient details page will display nothing.

[0052] There is a button group at the bottom right of the upper part of the interface, including query, add, modify and refresh / return list buttons. After clicking the add button, the clinical management module will pop up a patient information addition input box, such as Figure 4B As shown. Users can fill in the research number, age, gender, handedness, enrollment time and past medical history time by themselves, without filling in the patient number (the patient number is a 36-bit UUID number automatically assigned by the server). Click OK to complete the addition of patient information. Select the item to be modified in the table, and then click the Modify button. The clinical management module pops up a patient information modification input box, such as Figure 4B As shown. Users can modify age, gender, handedness, enrollment time and medical history, but cannot modify patient number and research number. Click OK to complete the modification of patient information.

[0053] The clinical management module achieves efficient management, query and maintenance of patient and device information through reasonable interface layout and functional design, which not only meets the daily clinical management needs of doctors, but also improves the efficiency of associating patient and device information, providing important technical support for clinical work.

[0054] The impedance query module is used to measure the impedance information of the electrodes in the current device, i.e., the brain-computer interface device implanted in the brain, and to plot the single-day historical impedance information within a given threshold in the form of a graph. Further, the impedance query module is configured to perform the following processing: Figure 5 As shown in the figure, the left side of the interface is the current impedance measurement result display page, and the right side is the single-day impedance condition query and display page. The current impedance measurement result display page contains the electrode channel group information and all electrode numbers and impedance values ​​in the channel group. The top of the single-day impedance condition query and display page is the condition query input box, and the lower half is the graphic display box. From left to right in the condition query input box are the channel group selection box, the lower threshold input box, the upper threshold input box, the impedance query date selection box, and the impedance query button. Click the "Impedance Query" button, and the program will automatically search for historical impedance measurement files that meet the query conditions in this disk according to the currently set impedance file save path, device number information, and the above query conditions. Subsequently, the program reads the historical impedance measurement file, and counts the number of electrodes whose impedance is within the range of the upper and lower impedance limits in each impedance measurement, and displays it in the form of a bar chart. The horizontal axis of the bar is the time of each measurement, and the vertical axis is the number of electrode channels.

[0055] The impedance query module provides users with a comprehensive monitoring and visualization tool for impedance data by combining real-time measurement and conditional query. The module can not only quickly present the current device impedance status, but also support flexible screening and analysis of historical data, providing strong support for electrode performance evaluation, equipment maintenance and anomaly detection, and significantly improving the reliability and user experience of the brain-computer interface system.

[0056] The signal monitoring module is used to display the neural activity signals of the cerebral cortex or deep structures in real time. Furthermore, the signal monitoring module is configured to perform the following processing: using Qpainter (Qpainter is a core graphics class in Qt) in Qt (Qt is a cross-platform C++ graphical user interface library) to depict the acquired neural data, draw it into a spike event grid chart and a channel firing rate chart, and then use the Qchart library in Qt (Qchart library is a module for data visualization in Qt, which provides a series of chart types, such as line charts, bar charts, pie charts, etc., suitable for various application scenarios that require data visualization) to draw the original electrophysiological seat number trajectory chart.

[0057] Specifically, in the process of using QPainter to draw the spike event grid and channel firing rate graph, in the paintEvent function of the signal monitoring module, you first need to create a QPainter object, which will be used for subsequent drawing operations, and then set the brush, pen and other properties through the QPainter object to prepare for drawing, and then use the drawRect function to draw a rectangular grid representing the spike event. Each rectangle represents a spike event, and the position and size are determined according to the neural data. Finally, use the drawText function to draw text representing the channel firing rate in the chart or use drawPie to draw a pie chart to represent the firing rate ratio of each channel.

[0058] Specifically, in the process of using QChart to draw the original electrophysiological seat number trajectory diagram, first introduce the QChart module into the project, ensure that the reference of QtCharts is added to the .pro file, and then create a QChartView object to display the QChart. Subsequently, according to the data type that needs to be displayed, create the corresponding sequence (such as QLineSeries, QSplineSeries, etc.), and then use Qt's timer function (QTimer) to regularly generate and add new data to the sequence to achieve dynamic effects. After that, ensure that when new data is added, the chart can be automatically redrawn to maintain a smooth user experience. Finally, support basic user interaction functions, such as adjusting the refresh rate or viewing data for a specific time period.

[0059] The signal monitoring module provides multi-dimensional neural signal visualization capabilities through real-time dynamic spike event grid diagrams, channel firing rate diagrams, and original trajectory diagrams. The signal monitoring module not only enhances the user's intuitive perception of neural activity, but also provides solid data support for signal decoding, pattern recognition, and clinical applications of the brain-computer interface system, significantly improving the system's analytical capabilities and practicality.

[0060] The physiological parameter module is used to realize the visualization of intracranial oxygen partial pressure and intracranial temperature data. Further, the physiological parameter module is configured to perform the following processing: real-time dynamic display of the waveform of the intracranial sensor data change, which can display up to 120 sampling points, and the specific coordinate value can be displayed when the cursor stays on the waveform line, and the right side monitors the numerical changes of intracranial oxygen partial pressure and intracranial temperature in real time, for example, using a label of one color to represent the intracranial temperature and another color label to represent the intracranial oxygen partial pressure.

[0061] The physiological parameter module provides an accurate and intuitive data monitoring tool for intracranial oxygen partial pressure and temperature through the combination of real-time dynamic waveform and numerical display. The module enhances data interactivity, improves user experience, and provides strong support for abnormal analysis and problem handling, ensuring the efficiency and reliability of the brain-computer interface system in clinical applications.

[0062] The file interaction module is used to upload local data files to the remote server, query and download remote server files. Further, the file interaction module is configured to perform the following processing: Figure 6 As shown in the figure, in the upper part of the interface, click the "Start automatic data upload" button in the "File upload" part. This program will run a file synchronization process with a UI interface in a separate form from the process, which is used to upload the data files of the device currently connected to the program to the remote server. The lower part of the interface is the file download function page. After this interface is opened, the research number column automatically displays the research number of the patient to which the currently logged-in doctor belongs and the number of the device bound to the patient. In the file download page, you can select the patient, the device implanted by the patient, the file type and the query date as the conditions for file query. After clicking the "File Query" button, the program sends these query conditions to the remote server, queries the remote server for file information that meets the conditions and returns it, and finally displays the number of files that meet the query conditions in the text box. The program will save the latest file query results by default, and the query results are valid for 20 minutes. Click the "File Download" button, and the program will download all files involved in the latest query results to the specified path. The program will download files in the background, and a message box will pop up to notify the user when all files are downloaded.

[0063] File interaction module data backup and sharing, remote access and download, data management and query.

[0064] The alarm prompt module is used to send out alarms and prompts when the sensor parameters exceed the threshold. Furthermore, the alarm prompt module is configured to perform the following processing: when the head-end device temperature, head-end device humidity, chest-end device temperature, chest-end device humidity, chest-end battery power and life, intracranial temperature, and intracranial oxygen partial pressure exceed or fall below the threshold, an alarm prompt will be issued. The alarm information will be displayed in the status bar, and the alarm method is to remind the user by flashing the Alarm log bar.

[0065] The alarm prompt module ensures the operation safety of the brain-computer interface device and the user's convenience through real-time monitoring and effective alarm mechanism. Its intuitive alarm mode and flexible parameter configuration not only enhance the reliability of the system, but also improve the user experience, providing a strong guarantee for the long-term stable operation of the equipment.

[0066] Although the above methods are illustrated and described as a series of actions for simplicity of explanation, it should be understood and appreciated that these methods are not limited by the order of the actions, because according to one or more embodiments, some actions may occur in a different order and / or concurrently with other actions from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art.

[0067] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0068] The various illustrative logic blocks, modules, and circuits described in conjunction with the embodiments disclosed herein may be implemented or performed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0069] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0070] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, a server, or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, wherein disk often reproduces data magnetically, while disc reproduces data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0071] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein, but should be granted the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A host computer system for a brain-computer interface device, characterized in that: It includes user login module, equipment connection module, data center module, signal processing module, equipment management module, signal monitoring module and clinical management module, among which: User login module, used for the management of the security permissions of the host computer system; Device connection module, used for wireless communication, custom message format parsing, protobuf structure data conversion and data encryption and decryption; Data center module, used to realize complex communication requirements between modules; Signal processing module for neural signal monitoring and decoding of brain-computer interface devices; A device management module is used to control the implantable brain-computer interface device and visualize the sensor data inside the brain-computer interface device. The device management module transmits control instruction data to the data center module; Signal monitoring module, used to display the neural activity signals of the cerebral cortex or deep structures in real time; The clinical management module is used to view, add and modify patient information and bind patient and device information.

2. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The device connection module is configured to perform the following processing: first, the device connection module scans the Bluetooth device, and after finding the Bluetooth device name, it connects to the Bluetooth device and establishes wireless communication to receive and send data. The received data is in a custom message data format, and the received data is parsed accordingly according to the rules. The received data includes neural signal data, impedance data, and sensor data. The parsed data is converted into protobuf structure data and then encrypted with the AES algorithm. Finally, the encrypted protobuf structure data is transmitted to the data center module, where the communication method between the device connection module and the data center module is the inter-process named pipe method.

3. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The data center module corresponds to the cross-process communication scenario, and uses named pipes. It corresponds to the cross-device communication scenario, and uses TCP. All independent modules establish a fixed named pipe with the data center module. At the same time, a TCP pipe is established between the data center module of the doctor-side software and the data center module of the patient-side software. No named pipe or TCP pipe connection will be established between all modules. The data center module acts as the central scheduling and distribution function of the data to realize the complex communication requirements between modules. The data center module is programmed in rust language.

4. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The signal processing module is configured to perform the following processing: ensuring the validity of the data by continuously monitoring the quality of neural signals in each channel; the monitoring process further includes: comparing the average firing rate of the channel over a period of time with historical data of a known normal ratio range, and automatically triggering an alarm if it is detected that the firing rate of one or some channels exceeds the preset normal ratio range.

5. The host computer system for a brain-computer interface device according to claim 4, characterized in that: The signal processing module also integrates a real-time neural decoding model training and deployment system, which works closely with the brain control calibration program on the patient side. During the first use or regular calibration, the data of a series of standardized tasks completed by the user are collected and preprocessed. The preprocessed collected data is used to train a personalized decoding model based on artificial neural network, Kalman filter or hidden Markov model. During the model training process, the collected data is used to adjust the model parameters, and the prediction error is minimized through the back propagation algorithm and gradient descent optimization method. After the model training is completed, it is verified on the validation set. After verification, it is deployed to actual applications to realize real-time decoding of the user's brain signals and convert them into corresponding computer instructions.

6. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The device management module is configured to perform the following processing: the information displayed by the internal sensors of the brain-computer interface device includes waveform display of the head-end device ambient temperature, the head-end device ambient humidity, the chest-end device ambient temperature, the chest-end device ambient humidity, and the chest-end battery power, and real-time label display of the head-end device ambient temperature, the head-end device ambient humidity, the chest-end device ambient temperature, the chest-end device ambient humidity, the chest-end battery power, the chest-end battery life, and the chest-end battery charging status; the device management module displays or hides the corresponding waveform graph by clicking on the legend on the display interface, and displays the coordinate values ​​of the X and Y axes in real time when the cursor moves on the waveform line on the drawing interface, and sets the display amplitude to change the Y-axis display coordinate range; the device control functions in the device management module include device startup, device shutdown, electrode group selection, electrode group switching, neuron discharge output, impedance measurement, and query and modification of the internal emergency shutdown alarm threshold parameters of the device, through Click the corresponding buttons, selection boxes and input boxes to set the head-end device temperature, head-end device humidity, chest-end device temperature, chest-end device humidity and chest-end battery power thresholds. Click the Set Alarm Threshold Parameters button to complete the alarm threshold parameter setting function; the single-channel selection page on the display interface of the device management module has multiple options. Click one of the buttons to complete the switching of the single channel. On the filter coefficient query and setting page, click the Query Filter Parameters button to return the current filter parameters to be displayed in the text box below. Set the corresponding values ​​of different filters in the text box to complete the filter coefficient setting. On the neuron discharge threshold query and setting page, first select the channel number, and then click the Query Neuron Discharge Threshold button. It will return multiple channel threshold parameters under the current channel number to be displayed in the text box below. Complete the neuron discharge threshold setting function by selecting the channel number and modifying the corresponding thresholds of multiple channels.

7. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The host computer system also includes: The impedance query module is used to measure the impedance information of the electrodes in the current device and to plot the single-day historical impedance information within a given threshold in the form of a graph.

8. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The host computer system also includes: Physiological parameter module, used to visualize intracranial oxygen partial pressure and intracranial temperature data.

9. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The host computer system also includes: The file interaction module is used to upload local data files to the remote server, and query and download remote server files.

10. The host computer system for a brain-computer interface device according to claim 1, characterized in that: The host computer system also includes: The alarm prompt module is used to issue an alarm and prompt when the sensor parameters exceed the threshold.

Images