Data acquisition method and system applied to brain-computer interface

Abstract

The invention relates to a data acquisition method and system applied to a brain-computer interface, and the method comprises the steps: obtaining a current monitoring image of a patient, and preliminarily determining the current state of the patient according to the current monitoring image and a state analysis model, the current state comprising a waking state and a sleep state; predicting the work and rest time of the patient in the current unit time according to the historical work and rest time of the patient, wherein the historical work and rest time comprises a historical sleep time period and a historical waking time period; according to the disease information, the work and rest time and the current state of the patient, dynamically adjusting the sampling frequency of the bio-electricity signal of the patient in the monitoring interval; and collecting a bio-electricity signal of the brain of the patient based on the sampling frequency. On the basis of meeting the use requirements, the sampling frequency is dynamically adjusted, the condition that the high sampling frequency is adopted all the time is avoided, and the data processing difficulty is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition, and in particular to a data acquisition method and system applied to a brain-computer interface. Background Art

[0002] Brain-Computer Interface (BCI) technology is a technology that establishes a direct communication and control channel between the human brain and external devices. It uses high-performance bioelectric signal acquisition equipment to record brain waves in real time, and uses computer algorithms to decode these signals and convert them into recognizable control commands or signals, thereby realizing the control of external devices. The data acquisition methods of brain-computer interfaces can be divided into three categories: non-invasive, semi-invasive, and invasive, according to the different signal acquisition methods. Non-invasive brain-computer interfaces do not require opening holes in the skull, but instead attach electrodes to the surface or near the scalp to collect brain response signals and obtain nervous system information through electroencephalograms, magnetic resonance imaging, etc. Use non-invasive brain-computer interface systems to explore multiple scenarios, including sleep status monitoring, sports rehabilitation training, using user brain waves to create music and control electrical appliances, and using user emotion recognition data for personalized recommendations. From the perspective of market structure, the global brain-computer interface market is currently dominated by non-invasive brain-computer interfaces. Generally speaking, the sampling frequency of EEG equipment is fixed and has certain limitations. Currently, in order to meet usage requirements, a higher sampling frequency is usually used. A higher sampling frequency will generate more data points and increase the complexity of data processing and storage. Summary of the invention

[0003] The present invention provides a data acquisition method and system for brain-computer interface to solve the technical problems mentioned in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions: A data acquisition method applied to a brain-computer interface, the method comprising: Acquire a current monitoring image of the patient, and preliminarily determine the current state of the patient based on the current monitoring image and a state analysis model, wherein the current state includes an awake state, a sleeping state, etc.; Predicting the patient's current work and rest time within a unit of time based on the patient's historical work and rest time, wherein the historical work and rest time includes historical sleeping time periods and historical awake time periods; determining to dynamically adjust the sampling frequency of the patient's bioelectric signal within the monitoring interval based on the patient's disease information, work and rest time and the current state; The bioelectric signals of the patient's brain are collected based on the sampling frequency.

[0005] As a further technical solution of the present invention, the step of obtaining the current monitoring image of the patient and preliminarily determining the current state of the patient according to the current monitoring image and the state analysis model includes: The patient's historical monitoring image data is used to train the neural network model to obtain a state analysis model; Obtain the current monitoring image of the patient, and detect and extract the patient's features based on a facial detection algorithm; The extracted features are input into the state analysis model to make a state judgment, and based on the output results of the state analysis model, it is determined whether the patient's current state is awake or asleep.

[0006] As a further technical solution of the present invention, the steps of predicting the patient's current work and rest time within a unit time according to the patient's historical work and rest time, and determining to dynamically adjust the sampling frequency of the patient's bioelectric signal according to the patient's disease information, work and rest time and the current state include: Based on the patient's authorization, the patient's historical work and rest time is obtained, and the patient's current work and rest time is predicted based on the patient's historical work and rest time, wherein the historical work and rest time includes a historical sleeping time period and a historical awake time period; Secondary confirmation of the patient's current status based on the patient's current work and rest schedule within a unit of time; Acquiring the patient's disease information, wherein the disease information includes the disease type (neurological disease, cardiovascular disease), and determining whether the patient is a patient with a neurological disease according to the patient's disease information; The sampling frequency of the patient's bioelectric signal within the monitoring interval is dynamically adjusted according to whether the patient is a patient with a neurological disease and the current status after secondary confirmation. The monitoring interval refers to a time interval with the current time as the starting point and the second preset time length as the length.

[0007] As a further technical solution of the present invention, the step of re-confirming the current state of the patient according to the patient's current work and rest time within a unit time includes: When it is preliminarily determined that the patient's current state is a sleeping state, determine whether the current time is within the patient's sleeping time period within the current unit time. If so, confirm that the patient's current state is a sleeping state for the second time. When not, obtain the patient's brain bioelectric signals (brain waves) within the historical monitoring interval, and determine whether the patient's current state is a sleeping state based on the patient's brain bioelectric signals within the historical monitoring interval. When the patient's brain bioelectric signals within the historical monitoring interval also determine that the patient's current state is a sleeping state, confirm that the patient's current state is a sleeping state.

[0008] As a further technical solution of the present invention, the step of dynamically adjusting the sampling frequency of the patient's bioelectric signal according to whether the patient is a patient with a nervous system disease and the current state after secondary confirmation includes: Sampling frequency = A*state frequency. When the patient is a patient with a neurological disease, the sampling weight A is taken as the first preset weight. When the patient is not a patient with a neurological disease, the sampling weight A is taken as the second preset weight, wherein the first preset weight is greater than the second preset weight. When the current state after the second confirmation is the awake state, the state frequency is the preset X1. When the current state after the second confirmation is the sleeping state, the state frequency is the preset X2, and X1>X2.

[0009] Another object of the present invention is to provide a data acquisition system for brain-computer interface, the system comprising: A state analysis module is used to obtain a current monitoring image of the patient and preliminarily determine the current state of the patient based on the current monitoring image and the state analysis model, wherein the current state includes awake state, sleeping state, etc.; A sampling frequency determination module is used to predict the patient's current work and rest time within a unit of time based on the patient's historical work and rest time, wherein the historical work and rest time includes historical sleeping time periods and historical awake time periods; and dynamically adjust the sampling frequency of the patient's bioelectric signal based on the patient's disease information, work and rest time and the current state; The sampling execution module is used to collect bioelectric signals from the patient's brain based on the sampling frequency.

[0010] As a further technical solution of the present invention, the sampling frequency determination module includes: A work and rest time prediction unit, used to obtain the patient's historical work and rest time based on the patient's authorization, and predict the patient's work and rest time in the current unit time according to the patient's historical work and rest time, wherein the historical work and rest time includes a historical sleeping time period and a historical awake time period; A status secondary confirmation unit, used to secondary confirm the patient's current status according to the patient's current work and rest time within a unit of time; A patient type determination unit is used to obtain the patient's disease information, wherein the disease information includes the disease type (neurological disease, cardiovascular disease), and determine whether the patient is a patient with a neurological disease according to the patient's disease information; The sampling frequency determination unit is used to dynamically adjust the sampling frequency of the patient's bioelectric signal in the monitoring interval according to whether the patient is a patient with a neurological disease and the current state after secondary confirmation. The monitoring interval refers to a time interval with the current time as the starting point and the second preset time length as the length.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention provides a data acquisition method and system for brain-computer interface, in which the current state of the patient is monitored in real time based on the monitoring image, and a preliminarily determined whether the current state of the patient is awake or asleep, and on this basis, the current state of the patient is further confirmed for a second time according to the patient's work and rest information and the bioelectric signals in the historical monitoring interval, to ensure the accuracy of the monitoring state, lay the foundation for adjusting the sampling frequency, and dynamically adjust the sampling frequency of the patient's bioelectric signals in combination with the patient's current state and disease information after the second confirmation, on the basis of meeting the use requirements, avoid using a higher sampling frequency all the time, and reduce the difficulty of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 The flowchart of the data acquisition method applied to brain-computer interface.

[0013] Figure 2 A flowchart for preliminarily determining the current state in a data acquisition method applied to a brain-computer interface.

[0014] Figure 3 A flowchart for determining the sampling frequency in a data acquisition method for a brain-computer interface.

[0015] Figure 4 This is a structural block diagram of the data acquisition system used in brain-computer interface. DETAILED DESCRIPTION

[0016] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] like Figure 1 As shown, an embodiment of the present invention provides a data acquisition method applied to a brain-computer interface, the method comprising: Step S100: Obtain the current monitoring image of the patient, and preliminarily determine the current state of the patient based on the current monitoring image and the state analysis model, wherein the current state includes awake state, sleeping state, etc. For details, please refer to Figure 2 ; Step S101: Use the patient's historical monitoring image data to train the neural network model to obtain a state analysis model: Obtain the patient's historical monitoring image data and mark the corresponding awake or sleeping state as the training set and validation set, select appropriate machine learning or deep learning models, such as support vector machine (SVM), random forest, convolutional neural network (CNN), etc., use the training set data to train the model, use the validation set data to validate the model, and evaluate the model's performance until the training result meets the preset accuracy threshold, and obtain a trained state analysis model; Step S102, obtaining the current monitoring image of the patient, detecting and extracting the patient's features based on a facial detection algorithm, wherein the features include facial features, and the facial features include the movement states of key parts such as eyes and mouth (such as the opening and closing of eyes, the degree of opening of mouth, etc.); other features related to state judgment may also be extracted as needed, such as head posture, body posture, etc.; Step S103: Input the extracted features into the state analysis model to perform state judgment, and determine whether the patient's current state is awake or asleep based on the output result of the state analysis model.

[0018] Step S200: predict the patient's current work and rest time in a unit time according to the patient's historical work and rest time, wherein the historical work and rest time includes the historical sleeping time period and the historical awake time period; dynamically adjust the sampling frequency of the patient's bioelectric signal in the monitoring interval according to the patient's disease information, work and rest time and the current state; please refer to Figure 3 ; Step S201: Based on the patient's authorization, the patient's historical work and rest time is obtained, and the patient's work and rest time in the current unit time is predicted based on the patient's historical work and rest time, wherein the historical work and rest time includes the historical sleeping time period and the historical awake time period; the step of predicting the patient's work and rest time in the current unit time based on the patient's historical work and rest time includes: based on the historical work and rest data, selecting a suitable prediction method (such as time series analysis, machine learning algorithm, etc.) to establish a prediction model. The current time is used as input, and the prediction model is applied to predict the patient's work and rest time in the current unit time; Step S202, reconfirming the patient's current state according to the patient's current work and rest time in a unit of time; Step S203, obtaining the patient's disease information, the disease information including the disease type (neurological disease, cardiovascular disease), and determining whether the patient is a patient with a neurological disease according to the patient's disease information; Step S204, dynamically adjust the sampling frequency of the patient's bioelectric signal within the monitoring interval according to whether the patient is a patient with a neurological disease and the current state after the second confirmation, wherein the monitoring interval refers to a time interval starting from the current time and having a second preset duration as the length.

[0019] In this embodiment, the step of re-confirming the patient's current state according to the patient's current work and rest time within a unit of time includes: When it is preliminarily determined that the patient's current state is a sleeping state, determine whether the current time is within the patient's sleeping time period within the current unit time. If so, confirm that the patient's current state is a sleeping state for the second time. When not, obtain the patient's brain bioelectric signals (brain waves) within the historical monitoring interval, and determine whether the patient's current state is a sleeping state based on the patient's brain bioelectric signals within the historical monitoring interval. When the patient's brain bioelectric signals within the historical monitoring interval also determine that the patient's current state is a sleeping state, confirm that the patient's current state is a sleeping state.

[0020] The step of secondarily determining whether the patient's current state is a sleeping state based on the bioelectrical signals of the patient's brain within the historical monitoring interval includes: preprocessing the collected EEG data, including filtering, amplification, denoising and other steps to improve the signal-to-noise ratio and readability of the data; extracting key features such as frequency, amplitude, waveform, etc. from the preprocessed EEG data. These features will be used for subsequent state determination; according to the different EEG characteristics, corresponding thresholds are set to determine whether the patient's current state is a sleeping state. For example, when the proportion of delta waves in the entire EEG activity exceeds a certain threshold, it can be determined that the patient is in a sleeping state.

[0021] In this embodiment, the step of dynamically adjusting the sampling frequency of the patient's bioelectric signal according to whether the patient is a patient with a nervous system disease and the current state after secondary confirmation includes: Sampling frequency = A*state frequency. When the patient is a patient with a neurological disease, the sampling weight A is taken as the first preset weight. When the patient is not a patient with a neurological disease, the sampling weight A is taken as the second preset weight, wherein the first preset weight is greater than the second preset weight. When the current state after the second confirmation is the awake state, the state frequency is the preset X1. When the current state after the second confirmation is the sleeping state, the state frequency is the preset X2, and X1>X2.

[0022] Step S300: collecting bioelectric signals of the patient's brain based on the sampling frequency.

[0023] In the present invention, the patient's current state is monitored in real time based on monitoring images, and a preliminary determination is made as to whether the patient's current state is awake or asleep. On this basis, the patient's current state is further confirmed for a second time based on the patient's work and rest information and the bioelectric signals in the historical monitoring interval, thereby ensuring the accuracy of the monitoring state and laying a foundation for adjusting the sampling frequency. The sampling frequency of the patient's bioelectric signals is dynamically adjusted in combination with the patient's current state and disease information after the second confirmation, thereby avoiding the use of a higher sampling frequency all the time while meeting usage requirements and reducing the difficulty of data processing.

[0024] See also Figure 4 Another object of the present invention is to provide a data acquisition system for brain-computer interface, the system comprising: The state analysis module 100 is used to obtain the current monitoring image of the patient and preliminarily determine the current state of the patient according to the current monitoring image and the state analysis model, wherein the current state includes awake state, sleeping state, etc.; The sampling frequency determination module 200 is used to predict the patient's current work and rest time in a unit time according to the patient's historical work and rest time, wherein the historical work and rest time includes the historical sleeping time period and the historical awake time period; and dynamically adjust the sampling frequency of the patient's bioelectric signal according to the patient's disease information, work and rest time and the current state; The sampling execution module 300 is used to collect bioelectric signals from the patient's brain based on the sampling frequency.

[0025] As a preferred embodiment of the present invention, the sampling frequency determination module 100 includes: A work and rest time prediction unit, used to obtain the patient's historical work and rest time based on the patient's authorization, and predict the patient's work and rest time in the current unit time according to the patient's historical work and rest time, wherein the historical work and rest time includes a historical sleeping time period and a historical awake time period; A status secondary confirmation unit, used to secondary confirm the patient's current status according to the patient's current work and rest time within a unit of time; A patient type determination unit is used to obtain the patient's disease information, wherein the disease information includes the disease type (neurological disease, cardiovascular disease), and determine whether the patient is a patient with a neurological disease according to the patient's disease information; The sampling frequency determination unit is used to dynamically adjust the sampling frequency of the patient's bioelectric signal in the monitoring interval according to whether the patient is a patient with a neurological disease and the current state after secondary confirmation. The monitoring interval refers to a time interval with the current time as the starting point and the second preset time length as the length.

[0026] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0027] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A data acquisition method for a brain-computer interface, characterized in that: The method comprises: Acquire a current monitoring image of the patient, and preliminarily determine the current state of the patient according to the current monitoring image and a state analysis model, wherein the current state includes an awake state and a sleeping state; Predicting the patient's current work and rest time within a unit of time based on the patient's historical work and rest time, wherein the historical work and rest time includes historical sleeping time periods and historical awake time periods; determining to dynamically adjust the sampling frequency of the patient's bioelectric signal within the monitoring interval based on the patient's disease information, work and rest time and the current state; The bioelectric signals of the patient's brain are collected based on the sampling frequency.

2. The data acquisition method for brain-computer interface according to claim 1 is characterized in that: The step of obtaining the current monitoring image of the patient and preliminarily determining the current state of the patient according to the current monitoring image and the state analysis model comprises: The patient's historical monitoring image data is used to train the neural network model to obtain a state analysis model; Acquire a current monitoring image of the patient, and detect and extract features of the patient based on a facial detection algorithm, the features including facial features; The extracted features are input into the state analysis model to make a state judgment, and based on the output results of the state analysis model, it is determined whether the patient's current state is awake or asleep.

3. The data acquisition method for brain-computer interface according to claim 2 is characterized in that: The steps of predicting the patient's current work and rest time within a unit time according to the patient's historical work and rest time, and determining to dynamically adjust the sampling frequency of the patient's bioelectric signal according to the patient's disease information, work and rest time and the current state include: Based on the patient's authorization, the patient's historical work and rest time is obtained, and the patient's current work and rest time is predicted based on the patient's historical work and rest time, wherein the historical work and rest time includes a historical sleeping time period and a historical awake time period; Secondary confirmation of the patient's current status based on the patient's current work and rest schedule within a unit of time; Acquiring the patient's disease information, wherein the disease information includes the disease type, and determining whether the patient is a patient with a nervous system disease according to the patient's disease information; The sampling frequency of the patient's bioelectric signal within the monitoring interval is dynamically adjusted according to whether the patient is a patient with a neurological disease and the current status after secondary confirmation. The monitoring interval refers to a time interval with the current time as the starting point and the second preset time length as the length.

4. The data acquisition method for brain-computer interface according to claim 3 is characterized in that: The steps of re-confirming the patient's current status based on the patient's current work and rest time in a unit of time include: When it is preliminarily determined that the patient's current state is a sleeping state, determine whether the current time is within the patient's sleeping time period within the patient's current unit time. If so, confirm that the patient's current state is a sleeping state for the second time. When not, obtain the bioelectric signals of the patient's brain within the historical monitoring interval, and determine whether the patient's current state is a sleeping state based on the bioelectric signals of the patient's brain within the historical monitoring interval. When the bioelectric signals of the patient's brain within the historical monitoring interval also determine that the patient's current state is a sleeping state, confirm that the patient's current state is a sleeping state.

5. The data acquisition method for brain-computer interface according to claim 3 is characterized in that: The steps of dynamically adjusting the sampling frequency of the patient's bioelectric signal according to whether the patient is a patient with a neurological disease and the current state after secondary confirmation include: Sampling frequency = A*state frequency. When the patient is a patient with a neurological disease, the sampling weight A is taken as the first preset weight. When the patient is not a patient with a neurological disease, the sampling weight A is taken as the second preset weight, wherein the first preset weight is greater than the second preset weight. When the current state after the second confirmation is the awake state, the state frequency is the preset X1. When the current state after the second confirmation is the sleeping state, the state frequency is the preset X2.

6. A data acquisition system for a brain-computer interface, characterized in that: The system comprises: A state analysis module is used to obtain a current monitoring image of the patient, and preliminarily determine the current state of the patient according to the current monitoring image and the state analysis model, wherein the current state includes an awake state and a sleeping state; A sampling frequency determination module is used to predict the patient's current work and rest time within a unit of time based on the patient's historical work and rest time, wherein the historical work and rest time includes historical sleeping time periods and historical awake time periods; and dynamically adjust the sampling frequency of the patient's bioelectric signal based on the patient's disease information, work and rest time and the current state; The sampling execution module is used to collect bioelectric signals from the patient's brain based on the sampling frequency.

7. The data acquisition system for brain-computer interface according to claim 6, characterized in that: The sampling frequency determination module comprises: A work and rest time prediction unit, used to obtain the patient's historical work and rest time based on the patient's authorization, and predict the patient's work and rest time in the current unit time according to the patient's historical work and rest time, wherein the historical work and rest time includes a historical sleeping time period and a historical awake time period; A status secondary confirmation unit, used to secondary confirm the patient's current status according to the patient's current work and rest time within a unit of time; A patient type determination unit, configured to obtain disease information of the patient, the disease information including the disease type, and determine whether the patient is a patient with a nervous system disease according to the disease information of the patient; The sampling frequency determination unit is used to dynamically adjust the sampling frequency of the patient's bioelectric signal in the monitoring interval according to whether the patient is a patient with a neurological disease and the current state after secondary confirmation. The monitoring interval refers to a time interval with the current time as the starting point and the second preset time length as the length.

Images