Physiological closed-loop stimulation device, electronic device and storage medium

Abstract

The invention discloses physiological closed-loop stimulation equipment, electronic equipment and a storage medium. The physiological closed-loop stimulation equipment comprises a control module, a signal processing module and a stimulation module, the control module is used for executing multiple test operations on the signal processing module and the stimulation module; the multiple test operations are used for determining target time delay; the signal processing module is used for acquiring a first electroencephalogram signal of the target object at the current moment; determining a first physiological state of a target object at the current moment according to the first electroencephalogram signal; according to the first physiological state, a target probability that a target object has a target physiological state at a target moment is predicted, and a time difference between the target moment and a current moment is a target time delay; and the stimulation module is used for sending a stimulation signal to the target object when the target probability is higher than a preset probability. By adopting the embodiment of the invention, the control precision of the stimulation signal can be improved when the physiological closed-loop stimulation is performed on the target object.

Description

Technical Field

[0001] This invention relates to the field of equipment control technology, and in particular to a physiological closed-loop stimulation device, electronic device, and storage medium. Background Technology

[0002] In fields such as industrial automation, smart homes, human-machine collaboration, and medical devices, the coordinated control of multiple devices is often involved, with each device exchanging data in real time via wired or wireless communication. Similarly, when performing closed-loop physiological stimulation on a user, there is a need for coordinated control of multiple devices; for example, it is typically necessary to coordinate multiple steps such as data acquisition, processing, and stimulation through multiple devices.

[0003] However, there is a time delay in the communication process between multiple devices in physiological closed-loop stimulation. There is a time difference between the time when the control command for the stimulation signal is sent and the actual time of action. As a result, the generation and execution of the control command cannot be completely matched with the real-time physiological state in actual operation, leading to low control accuracy of physiological closed-loop stimulation. Summary of the Invention

[0004] To address the aforementioned problems, embodiments of the present invention provide a physiological closed-loop stimulation device, an electronic device, and a storage medium, which can improve the control precision of the stimulation signal when performing physiological closed-loop stimulation on a target object.

[0005] In a first aspect, embodiments of the present invention provide a physiological closed-loop stimulation device, the physiological closed-loop stimulation device comprising a control module, a signal processing module, and a stimulation module; The control module is used to perform multiple test operations on the signal processing module and the stimulation module. In each test operation, the control module sends a first test signal to the signal processing module and simultaneously sends a second test signal to the stimulation module. The stimulation module is used to send a third test signal to the signal processing module after receiving the second test signal in each test operation. The signal processing module is used to determine the target delay based on the first test signal and the third test signal corresponding to each test operation; The signal processing module is also used to acquire the first EEG signal of the target object at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; The stimulation module is also used to send a stimulation signal to the target object when the target probability is higher than a preset probability.

[0006] Secondly, embodiments of the present invention provide a physiological closed-loop stimulation method, the method being applied to a physiological closed-loop stimulation device, the physiological closed-loop stimulation device comprising a control module, a signal processing module, and a stimulation module; the method comprising: The control module performs multiple test operations on the signal processing module and the stimulation module. In each test operation, the control module sends a first test signal to the signal processing module and simultaneously sends a second test signal to the stimulation module. After receiving the second test signal in each test operation, the stimulation module sends a third test signal to the signal processing module. The signal processing module determines the target delay based on the first test signal and the third test signal corresponding to each test operation; The signal processing module acquires the first EEG signal of the target object at the current moment; The signal processing module determines the first physiological state of the target object at the current moment based on the first EEG signal; The signal processing module predicts the target probability that the target object has the target physiological state at the target time based on the first physiological state; the time difference between the target time and the current time is the target delay; When the target probability is higher than a preset probability, the stimulation module sends a stimulation signal to the target object.

[0007] Thirdly, embodiments of the present invention provide an electronic device, the electronic device including a controller, a processor, a memory, and a stimulator, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the following steps: Multiple test operations are performed on the processor and the stimulator, wherein in each test operation the controller sends a first test signal to the processor and simultaneously sends a second test signal to the stimulator; After receiving the second test signal in each test operation, a third test signal is sent to the processor; The target delay is determined based on the first and third test signals corresponding to each test operation; Acquire the target object's first EEG signal at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; When the target probability is higher than the preset probability, a stimulus signal is sent to the target object.

[0008] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program for performing the following steps: Multiple test operations are performed on the processor and the stimulator, wherein in each test operation the controller sends a first test signal to the processor and simultaneously sends a second test signal to the stimulator; After receiving the second test signal in each test operation, a third test signal is sent to the processor; The target delay is determined based on the first and third test signals corresponding to each test operation; Acquire the target object's first EEG signal at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; When the target probability is higher than the preset probability, a stimulus signal is sent to the target object.

[0009] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, the computer program product being used to cause a computer to perform the following steps: Multiple test operations are performed on the processor and the stimulator, wherein in each test operation the controller sends a first test signal to the processor and simultaneously sends a second test signal to the stimulator; After receiving the second test signal in each test operation, a third test signal is sent to the processor; The target delay is determined based on the first and third test signals corresponding to each test operation; Acquire the target object's first EEG signal at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; When the target probability is higher than the preset probability, a stimulus signal is sent to the target object.

[0010] Implementing the embodiments of this application has the following beneficial effects: In this embodiment, the control module first performs multiple test operations on the signal processing module and the stimulation module. During each test operation, the control module sends a first test signal to the signal processing module and a second test signal to the stimulation module. Then, after receiving the second test signal in each test operation, the stimulation module sends a third test signal to the signal processing module. The signal processing module then determines the target delay based on the first and third test signals corresponding to each test operation. These multiple test operations quantify the inherent delays of the signal processing module and the signal transmission time of the stimulation module to determine the target delay, thus avoiding timing deviations caused by unknown delays. Finally, the signal... The processing module acquires the target object's first EEG signal at the current moment. Based on the first EEG signal, it determines the target object's first physiological state at the current moment. Based on the first physiological state, it predicts the target probability that the target object will have the target physiological state at the target moment. The time difference between the target moment and the current moment is the target delay. By predicting the evolution trend of the physiological state from the current moment to the target moment, the generation of stimulation instructions is based not on the current state, but on the expected state at the target moment. This avoids timing differences caused by time consumption in transmission and processing between modules. Finally, the stimulation module sends a stimulation signal to the target object when the target probability is higher than the preset probability, so that the stimulation signal acts on the target object precisely when the target physiological state occurs. Therefore, when implementing closed-loop physiological stimulation on the target object, the control precision of the stimulation signal can be improved, achieving precise stimulation. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the drawings used in the embodiments of the present invention or the background art will be described below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of a physiological closed-loop stimulation scenario provided in an embodiment of this application; Figure 2 This is a schematic diagram of a physiological closed-loop stimulation device provided in an embodiment of this application; Figure 3 This is a schematic diagram of a delay measurement system provided in an embodiment of this application; Figure 4This is a schematic diagram of another delay measurement system provided in an embodiment of this application; Figure 5 This is a schematic diagram of a delay time provided in an embodiment of this application; Figure 6 This is a schematic diagram illustrating the segmentation of a second EEG signal based on a time window, as provided in an embodiment of this application. Figure 7 This is a schematic diagram of a three-stage delay provided in an embodiment of this application; Figure 8 This is a flowchart of a physiological closed-loop stimulation method provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to these processes, methods, products, or devices.

[0015] In this document, the term "embodiment" means that a particular feature, result, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0016] The following describes the relevant content, concepts, technical issues, technical solutions, and beneficial effects involved in the embodiments of this application.

[0017] See Figure 1 , Figure 1 This is a schematic diagram of a physiological closed-loop stimulation scenario provided in an embodiment of this application. For example... Figure 1As shown, a physiological closed-loop stimulation device is used to perform physiological closed-loop stimulation on the target object. The device first obtains the target object's electroencephalogram (EEG) signal, then analyzes the EEG signal, and sends a stimulation signal to the target object based on the analysis results.

[0018] The electroencephalogram (EEG) signals in the embodiments of this application may include spindle waves, K-complex waves, long waves, etc.

[0019] See Figure 2 , Figure 2 This is a schematic diagram of a physiological closed-loop stimulation device provided in an embodiment of this application. Figure 2 As shown in the embodiment of this application, a physiological closed-loop stimulation device includes a control module, a signal processing module, and a stimulation module. The control module is used to perform multiple test operations on the signal processing module and the stimulation module. During each test operation, the control module sends a first test signal to the signal processing module and simultaneously sends a second test signal to the stimulation module. The stimulation module is used to send a third test signal to the signal processing module after receiving the second test signal during each test operation. The signal processing module is used to determine a target time delay based on the first and third test signals corresponding to each test operation. The signal processing module is also used to acquire a first EEG signal of the target object at the current moment; determine a first physiological state of the target object at the current moment based on the first EEG signal; and predict the target probability that the target object possesses the target physiological state at a target moment based on the first physiological state, wherein the time difference between the target moment and the current moment is the target time delay. The stimulation module is also used to send a stimulation signal to the target object when the target probability is higher than a preset probability.

[0020] Before the physiological closed-loop stimulation device is applied to the target object, the delay of the signal processing module and the stimulation module needs to be determined. The control module is used to perform multiple test operations on the signal processing module and the stimulation module to obtain the target time delay through these multiple test operations. In a specific application scenario, the signal processing module is used to acquire the EEG signal of the target object and process and analyze the EEG signal to obtain the target probability at the target time. The control module is used to receive the processed data from the signal processing module, which can be the target probability. When the target probability is higher than the preset probability, a trigger signal is sent to the stimulation module. After receiving the trigger signal, the stimulation module generates a stimulation signal and sends the stimulation signal to the target object.

[0021] In one possible embodiment, regarding determining the target delay based on the first test signal and the third test signal corresponding to each test operation, the signal processing module is specifically configured to: determine a first processing duration corresponding to each test operation based on a first moment and a second moment corresponding to each test operation; the first moment being the moment when the first test signal is received in each test operation, and the second moment being the moment when the control module sends the first test signal in each test operation; determine a first stimulus duration corresponding to each test operation based on the third moment and the fourth moment corresponding to each test operation, and the first processing duration; the third moment being the moment when the third test signal is received in each test operation, and the fourth moment being the moment when the control module sends the second test signal in each test operation; and determine the target delay based on the first processing duration and the first stimulus duration corresponding to each test operation.

[0022] Specifically, the first processing time refers to the time consumed by the signal processing module to acquire and process the signal in each test operation; the first stimulation time refers to the time required for the stimulation module to apply the stimulus to the target object in each test operation, including the generation time and transmission time of the stimulus signal.

[0023] In a specific embodiment, see Figure 3 , Figure 3 This is a schematic diagram of a delay measurement system provided in an embodiment of this application. In a test operation, the control module sends a first test signal S1 to the signal processing module at time t0, and simultaneously sends a second test signal to the stimulation module. The second test signal can be the same as the first test signal, and can be a pulse trigger signal. Alternatively, the control module can generate different test signals according to the different trigger signal requirements of the stimulation module and the signal processing module. Then, after receiving the second test signal, the stimulation module sends a third test signal S2 to the signal processing module. The time when the signal processing module receives the first test signal S1 is time t1, and the time when the signal processing module receives the third test signal S2 is time t2. Therefore, in this test operation, the corresponding first processing duration is t1-t0, and the corresponding first stimulation duration is t2-t1.

[0024] Specifically, the signal processing module judges the received test signal to determine the specific reception time of the test signal. After acquiring the signal, the signal processing module calculates the mean μ and standard deviation σ of the signal before the control module sends the test signal. After the control module sends the test signal, if the amplitude of the signal acquired by the signal processing module exceeds the signal noise range, it is considered that the test signal has been detected, and the time at this time is recorded as t1 or t2. The signal noise range can be (μ-3×σ, μ+3×σ).

[0025] In one possible embodiment, regarding determining the target delay based on a first processing duration and a first stimulus duration corresponding to each test operation, the signal processing module is specifically configured to: determine a first probability distribution based on a plurality of first processing durations corresponding to multiple test operations; the first probability distribution is used to reflect a first occurrence probability of each first processing duration; determine a target processing duration based on a plurality of first occurrence probabilities corresponding to the plurality of first processing durations; the target processing duration is the first processing duration with the highest first occurrence probability among the plurality of first processing durations; determine a second probability distribution based on a plurality of first stimulus durations corresponding to multiple test operations; the second probability distribution is used to reflect a second occurrence probability of each first stimulus duration; determine a target stimulus duration based on a plurality of second occurrence probabilities corresponding to the plurality of first stimulus durations; the target stimulus duration is the first stimulus duration with the highest second occurrence probability among the plurality of first stimulus durations; and determine a target delay based on the target processing duration and the target stimulus duration.

[0026] In a specific embodiment, the first probability distribution is a distribution reflecting the probability of each first processing duration occurring, formed statistically from multiple first processing durations obtained through multiple test operations; the second probability distribution is a distribution reflecting the probability of each first stimulus duration occurring, formed statistically from multiple first stimulus durations obtained through multiple test operations; the target processing duration is the duration with the highest probability of occurrence among multiple first processing durations; the target stimulus duration is the duration with the highest probability of occurrence among multiple first stimulus durations; the target delay is calculated based on the target processing duration and the target stimulus duration; and the target time is calculated based on the target delay and the current time, used for subsequent stimulation operations on the target object.

[0027] The signal processing module first collects the first processing duration for each of the multiple test operations. By statistically analyzing the frequency of each first processing duration, it calculates its proportion in the total number of occurrences, i.e., the first occurrence probability, and constructs a first probability distribution. This distribution intuitively reflects the likelihood of different first processing durations occurring. Based on this first probability distribution, the first processing duration with the highest occurrence probability is selected and determined as the target processing duration. This process is because the duration with the highest occurrence probability is statistically the most representative and can reflect the processing time in most cases.

[0028] Simultaneously, for multiple test operations, the duration of the first stimulus corresponding to each operation is collected. Using the same statistical method as used to determine the first probability distribution, the second probability of occurrence for each first stimulus duration is calculated, constructing a second probability distribution to reflect the likelihood of different first stimulus durations occurring. The first stimulus duration with the highest second probability of occurrence is selected from the second probability distribution and determined as the target stimulus duration. Similarly, this duration is the time required to generate and transmit stimulus signals in most tests.

[0029] In one possible embodiment, the target delay is the sum of the target processing duration and the target stimulus duration. The signal processing module uses the current moment as a starting point, superimposes the target processing duration and the target stimulus duration, and the result is the target moment. Since the target processing duration represents the typical time required for signal processing, and the target stimulus duration represents the typical time required for stimulus application, their sum reflects the total typical time required to complete signal processing and stimulus application from the current moment. The target moment determined based on this accurately corresponds to the execution node of the actual operation. For example, if the current moment is 0 milliseconds, the target processing duration is 10 milliseconds, and the target stimulus duration is 15 milliseconds, then the target delay is 25 milliseconds, and the target moment is 25 milliseconds.

[0030] In this embodiment, the most representative target duration is selected to determine the target time by statistically analyzing the probability distribution of processing time and stimulus duration from multiple tests. This improves the accuracy and reliability of target time calculation and better adapts to the delay patterns in actual application scenarios.

[0031] In one possible embodiment, the control module includes a sub-control unit and a signal triggering unit; in performing multiple test operations on the signal processing module and the stimulation module, the sub-control unit is used to send multiple signal triggering instructions to the signal triggering unit, the multiple signal triggering instructions corresponding one-to-one with the multiple test operations; the signal triggering unit is used to respond to each signal triggering instruction sent by the sub-control unit, to execute the test operation corresponding to the signal triggering instruction, to send a first test signal corresponding to the test operation to the signal processing module, and simultaneously send a second test signal corresponding to the test operation to the stimulation module.

[0032] In a specific embodiment, see Figure 4 , Figure 4 This is a schematic diagram of another delay measurement system provided in the embodiments of this application. Figure 4 The controller in the middle can be one of the aforementioned sub-control units. Figure 4 The trigger generator in the text can be the signal triggering unit mentioned above. Figure 4 The stimulator in the middle can be the stimulation module mentioned above. Figure 4 The signal acquisition device in the above-mentioned signal processing unit can perform calculation and processing operations on the acquired signal.

[0033] Furthermore, during a test operation, the controller sends a pulse trigger signal to the trigger generator and records the signal emission time as t0. The trigger generator simultaneously sends two test signals: a first test signal and a second test signal, which are two logic (Transistor-Transistor Logic, TTL) trigger levels. One level is sent to the stimulator, and the other level is sent directly to the electrodes of the signal acquisition unit. After receiving the second test signal, i.e., the trigger level, the stimulator releases a stimulation pulse to the electrodes of the signal acquisition unit. The signal acquisition unit synchronously acquires the stimulation pulse signal, i.e., the third test signal S2, and the level signal applied by the trigger generator, i.e., the first test signal S1. The controller extracts the S1 and S2 signals from the signal acquisition unit at times t1 and t2, respectively.

[0034] Furthermore, the above test operation steps are repeated multiple times. Each time, the duration of the first stimulus t_stim=t2-t1 and the duration of the first treatment t_record=t1-t0 are calculated. Gaussian fitting is calculated on the data from multiple tests, and the values ​​of the highest points of the Gaussian distribution t_stim_mean and t_record_mean are extracted.

[0035] During human stimulation, the physiological state W(t) of the human body is continuously collected by a signal acquisition device. This physiological state W(t) can be a brain state or a state of other areas of the body. The brain state can include at least one of the following: sleep state, awake state, alert state, relaxed state, anesthesia state, coma state, disease state, and meditation state. The physiological state acquired by the controller at the current time point is W(i). By using a hidden Markov prediction algorithm to estimate the physiological state at future time points, the actual physiological state of the human body is W(i+t_record_mean), and the physiological state at the actual time point that the stimulator can stimulate is W(i+t_record_mean+t_stim_mean). For example, see [link to relevant documentation]. Figure 5 , Figure 5 This is a schematic diagram illustrating a delay time provided in an embodiment of this application. For example... Figure 5As shown, EEG signals change over time. If the target object's EEG signal is acquired at time 1, the physiological state corresponding to time 1 is W(i). Due to the delay in signal acquisition and processing, when the signal acquisition device obtains the EEG signal corresponding to time 1, the target object's EEG signal is already at the EEG signal corresponding to time 2, and the physiological state corresponding to time 2 is W(i+t_record_mean). If it is determined to stimulate the target object when the signal acquisition device obtains the EEG signal corresponding to time 1, due to the delay in the generation and transmission of the stimulation signal, when the stimulation signal reaches the target object, the target object's EEG signal is already at the EEG signal corresponding to time 3, and the physiological state corresponding to time 3 is W(i+t_record_mean+t_stim_mean). Therefore, it is necessary to analyze W(i+t_record_mean+t_stim_mean) to determine whether the stimulation conditions are met.

[0036] Then, the physiological state W(i+t_record_mean+t_stim_mean) that can be reached by the stimulus is judged. If the preset stimulus conditions are met, the controller sends a stimulus signal to the Trigger generator and stimulates the human body through the stimulator. If the preset stimulus conditions are not met, the controller continues to wait.

[0037] In one possible embodiment, in determining the first physiological state of the target object at the current moment based on the first EEG signal, the signal processing module is specifically configured to: acquire the second EEG signal of the target object at the current moment; determine n candidate physiological states of the target object based on the second EEG signal and a first correspondence; the first correspondence is used to indicate the mapping relationship between the EEG signal and the physiological state; and determine the first physiological state from the n candidate physiological states based on the first EEG signal and the first correspondence.

[0038] Specifically, the first EEG signal refers to the EEG signal used to determine the physiological state at the current moment; the second EEG signal refers to the EEG signal synchronously acquired at the current moment for preliminary screening of candidate physiological states, and the acquisition duration of the second EEG signal is longer than that of the first EEG signal; the first correspondence is a pre-established mapping rule used to characterize the association between EEG signal features and physiological states. This rule can be obtained by training on a large amount of sample data, such as the correspondence between different frequency band EEG power, waveform features, etc., and physiological states such as wakefulness, different stages of sleep, alertness, etc.; n candidate physiological states refer to n physiological states that may match the current state of the target object based on the preliminary screening of the second EEG signal, where n is a positive integer; the first physiological state refers to the physiological state of the target object at the current moment corresponding to the first EEG signal.

[0039] The signal processing module first acquires the target object's second EEG signal at the current moment. This signal contains the electrophysiological characteristics generated by the activity of brain neurons at the current moment, such as the amplitude and frequency distribution of EEG waves in each frequency band.

[0040] Subsequently, the signal processing module invokes the pre-stored first correspondence to compare the features of the second EEG signal, such as the power ratio of delta waves, theta waves, and alpha waves, and the frequency of specific waveforms, with the EEG signal features recorded in the first correspondence. This process filters out n physiological states with high feature matching degrees as candidate physiological states. By utilizing the mapping rules of the first correspondence, the possible range of physiological states is narrowed down, reducing the computational load of subsequent determination processes. In practical applications, this approach aligns with the actual physiological states of different target objects, ensuring the efficiency of physiological state determination.

[0041] Subsequently, the signal processing module compares the features of the first EEG signal with the features of the EEG signals corresponding to the n candidate physiological states based on the first correspondence relationship, calculates the matching degree between each candidate physiological state and the first EEG signal, and finally selects the physiological state with the highest matching degree and determines it as the first physiological state.

[0042] In one possible embodiment, in predicting the probability that a target object possesses a target physiological state at a target time based on a first physiological state, the signal processing module is specifically configured to: Based on the second EEG signal, determine the transition probability matrix between n candidate physiological states; Based on the second EEG signal, multiple observation probabilities of each candidate physiological state under multiple preset observation indicators are determined; multiple preset observation indicators correspond one-to-one with multiple observation probabilities, and the observation probability under each preset observation indicator is used to indicate the probability that each candidate physiological state belongs to each preset observation indicator. Based on the multiple observation probabilities of each candidate physiological state under multiple preset observation indicators, determine m candidate observation indicators corresponding to the target object; Based on the observation probability of each candidate physiological state under m candidate observation indicators, determine the observation probability matrix between n candidate physiological states and m candidate observation indicators; Based on the transition probability matrix and the first physiological state, predict the first probability of transitioning from the first physiological state to the target physiological state at the target time. Based on the observation probability matrix and the first physiological state, predict the second probability of the existence of the target observation index in the first physiological state; the target observation index is the candidate observation index that corresponds to the transition from the first physiological state to the target physiological state among m candidate observation indices. Determine the target probability based on the first probability and the second probability.

[0043] Specifically, the transition probability matrix is ​​a matrix used to describe the probability of transitioning between n candidate physiological states, where the matrix elements represent the probability of transitioning from one candidate physiological state to another; the preset observation index is a pre-defined observable parameter used to characterize the features of the physiological state, such as the waveform change trend of the EEG signal, which includes rising, falling, etc. The preset observation index can also be the power of a specific frequency band of the EEG signal, heart rate, etc.; the candidate observation index is m observation indexes selected from multiple preset observation indexes that have a high correlation with the physiological state of the target object, where m is a positive integer; the target observation index is the observation index among the m candidate observation indexes that corresponds to the process of transitioning from the first physiological state to the target physiological state; the first probability refers to the probability of transitioning from the first physiological state to the target physiological state at the target time; the second probability refers to the probability of the target observation index appearing in the first physiological state; the target probability is the probability that the target object exists in the target physiological state at the target time after combining the first probability and the second probability.

[0044] First, the signal processing module uses the second EEG signal to statistically analyze the transitions of n candidate physiological states over time, i.e., the number of times a candidate physiological state transitions to other candidate physiological states at subsequent times. By calculating the proportion of this number to the total number of transitions, the transition probability between each candidate physiological state is obtained, and then a transition probability matrix is ​​constructed. This matrix intuitively reflects the dynamic transition patterns between candidate physiological states.

[0045] Next, for each candidate physiological state, its performance under multiple preset observation indicators is analyzed in conjunction with the second EEG signal. The frequency of each candidate physiological state conforming to the characteristics of each preset observation indicator is counted. The ratio of this frequency to the total number of counts is used as the observation probability, thereby obtaining multiple observation probabilities of each candidate physiological state under multiple preset observation indicators, thus quantifying the correlation strength between the candidate physiological state and the preset observation indicators.

[0046] Then, based on the observation probability of each candidate physiological state under multiple preset observation indicators, m preset observation indicators with higher observation probabilities are selected as candidate observation indicators corresponding to the target object. These indicators can more accurately reflect the physiological state characteristics of the target object.

[0047] Then, based on the observation probability of each candidate physiological state under m candidate observation indicators, an observation probability matrix is ​​constructed between n candidate physiological states and m candidate observation indicators. This matrix reflects the probabilistic correlation between the observation indicators and the candidate physiological states.

[0048] Next, using the transition probability matrix, the probability value of transitioning from the first physiological state to the target physiological state is determined, and this probability is set as the first probability.

[0049] Meanwhile, based on the observation probability matrix, the target observation index corresponding to the transition of the target physiological state in the first physiological state is located, and the observation probability corresponding to the index is used as the second probability, which reflects the degree of matching between the state and the observation index.

[0050] Finally, by comprehensively calculating the first probability and the second probability, the target probability of the target object having the target physiological state at the target time is obtained.

[0051] In this embodiment of the application, by constructing a transition probability matrix and an observation probability matrix, and comprehensively considering the matching degree between the transition trend of physiological state and the observation indicators, the probability prediction accuracy of the target object having a target physiological state at the target time is improved.

[0052] In a specific embodiment, the physiological state corresponding to the human physiological signal S(t) is W(t), and this human physiological signal can be an electroencephalogram (EEG) signal. It is assumed that the set of all possible states is as follows: N is the total number of candidate physiological states, and the set of all possible observation indicators is: M is the total number of all candidate observation indicators.

[0053] The transition probability matrix between states is: , in ), i,j=1,2,…,N; represent the state at time t. Under the condition that the state transitions at time t+1, The probability of.

[0054] The observation probability matrix is: , in ), i=1,2,…,N; k=1,2,…,M; indicating the state at time t. Observations generated under the conditions The probability of.

[0055] Based on the collected human physiological signal S(t), the number of defined states, and their relationship with the physiological signal, the state set W and the observation set V can be calculated, and the state transition probability matrix A and the observation probability matrix B can be calculated. Therefore, the predicted state W(t+1) for the next time is W(t) = A(t) × B(t) | W(t). In this way, the human physiological state at future time points can be inferred and predicted.

[0056] In one possible embodiment, in determining the transition probability matrix between n candidate physiological states based on the second EEG signal, the signal processing module is specifically configured to: The second EEG signal is segmented according to the time window to obtain the sub-EEG signal corresponding to each time window; Based on the first correspondence and the sub-EEG signals corresponding to each time window, the candidate physiological states corresponding to each time window are determined; The candidate physiological states corresponding to each time window are arranged in chronological order to obtain a physiological state sequence. Based on the physiological state sequence, determine the transition probability matrix between n candidate physiological states.

[0057] Specifically, a time window refers to a time segment in which a continuous second EEG signal is divided according to a preset duration. This segment is used to discretize the continuous signal into processable units. The time window can be preset, such as 10 seconds per window, or it can be determined based on the target time delay between the current time and the target time. For example, the length of the time window can be consistent with the target time delay. A sub-EEG signal refers to the EEG signal segment contained within each time window, which contains the characteristics of EEG activity within that time period. A physiological state sequence refers to an ordered sequence formed by arranging the candidate physiological states corresponding to each time window in chronological order, reflecting the evolution of physiological states over time.

[0058] The signal processing module first segments the second EEG signal according to preset time window parameters, obtaining several continuous and non-overlapping or partially overlapping sub-EEG signals. The time window parameters include the window duration and the sliding step size. The sliding step size can be equal to the window duration to avoid signal overlap, or less than the window duration to preserve signal continuity. Each sub-EEG signal corresponds to a time window, containing the EEG characteristics within that window, such as power of each frequency band and waveform rhythm.

[0059] Subsequently, based on the first correspondence, namely the mapping rule between EEG signals and physiological states, feature extraction and matching are performed on each sub-EEG signal. Specifically, key features of the sub-EEG signal, such as the proportion of delta waves and the peak frequency of alpha waves, are extracted and compared with the typical EEG features of each candidate physiological state recorded in the first correspondence. The matching degree is calculated, and the candidate physiological state with the highest matching degree is determined as the candidate physiological state corresponding to that time window.

[0060] Next, according to the order of the time windows, that is, the time sequence of the acquisition of the sub-EEG signals, the candidate physiological states corresponding to each window are arranged in sequence to form a physiological state sequence.

[0061] Finally, the transition frequencies between n candidate physiological states are statistically analyzed based on the physiological state sequence. Specifically, for each adjacent pair of states in the sequence, such as the first state in window t and the second state in window t+1, the number of transitions from the first state to the second state is recorded. For each first state, the total number of transitions to all other states is calculated, and then the number of transitions from the first state to the second state is divided by the total number of transitions to obtain the transition probability from the first state to the second state. Integrating all n×n transition probabilities forms the transition probability matrix between the n candidate physiological states.

[0062] In this embodiment of the application, continuous EEG signals are transformed into quantifiable state transition data through time window segmentation and state sequence analysis. The transition probability matrix calculated based on this can accurately reflect the dynamic transition law of physiological state.

[0063] In a specific embodiment, see Figure 6 , Figure 6 This is a schematic diagram illustrating the segmentation of a second EEG signal based on a time window, as provided in an embodiment of this application. As shown in the figure, the second EEG signal can be divided into 9 sub-EEG signals according to the time window. The 9 sub-EEG signals correspond to 9 physiological states, which are states 1 to 9, and the 9 physiological states can contain the same physiological state.

[0064] In one possible embodiment, regarding predicting a second probability of the presence of a target observation index in the first physiological state based on the observation probability matrix and the first physiological state, the signal processing module is specifically configured to: Based on the second EEG signal, the target observation index corresponding to the transition from the first physiological state to the target physiological state is determined from m candidate observation indicators; Based on the observation probability matrix, the probability of the target observation index existing in the first physiological state is determined, and the second probability is obtained.

[0065] Specifically, the second probability refers to the probability value of the target observation indicator appearing in the first physiological state, which is used to quantify the degree of matching between the physiological state and the observation indicator.

[0066] The signal processing module first analyzes the feature associations of the transition from the first physiological state to the target physiological state based on the second EEG signal. Specifically, it extracts the segment from the second EEG signal corresponding to the state transition process, analyzes the performance of m candidate observation indicators in the segment, such as the trend of indicator value changes and frequency of occurrence, and selects the candidate observation indicator with the most significant features in the transition process, such as the highest probability of occurrence and the strongest synchronization between the value change and the state transition, and determines it as the target observation indicator.

[0067] Subsequently, the constructed observation probability matrix is ​​invoked, and the row corresponding to the first physiological state and the column corresponding to the target observation index in the matrix are located. The probability value at the intersection of the row and column is the probability that the target observation index exists in the first physiological state, and it is determined as the second probability.

[0068] In one possible embodiment, in addition to determining the target time based on the current time, the target processing duration, and the target stimulus duration, the target time is also determined based on the calculation duration of the signal processing module.

[0069] In a specific embodiment, see Figure 7 , Figure 7 This is a schematic diagram of a three-stage delay provided in an embodiment of this application. For example... Figure 7 As shown, taking the time axis as an example, there are multiple delays between the current moment and the stimulus generation moment. Since the signal processing module has a calculation delay in addition to the acquisition delay, that is, the delay 2 between the acquisition completion moment and the calculation completion moment, the above embodiment has introduced how to calculate the delay 1 from the current moment to the acquisition completion moment, which is the first processing duration, and the delay 3 from the calculation completion moment to the stimulus generation moment, which is the first stimulus duration. Furthermore, in practical application scenarios, the target moment can be obtained by superimposing delay 1, delay 2 and delay 3 on the current moment. Delay 2 is the target computation duration, which can be preset or determined by performing multiple computation test operations on the signal processing module based on a computation delay test set. This computation delay test set includes multiple computation test signals, each corresponding to a computation test operation. Multiple first computation durations are determined based on the computation test signals of each computation test operation. Then, a third probability distribution is determined based on these multiple first computation durations. The third probability distribution reflects the third occurrence probability of each first computation duration. The target computation duration is determined based on the multiple third occurrence probabilities corresponding to the multiple first computation durations. The target computation duration is the first computation duration with the highest third occurrence probability among the multiple first computation durations. For example, the computation duration with the highest occurrence probability is used as delay 2.

[0070] In one possible embodiment, the target time is determined based on the current time, the target computation time, the target processing time, and the target stimulus time. Specifically, the current time is used as a starting reference, and the target computation time, target processing time, and target stimulus time are superimposed to obtain the target time.

[0071] In one possible embodiment, the first calculation duration is calculated as follows: the first calculation duration of each calculation test operation = the completion time of each calculation test operation - the transmission time of each calculation test signal - the target processing duration. For example, if the transmission time of the calculation test signal is 0 milliseconds, the completion time of the calculation test operation is 15 milliseconds, and the target processing duration is 10 milliseconds, then the first calculation duration of this calculation test operation is 5 milliseconds.

[0072] In one possible embodiment, the controller can also be connected to multiple trigger generators, each of which is connected to a stimulator and a signal acquisition unit. Thus, a single controller can perform stimulation operations on multiple target objects. Specifically, a trigger generator is a device for generating trigger signals. It receives instructions from the controller and outputs synchronization control signals to coordinate the timing of the stimulator and the signal acquisition unit.

[0073] In this embodiment, the controller establishes connections with multiple trigger generators to form a centralized control architecture. By centrally controlling multiple trigger generators and associated stimulators and signal acquisition devices through a single controller, unified scheduling of stimulation operations for multiple target objects is achieved, reducing equipment redundancy, improving synchronization and operational efficiency, and facilitating centralized monitoring and coordination of the stimulation process for multiple target objects.

[0074] This application also provides a physiological closed-loop stimulation method, which is applied to the aforementioned physiological closed-loop stimulation device. The physiological closed-loop stimulation device includes a control module, a signal processing module, and a stimulation module. See also... Figure 8 , Figure 8 This is a flowchart of a physiological closed-loop stimulation method provided in an embodiment of this application. Figure 8 As shown, the physiological closed-loop stimulation method provided in this application includes, but is not limited to, the following steps: Step S101: The control module performs multiple test operations on the signal processing module and the stimulation module; In each test operation, the control module sends a first test signal to the signal processing module and simultaneously sends a second test signal to the stimulation module. Step S102: After receiving the second test signal in each test operation, the stimulation module sends the third test signal to the signal processing module; Step S103: The signal processing module determines the target delay based on the first test signal and the third test signal corresponding to each test operation; Step S104: The signal processing module acquires the first EEG signal of the target object at the current moment; Step S105: The signal processing module determines the first physiological state of the target object at the current moment based on the first EEG signal; Step S106: The signal processing module predicts the probability that the target object will have the target physiological state at the target time based on the first physiological state. The time difference between the target time and the current time is the target delay; Step S107: When the target probability is higher than the preset probability, the stimulation module sends a stimulation signal to the target object.

[0075] It should be noted that each module in the above-mentioned physiological closed-loop stimulation method can perform the function of the corresponding module in the above-mentioned physiological closed-loop stimulation device.

[0076] See Figure 9 , Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 9 The illustrated electronic device includes a controller, a stimulator, a memory, a processor, a communication interface, and a bus. The controller, stimulator, memory, processor, and communication interface are interconnected via the bus. The electronic device can be the aforementioned physiological closed-loop stimulation device. The processor implements the functions of the aforementioned signal processing module. The controller implements the functions of the aforementioned control module. The stimulator implements the functions of the aforementioned stimulation module.

[0077] The processor can integrate the functions of the aforementioned signal processing module, for example, to acquire the target object's first EEG signal at the current moment; to determine the target object's first physiological state at the current moment based on the first EEG signal; and to predict the target probability that the target object will have the target physiological state at the target moment based on the first physiological state. The controller can integrate the functions of the aforementioned control module, for example, to perform multiple test operations on the processor and stimulator. The stimulator can integrate the functions of the aforementioned stimulation module, for example, to send a stimulation signal to the target object when the target probability is higher than a preset probability.

[0078] The memory can be read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory can store programs, and when the programs stored in the memory are executed by the processor, the processor and the communication interface are used to execute the various steps of the embodiments of this application.

[0079] The processor can be a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), graphics processing unit (GPU), or one or more integrated circuits to execute related programs.

[0080] The processor can also be an integrated circuit chip with signal processing capabilities. In implementation, each step in the target probability determination method of this application can be completed by the integrated logic circuits in the processor's hardware or by software instructions. The aforementioned processor can also be 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 devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory; the processor reads the information in the memory and, in conjunction with its hardware, completes the functions required by the embodiments of this application, or executes the various steps of the method embodiments of this application.

[0081] Communication interfaces use transceiver devices, such as, but not limited to, transceivers and input / output devices, to enable communication between electronic devices and other devices or communication networks.

[0082] A bus can include a path for transmitting information between various components of a device's electronic equipment.

[0083] It should be noted that, although Figure 9The illustrated electronic device only shows the controller, stimulator, memory, processor, and communication interface. However, those skilled in the art should understand that in actual implementation, the electronic device may also include other components necessary for normal operation. Furthermore, depending on specific needs, those skilled in the art should understand that the electronic device may also include hardware components to implement other additional functions. Moreover, those skilled in the art should understand that the electronic device may only include the components necessary for implementing the embodiments of this application, and may not necessarily include... Figure 9 All the devices shown.

[0084] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0085] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or modules may be electrical or other forms.

[0087] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0088] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software program modules.

[0089] If the integrated module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0090] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A physiological closed-loop stimulation device, characterized in that, The physiological closed-loop stimulation device includes a control module, a signal processing module, and a stimulation module; The control module is used to perform multiple test operations on the signal processing module and the stimulation module. In each test operation, the control module sends a first test signal to the signal processing module and simultaneously sends a second test signal to the stimulation module. The stimulation module is used to send a third test signal to the signal processing module after receiving the second test signal in each test operation. The signal processing module is used to determine the target delay based on the first test signal and the third test signal corresponding to each test operation; The signal processing module is also used to acquire the first EEG signal of the target object at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; The stimulation module is also used to send a stimulation signal to the target object when the target probability is higher than a preset probability.

2. The device as described in claim 1, characterized in that, In determining the target delay based on the first and third test signals corresponding to each test operation, the signal processing module is specifically used for: Based on the first moment and the second moment corresponding to each test operation, the first processing duration corresponding to each test operation is determined; the first moment is the moment when the first test signal is received in each test operation, and the second moment is the moment when the control module sends the first test signal in each test operation. The first stimulus duration corresponding to each test operation is determined based on the third and fourth moments corresponding to each test operation and the first processing duration; the third moment is the moment when the third test signal is received in each test operation, and the fourth moment is the moment when the control module sends the second test signal in each test operation. The target delay is determined based on the first processing duration and the first stimulus duration corresponding to each test operation.

3. The device as described in claim 2, characterized in that, In determining the target delay based on the first processing duration and the first stimulus duration corresponding to each test operation, the signal processing module is specifically used for: A first probability distribution is determined based on multiple first processing durations corresponding to the multiple test operations; the first probability distribution is used to reflect the first occurrence probability of each first processing duration. The target processing time is determined based on the multiple first occurrence probabilities corresponding to the multiple first processing times; The target processing time is the first processing time with the highest probability of occurrence among the plurality of first processing times; A second probability distribution is determined based on the duration of multiple first stimuli corresponding to the multiple test operations; the second probability distribution is used to reflect the second probability of occurrence for each duration of the first stimulus. The target stimulus duration is determined based on the multiple second occurrence probabilities corresponding to the multiple first stimulus durations; the target stimulus duration is the first stimulus duration with the highest second occurrence probability among the multiple first stimulus durations. The target delay is determined based on the target processing duration and the target stimulus duration.

4. The device as described in claim 2 or 3, characterized in that, The control module includes a sub-control unit and a signal triggering unit; regarding the execution of multiple test operations on the signal processing module and the stimulation module... The sub-control unit is used to send multiple signal triggering instructions to the signal triggering unit, and the multiple signal triggering instructions correspond one-to-one with the multiple test operations. The signal triggering unit is configured to respond to each signal triggering command sent by the sub-control unit, execute a test operation corresponding to the signal triggering command, and send a first test signal corresponding to the test operation to the signal processing module, and simultaneously send a second test signal corresponding to the test operation to the stimulation module.

5. The device as described in any one of claims 1-3, characterized in that, In determining the first physiological state of the target object at the current moment based on the first EEG signal, the signal processing module is specifically used for: Acquire the second EEG signal of the target object at the current moment; Based on the second EEG signal and the first correspondence, n candidate physiological states of the target object are determined; The first correspondence is used to indicate the mapping relationship between electroencephalogram (EEG) signals and physiological states; Based on the first EEG signal and the first correspondence, the first physiological state is determined from the n candidate physiological states.

6. The device as described in claim 5, characterized in that, In predicting the probability that the target object possesses the target physiological state at the target time based on the first physiological state, the signal processing module is specifically used for: Based on the second EEG signal, determine the transition probability matrix between the n candidate physiological states; Based on the second EEG signal, determine multiple observation probabilities for each candidate physiological state under multiple preset observation indicators; The plurality of preset observation indicators correspond one-to-one with the plurality of observation probabilities, and the observation probability under each preset observation indicator is used to indicate the probability that each candidate physiological state belongs to each preset observation indicator. Based on the multiple observation probabilities of each candidate physiological state under multiple preset observation indicators, determine m candidate observation indicators corresponding to the target object; Based on the observation probability of each candidate physiological state under the m candidate observation indicators, determine the observation probability matrix between the n candidate physiological states and the m candidate observation indicators; Based on the transition probability matrix and the first physiological state, predict the first probability of transitioning from the first physiological state to the target physiological state at the target time; Based on the observation probability matrix and the first physiological state, predict the second probability that the target observation index exists in the first physiological state; the target observation index is the candidate observation index among the m candidate observation indices that corresponds to the transition from the first physiological state to the target physiological state. The target probability is determined based on the first probability and the second probability.

7. The device as described in claim 6, characterized in that, In determining the transition probability matrix between the n candidate physiological states based on the second EEG signal, the signal processing module is specifically configured to: The second EEG signal is segmented according to the time window to obtain the sub-EEG signal corresponding to each time window; Based on the first correspondence and the sub-EEG signal corresponding to each time window, the candidate physiological state corresponding to each time window is determined; The candidate physiological states corresponding to each time window are arranged in chronological order to obtain a physiological state sequence. Based on the physiological state sequence, determine the transition probability matrix between the n candidate physiological states.

8. The device as described in claim 6, characterized in that, In predicting the second probability of the presence of a target observation index in the first physiological state based on the observation probability matrix and the first physiological state, the signal processing module is specifically used for: Based on the second EEG signal, a target observation indicator corresponding to the transition from the first physiological state to the target physiological state is determined from the m candidate observation indicators; Based on the observation probability matrix, the probability of the target observation index existing in the first physiological state is determined, and the second probability is obtained.

9. An electronic device, characterized in that, include: The electronic device includes a controller, a processor, a memory, and a stimulator. The processor is connected to the memory, which stores a computer program. The processor executes the computer program stored in the memory to cause the electronic device to perform the following steps: Multiple test operations are performed on the processor and the stimulator, wherein in each test operation the controller sends a first test signal to the processor and simultaneously sends a second test signal to the stimulator; After receiving the second test signal in each test operation, a third test signal is sent to the processor; The target delay is determined based on the first and third test signals corresponding to each test operation; Acquire the target object's first EEG signal at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; When the target probability is higher than the preset probability, a stimulus signal is sent to the target object.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions for performing the following steps: Multiple test operations are performed on the processor and the stimulator, wherein in each test operation the controller sends a first test signal to the processor and simultaneously sends a second test signal to the stimulator; After receiving the second test signal in each test operation, a third test signal is sent to the processor; The target delay is determined based on the first and third test signals corresponding to each test operation; Acquire the target object's first EEG signal at the current moment; Based on the first EEG signal, determine the first physiological state of the target object at the current moment; Based on the first physiological state, predict the target probability that the target object has the target physiological state at the target time; the time difference between the target time and the current time is the target delay; When the target probability is higher than the preset probability, a stimulus signal is sent to the target object.

Images