Method and system for processing physiological information

Abstract

The present disclosure relates to the field of medical technology, and in particular, to a method and system for processing physiological information. The method comprises: acquiring a physiological signal of a target object acquired by a physiological information acquisition apparatus; determining a first signal of the target object on the basis of the physiological signal, wherein the frequency range corresponding to the first signal is lower than a first predetermined threshold value; determining a first sub-band feature of at least one sub-band of a plurality of sub-bands in the first signal; and determining a noxious stimulation received by the target object at least on the basis of the first sub-band feature.

Description

Physiological information processing method and system TECHNICAL FIELD

[0001] The present specification relates to the technical field of medical treatment, and in particular to a physiological information processing method and system. BACKGROUND

[0002] Pain is a subjective experience, while nociceptive stimulation is an objective encoding of nociceptive stimulation, and during general anesthesia surgery, the patient is in an anesthetized state without the experience of pain. Nociceptive stimulation can reflect to some extent the degree of disturbance of the balance between nociceptive stimulation and the antagonistic relationship of analgesic drugs in the patient's body caused by the enhancement of external nociceptive stimulation during the operation, and by determining the nociceptive stimulation, the use of intraoperative analgesic drugs can be guided. If the analgesic drugs are not used enough, the intraoperative nociceptive stimulation will break the balance of the antagonistic effect of the analgesic drugs, which will cause the patient to have a strong physical stress response, and the most serious can cause intraoperative awareness. On the contrary, if the analgesic drugs are used in excess (such as excessive use of opioid drugs), it may induce drug side effects such as hyperalgesia.

[0003] Therefore, during the operation, how to accurately determine the nociceptive stimulation of the patient and then select the appropriate dose of analgesic drugs becomes a problem to be solved.

[0004] SUMMARY

[0005] One of the embodiments of the present specification provides a physiological information processing method, comprising: acquiring a physiological signal of a target object collected by a physiological information collection device; determining a first signal of the target object based on the physiological signal, the frequency range corresponding to the first signal being lower than a first preset threshold; determining a first sub-band feature of at least one of a plurality of sub-bands in the first signal; and determining the nociceptive stimulation received by the target object based on at least the first sub-band feature.

[0006] One of the embodiments of the present specification also provides a physiological information processing system, comprising: a physiological signal acquisition module for acquiring a physiological signal of a target object collected by a physiological information collection device; a first signal determination module for determining a first signal of the target object based on the physiological signal, the frequency range corresponding to the first signal being lower than a first preset threshold; a first sub-band feature determination module for determining a first sub-band feature of at least one of a plurality of sub-bands in the first signal; and a nociceptive stimulation determination module for determining the nociceptive stimulation received by the target object based on at least the first sub-band feature.

[0007] One of the embodiments of the present specification also provides a physiological information processing device, comprising a processor, characterized in that the processor is configured to execute the above-mentioned physiological information processing method.

[0008] One of the embodiments of the present specification also provides a computer readable storage medium, the storage medium stores computer instructions, when the computer reads the computer instructions in the storage medium, the computer executes the physiological information processing method described above. BRIEF DESCRIPTION OF DRAWINGS

[0009] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers refer to the same structures, wherein:

[0010] FIG. 1 is a schematic diagram of an application scenario of a physiological information processing system according to some embodiments of the present specification;

[0011] FIG. 2 is a schematic diagram of an exemplary computing device according to some embodiments of the present specification;

[0012] FIG. 3 is an exemplary flowchart of a physiological information processing method according to some embodiments of the present specification;

[0013] FIG. 4 is an exemplary flowchart of determining a first energy feature according to some embodiments of the present specification;

[0014] FIG. 5 is an exemplary flowchart of a physiological information processing method according to yet some embodiments of the present specification;

[0015] FIG. 6 is an exemplary block diagram of a physiological information processing system according to yet some embodiments of the present specification. DETAILED DESCRIPTION

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can also be applied to other similar scenarios without creative labor. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

[0017] It should be understood that the "system", "device", "unit" and / or "module" used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0018] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0019] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0020] In some scenarios, noxious stimulation to patients during surgery can be determined through indicators such as vasoconstriction and cardiac autonomic nervous system tone (SPI index) or changes in sinus rhythm with respiration (ANI index). However, the SPI index cannot effectively identify patients with heart lesions or abnormalities, and may only be applicable to patients undergoing general anesthesia. In actual surgery, many factors can interfere with the SPI index, such as patient population, surgical position, anesthesia method, patient consciousness, and whether vasoactive drugs are used, all of which may affect the accuracy of the SPI index. In addition, the ANI index reflects noxious stimulation and analgesia level by analyzing the variability of respiratory sinus arrhythmia (i.e., changes in sinus rhythm with respiration). It is easy to understand that factors that have a significant impact on respiration will also affect the measurement results of the ANI index.

[0021] In view of this, some embodiments of this specification provide a physiological information processing method and system, which collects the patient's physiological signals (such as EEG signals and / or EMG signals) and further processes the signals within a specific frequency range of the physiological signals to determine harmful stimuli.

[0022] FIG1 is a schematic diagram of an application scenario of a physiological information processing system according to some embodiments of this specification.

[0023] As shown in FIG. 1 , in some embodiments, a physiological information processing system 100 may include a physiological information collection device 110 , a processing device 120 , a storage device 130 , a terminal 140 , and a network 150 .

[0024] The physiological information acquisition device 110 refers to a device used by a user to acquire physiological signals (e.g., electroencephalogram signals and / or electromyogram signals) of a patient during an anesthesia process, such as an electroencephalogram monitor and an electromyograph, etc. In some embodiments, the physiological information acquisition device 110 can exchange data and / or information with other components (e.g., the processing device 120, the storage device 130, the terminal 140) in the system 100 through the network 150. In some embodiments, the physiological information acquisition device 110 can be directly connected with other components in the system 100. In some embodiments, one or more components (e.g., the processing device 120, the storage device 130, the terminal 140) in the system 100 can be included in the physiological information acquisition device 110.

[0025] The processing device 120 can process data and / or information obtained from other devices or system components, perform the physiological information processing method shown in some embodiments of the present specification based on the data, information and / or processing results, and complete one or more functions described in some embodiments of the present specification. For example, the processing device 120 can acquire information such as the intensity (amplitude) of the electroencephalogram / electromyogram of the patient based on the physiological information acquisition device 110. In some embodiments, the processing device 120 can acquire pre-stored data and / or information such as anesthetic drug categories, patient information, etc. from the storage device 130 for performing the physiological information processing method shown in some embodiments of the present specification.

[0026] In some embodiments, the processing device 120 can include one or more sub-processing devices (e.g., single-core processing devices or multi-core multi-core processing devices). For example only, the processing device 120 can include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction processor (ASIP), a graphics processing unit (GPU), a physics processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0027] The storage device 130 can store data or information generated by other devices. In some embodiments, the storage device 130 can store data and / or information acquired by the physiological information acquisition device 110. In some embodiments, the storage device 130 can store data and / or information processed by the processing device 120, such as the first sub-band feature and the second sub-band feature, etc. The storage device 130 can include one or more storage components, each of which can be a separate device or a part of other devices. The storage device can be local or implemented through the cloud.

[0028] The terminal 140 can control the operation of the physiological information acquisition apparatus 110. A physician can issue an operation instruction to the physiological information acquisition apparatus 110 through the terminal 140 to make the physiological information acquisition apparatus 110 complete a designated operation, for example, acquire the electroencephalogram information of the patient in a specific time period, etc. In some embodiments, the terminal 140 can make the processing device 120 perform parameter measurement as shown in some embodiments of the present specification through an instruction, etc. In some embodiments, the terminal 140 can receive information obtained during and / or after the processing process from the processing device 120, for example, determine the injurious stimulus suffered by the target object based on the first sub-band feature. In some embodiments, the terminal 140 can output the received information, for example, the terminal 140 can output (such as display, voice broadcast, etc.) the injurious stimulus of the patient. In some embodiments, the terminal 140 can be one or any combination of a mobile device 140-1, a tablet computer 140-2, a laptop computer 140-3, a desktop computer, etc. other devices with input and / or output functions.

[0029] The network 150 can connect the components of the system and / or connect the system with external resource parts. The network 150 enables communication between the components and other parts outside the system, and facilitates exchange of data and / or information. In some embodiments, one or more components in the system 100 (for example, the physiological information acquisition apparatus 110, the processing device 120, the storage device 130, the terminal 140) can send data and / or information to other components through the network 150. In some embodiments, the network 150 can be any one or more of a wired network or a wireless network.

[0030] It should be noted that the above description is provided for illustrative purposes only and is not intended to limit the scope of the present specification. Various changes and modifications can be made by those of ordinary skill in the art under the guidance of the present specification. The features, structures, methods and other characteristics of the exemplary embodiments described in the present specification can be combined in various ways to obtain additional and / or alternative exemplary embodiments. For example, the processing device 120 can be based on a cloud computing platform, such as a public cloud, a private cloud, a community cloud, and a hybrid cloud, etc. However, these changes and modifications will not depart from the scope of the present specification.

[0031] FIG. 2 is a schematic diagram of an exemplary computing device on which at least a part of the physiological information processing system 100 can be implemented, according to some embodiments of the present specification.

[0032] As shown in FIG. 2, the computing device 200 can include a processor 210, a memory 220, an input / output (I / O) 230, and a communication port 240.

[0033] The processor 210 can execute computer instructions (e.g., program code) and perform the functions of the processing device 120 according to the techniques described in this specification. The computer instructions can include, for example, routines, programs, objects, components, data structures, procedures, modules, and functions that perform particular functions described in this specification. For example, the processor 210 can process data or information obtained from the physiological information acquisition apparatus 110, the storage device 130, the terminal 140, and / or any other component of the physiological information processing system 100. In some embodiments, the processor 210 can include one or more hardware processors, any circuit or processor capable of executing one or more functions, etc., or a combination thereof.

[0034] For illustration only, only one processor is described in the computing device 200. However, it should be noted that the computing device 200 disclosed in this specification can also include multiple processors. Therefore, the operations and / or method steps disclosed in this specification as performed by one processor can also be performed jointly or separately by multiple processors. For example, if in this specification, the processor of the computing device 200 performs operation A and operation B, it should be understood that operation A and operation B can also be performed jointly or separately by two or more different processors in the computing device 200 (e.g., a first processor performs operation A, a second processor performs operation B, or a first processor and a second processor jointly perform operations A and B).

[0035] The memory 220 can store data / information obtained from the physiological information acquisition apparatus 110, the storage device 130, the terminal 140, and / or any other component of the physiological information processing system 100. In some embodiments, the memory 220 can include a mass storage, a removable storage, a volatile read / write memory, a read-only memory, etc., or any combination thereof. In some embodiments, the memory 220 in the computing device 200 can store a computer program, which can be executed by the processor 210 to implement the physiological information processing method.

[0036] The input / output 230 (I / O) can input and / or output signals, data, information, etc. In some embodiments, the input / output 230 can enable a user to interact with the processing device 120. In some embodiments, the input / output 230 can include input devices and output devices. Exemplary input devices can include a keyboard, a mouse, a touch screen, a microphone, etc., or a combination thereof. Exemplary output devices can include a display device, a speaker, a printer, a projector, etc., or a combination thereof. Exemplary display devices can include a liquid crystal display (LCD), a light-emitting diode (LED)-based display, a flat panel display, a curved screen, a television device, a cathode ray tube (CRT), a touch screen, etc., or a combination thereof.

[0037] The communication port 240 can be connected to a network (e.g., the network 150) to facilitate data communication. The communication port 240 can establish a connection between the processing device 120 and the physiological information collection apparatus 110, the storage device 130, and / or the terminal 140. The connection can be a wired connection, a wireless connection, any other communication connection that enables data transmission and / or reception, and / or a combination of these connections. The wired connection can include, for example, a cable, an optical cable, a telephone line, etc., or any combination thereof. The wireless connection can include, for example, Bluetooth, Wi-Fi, WiMax, a wireless local area network, ZigBee, a mobile network (e.g., 3G, 4G, 5G), etc., or a combination thereof. In some embodiments, the communication port 240 can be and / or include a standardized communication port, such as, for example, RS232, RS485, etc. In some embodiments, the communication port 240 can be a specially designed communication port. For example, the communication port 240 can be designed according to the Digital Imaging and Communications in Medicine (DICOM) protocol.

[0038] FIG. 3 is an exemplary flowchart of a physiological information processing method according to some embodiments of the present specification. As shown in FIG. 3, the flow 300 includes the following steps. In some embodiments, one or more steps in the flow 300 can be performed by the processor 210.

[0039] At step 310, a physiological signal of a target object collected by a physiological information collection apparatus is obtained. In some embodiments, step 310 can be performed by a physiological signal collection module.

[0040] Further description of the physiological information collection apparatus can be found in relation to the physiological information collection apparatus 110 of FIG. 1, which will not be repeated here.

[0041] The physiological signal of the target object (i.e., the patient) can include an electroencephalogram signal and / or an electromyogram signal. In some embodiments, the electroencephalogram signal and / or the electromyogram signal can be collected by the physiological information collection apparatus on the forehead of the target object. In some embodiments, the electroencephalogram signal and the electromyogram signal can be collected simultaneously or separately by the physiological information collection apparatus.

[0042] In some embodiments, the frequency range of the physiological signal can be between 0 and 500 Hz. In some embodiments, the frequency range of the physiological signal can be controlled to be between 0.5 and 200 Hz to reduce the amount of data in the physiological signal processing process.

[0043] In some embodiments, the electroencephalogram signal and the electromyogram signal in the electrical signal collected by the physiological information collection apparatus can be superimposed or mixed with each other, and therefore, the electrical signal can be processed, for example, by a mathematical model to separate the electroencephalogram signal from the electromyogram signal for subsequent processing.

[0044] In some embodiments, to reduce the interference in the physiological signal, a filter such as a power frequency filter, a direct current filter, etc. can also be used on the electrical signal collected by the physiological information collection device to remove the interference components in the collected signal. In some embodiments, an artifact removal algorithm can also be used to remove artifacts in the signal collected by the physiological information collection device to avoid affecting the physiological signal.

[0045] At step 320, a first signal of the target object is determined based on the physiological signal. In some embodiments, step 320 can be performed by a first signal determination module.

[0046] In some embodiments, the frequency range corresponding to the first signal is lower than a first preset threshold. Further processing of the signal of a specific frequency in the physiological signal can better determine the harmful stimulus received by the target object.

[0047] The first preset threshold can be set by a doctor or other operator according to experience or actual needs. In some embodiments, in the process of determining the harmful stimulus received by the target object through the physiological signal, the first signal can be mainly analyzed in the feature of the electroencephalogram signal, i.e., the physiological signal with a frequency range of 0.5-40 Hz is obtained as the first signal, and the corresponding first preset threshold can be set to 40 Hz. In some embodiments, the physiological signal with a frequency range of 0-44 Hz can be obtained as the first signal to determine the process of the harmful stimulus received by the target object, and at this time the first preset threshold can be set to 44 Hz.

[0048] In some embodiments, the first signal can be in the form of a frequency domain signal or a time domain signal. Generally, the physiological signal of the target object collected by the physiological information collection device is a time domain signal, and in order to obtain the first signal in the form of a frequency domain signal, in some embodiments, frequency domain conversion can also be performed in the process of determining the first signal of the target object based on the physiological signal to obtain the first signal in the form of a frequency domain signal.

[0049] In some embodiments, the first signal of the target object can be determined by filtering the physiological signal, for example, by using a band-pass filter, ICA filtering, etc. The manner of filtering is not limited in the present specification.

[0050] At step 330, a first sub-band feature of at least one sub-band in a plurality of sub-bands in the first signal is determined. In some embodiments, step 330 can be performed by a first sub-band feature determination module.

[0051] A sub-band refers to a part of the first signal, and a segment of the first signal can include a plurality of sub-bands. In some embodiments, the first signal can be segmented in a certain manner to obtain a plurality of segments, and each segment corresponds to a sub-band.

[0052] Similar to the first signal, the sub-band can be in the form of a frequency domain signal or a time domain signal. In some embodiments, the plurality of sub-bands obtained by dividing the first signal in the form of a time domain signal are also in the form of a time domain signal, and each sub-band can be referred to as a time band. The plurality of sub-bands obtained by dividing the first signal in the form of a frequency domain signal are also in the form of a frequency domain signal, and each sub-band can be referred to as a frequency band. In some embodiments, the time band or the frequency band can be converted as needed (for example, by Fourier transform to convert the time band or the frequency band into each other).

[0053] The first sub-band feature is characteristic data capable of representing the corresponding sub-band part information of the first signal, and the first sub-band feature can be obtained by processing the sub-band. In some embodiments, the first sub-band feature can include, for example, a first relative energy, a first energy rate of change, or an energy entropy feature, and specific details can be referred to in the relevant description below.

[0054] At step 340, the nociceptive stimulation received by the target object is determined based at least on the first sub-band feature. In some embodiments, step 340 can be performed by a nociceptive stimulation determination module.

[0055] The nociceptive stimulation received by the target object reflects the degree to which the balance between the nociceptive stimulation and the antagonism of the analgesic drug in the patient's body is broken due to the enhancement of the external sudden stimulation during the surgical procedure.

[0056] In some embodiments, the nociceptive stimulation received by the target object can be a numerical value, for example, the nociceptive stimulation can be a value between 1 and 100, and the higher the value of the nociceptive stimulation, the more intense the nociceptive stimulation received by the target object. In some embodiments, in order to better determine the degree of nociceptive stimulation received by the target object, the nociceptive stimulation received by the target object can be divided into multiple intervals. For example, when the nociceptive stimulation is between 0 and 30, it represents that the antagonistic balance is difficult to break; when the nociceptive stimulation is between 31 and 60, it represents that the antagonistic balance can be broken; and when the nociceptive stimulation is between 61 and 100, it represents that the antagonistic balance is easy to break.

[0057] In some embodiments, the nociceptive stimulation received by the target object can be determined based on the first sub-band features of a plurality of sub-bands within a period of time. For example, assuming that data of a 30-second period is selected to determine the nociceptive stimulation, and there are 10 sub-bands in this period, then the first sub-band features of each of the 10 sub-bands can be converted into a stimulation factor based on a preset algorithm, and the average value of the 10 stimulation factors can be calculated to obtain the nociceptive stimulation received by the target object, wherein the preset algorithm can convert the input first sub-band feature into a stimulation factor with a value range of 0 to 100.

[0058] In some embodiments, information contained in the sub-band frequency domain signal can be acquired, and thus the first sub-band feature can include a first relative energy and a first energy change rate, and the processor can determine the injurious stimulus received by the target object based on at least the first relative energy and the first energy change rate.

[0059] In step 330, a first energy feature corresponding to at least one of the plurality of sub-bands in the first signal can be determined first; and based on the first energy feature, a first relative energy and a first energy change rate can be determined.

[0060] The first energy feature is a feature of a sub-band (frequency band) in the form of a frequency domain signal. In some embodiments, the first energy feature can represent the energy distribution at different frequencies within the frequency space of the signal, so as to facilitate subsequent calculations. By determining the energy distribution of the signal within the frequency space, the injurious stimulus received by the target object can be better determined.

[0061] In some embodiments, the first energy feature can be acquired by a specific algorithm. For example, the first energy feature corresponding to a sub-band can be acquired by wavelet transform (WT), a spectrum estimation method (such as the Bartlett method, the Welch method, or a method using an autocorrelation function), or the like.

[0062] In some embodiments, in order to determine the first energy feature, step 330 can further include:

[0063] Step 410, determining a first time window based on the frequency range of the first signal.

[0064] The time window is a sampling interval corresponding to a frequency signal, and different time windows can be used for different frequency ranges. In some embodiments, the first time window can include a plurality of time windows corresponding to a plurality of different frequency ranges.

[0065] In some embodiments, for signals with higher frequencies, a smaller time window can be used to obtain higher time resolution; for signals with lower frequencies, a larger time window can be used to obtain more signal cycles within the same frequency, preventing information loss during time-frequency analysis.

[0066] For example, for a signal with a frequency of 0.5 Hz, the period is 2 s, and if a 1 s time window is used, each event length will only contain half a period. Therefore, in some embodiments, the first time window can be configured as follows: for signals in the first signal with a frequency range of 0.5-4 Hz, the corresponding first time window is 10 s; for signals with a frequency range of 4-50 Hz, the corresponding first time window is 4 s; for signals with a frequency range of 50-200 Hz, the corresponding first time window is 2 s; and for high-frequency signals (such as signals greater than 200 Hz), the corresponding first time window is 1 s.

[0067] Step 420: Based on a first preset interval, the first signal is divided into a first time window to obtain a plurality of sub-bands.

[0068] The preset interval represents the time interval for sampling based on the time window. In some embodiments, the same preset interval can be used for different time windows, or different preset intervals can be used for different time windows. For ease of description, in the following examples, the same first preset interval is used for a first time window including multiple different time windows, and the first preset interval is 1 second.

[0069] Based on the first preset interval, the first signal is segmented through the first time window to obtain multiple sub-bands with a duration equal to the length of the time window corresponding to the frequency. For example, for a signal with a frequency range of 0.5 to 4 Hz as mentioned above, the corresponding first time window is 10 seconds, and the first preset interval is 1 second. Then, after segmentation, the sub-band duration is 10 seconds, and the starting point of the next sub-band is 1 second after the start time of the previous sub-band. That is, assuming that the first sub-band corresponds to the signal from time 0s to 10s in the first signal, the next sub-band corresponds to the signal from time 1s to 11s in the first signal, and the next sub-band corresponds to the signal from time 2s to 12s in the first signal, and so on. Then, based on the first preset interval, the time slice can be further segmented into multiple sub-bands. Multiple sub-bands are obtained by segmentation.

[0070] Step 430: Perform frequency domain conversion on the signal of at least one sub-band to obtain corresponding frequency domain features, and determine a first energy feature based on the frequency domain features.

[0071] In some embodiments, the first energy signature can be represented as X (n) , where n = 0, 1, 2, …, N-1, N is the number of subbands, and n is the sequence number of the subband.

[0072] As mentioned above, the subband can be in the form of a frequency domain signal or a time domain signal. In some embodiments, when the subband is a time domain signal, the first energy feature can be determined by converting the subband into a corresponding frequency domain feature. Specifically, the subband in the form of a time domain signal can be expressed as x (n) In some embodiments, the formula X (n) =DFT[x (n) ], for x (n) Perform a Fast Fourier Transform (FFT) to obtain frequency domain information; where DFT[·] is a discrete Fourier transform function, and the Fast Fourier Transform is an efficient computational form of the discrete Fourier transform function.

[0073] In some embodiments, when the sub-band is a frequency domain signal, the first energy feature X can be directly determined.(n) .

[0074] The first time window determined in the above manner can better obtain the characteristics of signals in different frequency ranges, reduce the loss of information in the segmentation process, and facilitate further calculation by the subbands segmented by the first time window.

[0075] In some embodiments, after the step 430 obtains the first energy feature, the process of further determining the first relative energy and the first energy change rate can further include:

[0076] In step 440, based on the first energy features corresponding to the plurality of subbands, a total energy feature is determined.

[0077] The total energy feature is the sum of the first energy features corresponding to the plurality of subbands. In some embodiments, the total energy feature can be represented as total_value, and the total energy feature can be calculated by total_value=∑X (n) ; wherein X (n,i) _value represents the i-th frequency band feature of the n-th subband, low i represents the lower limit of the i-th frequency band, and high i represents the upper limit of the i-th frequency band. A frequency band represents a signal in a smaller frequency range, and a subband can include multiple frequency bands. Taking the alpha frequency band commonly used in electroencephalogram signals as an example, the frequency band range is generally between 8-12 Hz. For the above formula, the corresponding low i is 8 Hz, and the high i is 12 Hz.

[0078] In step 450, based on the first energy feature and the total energy feature, a first relative energy is determined.

[0079] The first relative energy represents the proportion of the corresponding first energy feature in the total energy feature. In some embodiments, the first relative energy can include a group of relative energy values. For the i-th frequency band feature of the n-th subband, the relative energy value can be represented as Y (n,i) _value. The calculation formula of the relative energy value can be represented as: The relative energy value Y (n,i) _value ranges from 0 to 1, and represents the proportion of the energy of a specific frequency band (i-th frequency band) in the total energy of the frequency band, i.e., more energy is concentrated in a certain frequency band.

[0080] In step 460, based on the first energy feature of the subband and the first energy feature of the adjacent subband, a first energy change rate is determined.

[0081] The first energy change rate indicates the degree of energy change of a group of adjacent subbands. In some embodiments, the first energy change rate can be the change rate relative to the previous subband of the current subband, or the change rate relative to the next subband of the current subband.

[0082] In some embodiments, the first energy change rate can include a variation rate Z (n,i) _value or a standard deviation SD (n,i) _value. Taking the variation rate as an example, the variation rate of the i-th frequency band of the n-th subband can be obtained by calculating .

[0083] The harmful stimulus received by the target object is a sudden stimulus from the outside world. After receiving the harmful stimulus, the physiological signal will change accordingly. Therefore, the relative energy and the energy change rate obtained by the above method can better reflect the intensity of the harmful stimulus.

[0084] In some embodiments, the information contained in the time domain signal in the time domain form of the subband can be directly obtained. Therefore, in some embodiments, the first subband feature can include an energy entropy feature. In some embodiments, step 330 can include: determining a first time window based on the frequency range of the first signal; based on a first preset interval, the first signal is divided by the first time window to obtain a plurality of subbands; and determining an energy entropy feature based on the signal of at least one subband.

[0085] The determination method of the first time window and the method of dividing the first signal by the first time window based on the first preset interval can be the same as described above. For details, please refer to the description of steps 410-420.

[0086] In some embodiments, determining an energy entropy feature based on the signal of at least one time domain signal form subband can include calculating the fuzzy entropy or approximate entropy of a plurality of subbands, etc. In some embodiments, for the signal of the subband in the frequency domain signal form, the signal of the subband in the time domain signal form can be obtained by frequency domain conversion (such as by the fast Fourier transform described above), and the energy entropy feature is further calculated.

[0087] By calculating the energy entropy of the subband in the time domain signal form, the complexity of the energy change of the subband signal can be measured, which can provide a reference for calculating the harmful stimulus received by the target object.

[0088] In some embodiments, at least a part of the first relative energy and the first energy change rate can be input into a trained first evaluation model to obtain the harmful stimulus. In some embodiments, the first evaluation model is a machine learning model obtained by training. In some embodiments, the first evaluation model can be a neural network model, such as a convolutional neural network (CNN), a deep neural network (DNN), etc.

[0089] In some embodiments, the input of the first evaluation model can be one or more first relative energies and one or more first energy change rates, the number of input first relative energies and first energy change rates can be the same or different; the output of the model is the harmful stimulus received by the target object determined based on the first sub-band features.

[0090] In some embodiments, the determined first sub-band features include first relative energies and first energy change rates corresponding to multiple sub-bands and different frequency bands in the sub-bands, and not all first relative energies and first energy change rates corresponding to all sub-bands and different frequency bands in the sub-bands have the same importance. For example, when the frequency intervals of certain frequency bands overlap, only selecting part of the first relative energies and the first energy change rates can obtain the features of the signal.

[0091] In some embodiments, the input of the first evaluation model includes: first, sorting according to the repetition degree of the lower limit and upper limit of the frequency of the frequency band in the sub-band; then selecting the first relative energy and the first energy change rate corresponding to the frequency band in the sub-band with low repetition degree to input into the trained first evaluation model.

[0092] In some embodiments, the higher the repetition degree of the lower limit and upper limit of the frequency of the frequency band in the sub-band, the more the frequency interval of the frequency band overlaps with the frequency interval of other frequency bands, and therefore selecting the frequency band in the sub-band with low repetition degree and inputting the corresponding first relative energy and first energy change rate into the trained first evaluation model can make the input data of the model more representative and avoid increasing invalid information due to overlapping of frequency intervals, so as to make the information amount in the input data larger.

[0093] For example, in some embodiments, assuming that 5 groups of frequency bands are selected, the frequency ranges of the frequency bands can be 0.5-4 Hz, 4-15 Hz, 15-60 Hz, 60-200 Hz, and 200-1000 Hz, respectively. It can be seen that the frequency bands thus selected only have the frequency of the end point repeated, so that each frequency band has a larger information amount.

[0094] In some embodiments, the first evaluation model can be a classification model, which can divide the harmful stimulus into n classes, for example, n=10, then corresponding to 10 interval harmful stimuli. The classification model can be trained by supervised learning through training samples containing labels.

[0095] Specifically, in some embodiments, the initial first evaluation model can be trained by the training samples to adjust the first evaluation model parameters as the goal of reducing the value of the loss function, and when the value of the loss function converges or reaches a preset number of iterations, the current model can be taken as the trained first evaluation model. Wherein, the loss function can be a commonly used loss function of a classification model, which is not limited in the specification.

[0096] The training sample includes a sample sub-band feature as training data and a harmful stimulus determined based on blood pressure corresponding to the sample sub-band feature as a label; the sample sub-band feature includes a sample frequency range corresponding to the sample sub-band, a sample relative energy, and a sample energy change rate. The training sample can use the sub-band feature obtained during the historical surgery process as the sample sub-band feature. In some embodiments, the sample sub-band feature includes a sample frequency range corresponding to the sample sub-band, a sample relative energy, and a sample energy change rate; wherein the sample relative energy and the sample energy change rate corresponding to the sub-band obtained during the historical surgery process can be obtained in a manner similar to steps 410-460 described above. The change of blood pressure is mainly due to the imbalance of sympathetic and parasympathetic nerves, which can to some extent depict the harmful stimulus received by the target object, and therefore, in some embodiments, blood pressure is used as a reference standard for harmful stimulus, and the harmful stimulus determined by blood pressure is used as a label corresponding to the sample sub-band feature. In some embodiments, the blood pressure during the historical surgery process can be the actual blood pressure condition obtained after excluding interference factors such as vasoactive drugs and muscle relaxants according to the actual situation of the historical surgery, and further determining the harmful stimulus as a label.

[0097] In the medical field, expert knowledge (prior knowledge) has great value, in addition, different patient individual differences are large, which may result in contradictory data in actual data, and traditional algorithms cannot effectively solve this problem. Therefore, in order to take into account the expert knowledge, in some embodiments, the first evaluation model can be a fuzzy neural network model. Fuzzy neural network is a product of the combination of fuzzy theory and neural network or deep learning network, which integrates the advantages of neural network and fuzzy theory. In some embodiments, the first evaluation model at least includes a membership function calculation layer and a rule layer.

[0098] In some embodiments, the membership function calculation layer is obtained based on the membership function constructed based on the sample first sub-band feature. The sample first sub-band feature at least includes a sample relative energy and a sample energy change rate. The membership function calculation layer is used to convert the input variable (i.e. the first relative energy and the first energy change rate) into fuzzy values, which represent the degree to which the input variable belongs to a certain fuzzy set.

[0099] The membership function calculation layer includes a preset set of membership functions, each function corresponding to a fuzzy set, and each input variable can obtain its membership corresponding to each fuzzy set. For example, including three fuzzy sets of "low", "medium", "high", that is, each input can obtain the membership corresponding to the three fuzzy sets respectively.

[0100] In some embodiments, the shape of the membership function is Gaussian. Specifically, in some embodiments, the membership function μ(x) can be expressed as: where x is the input variable of the membership function, c is the center of the Gaussian function (representing the center value of the fuzzy set), and σ is the standard deviation (controlling the width of the membership function). It should be noted that in some embodiments, the shape of the membership function can also be other forms, such as bell-shaped or parabolic.

[0101] In some embodiments, the rule layer can be obtained based on a fuzzy rule database, which is constructed based on prior knowledge. The rule layer is used to define the logical basis of the fuzzy neural network model, that is, how to infer the fuzzy value of the output variable (i.e. the harmful stimulus) according to the fuzzy value of the input variable. Prior knowledge includes expert knowledge in the medical field, and prior knowledge is usually stored in the form of "if-then" in the fuzzy rule database. For example, a piece of prior knowledge can be expressed as "if the first relative energy is high and the first energy rate is medium, then the harmful stimulus is high".

[0102] In some embodiments, the fuzzy neural network model can obtain the harmful stimulus by performing three steps of fuzzification (converting input variables to fuzzy values), reasoning (applying fuzzy rules), and defuzzification (converting fuzzy results to specific output results) according to its fuzzy logic reasoning function. In some embodiments, in the defuzzification step, algorithms such as centroid method (center average method), maximum membership degree method, etc. can be used to convert the output result of fuzzy reasoning to a specific value, i.e. the harmful stimulus.

[0103] In some embodiments, the membership function calculation layer and the rule layer can be integrated into a neural network (or deep learning network) structure to obtain an initial fuzzy neural network model, and the initial fuzzy neural network model can automatically adjust the parameters of the membership function (such as the center c and the standard deviation σ of the Gaussian function mentioned above) and the weights of the prior knowledge in the rule database through training samples. The training samples and training methods of the initial fuzzy neural network model can be the same as those of the classification model mentioned above, which will not be described here.

[0104] The trained fuzzy neural network model can take into account expert knowledge and effectively solve data that is prone to contradictions, thereby enabling the trained fuzzy neural network model to more accurately determine the harmful stimulus received by the target object.

[0105] To make the result of determining the target object suffering from the harmful stimulation more comprehensive, in some embodiments, the physiological information processing method can further include:

[0106] In step 510, a second signal of the target object is determined based on the physiological signal.

[0107] In some embodiments, the frequency range corresponding to the second signal is higher than a second preset threshold. It should be noted that the second preset threshold can be higher than, lower than, or equal to the first preset threshold. As described above, the first signal is mainly the electroencephalogram signal, and the first preset threshold can be set to 40 Hz. The second signal can be mainly the electromyogram signal, and in some embodiments, the second preset threshold is set to 30 Hz. Since the frequency range of the selected physiological signal can be between 0.5 and 200 Hz, the frequency range of the second signal is between 30 and 200 Hz. It should be noted that in some embodiments, the frequency range of the second signal can also be between 40 and 200 Hz, and the second preset threshold and the first preset threshold are both 40 Hz, reducing the overlap between the first signal and the second signal.

[0108] In some embodiments, the second signal can be in the form of a frequency domain signal or a time domain signal.

[0109] In step 520, a second sub-band feature of at least one sub-band in the plurality of sub-bands in the second signal is determined.

[0110] As described above, in some embodiments, the first sub-band feature includes the first relative energy and the first energy change rate. Similarly to the first sub-band feature, the second sub-band feature can include the second relative energy and the second energy change rate.

[0111] In some embodiments, determining the second sub-band feature of at least one sub-band in the plurality of sub-bands in the second signal includes: determining a second time window based on the frequency range of the second signal; dividing the second signal by the second time window based on a second preset interval to obtain a plurality of sub-bands; performing frequency domain conversion on the signal of at least one sub-band in the plurality of sub-bands to obtain a corresponding frequency domain feature, and calculating a second energy feature based on the frequency domain feature; and determining the second relative energy and the second energy change rate based on the second energy feature.

[0112] The determination method of the second time window can be the same as or similar to the first time window. Since the second signal is similar to the first signal, the only difference is that the frequency ranges of the two are different. Therefore, the determination method of the second energy feature, the second relative energy, and the second energy change rate can be similar to the determination method of the first energy feature, the first relative energy, and the first energy change rate. For details, please refer to the related description of steps 410-440.

[0113] At step 530, the harmful stimulation received by the target object is determined based on the first sub-band feature and the second sub-band feature.

[0114] In some embodiments, the harmful stimulation received by the target object can be determined based on both the first sub-band feature and the second sub-band feature, or the initial harmful stimulation can be determined based on the first sub-band feature or the second sub-band feature, and the initial harmful stimulation is further corrected by the other sub-band feature.

[0115] In some embodiments, the harmful stimulation received by the target object can be determined by a second evaluation model.

[0116] The input of the second evaluation model includes the first sub-band feature, the muscle relaxant use information, and the second relative energy and the second energy change rate, and the output of the model is the harmful stimulation. The muscle relaxant use information can include whether muscle relaxant is used in the current operation and the amount of use. Since the second signal corresponds to the electromyographic signal, adding the muscle relaxant use information can make the output result of the model more objective.

[0117] In some embodiments, the input of the second evaluation model can only include the second relative energy and the second energy change rate corresponding to the high-frequency sub-band in the second sub-band feature. The high-frequency sub-band in the second sub-band feature can be a sub-band with a frequency greater than 50 Hz. Compared with the first sub-band feature corresponding to the first information, the high-frequency sub-band pays more attention to the information in the electromyographic signal, and increases the amount of information of the input of the model (i.e., the second relative energy and the second energy change rate part).

[0118] In some embodiments, the training data and the training method of the second evaluation model are similar to those of the first evaluation model, which will not be described here. The difference between the two is that the sample sub-band feature in the training data of the second evaluation model also includes sample muscle relaxant use information.

[0119] By simultaneously using the electroencephalogram signal and the electromyographic signal, the state of the target object can be more comprehensively analyzed, and thus a more objective and stable harmful stimulation can be obtained.

[0120] In some embodiments, the second sub-band feature can be input into a third evaluation model, and the output of the model is the muscle activity level of the target object; the harmful stimulation is verified based on the muscle activity level, and the harmful stimulation and / or the prompt information is adjusted according to the verification result.

[0121] The third evaluation model is a machine learning model obtained by training; and the second sub-band feature includes the second relative energy and the second energy change rate. In some embodiments, the training data and the training method of the third evaluation model are similar to those of the first evaluation model, which will not be described here.

[0122] In some embodiments, the muscle activity level can be a value similar to the nociceptive stimulus. Verifying the nociceptive stimulus based on the muscle activity level can include comparing the values of the muscle activity level and the nociceptive stimulus, for example, by correlation analysis, consistency test, etc., to obtain a verification result.

[0123] In some embodiments, if the verification result indicates that the correlation / consistency between the muscle activity level and the nociceptive stimulus is poor, the nociceptive stimulus and / or the output prompt information can be adjusted.

[0124] In some embodiments, the way to adjust the nociceptive stimulus based on the verification result can be that if the increase in muscle activity level does not lead to a corresponding increase in nociceptive stimulus, it is considered that the nociceptive stimulus may underestimate the actual stimulation intensity; if the muscle activity level decreases but the nociceptive stimulus increases, it may indicate that the nociceptive stimulus overestimates the actual stimulation intensity, and based on this, the nociceptive stimulus is corrected to determine a new nociceptive stimulus and output. In some embodiments, the nociceptive stimulus can also be adjusted in other ways, such as adjusting the nociceptive stimulus based on the preset weight of the muscle activity level and the nociceptive stimulus, etc.

[0125] In some embodiments, the prompt information is used to remind the doctor that the current output of the nociceptive stimulus result may not be accurate or high / low, and suggests continuous observation, etc. In some embodiments, the prompt information can also provide relevant suggestions for operation based on the inconsistent verification result, for example, suggesting re-evaluating the patient's pain state / considering adjusting the analgesic drug dose, etc.

[0126] Since the electromyogram is significantly affected by the muscle relaxants used in surgery, in some scenarios, the electromyogram is not directly used to participate in the determination of the nociceptive stimulus, but the result of the electromyogram is used to verify the result of the nociceptive stimulus determined by the electroencephalogram, which helps to further improve the accuracy of the determined nociceptive stimulus.

[0127] In some embodiments, verifying the nociceptive stimulus based on the muscle activity level can further include determining the degree of stress muscle activity based on the muscle activity level; and verifying the nociceptive stimulus according to the degree of stress muscle activity.

[0128] In some embodiments, the stress muscle activity can be divided into yes and no, and the stress muscle activity is further used to determine whether the interval of the nociceptive stimulus is accurate. For example, if there is stress muscle activity, it means that the nociceptive stimulus is sufficient to stimulate muscle activity, at this time the nociceptive stimulus should at least be between 31-60, if the current nociceptive stimulus is not located in this interval, a prompt can be output.

[0129] In some embodiments, the muscle activity level can be divided into multiple levels, and the level of stress muscle activity can be determined. For example, assuming that the muscle activity level is a value between 0 and 100, the muscle activity level of 0-20 can be divided into stress muscle activity level 1, the muscle activity level of 21-40 can be divided into stress muscle activity level 2, the muscle activity level of 41-60 can be divided into stress muscle activity level 3, the muscle activity level of 61-80 can be divided into stress muscle activity level 4, and the muscle activity level of 81-100 can be divided into stress muscle activity level 5, so as to obtain the stress muscle activity. It should be noted that in some embodiments, the multiple levels of stress muscle activity and the noxious stimulus can not be one-to-one corresponding, for example, stress muscle activity level 1 and 2 can correspond to a lower interval of noxious stimulus (such as 0-30 interval).

[0130] Since the muscle activity level is greatly affected by the use of muscle relaxants, it is difficult to directly use the muscle activity level to determine the noxious stimulus, and then the level of stress muscle activity is used to indirectly verify whether the noxious stimulus is in the appropriate interval, which can better verify the noxious stimulus determined based on the electroencephalogram signal to improve the accuracy.

[0131] In some embodiments, the verification of the noxious stimulus can be realized by a fourth evaluation model. In some embodiments, the verification of the noxious stimulus based on the muscle activity level comprises: inputting the muscle activity level into the fourth evaluation model, and the model outputs a first noxious stimulus risk value; comparing the noxious stimulus and the first noxious stimulus risk value to verify the noxious stimulus; wherein the fourth evaluation model is a fuzzy neural network model.

[0132] In some embodiments, the value range of the first noxious stimulus risk value can be the same as that of the noxious stimulus, for example, the first noxious stimulus risk value and the noxious stimulus can be a value between 0 and 100.

[0133] In some embodiments, the fourth evaluation model can include a membership function calculation layer and a rule layer. The membership function calculated based on the sample muscle activity level is obtained, and the membership function calculated based on the sample muscle activity level can be consistent with the membership function μ(x) calculated based on the sample first sub-band feature in the foregoing, so as to map the muscle activity level to a fuzzy set (for example, including “low”, “medium”, “high”, “severe fluctuation” and the like), and the shape of the membership function is Gaussian type. The rule layer is obtained based on a fuzzy rule database, and the fuzzy rule database is constructed based on prior knowledge. In some embodiments, the form of the prior knowledge can be “if the muscle activity level is high, the risk of the patient being subjected to the noxious stimulus is high”; “if the muscle activity level is low, the risk of the patient being subjected to the noxious stimulus is low”; “if the muscle activity level fluctuates severely, the risk of the patient being subjected to the noxious stimulus is high” and the like.

[0134] In some embodiments, the membership function calculation layer and the rule layer can be integrated into one neural network (or deep learning network) structure to obtain an initial fuzzy neural network model, and the initial fuzzy neural network model can automatically adjust the parameters of the membership function and the weights of the prior knowledge in the rule database through training samples. The training samples and the training method of the initial fuzzy neural network model can be the same as those of the fuzzy neural network model described above, and will not be described here.

[0135] In some embodiments, the second sub-band feature can be directly input into the fifth evaluation model, the model outputs a second nociceptive stimulus risk value, and the nociceptive stimulus is verified based on the second nociceptive stimulus risk value.

[0136] In some embodiments, the fifth evaluation model is a fuzzy neural network model, and the fifth evaluation model includes a membership function calculation layer and a rule layer.

[0137] The membership function calculation layer is obtained based on a membership function constructed based on sample second sub-band features. The membership function constructed based on sample second sub-band features can be consistent with the membership function μ(x) constructed based on sample first sub-band features described above, so as to map the sample second sub-band features to a fuzzy set (for example, a fuzzy set including “low”, “medium”, “high”, etc.), and the shape of the membership function is Gaussian. The rule layer is obtained based on a fuzzy rule database, and the fuzzy rule database is constructed based on prior knowledge. The prior knowledge can be expressed as “if the second relative energy is high, and the second energy change rate is medium, then the nociceptive stimulus is high”.

[0138] In some embodiments, the membership function calculation layer and the rule layer can be integrated into one neural network (or deep learning network) structure to obtain an initial fuzzy neural network model, and the initial fuzzy neural network model can automatically adjust the parameters of the membership function and the weights of the prior knowledge in the rule database through training samples. The training samples and the training method of the initial fuzzy neural network model can be the same as those of the fuzzy neural network model described above, and will not be described here.

[0139] Similar to the first nociceptive stimulus risk value output by the fourth evaluation model, in some embodiments, the second nociceptive stimulus risk value output by the fifth evaluation model can be used to replace the nociceptive stimulus to verify the nociceptive stimulus. The difference is that the second nociceptive stimulus risk value obtained by the fifth evaluation model does not need to reflect the muscle activity condition of the second sub-band feature, but is directly used to verify the nociceptive stimulus, which is suitable for a scene that pays more attention to the data condition of the second sub-band feature.

[0140] The expert knowledge and the machine learning model are combined through the fuzzy algorithm, the nociceptive stimulation obtained from the electromyogram signal is effectively verified, and the verified nociceptive stimulation is more accurate and can reflect the objective situation of the target object.

[0141] It should be noted that the above description of the flow 300, the steps 410-460 and the steps 510-530 is only for example and illustration, and does not limit the scope of the present specification. Those skilled in the art can make various modifications and changes to the flow 300, the steps 410-460 and the steps 510-530 under the guidance of the present specification. However, these modifications and changes are still within the scope of the present specification.

[0142] FIG. 6 is an exemplary block diagram of a physiological information processing system according to yet some embodiments of the present specification. As shown in FIG. 6, in some embodiments, the physiological information processing system 600 can include a physiological signal acquisition module 610, a first signal determination module 620, a first sub-band feature determination module 630 and a nociceptive stimulation determination module 640.

[0143] The physiological signal acquisition module 610 can be configured to acquire the physiological signal of the target object collected by the physiological information acquisition device.

[0144] In some embodiments, more description about the physiological signal of the target object can be referred to the content related to the step 310, which will not be repeated here.

[0145] The first signal determination module 620 can be configured to determine a first signal of the target object based on the physiological signal, the first signal corresponding to a frequency range lower than a first preset threshold.

[0146] In some embodiments, more description about the first signal can be referred to the content related to the step 320, which will not be repeated here.

[0147] The first sub-band feature determination module 630 can be configured to determine a first sub-band feature of at least one of a plurality of sub-bands in the first signal.

[0148] In some embodiments, more description about the first sub-band feature can be referred to the content related to the step 330, which will not be repeated here.

[0149] The nociceptive stimulation determination module 640 can be configured to determine a nociceptive stimulation received by the target object based on at least the first sub-band feature.

[0150] In some embodiments, more description about the nociceptive stimulation received by the target object can be referred to the content related to the step 340, which will not be repeated here.

[0151] Having described the basic concepts, it is obvious that the above detailed disclosure is intended to be illustrative only and not restrictive of the present description. Although the present description has been described with reference to specific exemplary embodiments, it will be apparent to those having ordinary skill in the art that a variety of modifications, improvements and / or alterations can be made to the present description. Such modifications, improvements and / or alterations are therefore contemplated and are within the spirit and scope of the exemplary embodiments of the present description.

[0152] Also, the present description can use particular terminology when describing embodiments of the present description. For example, the terms "one embodiment," "an embodiment," "some embodiments," or "one alternative" are used interchangeably, and mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present description. The appearances of the phrase "in one or more embodiments" or "in at least one embodiment" in various places in the specification are not necessarily referring to the same embodiment.

[0153] Furthermore, the order of presentation of the processes and steps of the methods described herein are not necessarily the order in which the processes and steps are performed. Also, the use of numbering and / or letters in the examples, if any, are not intended to limit the number of various aspects, methods, parameters, and / or other parameters, but are used for illustrative purposes. Although the present description has been described with reference to exemplary embodiments, it is understood that the terms used are intended to describe illustrative embodiments and not to limit the claimed invention. Various modifications, changes, omissions, combinations, sub-combinations and / or additions of one or more specific embodiments disclosed herein are also within the scope of others embodiments as can occur to one skilled in the art. Therefore, the application should not be restricted to one or more embodiments, but should be understood to include all alternatives, modifications and / or substitutions for one or more elements by one of ordinary skill in the art.

[0154] Similarly, it is to be noticed that the term "comprising", used in the present description, should not be interpreted as being restricted to the means provided by the ensuing enumeration, but is intended to cover the presence of any additional element that is not specified in the description. Also, the use of "a" or "an" terms is not intended to be construed to mean only one of the possible elements, but rather, is used to describe at least one of the possible elements. Furthermore, the use of the term "about" is intended to cover variations that are reasonably close to the value being described, such as within 10% of the value being described.

[0155] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0156] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0157] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A physiological information processing method, comprising: Acquiring physiological signals of the target object collected by the physiological information collection device; determining a first signal of the target object based on the physiological signal, wherein a frequency range corresponding to the first signal is lower than a first preset threshold; determining a first sub-band characteristic of at least one of the plurality of sub-bands in the first signal; The harmful stimulus suffered by the target object is determined based at least on the first sub-band feature.

2. The method according to claim 1, wherein The first sub-band characteristic includes a first relative energy and a first energy change rate; and determining the first sub-band characteristic of at least one of the plurality of sub-bands in the first signal includes: determining a first energy characteristic corresponding to at least one of the plurality of sub-bands in the first signal; Based on the first energy characteristic, the first relative energy and the first energy change rate are determined.

3. The method according to claim 2, wherein determining a first energy characteristic corresponding to at least one of the plurality of sub-bands in the first signal comprises: determining a first time window based on a frequency interval of the first signal; Based on a first preset interval, dividing the first signal by the first time window to obtain the plurality of sub-bands; Perform frequency domain conversion on a signal of at least one of the sub-bands to obtain corresponding frequency domain features, and determine the first energy feature based on the frequency domain features.

4. The method of claim 3, wherein determining the first relative energy and the first energy change rate based on the first energy characteristic comprises: determining a total energy feature based on the first energy features corresponding to the plurality of sub-bands; determining the first relative energy based on the first energy characteristic and the total energy characteristic; The first energy change rate is determined based on the first energy characteristic of the sub-band and the first energy characteristic of an adjacent sub-band.

5. The method according to claim 1, wherein The first sub-band feature includes an energy entropy feature; The determining a first sub-band characteristic of at least one of the plurality of sub-bands in the first signal comprises: determining a first time window based on a frequency interval of the first signal; Based on a first preset interval, dividing the first signal by the first time window to obtain the plurality of sub-bands; The energy entropy feature is determined based on a signal of at least one of the sub-bands.

6. The method according to claim 2, wherein determining the harmful stimulus suffered by the target object based at least on the first sub-band feature comprises: At least a portion of the first relative energy and the first energy change rate are input into a trained first evaluation model to obtain the harmful stimulus; wherein the first evaluation model is a trained machine learning model.

7. The method of claim 6, wherein inputting at least a portion of the first relative energy and the first energy change rate into a trained first evaluation model comprises: Sorting the sub-bands according to the repetition of the lower frequency limit and the upper frequency limit of the frequency band; The first relative energy and the first energy change rate corresponding to the sub-band frequency band with low repetition ranking are selected and input into the trained first evaluation model.

8. The method according to claim 7, wherein the first evaluation model is a classification model, and the trained first evaluation model is obtained by: Constructing a training sample, wherein the training sample includes sample sub-band features as training data and noxious stimuli corresponding to the sample sub-band features and determined based on blood pressure as labels; the sample sub-band features include a sample frequency range, sample relative energy, and sample energy change rate corresponding to the sample sub-band; An initial first evaluation model is trained based on the training samples, and model parameters are adjusted to obtain the trained first evaluation model.

9. The method according to claim 7, wherein the first evaluation model is a fuzzy neural network model, and the first evaluation model comprises: A membership function calculation layer is obtained based on a membership function constructed based on the first sub-band feature of the sample, wherein the shape of the membership function is Gaussian; The rule layer is obtained based on a fuzzy rule database, which is constructed based on prior knowledge.

10. The method of claim 1, further comprising: determining a second signal of the target object based on the physiological signal, wherein a frequency range corresponding to the second signal is higher than a second preset threshold; determining a second subband characteristic of at least one subband among a plurality of subbands in the second signal; The determining the harmful stimulus suffered by the target object based at least on the first sub-band feature includes: The harmful stimulus suffered by the target object is determined based on the first sub-band feature and the second sub-band feature.

11. The method of claim 10, wherein the first sub-band characteristic comprises a first relative energy and a first energy change rate; and the second sub-band characteristic comprises a second relative energy and a second energy change rate. The determining a first sub-band characteristic of at least one of the plurality of sub-bands in the first signal comprises: determining a first energy characteristic corresponding to at least one of the plurality of sub-bands in the first signal; determining the first relative energy and the first energy change rate based on the first energy characteristic; The determining a second sub-band characteristic of at least one of the plurality of sub-bands in the second signal comprises: determining a corresponding second energy characteristic of at least one of the plurality of subbands in the second signal; Based on the second energy characteristic, the second relative energy and the second energy change rate are determined.

12. The method according to claim 11, wherein determining a first energy characteristic corresponding to at least one of the plurality of sub-bands in the first signal comprises: determining a first time window based on a frequency interval of the first signal; Based on a first preset interval, dividing the first signal by the first time window to obtain the plurality of sub-bands; Performing frequency domain conversion on a signal of at least one of the sub-bands to obtain corresponding frequency domain features, and determining the first energy feature based on the frequency domain features; The determining a second energy characteristic corresponding to at least one of the sub-bands in the second signal includes: determining a second time window based on a frequency interval of the second signal; Based on a second preset interval, dividing the second signal by the second time window to obtain the plurality of sub-bands; Perform frequency domain conversion on a signal of at least one of the multiple sub-bands to obtain a corresponding frequency domain feature, and calculate the second energy feature based on the frequency domain feature.

13. The method according to claim 11, wherein determining the harmful stimulus suffered by the target object based on the first sub-band feature and the second sub-band feature comprises: Inputting the first sub-band feature, muscle relaxant usage information, and the second relative energy and the second energy change rate corresponding to the high-frequency sub-band in the second sub-band feature into a trained second evaluation model to obtain a noxious stimulus; wherein the second evaluation model is a trained machine learning model; The harmful stimulus received by the target object is determined based on the harmful stimulus.

14. The method according to claim 10, wherein the second sub-band feature is a second relative energy and a second energy change rate; and determining the noxious stimulus to the target object based on the first sub-band feature and the second sub-band feature comprises: inputting the second sub-band features into a third evaluation model to obtain the muscle activity level of the target object; The third evaluation model is a trained machine learning model; verifying the noxious stimulus based on the muscle activity level; The harmful stimulation is adjusted and / or prompt information is output according to the verification result.

15. The method of claim 14, wherein the verifying the noxious stimulus based on the muscle activity level comprises: determining a degree of irritative muscle activity based on the muscle activity level; The noxious stimulus is verified according to the degree of the irritative muscle activity.

16. The method of claim 14, wherein the verifying the noxious stimulus based on the muscle activity level comprises: inputting the muscle activity level into a fourth assessment model to obtain a first noxious stimulus risk value; The noxious stimulus is verified by comparing the noxious stimulus with the first noxious stimulus risk value; wherein the fourth evaluation model is a fuzzy neural network model, and the fourth evaluation model includes: A membership function calculation layer is obtained based on a membership function constructed based on the sample muscle activity level, wherein the shape of the membership function is Gaussian; The rule layer is obtained based on a fuzzy rule database, which is constructed based on prior knowledge.

17. The method according to claim 10, wherein the second sub-band feature is a second relative energy and a second energy change rate; and determining the harmful stimulus to the target object based on the first sub-band feature and the second sub-band feature comprises: inputting the second sub-band feature into a fifth evaluation model to obtain a second harmful stimulus risk value; The harmful stimulus is verified based on the second harmful stimulus risk value; wherein the fifth evaluation model is a fuzzy neural network model, and the fifth evaluation model includes: A membership function calculation layer is obtained based on a membership function constructed based on the second sub-band features of the sample, wherein the shape of the membership function is Gaussian; The rule layer is obtained based on a fuzzy rule database, which is constructed based on prior knowledge.

18. A physiological information processing system comprising: A physiological signal acquisition module is used to acquire the physiological signals of the target object collected by the physiological information acquisition device; a first signal determining module, configured to determine a first signal of the target object based on the physiological signal, wherein a frequency range corresponding to the first signal is lower than a first preset threshold; A first sub-band feature determination module, configured to determine a first sub-band feature of at least one of the multiple sub-bands in the first signal; The harmful stimulus determination module is configured to determine the harmful stimulus suffered by the target object based at least on the first sub-band feature.

19. A physiological information processing device, comprising a processor, characterized in that: The processor is used to execute the physiological information processing method according to any one of claims 1 to 17.

20. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the physiological information processing method according to any one of claims 1 to 17.

Images