Physiological signal processing method and device based on human factor intelligence, model training and prediction method and device based on human factor intelligence, edge equipment and medium

Abstract

The invention discloses a physiological signal processing method and device based on human intelligence, a model training and prediction method and device based on human intelligence, edge equipment and a medium. The physiological signal processing method based on human intelligence comprises the following steps: acquiring reference physiological data; extracting a plurality of data segments from the reference physiological data; performing feature extraction on the plurality of data fragments to obtain a plurality of initial feature data; and fusing the plurality of initial feature data to obtain a baseline feature which is used as a reference feature for physiological state prediction.

Description

Technical Field

[0001] The present invention relates to technical fields such as computer vision and human intelligence, and in particular to a method, device, edge device and medium for physiological signal processing, model training and prediction based on human intelligence. Background Art

[0002] Physiological signals have attracted extensive attention from researchers because they can objectively and truly reflect an individual's physiological, mental, and emotional states. However, how to process physiological signal data to obtain the required key feature information has become the focus of research.

[0003] Related technologies usually directly extract a data segment from the collected physiological signals for related processing to obtain baseline features. The baseline features rely on personal experience in selecting data segments, resulting in low accuracy and reference value of the baseline features. Subsequent related data processing based on the baseline features will affect the accuracy of the processing results. Summary of the invention

[0004] The embodiments of the present invention aim to solve at least one of the technical problems in the related art to a certain extent. To this end, one object of the present invention is to propose a physiological signal processing method based on human factor intelligence, a training method for a physiological state model, a physiological state prediction method, an apparatus, an edge device and a storage medium to improve the accuracy and reference of baseline characteristics.

[0005] An embodiment of the present invention provides a physiological signal processing method based on human factors intelligence. The physiological signal processing method based on human factors intelligence includes: obtaining reference physiological data; extracting multiple data segments from the reference physiological data; performing feature extraction on the multiple data segments respectively to obtain multiple initial feature data; fusing the multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

[0006] Exemplarily, each initial feature data includes I sub-feature data, where I is an integer greater than or equal to 1; multiple initial feature data are fused to obtain baseline features, including: for the i-th sub-feature data corresponding to each initial feature data, multiple i-th sub-feature data corresponding to the multiple initial feature data are processed to obtain feature values, where 1≤i≤I; and based on the I feature values, the baseline features are obtained.

[0007] Exemplarily, the reference physiological data includes data corresponding one-to-one to K acquisition moments, where K is an integer greater than 1; extracting multiple data segments from the reference physiological data includes: extracting each data segment from the reference physiological data according to a preset data length k, wherein 1≤k≤K, the data length of each data segment is the preset data length k, and there may or may not be duplication between any two data segments among the multiple data segments.

[0008] Exemplarily, the reference physiological data includes M sequence data, where M is an integer greater than or equal to 1, and each sequence data is acquired through a corresponding data acquisition channel; multiple data fragments are extracted from the reference physiological data, including: extracting part of the sequence data from each sequence data to obtain M subsequence data, and the M subsequence data constitute a data fragment.

[0009] Exemplarily, the reference physiological data includes N groups of data, where N is an integer greater than or equal to 1, and each group of data is obtained by collecting data from the corresponding person being tested; each group of data includes M sequence data, where M is an integer greater than or equal to 1, and each sequence data is collected through a corresponding data acquisition channel; multiple data fragments are extracted from the reference physiological data, including: for M×N sequence data, extracting part of the sequence data from each sequence data to obtain M×N subsequence data, and the M×N subsequence data constitute a data fragment.

[0010] Another embodiment of the present invention provides a training method for a physiological state model, and the training method for the physiological state model includes: obtaining physiological sample data, wherein the physiological sample data includes a state label; performing feature extraction on the physiological sample data to obtain sample feature data; performing standardization on the sample feature data based on baseline features to obtain standardized sample feature data, wherein the baseline features are obtained based on the above-mentioned physiological signal processing method based on human factors intelligence; inputting the standardized sample feature data into the physiological state model to be trained to perform state prediction to obtain a physiological state prediction result; and adjusting the model parameters of the physiological state model to be trained based on the physiological state prediction result and the state label.

[0011] Another embodiment of the present invention provides a physiological state prediction method, which includes: acquiring physiological data to be predicted; performing feature extraction on the physiological data to be predicted to obtain target feature data; performing standardization processing on the target feature data based on baseline features to obtain standardized target feature data, wherein the baseline features are obtained based on the above-mentioned physiological signal processing method based on human factors intelligence; inputting the standardized target feature data into a trained physiological state model to perform state prediction to obtain a physiological state prediction result.

[0012] Another embodiment of the present invention provides a physiological signal processing device based on human factors intelligence, and the physiological signal processing device based on human factors intelligence includes: a first acquisition module, used to acquire reference physiological data; a first extraction module, used to extract multiple data segments from the reference physiological data, perform feature extraction on the multiple data segments respectively, and obtain multiple initial feature data; a fusion module, used to fuse the multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

[0013] Another embodiment of the present invention provides a training device for a physiological state model, and the training device for the physiological state model includes: a second acquisition module, used to acquire physiological sample data, wherein the physiological sample data includes a state label; a second extraction module, used to perform feature extraction on the physiological sample data to obtain sample feature data; a first processing module, which performs standardization on the sample feature data based on the baseline feature to obtain standardized sample feature data, wherein the baseline feature is obtained based on the above-mentioned physiological signal processing device based on human factors intelligence; a first prediction module, which inputs the standardized sample feature data into the physiological state model to be trained for state prediction to obtain a physiological state prediction result; and an adjustment module, which adjusts the model parameters of the physiological state model to be trained based on the physiological state prediction result and the state label.

[0014] Another embodiment of the present invention provides a physiological state prediction device, which includes: a third acquisition module, used to acquire physiological data to be predicted; a third extraction module, used to perform feature extraction on the physiological data to be predicted to obtain target feature data; a second processing module, used to perform standardization processing on the target feature data based on baseline features to obtain standardized target feature data, wherein the baseline features are obtained based on the above-mentioned physiological signal processing device based on human factors intelligence; and a second prediction module, used to input the standardized target feature data into a trained physiological state model for state prediction to obtain a physiological state prediction result.

[0015] Another embodiment of the present invention provides an edge device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of any one of the above embodiments when executing the computer program.

[0016] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of any one of the above embodiments are implemented.

[0017] In the above implementation, the physiological signal processing method based on human factor intelligence includes: obtaining reference physiological data; extracting multiple data segments from the reference physiological data; performing feature extraction on the multiple data segments respectively to obtain multiple initial feature data; fusing the multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction. The above method extracts features from multiple data segments to obtain multiple initial feature data, and fuses the multiple initial feature data to obtain baseline features, thereby improving the accuracy and reference of baseline features.

[0018] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a physiological signal processing method based on human factors intelligence provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of extracting features of resting-state brain physiological signals provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of acquiring physiological signal data of multiple individuals provided by an embodiment of the present invention;

[0022] Figure 4 A flow chart of a physiological state model training method provided by another embodiment of the present invention;

[0023] Figure 5 A schematic diagram of extracting physiological signal features of a brain task state provided by another embodiment of the present invention;

[0024] Figure 6 A flow chart of a physiological state prediction method provided by another embodiment of the present invention;

[0025] Figure 7 A block diagram of a physiological signal processing device based on human factors intelligence provided by another embodiment of the present invention;

[0026] Figure 8 A block diagram of a training device for a physiological state model provided by another embodiment of the present invention;

[0027] Fig. 9 This is a block diagram of a physiological state prediction device provided in another embodiment of the present invention. DETAILED DESCRIPTION

[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0029] Physiological signals have attracted extensive attention from researchers because they can objectively and truly reflect an individual's physiological, mental, and emotional states. However, how to process physiological signal data to obtain the required key feature information has become the focus of research.

[0030] When using machine learning methods to obtain baseline features, you can obtain physiological signal data of the brain over a period of time and extract features, subtract or divide the brain task state data from the baseline features, or divide them after subtraction, to obtain the feature information needed for the study as baseline features. When using a purely offline method to obtain baseline features, you can extract data fragments from a period of time before the event, and extract the features of the data as baseline features. The selection of data fragments is interfered by factors such as stability, and the selection of data fragments is more biased towards personal experience, which will affect the results of subsequent data processing based on baseline features.

[0031] To this end, an embodiment of the present invention provides a physiological signal processing method based on human factors intelligence. By extracting features from multiple data segments, multiple initial feature data are obtained, and the multiple initial feature data are fused to obtain baseline features. This method solves the deviation problem caused by human experience and too few baseline feature extraction samples. It is more suitable for use in real-time operations for the same subject in different time periods and across subjects, and is more stable, and improves the accuracy and reference of baseline features.

[0032] This article uses brain electrophysiological information data as an example to explain the physiological signal processing method based on human intelligence. Brain electrophysiological information data is divided into resting state data and task state data. Task state mainly refers to the state of the brain when it performs specific tasks such as memory, recognition, and movement, while resting state refers to the state when the brain does not perform specific cognitive tasks, remains quiet, relaxed, and awake. It is the basic state and essential state among the various complex states of the brain.

[0033] Figure 1 A flow chart of a physiological signal processing method based on human factors intelligence provided by an embodiment of the present invention;

[0034] like Figure 1 As shown, the physiological signal processing method 100 based on human intelligence includes steps S110 to S140.

[0035] Step S110, obtaining reference physiological data.

[0036] Exemplarily, physiological signals of an individual are collected to obtain reference physiological data, and the reference physiological data includes, for example, physiological signal data such as electroencephalogram, electrocardiogram, electrodermal conductivity, electromyography, blood oxygen, respiration, and pupil.

[0037] Step S120: extracting a plurality of data segments from the reference physiological data.

[0038] Exemplarily, multiple data are extracted from the reference physiological data according to corresponding rules to form multiple data segments.

[0039] Step S130, extracting features from the multiple data segments respectively to obtain multiple initial feature data.

[0040] Exemplarily, for a plurality of data segments, feature extraction is performed on each data segment to obtain a plurality of feature data, and the plurality of feature data are used as initial feature data.

[0041] Step S140, fusing multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

[0042] For example, for the brain, baseline characteristics usually refer to feature data obtained by extracting and fusing the brain's resting state data. When predicting the physiological state (usually the task state), it is necessary to extract features from the task state data, perform correlation operations on the obtained feature data and the baseline characteristics, and input the results into the relevant model to obtain the predicted results of the physiological state.

[0043] In the above embodiment, by performing feature extraction on multiple data segments to obtain multiple initial feature data, and fusing the multiple initial feature data to obtain baseline features, this method solves the problem of deviation caused by human experience and too few baseline feature extraction samples, and improves the accuracy and reference value of baseline features.

[0044] Figure 2 A schematic diagram of extracting features of resting-state brain physiological signals provided in an embodiment of the present invention.

[0045] The reference physiological data includes M sequence data, where M is an integer greater than or equal to 1, and each sequence data is acquired through a corresponding data acquisition channel; extracting multiple data fragments from the reference physiological data, including: extracting part of the sequence data from each sequence data to obtain M subsequence data, and the M subsequence data constitute a data fragment.

[0046] For example, Figure 2 As shown in the figure, the horizontal axis represents the time of collecting physiological data, and the vertical axis represents the channel. Reference physiological data is obtained through different collection channels. For example, M sequence data are collected through M channels. Figure 2 In the example, the reference physiological data includes 14 sequence data (ie, M=14), and each sequence data corresponds to a data acquisition channel.

[0047] by Figure 2 For example, 6 data segments are extracted from the reference physiological data, namely data segment 01, data segment 02, data segment 03, data segment 04, data segment 05, and data segment 06. Each data segment corresponds to extracting partial sequence data from each sequence data. Taking data segment 01 as an example, data segment 01 obtains partial sequence data from 14 sequence data, and 14 subsequence data can be obtained. Data segment 01 is composed of 14 subsequence data.

[0048] In the above embodiment, when a single channel is used for data collection, since there is no need for complex multi-channel synchronization and coordination circuits, the cost is low and it is easy to implement and operate. When multiple channels are used for data collection, different types of data from multiple channels can be collected simultaneously, which greatly improves the efficiency of data collection, and can obtain richer information and accurately analyze the status of the person being measured.

[0049] In one example, the reference physiological data includes data corresponding to K collection moments one by one, where K is an integer greater than 1; extracting multiple data segments from the reference physiological data includes: extracting each data segment from the reference physiological data according to a preset data length k, wherein 1≤k≤K, the data length of each data segment is the preset data length k, and there may or may not be duplication between any two data segments among the multiple data segments.

[0050] For example, Figure 2 As shown, the time of the horizontal axis includes multiple acquisition moments (i.e., K acquisition moments), and 6 data segments are extracted from the reference physiological data, namely, data segment 01, data segment 02, data segment 03, data segment 04, data segment 05, and data segment 06. Taking the extraction of data segment 01 as an example, when extracting M=14 sequence data, 14 subsequence data of length k can be obtained according to the preset length k, thereby forming data segment 01. Figure 2 As shown, there are repeated parts among data segments 01, data segments 02, data segments 03, data segments 04, data segments 05, and data segments 06, and there may also be non-repeated parts. The repeated parts are taken as an example in the analysis, but are not specifically limited.

[0051] In the above embodiment, when extracting data segments, multiple data segments are extracted according to the preset data length, which avoids the problem of small sampling samples at a single moment and the problem of mismatched lengths between data, and is more in line with the use scenario of real-time prediction. In addition, if there is no duplication between data segments, more and richer information can be extracted from the reference physiological data to obtain baseline features. If there is duplication between data segments, it is suitable for scenarios with less data volume of reference physiological data.

[0052] In one embodiment, the feature data may be extracted and used as the initial feature data.

[0053] For example, feature extraction processing may be performed on multiple data segments according to preset feature indicators to obtain feature data corresponding to the preset feature indicators, and the multiple feature data corresponding to the preset feature indicators are used as initial feature data.

[0054] The preset characteristic indicators may include, for example: (δ+θ+α+β) total energy, δ wave absolute energy, θ wave absolute energy, α wave absolute energy, β wave absolute energy, Renyi entropy, wavelet transform (Wavelet Transform), wavelet absolute mean (Wavelet Absolute Mean), Fourier transform average coefficient (FFT Mean Coefficient), minimum index, maximum index, average index, variance index, standard deviation index, differential median index, spectrum maximum peak index, etc. The preset characteristic indicators can be set according to actual conditions, and examples are not given one by one here.

[0055] In another embodiment, a neural network may be used to extract features of multiple data segments to obtain initial feature data.

[0056] For example, the subsequence data corresponding to each data segment is input into a neural network for feature extraction to obtain initial feature data.

[0057] Neural networks include, for example, long short-term memory networks (LSTM), bidirectional long short-term memory networks BiLSTM, etc., and may also be other networks that can extract features from time series data.

[0058] As a deep learning method, neural networks have powerful signal processing and recognition capabilities. Neural networks can be applied to the analysis of physiological signals. When using neural networks to detect physiological signals, you first need to select a suitable network structure and set corresponding parameters to learn and train physiological data. Compared with traditional machine learning algorithms that require manual feature extraction and screening, neural networks can automatically select and extract features from input physiological data, reducing labor costs and improving feature extraction effects.

[0059] In another example, each initial feature data includes I sub-feature data, where I is an integer greater than or equal to 1; multiple initial feature data are fused to obtain baseline features, including: for the i-th sub-feature data corresponding to each initial feature data, multiple i-th sub-feature data corresponding to the multiple initial feature data are processed to obtain feature values, where 1≤i≤I; and based on the I feature values, the baseline features are obtained.

[0060] For example, Figure 2 As shown in FIG. 1 , feature extraction is performed on data segments 01, 02, 03, 04, 05, and 06 to obtain 6 initial feature data. Taking the initial feature data corresponding to data segment 01 as an example, it includes I sub-feature data, namely, X 1,1 , X 1,2 …X 1,I-1 , X 1,I By fusing the 6 initial feature data corresponding to the 6 data segments, an initial feature matrix of size 6xI can be obtained. By performing a median operation on each column of the initial feature matrix, the eigenvalue of each column can be obtained, that is, I eigenvalues ​​can be obtained. By concatenating the I eigenvalues, the baseline feature can be obtained.

[0061] For example, taking the first column of the initial feature matrix as an example (i.e., i=1), the median of the six sub-feature data in the first column is taken to obtain the eigenvalue m1. In this way, I eigenvalues ​​can be obtained. By concatenating the I eigenvalues, the baseline feature [m1, m2, …, m I-1 ,m I ].

[0062] In the above embodiment, when processing the sub-feature data of the multiple initial feature data, the median is taken. Compared with the mean, the median can avoid the problem of unstable baseline features caused by encountering the maximum and minimum values, and the median is more stable. Of course, in addition to the median, other feature values ​​can also be used, such as weighted average, median, etc.

[0063] Figure 3 A schematic diagram of acquiring physiological signal data of multiple individuals provided in an embodiment of the present invention.

[0064] The reference physiological data includes N groups of data, where N is an integer greater than or equal to 1, and each group of data is obtained by collecting data from the corresponding person being tested; each group of data includes M sequence data, where M is an integer greater than or equal to 1, and each sequence data is collected through a corresponding data acquisition channel; and multiple data fragments are extracted from the reference physiological data, including: for M×N sequence data, extracting part of the sequence data from each sequence data to obtain M×N subsequence data, and the M×N subsequence data constitute a data fragment.

[0065] For example, Figure 3 As shown in the figure, the horizontal axis represents the time of collecting physiological data, and the vertical axis represents the channel. The reference physiological data in the figure is N groups, that is, N persons under test, each of which includes M sequence data, and the M sequence data are collected from M channels respectively. Taking the extraction of data segment 01 as an example, partial sequence data are extracted from persons under test 1, persons under test 2, ... persons under test respectively, for example, M partial sequence data are extracted from person under test 1 to obtain M subsequence data, and M partial sequence data are extracted from person under test 2 to obtain M subsequence data, and so on, M×N subsequence data are obtained, and M×N subsequence data constitute data segment 01.

[0066] In the above embodiment, multiple sequence data of multiple subjects can be extracted and analyzed. This method is more suitable for use in real-time operations for the same subject in different time periods and across subjects, and is more stable. By improving the physiological state data of multiple subjects, the sample size for obtaining baseline characteristics can be increased, thereby avoiding the occurrence of inaccurate baseline characteristics due to errors in one person's signal.

[0067] Figure 4 A flow chart of a physiological state model training method provided in another embodiment of the present invention.

[0068] like Figure 4 As shown, the physiological state model training method 400 includes steps S410 to S450.

[0069] Step S410: Acquire physiological sample data, wherein the physiological sample data includes a status tag.

[0070] Exemplarily, the state labels include physiological states such as fatigue, excitement, and happiness. The state labels can be represented by 0, 1, 2, etc. For example, 0 represents fatigue, 1 represents excitement, and 2 represents happiness.

[0071] Step S420: extract features from the physiological sample data to obtain sample feature data.

[0072] Exemplarily, partial sequence data is extracted from each sequence data of the physiological sample data to obtain a plurality of subsequence data, the plurality of subsequence data constitute a data segment, and feature extraction is performed on the plurality of data segments respectively to obtain sample feature data.

[0073] Step S430, standardizing the sample characteristic data based on the baseline characteristics to obtain standardized sample characteristic data, wherein the baseline characteristics are obtained based on any one of the above-mentioned physiological signal processing methods based on human factor intelligence.

[0074] For example, Figure 5 A schematic diagram of extracting physiological signal features of a brain task state provided by another embodiment of the present invention is shown in FIG. Figure 5 As shown, based on the obtained sample characteristic data (represented by X) and the baseline characteristic (represented by m), the sample characteristic data is divided by the baseline characteristic (ie, normalization processing) to obtain the standardized sample characteristic data.

[0075] Step S440, inputting the standardized sample feature data into the physiological state model to be trained to perform state prediction, and obtaining a physiological state prediction result.

[0076] Step S450: adjusting the model parameters of the physiological state model to be trained based on the physiological state prediction result and the state label.

[0077] For example, the physiological state prediction result is expressed as a combination sequence of 0, 1, or 0 and 1. Based on the deviation between the physiological state prediction result and the state label, the model parameters of the physiological state model to be trained are reversely adjusted so that the deviation between the subsequently predicted physiological state prediction result and the state label is reduced. The iterative training is performed in sequence. When the deviation is less than a preset threshold or other training convergence conditions are met, the training is stopped and a trained physiological state model is obtained.

[0078] In the above embodiment, the sample feature data is standardized based on the baseline feature, and the standardized sample feature data is input into the physiological state model to be trained for state prediction to obtain the physiological state prediction result. In the above method, since the baseline feature can accurately reflect the characteristics of the physiological data, the model training accuracy is also improved.

[0079] Figure 6 This is a flow chart of a physiological state prediction method provided in another embodiment of the present invention.

[0080] like Figure 6 As shown, the physiological state prediction method 600 includes steps S610 to S640.

[0081] Step S610, obtaining physiological data to be predicted.

[0082] Step S620: extracting features from the physiological data to be predicted to obtain target feature data.

[0083] Exemplarily, part of the sequence data is extracted from each sequence data of the physiological data to be predicted to obtain a plurality of subsequence data, the plurality of subsequence data constitute a data segment, and feature extraction is performed on the plurality of data segments respectively to obtain target feature data.

[0084] Step S630, standardizing the target feature data based on the baseline feature to obtain standardized target feature data, wherein the baseline feature is obtained based on any one of the above-mentioned physiological signal processing methods based on human factor intelligence.

[0085] Exemplarily, based on the obtained target feature data and the baseline feature, the target feature data is divided by the baseline feature (ie, normalization processing) to obtain the standardized target feature data.

[0086] Step S640, inputting the standardized target feature data into the trained physiological state model for state prediction to obtain a physiological state prediction result.

[0087] In the above embodiment, the target feature data is standardized based on the baseline feature, and the standardized target feature data is input into the trained physiological state model for state prediction to obtain the physiological state prediction result. In the above method, since the baseline feature can accurately reflect the characteristics of the physiological data, the accuracy of the physiological state model is also improved when performing state prediction.

[0088] Figure 7 A block diagram of a physiological signal processing device based on human factors intelligence provided in another embodiment of the present invention.

[0089] The embodiment of the present invention provides a physiological signal processing device 700 based on human factor intelligence, please refer to Figure 7 The physiological signal processing device 700 based on human factor intelligence includes: a first acquisition module 710, a first extraction module 720, and a fusion module 730.

[0090] Exemplarily, the first acquisition module 710 is used to acquire reference physiological data.

[0091] Exemplarily, the first extraction module 720 is used to extract multiple data segments from the reference physiological data, perform feature extraction on the multiple data segments respectively, and obtain multiple initial feature data.

[0092] Exemplarily, the fusion module 730 is used to fuse multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

[0093] It can be understood that for the specific description of the physiological signal processing device 700 based on human factors intelligence, reference can be made to the description of the physiological signal processing method based on human factors intelligence in the above text, which will not be repeated here.

[0094] Figure 8 A block diagram of a training device for a physiological state model provided in another embodiment of the present invention.

[0095] The embodiment of the present invention provides a training device 800 for a physiological state model. Figure 8 The training device 800 of the physiological state model includes: a second acquisition module 810, a second extraction module 820, a first processing module 830, a first prediction module 840, and an adjustment module 850.

[0096] Exemplarily, the second acquisition module 810 is used to acquire physiological sample data, wherein the physiological sample data includes a state tag.

[0097] Exemplarily, the second extraction module 820 is used to perform feature extraction on the physiological sample data to obtain sample feature data.

[0098] Exemplarily, the first processing module 830 is used to perform standardization processing on the sample characteristic data based on the baseline characteristics to obtain standardized sample characteristic data, wherein the baseline characteristics are obtained based on the above-mentioned physiological signal processing device based on human factors intelligence.

[0099] Exemplarily, the first prediction module 840 is used to input the standardized sample feature data into the physiological state model to be trained to perform state prediction and obtain a physiological state prediction result.

[0100] Exemplarily, the adjustment module 850 is used to adjust the model parameters of the physiological state model to be trained based on the physiological state prediction result and the state label.

[0101] It can be understood that for the specific description of the training device 800 for the physiological state model, reference can be made to the description of the training method for the physiological state model above, which will not be repeated here.

[0102] Fig. 9 This is a block diagram of a physiological state prediction device provided in another embodiment of the present invention.

[0103] The embodiment of the present invention provides a physiological state prediction device 900, see Fig. 9 The physiological state prediction device 900 includes: a third acquisition module 910, a third extraction module 920, a second processing module 930, and a second prediction module 940.

[0104] Exemplarily, the third acquisition module 910 is used to acquire physiological data to be predicted.

[0105] Exemplarily, the third extraction module 920 is used to perform feature extraction on the physiological data to be predicted to obtain target feature data.

[0106] Exemplarily, the second processing module 930 is used to perform standardization processing on the target feature data based on the baseline feature to obtain the standardized target feature data, wherein the baseline feature is obtained based on the above-mentioned physiological signal processing device based on human factors intelligence.

[0107] Exemplarily, the second prediction module 940 is used to input the standardized target feature data into the trained physiological state model to perform state prediction to obtain a physiological state prediction result.

[0108] It can be understood that for the specific description of the physiological state prediction device 900, reference can be made to the description of the physiological state prediction method above, which will not be repeated here.

[0109] An embodiment of the present invention provides an edge device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of any one of the above embodiments when executing the computer program.

[0110] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of any one of the above embodiments are implemented.

[0111] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of the present invention, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] In the description of the present invention, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0114] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0115] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.

[0116] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.

[0117] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0118] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A physiological signal processing method based on human intelligence, characterized in that: The method comprises: Obtain reference physiological data; extracting a plurality of data segments from the reference physiological data; Extracting features from the multiple data segments respectively to obtain multiple initial feature data; The multiple initial feature data are fused to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

2. The method according to claim 1, characterized in that: Each initial feature data includes I sub-feature data, where I is an integer greater than or equal to 1; the fusion of the multiple initial feature data to obtain the baseline feature includes: For each i-th sub-feature data corresponding to the initial feature data, multiple i-th sub-feature data corresponding to the multiple initial feature data are processed to obtain a feature value, wherein 1≤i≤I; Based on I feature values, the baseline feature is obtained.

3. The method according to claim 1 or 2, characterized in that: The reference physiological data includes data corresponding to K acquisition moments one by one, where K is an integer greater than 1; and extracting a plurality of data segments from the reference physiological data includes: Each data segment is extracted from the reference physiological data according to a preset data length k, wherein 1≤k≤K, the data length of each data segment is the preset data length k, and there may or may not be duplication between any two data segments among the multiple data segments.

4. The method according to claim 1 or 2, characterized in that: The reference physiological data includes M sequence data, where M is an integer greater than or equal to 1, and each sequence data is acquired through a corresponding data acquisition channel; The step of extracting a plurality of data segments from the reference physiological data comprises: Part of the sequence data is extracted from each sequence data to obtain M subsequence data, and the M subsequence data constitute one data segment.

5. The method according to claim 1 or 2, characterized in that: The reference physiological data includes N groups of data, N is an integer greater than or equal to 1, and each group of data is obtained by collecting data from a corresponding person under test; each group of data includes M sequence data, M is an integer greater than or equal to 1, and each sequence data is collected through a corresponding data collection channel; The step of extracting a plurality of data segments from the reference physiological data comprises: For M×N sequence data, part of the sequence data is extracted from each sequence data to obtain M×N subsequence data, and the M×N subsequence data constitute one data segment.

6. A method for training a physiological state model, characterized in that: The method comprises: Acquiring physiological sample data, wherein the physiological sample data includes a state tag; Extracting features from the physiological sample data to obtain sample feature data; Standardizing the sample characteristic data based on the baseline characteristics to obtain standardized sample characteristic data, wherein the baseline characteristics are obtained based on the method of any one of claims 1 to 5; Inputting the standardized sample feature data into the physiological state model to be trained to perform state prediction, and obtaining a physiological state prediction result; Based on the physiological state prediction result and the state label, the model parameters of the physiological state model to be trained are adjusted.

7. A physiological state prediction method, characterized in that: The method comprises: Acquiring physiological data to be predicted; Extracting features of the physiological data to be predicted to obtain target feature data; Standardizing the target feature data based on the baseline feature to obtain standardized target feature data, wherein the baseline feature is obtained based on the method of any one of claims 1 to 5; The standardized target feature data is input into the trained physiological state model for state prediction to obtain the physiological state prediction result.

8. A physiological signal processing device based on human intelligence, characterized in that: The device comprises: A first acquisition module, used for acquiring reference physiological data; A first extraction module, used to extract multiple data segments from the reference physiological data, and perform feature extraction on the multiple data segments respectively to obtain multiple initial feature data; The fusion module is used to fuse the multiple initial feature data to obtain baseline features, wherein the baseline features are used as reference features for physiological state prediction.

9. An edge device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images