Physiological and psychological collaborative treatment system and method for pets

Abstract

The invention discloses a pet physiological and psychological collaborative treatment system and method, and relates to the technical field of pet medical treatment, and the method comprises the following steps: continuously obtaining first behavior data, first respiration data and first physiological data of a pet at a time window; performing spatio-temporal change analysis on the first behavior data to obtain second behavior data representing behavior complexity; and performing nonlinear calculation on the first breathing data and the second behavior data to obtain second breathing data. According to the scheme, abnormal fluctuation caused by psychological factors is effectively separated through phase difference analysis and nonlinear calculation, in addition, judgment standards can be adaptively adjusted according to individual differences through dynamic clustering and mapping modeling, the suitability of a treatment scheme is remarkably improved, and accurate recognition and quantitative evaluation of the psychological stress state of the pet are achieved.

Description

Technical Field

[0001] This invention relates to the field of pet medical technology, specifically to a system and method for the synergistic treatment of pet physiology and psychology. Background Technology

[0002] With the development of pet medical technology, pet health management has gradually evolved from simply treating physiological diseases to coordinating physiological and psychological interventions. Respiratory diseases are among the most common ailments in pets, and their treatment involves not only the regulation of physiological indicators but is also significantly influenced by the pet's psychological state.

[0003] However, in the process of implementing the technical solution of the invention in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0004] In existing technologies, treatments for pet respiratory diseases primarily focus on the physiological level. Some high-end devices can also perform simple monitoring of pet behavior, providing auxiliary data support in disease management. However, they fail to consider that the pet's psychological state can simultaneously affect both behavioral and respiratory data, leading to significant fluctuations in these data. Furthermore, current methods that only superficially monitor pet behavior struggle to accurately identify and quantify psychological stress behaviors, hindering the precise monitoring and quantitative assessment of the pet's psychological state. Additionally, the lack of mapping and modeling between the pet's physiological and behavioral data when psychological stress behaviors are identified makes it difficult to capture the simultaneous impact on physiological data during psychological treatment through behavioral adjustments. This results in insufficient scientific rigor in the generated treatment adjustment plans, impacting the effectiveness of pet disease treatment. Summary of the Invention

[0005] The purpose of this invention is to provide a system and method for the coordinated treatment of pet physiology and psychology, in order to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the technical solution of the present invention is as follows:

[0007] In a first aspect, this invention discloses a synergistic physiological and psychological treatment method for pets with respiratory diseases, which is applied to the synergistic physiological and psychological treatment of pets, including the following steps:

[0008] Continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window;

[0009] Spatiotemporal variation analysis is performed on the first behavioral data to obtain second behavioral data that characterizes the complexity of the behavior.

[0010] The first respiratory data and the second behavioral data are subjected to nonlinear calculations to obtain the second respiratory data.

[0011] Phase transformation is performed on the second behavioral data and the second respiratory data respectively, and the difference between the phase transformation results is calculated to obtain the first phase data;

[0012] Fluctuation analysis is performed on the first phase data to obtain the second and third phase data;

[0013] Determine whether the third phase data is greater than a preset abnormal threshold; if so, determine that the time window is a psychological stress window.

[0014] The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window.

[0015] Cluster analysis was performed on the second behavioral data and the first physiological data within the psychological stress window, and then mapping was performed to obtain a behavioral-physiological regulation synergy map;

[0016] The system invokes predefined decision rules and outputs treatment adjustment data based on the psychological stress index and the behavioral-physiological regulation synergy map, thereby generating a treatment adjustment plan.

[0017] Secondly, this invention discloses a synergistic physiological and psychological treatment system for pets, comprising:

[0018] The data acquisition module is used to continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window;

[0019] The data processing module is used to perform spatiotemporal variation analysis on the first behavioral data to obtain second behavioral data that characterizes the complexity of the behavior.

[0020] The first respiratory data and the second behavioral data are subjected to nonlinear calculations to obtain the second respiratory data.

[0021] The phase data calculation module is used to perform phase transformation on the second behavioral data and the second respiratory data respectively, and to calculate the difference between the phase transformation results to obtain the first phase data;

[0022] Fluctuation analysis is performed on the first phase data to obtain the second and third phase data;

[0023] The psychological stress index calculation module is used to determine whether the third phase data is greater than a preset abnormal threshold. If so, the time window is determined to be a psychological stress window.

[0024] The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window.

[0025] The regulation-coordination map generation module is used to perform cluster analysis on the second behavioral data and the first physiological data within the psychological stress window, and then perform mapping to obtain a behavior-physiological regulation-coordination map;

[0026] The treatment adjustment plan output module is used to call predefined decision rules, output treatment adjustment data based on the psychological stress index and the behavior-physiological regulation synergy map, and then generate a treatment adjustment plan.

[0027] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0028] 1. This solution effectively separates abnormal fluctuations caused by psychological factors through phase difference analysis and nonlinear calculation. In addition, through dynamic clustering and mapping modeling, it can adaptively adjust the judgment criteria according to individual differences, significantly improving the adaptability of the treatment plan. It achieves accurate identification and quantitative assessment of the pet's psychological stress state. By constructing a dynamic correlation model of behavioral and physiological data, it can capture the pet's state changes in real time during treatment, effectively reducing the problem of prolonged treatment cycle caused by unrecognized psychological stress, and improving the overall efficiency of respiratory disease treatment.

[0029] 2. This approach significantly improves the accuracy of analysis under different data formats by dynamically selecting clustering algorithms. Furthermore, it introduces cross-correlation functions to construct a time-frequency domain correlation model, accurately capturing the dynamic coupling characteristics between the two. This enables accurate identification of abnormal physiological disturbance patterns under psychological stress. The dynamic algorithm selection enhances the adaptability of clustering analysis, and the combination of time-frequency domain correlation analysis reveals the deep coupling relationship between physiological and respiratory data, ultimately providing a reliable data foundation for generating precise collaborative treatment plans.

[0030] 3. This solution constructs a joint representation feature vector to dynamically link psychological stress levels with behavioral-physiological synergy patterns. It can dynamically generate personalized treatment plans based on the pet's real-time psychological-physiological interaction state, solving the problem of the single treatment strategy in existing technologies. Through data-driven decision rule matching, it significantly improves the scientificity and adaptability of treatment adjustment plans. Attached Figure Description

[0031] The disclosure of this invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings, the same reference numerals are used to refer to the same parts. Wherein:

[0032] Figure 1 This is a flowchart illustrating the steps of a synergistic physiological and psychological treatment method for pets according to the present invention.

[0033] Figure 2 This is a schematic diagram of the process for obtaining second respiratory data provided by the present invention;

[0034] Figure 3 This is a schematic diagram of the process for performing cluster analysis on the second behavioral data and the first physiological data, as provided by the present invention.

[0035] Figure 4 This is a schematic diagram of the process for obtaining a behavioral-physiological regulation synergy map provided by the present invention;

[0036] Figure 5 This is a schematic diagram of the module functions of a pet physiological and psychological synergistic treatment system provided by the present invention. Detailed Implementation

[0037] It is readily understood that, based on the technical solution of this invention, those skilled in the art can propose various interchangeable structural methods and implementations without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of this invention.

[0038] Application Overview:

[0039] In existing technologies, the treatment of respiratory diseases in pets mainly focuses on the regulation of physiological indicators, lacking effective identification and quantitative assessment of psychological stress behaviors. Traditional monitoring equipment can only acquire surface behavioral data and cannot capture the deep impact of psychological state on respiratory and physiological data, making it difficult for treatment plans to dynamically adapt to the real-time changes in the pet's state, thus limiting the treatment effect. For example, when a pet experiences anxiety due to environmental stress, its respiratory rhythm and behavioral patterns may fluctuate non-linearly, but existing methods cannot accurately distinguish the coupling effect between physiological abnormalities and psychological stress, resulting in a lack of targeted treatment strategies.

[0040] To address these issues, research has found that psychological stress affects respiratory rate and behavioral patterns through the autonomic nervous system, but current technologies have failed to establish a dynamic correlation model between respiratory, behavioral, and physiological data. The research indicates that multi-dimensional data fusion and nonlinear analysis methods are needed to capture the spatiotemporal characteristics of psychological stress and construct a synergistic regulatory mechanism between behavior and physiology. By introducing phase transformation and fluctuation analysis techniques, abnormal fluctuations caused by psychological stress can be effectively separated, thereby enabling dynamic optimization of treatment plans.

[0041] After introducing the basic concept of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0042] Example 1:

[0043] Please see Figure 1A synergistic physiological and psychological treatment method for pets with respiratory diseases, comprising the following steps:

[0044] Continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window;

[0045] Spatiotemporal variation analysis of the first behavioral data is performed to obtain the second behavioral data that characterizes the complexity of the behavior.

[0046] Nonlinear calculations are performed on the first respiratory data and the second behavioral data to obtain the second respiratory data;

[0047] Phase transformations were performed on the second line data and the second respiratory data respectively, and the difference between the phase transformation results was calculated to obtain the first phase data;

[0048] Fluctuation analysis is performed on the first phase data to obtain the second and third phase data;

[0049] Determine whether the third phase data is greater than the preset abnormal threshold; if so, determine that the time window is a psychological stress window.

[0050] The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window.

[0051] Cluster analysis was performed on the second behavioral data and the first physiological data within the psychological stress window, and then mapping was performed to obtain a behavioral-physiological regulation synergy map;

[0052] It invokes predefined decision rules, outputs treatment adjustment data based on psychological stress index and behavioral-physiological regulation synergy map, and then generates a treatment adjustment plan.

[0053] Among them, the first behavioral data refers to the raw behavioral observation data of the pets collected, including but not limited to movement behavior, posture data, changes in spatial position, and interactive behavior;

[0054] First respiratory data refers to real-time data collected on a pet's respiratory activity, including but not limited to respiratory rate, respiratory amplitude, and respiratory rhythm.

[0055] First physiological data refers to raw data on the physiological state of a pet that are continuously collected from the pet, including but not limited to heart rate, heart rate variability, skin conductance, body surface temperature, and blood oxygen saturation.

[0056] Spatiotemporal change analysis refers to capturing the dynamic evolution patterns of behavioral data through time series modeling and spatial feature extraction;

[0057] The second behavioral data refers to the trajectory reconstruction of the first behavioral data, followed by analysis of its spatiotemporal variation characteristics, and the extraction of behavioral complexity indicators, including but not limited to behavioral change rate, spatial coverage, and behavioral diversity index.

[0058] Nonlinear computation refers to constructing an adaptive filtering function using correlation coefficients and mutation detection;

[0059] Second respiratory data refers to a type of data that dynamically reflects the trend of changes in the stability of a pet's breathing, formed by fusing respiratory signals and behavioral complexity features and processing them through nonlinear operations.

[0060] Phase transformation refers to the process of analyzing the instantaneous phase information of a signal using the Hilbert transform.

[0061] The first phase data refers to the sequence of instantaneous phase differences between a pet's behavioral rhythm and respiratory rhythm within the same time window;

[0062] Wave analysis refers to the extraction of statistical features and calculation of derivatives from phase data;

[0063] Second phase data refers to a derivative indicator used to quantify phase stability after fluctuation analysis of first phase data;

[0064] Third phase data refers to the numerical description used to quantify the rate of change of phase difference;

[0065] The abnormal threshold is the data used to determine whether the third phase data has deviated from the normal rhythm range;

[0066] The psychological stress window refers to the time frame in which a pet's behavior and respiratory rhythm experience significant synchronicity disruptions or drastic fluctuations due to psychological stress factors.

[0067] The psychological stress index is a comprehensive indicator used to quantify the degree of stress in pets during oxygen therapy, resulting from the interaction of behavioral and respiratory data.

[0068] Cluster analysis refers to selecting the K-means or DBSCAN algorithm based on the data distribution characteristics. For example, density clustering can be performed on the frequency domain characteristics of physiological data to separate abnormal physiological patterns.

[0069] Mapping refers to the calculation of weighting factors and multidimensional similarity, such as constructing a two-dimensional synchronization offset map to quantify the intensity of coordinated regulation between behavior and physiology;

[0070] The behavior-physiological regulation synergy map refers to a multidimensional data structure used to characterize the positive and negative regulatory relationship between pet behavior patterns and corresponding physiological states;

[0071] Decision rules refer to a set of logical rules based on various quantitative indicators in the psychological stress index, third physiological data, and behavioral-physiological regulation synergy map;

[0072] Treatment adjustment data refers to a set of structured control parameters and strategy instructions automatically generated based on the pet's current psychological stress index and behavioral-physiological regulation synergy map;

[0073] A treatment adjustment plan refers to a set of directly executable intervention instructions that are generated and issued to the treatment equipment or operator after the aforementioned data analysis and decision rule matching are completed.

[0074] In this application, the ordinal numbers such as "first" and "second" mentioned are used to distinguish multiple objects, and are not used to limit the order, timing, priority or importance of multiple objects; for example, the preset abnormal threshold and the adjusted abnormal threshold are only used to distinguish different abnormal thresholds, and do not indicate the difference in priority or importance of the two abnormal thresholds.

[0075] This solution effectively separates abnormal fluctuations caused by psychological factors through phase difference analysis and nonlinear calculation, enabling accurate identification and quantitative assessment of pets' psychological stress state. It solves the technical problem that traditional methods cannot distinguish the coupling effect between physiological abnormalities and psychological stress. In addition, through dynamic clustering and mapping modeling, this solution can adaptively adjust the judgment criteria according to individual differences, effectively reducing the problem of prolonged treatment cycle caused by unrecognized psychological stress and improving the overall efficiency of respiratory disease treatment.

[0076] The above describes a complete treatment plan that integrates physiological and psychological aspects in pets. The following section outlines the initial image data acquisition process for the pet before implementing this plan, specifically including:

[0077] Acquire the pet's initial image data via camera;

[0078] Image detection and contour extraction are performed on the first image data to obtain second image data representing the nose contour;

[0079] The second image data is matched with preset cat nose feature templates and dog nose feature templates to output pet species data;

[0080] Determine the basic respiratory regulation airflow pattern based on pet species data:

[0081] If it is a cat, then set the basic airflow mode to laminar flow mode and the airflow rate to 4L / min;

[0082] If it is a dog, then the basic airflow mode should be set to turbulence mode and the airflow rate should be 6L / min.

[0083] The first image data refers to the raw image data of the pet's facial area captured by an optical sensor;

[0084] Image detection and contour extraction refers to using computer vision algorithms to locate and identify specific regions from the acquired first image data, and extract contour boundary points or structural features from the image based on the detected specific regions.

[0085] The second image data refers to the contour information of the nasal region that is retained after processing by the image segmentation algorithm;

[0086] A feline nasal feature template is a pre-defined feature model used to identify and match the nasal structural features of a cat when using image recognition for pet species identification.

[0087] A canine nasal feature template is a pre-defined feature model used to identify and match the nasal structural features of dogs when using image recognition for pet species identification.

[0088] Pet species data refers to the classification results of cats or dogs determined by template matching algorithms;

[0089] The basic respiratory regulation airflow pattern refers to the gas delivery mode set according to the physiological differences of species.

[0090] This solution uses image recognition technology to automatically identify species and sets differentiated airflow parameters based on differences in anatomical features. Through the above technical solution, this application achieves accurate matching of the basic parameters of the respiratory therapy device with the pet species, effectively avoiding secondary stress reactions caused by improper airflow patterns.

[0091] The above describes how to obtain the first image data of the pet. The following describes how to obtain the second behavioral data, which represents the complexity of the behavior, specifically including:

[0092] Extract time-series features and spatial distribution features from the continuously collected first-line data;

[0093] Time series features cover the frequency, duration and trend of behavior, while spatial distribution features cover the pet's location changes, movement trajectory and posture dynamics in the environment;

[0094] Next, a multi-scale analysis method was applied to divide the first row of data into different time windows and spatial regions. The sliding window technique was used to capture the local changes in the first row of data, and the spatial clustering algorithm was used to identify the regional distribution characteristics of the first row of data.

[0095] Subsequently, in conjunction with the calculation of spatiotemporal correlation, nonlinear dynamic indicators (such as phase space reconstruction, fractal dimension and Lyapunov exponent) were used to evaluate the complexity of the data in the first row.

[0096] In addition, behavioral pattern conversion detection is introduced, and sudden changes in the first behavioral data are identified through mutation detection algorithms to capture potential abnormal or stressful behavioral manifestations.

[0097] Finally, the above multidimensional spatiotemporal features are comprehensively processed, and a unified behavioral complexity index is generated through feature fusion and dimensionality reduction techniques, which serves as the core expression of the second behavioral data.

[0098] This approach uses nonlinear dynamic indicators to quantify behavioral complexity, enhancing a deeper understanding of behavioral patterns. The unified behavioral complexity indicator generated through feature fusion and dimensionality reduction facilitates subsequent collaborative analysis with respiratory and physiological data, achieving effective coupling between multidimensional data and providing a solid data foundation for accurate psychophysiological assessment and personalized treatment planning.

[0099] The above describes how to obtain the second behavioral data that represents behavioral complexity. The following describes how to obtain the second respiratory data; please refer to [link / reference]. Figure 2 , Figure 2 This is a schematic diagram of the process for obtaining second respiratory data provided in an embodiment of this application. Obtaining second respiratory data specifically includes:

[0100] Extract the first respiration data and the second line data within the same time window;

[0101] Calculate the correlation coefficient between the first respiratory data and the second behavioral data;

[0102] Mutation detection was performed on the first respiratory data and the second behavioral data to obtain the first time point and the second time point;

[0103] The first delay time is obtained by calculating the difference between the first time point and the second time point.

[0104] If the first delay time is greater than the preset first time threshold, the first respiratory data is processed in combination with the correlation coefficient to obtain the second respiratory data that characterizes respiratory stability.

[0105] Otherwise, the first respiratory data is processed by combining the correlation coefficient and the first delay time to obtain the second respiratory data that characterizes respiratory stability.

[0106] Among them, the correlation coefficient is an indicator used to quantify the dynamic correlation between respiratory data and behavioral data within the same time window;

[0107] Mutation detection refers to the use of statistical methods to identify moments of sudden change in a data sequence;

[0108] The first time point refers to the point in time when a mutation is first detected from the first breath data during the mutation detection process;

[0109] The second time point refers to the point in time when the mutation was first detected from the second set of data during the mutation detection process;

[0110] The first delay time refers to the time difference between a change in respiratory data and a change in behavioral data.

[0111] The first time threshold is a threshold parameter used to measure the maximum permissible time difference (i.e., the first delay time) between the time point of behavioral change (second time point) and the time point of respiratory change (first time point) of a pet within the same time window.

[0112] The following is a detailed explanation of how to calculate the correlation coefficient between the first respiratory data and the second behavioral data:

[0113] The specific calculation formula is as follows:

[0114]

[0115] In the formula, Indicates the first The correlation coefficient between the first respiratory data and the second behavioral data within a time window. Indicates the first Within a time window First breath data at any given moment Indicates the first Within a time window The second line of data at each moment, Indicates the first The mean of the first breath data within each time window Indicates the first The second row of data within each time window is the mean of the data.

[0116] The following is a detailed explanation of how to determine whether the first delay time is greater than a preset first time threshold:

[0117] Therefore, the first respiratory data is processed by combining the correlation coefficient to obtain the second respiratory data. The specific calculation formula is as follows:

[0118]

[0119] In the formula, Indicates the first Within a time window Second respiratory data at any given time Indicates the first Within a time window The first respiratory data at time 10:00 after processing by the correlation adaptive filtering function;

[0120] Otherwise, feature processing is performed on the first respiratory data by combining the correlation coefficient and the first delay time to obtain the second respiratory data. The specific calculation formula is as follows:

[0121]

[0122] In the formula, Indicates the first delay time. This represents the dynamic weighting coefficient function. Indicates the first Within a time window The first respiratory data after filtering at any given time.

[0123] To better understand the above content, an application scenario example is provided as follows:

[0124] Take a pet dog suffering from mild chronic bronchitis as an example;

[0125] During treatment, a behavioral sensor array integrating a triaxial accelerometer and gyroscope (sampling rate 200Hz) was worn on the neck, chest, back, and limbs; a thermistor-based nasal respiratory flow monitoring module (sampling rate 150Hz) and an implanted heart rate variability (HRV) monitoring chip (sampling rate 1000Hz) were worn simultaneously to form a complete respiratory-behavioral-physiological data acquisition system.

[0126] In the "smell-sit-rapid transfer" behavioral sequence, the pet dog was monitored to continuously engage in spontaneous transfer behavior within 18 to 25 seconds. The behavioral data showed an increase in complexity, with the peak trunk rotational angular velocity reaching 147° / s and the average posture change frequency increasing from 0.8Hz to 1.4Hz. Within the same time window, the nasal airflow signal showed frequency drift and increased fluctuation amplitude, with the respiratory rate surging from the normal 8.3Hz to 11.1Hz and the flow velocity coefficient of variation (CV) reaching 0.38.

[0127] The raw respiratory data and the characteristic behavioral data after behavioral complexity analysis were extracted within the 5th time window (sampling interval t=20s-25s), and the Pearson correlation coefficient was calculated between the two, with a result of 0.67.

[0128] Subsequently, a mutation detection algorithm (based on the sliding window difference maximum value identification method) was applied to the respiratory signal and the behavioral signal respectively. The mutation point of the behavioral signal was identified as t1=21.3s and the mutation point of the respiratory signal was identified as t2=21.8s. The first delay time was calculated to be 0.5s.

[0129] The built-in first time threshold (preset value τ1=0.35s) is called for judgment. Since the first delay time is greater than the first time threshold, it is determined that there is a significant delay response. Based on this, the respiratory signal is processed by the correlation adaptive filtering function, and the processing result generates the second respiratory data.

[0130] This solution introduces a mutation detection and delay time judgment mechanism to dynamically adjust the data processing strategy. Through the above technical solution, this application can accurately capture the correlation characteristics between respiratory data and behavioral data when pets experience psychological stress, eliminate the feature shift caused by the difference in response speed between the two, provide a reliable data foundation for subsequent phase analysis and stress index calculation, thereby improving the scientific nature of the treatment adjustment plan.

[0131] The above describes how to obtain the second respiratory data. The following describes how to obtain the first phase data, specifically including:

[0132] Extract the second respiratory data and the second behavioral data within the same time window;

[0133] The second respiratory data and the second behavioral data are filtered and noise and high-frequency interference are removed.

[0134] The second respiratory data and the second behavioral data are analyzed by Hilbert transform to generate the first analytical signal and the second analytical signal.

[0135] Calculate the instantaneous phases of the first analytic signal and the second analytic signal to obtain the first instantaneous phase and the second instantaneous phase accordingly;

[0136] The difference between the first instantaneous phase and the second instantaneous phase is calculated point by point to obtain the first phase data.

[0137] Among them, filtering refers to eliminating interference components introduced during signal acquisition;

[0138] Noise removal refers to the use of algorithms to eliminate non-target, random, or external interference components in a signal;

[0139] High-frequency interference processing refers to eliminating signal disturbances with frequencies much higher than the target physiological rhythm through Fourier transform;

[0140] The Hilbert transform is a linear transformation that maps a real-time signal to a new real-time signal.

[0141] The first analytical signal refers to the transformation of the second respiratory data into a complex signal that includes the original signal and its Hilbert transform;

[0142] The second analytic signal refers to the transformation of the second row of data into a complex-valued signal that includes the original signal and its Hilbert transform;

[0143] The first instantaneous phase refers to the phase angle value of the first analytical signal at each moment;

[0144] The second instantaneous phase refers to the phase angle value of the second analytical signal at each moment.

[0145] This scheme constructs an analytical signal through Hilbert transform, which can accurately extract the instantaneous phase information of non-stationary signals. Combined with the difference calculation method, it can effectively identify the synchronicity abnormalities between breathing and behavior. Through the above technical solution, this application can accurately quantify the dynamic phase relationship between respiratory rhythm and behavioral pattern, providing high-precision input data for subsequent fluctuation analysis, and solving the problem of misjudgment of stress window caused by neglecting the dynamic phase characteristics of traditional methods.

[0146] The above describes how to obtain the first phase data. The following describes how to obtain the second and third phase data, specifically including:

[0147] The first phase data is subjected to phase unwrapping and noise reduction filtering.

[0148] Calculate the statistical characteristics of the processed first-phase data; the statistical characteristics include standard deviation, sample entropy, and mean.

[0149] Nonlinear calculations are performed on the statistical characteristics to obtain second phase data that characterizes phase stability;

[0150] The first-order derivative of the first phase data is used to obtain the third phase data, which characterizes the rate of phase change.

[0151] The synchronization offset value is obtained by linearly superimposing the second phase data and the first phase data.

[0152] Construct a two-dimensional synchronization offset graph containing an X-axis, a Y-axis, and an origin; where the X-axis represents the time series including the time window, the Y-axis represents the synchronization offset value, and the origin represents the 0 point.

[0153] Phase unwrapping refers to the operation of restoring continuity from discontinuities in phase data.

[0154] Denoising filtering refers to removing noise components from phase data using wavelet thresholding or Kalman filtering methods.

[0155] Statistical characteristics refer to the quantitative analysis of first-phase data, which describes the distribution pattern and complexity of the data to help determine the psychological stress state of pets;

[0156] Standard deviation is a statistic that reflects the dispersion of data, indicating the degree to which a data point deviates from the mean.

[0157] Sample entropy refers to data used to measure the complexity or irregularity of a time series.

[0158] The mean refers to the arithmetic average of the phase data from all sampling points;

[0159] First-order differentiation refers to calculating the instantaneous rate of phase change using the finite difference method;

[0160] Synchronization offset is a quantitative indicator that represents the phase synchronization deviation and dynamic fluctuation characteristics between a pet's respiratory rhythm and behavioral rhythm.

[0161] The two-dimensional synchronous offset plot uses the time window as the horizontal axis and the synchronous offset value as the vertical axis. The origin represents the state without offset, and it visualizes the relationship between data fluctuations and time.

[0162] This solution, through phase unwrapping, multi-feature fusion, and dynamic rate calculation, can more accurately capture the nonlinear correlation between behavioral and respiratory data. In addition, the construction of a two-dimensional synchronous offset map breaks through the limitations of traditional tabular data display, making data fluctuation patterns easier to observe and analyze. Through the above technical solutions, this application can effectively identify abnormal fluctuations in respiratory and behavioral data caused by psychological stress, providing high-precision data support for subsequent treatment adjustment plans and solving the problem of treatment delay caused by misjudgment of data fluctuations in existing technologies.

[0163] The above describes how to obtain the first phase data. The following describes how to obtain the psychological stress index, which includes:

[0164] Take the first phase data, second phase data, and third phase data that are within the psychological stress window;

[0165] The first phase data, the second phase data, and the third phase data are subjected to feature processing respectively to construct corresponding feature vectors;

[0166] The three sets of feature vectors are linearly weighted and fused according to preset weight parameters;

[0167] The weight parameters are determined based on empirical rules or through machine learning models (such as weighted models trained on historical labeled data).

[0168] The fused feature vectors are mapped to a scalar psychological stress index through a nonlinear mapping function (such as the nonlinear kernel function of multilayer perceptron MLP, support vector machine SVM, or Gaussian process regression).

[0169] By performing nonlinear feature extraction and fusion analysis on multiple phase data, this application can effectively characterize the psychological stress response of pets within the psychological stress window, construct a continuous and dynamic psychological stress index, and improve the accuracy and sensitivity of psychological stress identification.

[0170] The above describes how to obtain the psychological stress index. Below, we will introduce cluster analysis for the second behavioral data and the first physiological data respectively. Please refer to [the relevant documentation]. Figure 3 , Figure 3 This is a flowchart illustrating the cluster analysis of the second behavioral data and the first physiological data provided in this application embodiment. The cluster analysis of the second behavioral data and the first physiological data specifically includes:

[0171] Within the psychological stress window, frequency domain features are extracted from the first physiological data to form a feature vector;

[0172] Cluster analysis is performed on the feature vectors, and perturbation clusters are identified based on the cluster analysis results;

[0173] The first physiological data corresponding to the perturbation cluster is used as the second physiological data;

[0174] Cross-correlation analysis was performed on the second physiological data and the second respiratory data to obtain the cross-correlation analysis results.

[0175] Determine whether the maximum value of the cross-correlation analysis result is greater than the preset perturbation threshold. If so, determine that the frequency corresponding to the maximum value of the cross-correlation analysis result is an abnormal frequency.

[0176] Peak detection is performed on the first physiological data, and the third time point is output. The difference between the third time point and the second time point is calculated to obtain the second delay time.

[0177] Based on the second delay time, the second physiological data corresponding to the abnormal frequency is time-corrected to obtain the third physiological data;

[0178] Cluster analysis is performed on the third physiological data to output fourth physiological data that characterizes the physiological perturbation pattern;

[0179] Cluster analysis is performed on the second behavioral data within the psychological stress window to output the third behavioral data representing the behavioral pattern.

[0180] Among them, frequency domain feature extraction refers to converting physiological data to the frequency domain to capture periodic change features;

[0181] Cluster analysis refers to selecting the optimal grouping method based on the characteristics of data distribution;

[0182] The second physiological data refers to the subset of physiological data with significant rhythmic perturbation characteristics extracted within the identified psychological stress window after clustering based on the first physiological data;

[0183] The disturbance threshold is a criterion used to identify whether a pet is in an abnormal or stressed state of physiological or psychological condition.

[0184] The third time point refers to the moment when the physiological peak occurs, obtained by peak detection and analysis of the first physiological data within the psychological stress window;

[0185] The second delay time refers to the time difference between the behavioral mutation signal (second time point) and the peak physiological disturbance signal (third time point) within the psychological stress window;

[0186] Cross-correlation analysis refers to calculating the correlation strength between physiological data and respiratory data at different frequencies;

[0187] Timing correction refers to adjusting the timing alignment of abnormal frequency data based on peak detection results;

[0188] The third physiological data refers to the set of characteristic physiological data extracted within the psychological stress window to characterize the dynamic response to physiological disturbances;

[0189] The fourth physiological data refers to the set of characteristic physiological parameters that reflect physiological disturbance patterns within the psychological stress window;

[0190] Third behavioral data refers to the set of data that characterizes the behavioral patterns of pets under stress within the psychological stress window.

[0191] The following section details the cluster analysis performed on the feature vectors, identifying perturbation clusters based on the results:

[0192] Based on the primary physiological data, different clustering methods were selected:

[0193] If the first physiological data shows a spherical distribution, use the K-means clustering algorithm;

[0194] If the first physiological data exhibits a non-linear distribution, the DBSCAN density clustering algorithm is employed.

[0195] The following section details the cross-correlation analysis performed on the second physiological data and the second respiratory data, and provides a detailed explanation of the results:

[0196] The specific calculation formula is as follows:

[0197]

[0198] In the formula, Indicates frequency as The time delay is Second physiological data at time Second respiratory data The cross-correlation function value, Indicates frequency The second physiological data at the site, Indicates frequency Second respiratory data at the location, Indicates frequency as The time delay is The complex exponential function at time t.

[0199] This approach significantly improves the accuracy of analysis under different data formats by dynamically selecting clustering algorithms, and introduces cross-correlation functions to construct a time-frequency domain correlation model, accurately capturing the dynamic coupling characteristics between the two. Through the above technical solutions, this application can accurately identify abnormal physiological disturbance patterns under psychological stress, improve the adaptability of clustering analysis through dynamic algorithm selection, and reveal the deep coupling relationship between physiological and respiratory data by combining time-frequency domain correlation analysis, ultimately providing a reliable data foundation for generating precise collaborative treatment plans.

[0200] The above describes the cluster analysis performed on the second behavioral data and the first physiological data respectively. The following describes the obtained behavioral-physiological regulation synergy map; please refer to it. Figure 4 , Figure 4 This is a schematic flowchart illustrating the process of obtaining a behavioral-physiological regulation synergy map provided in this application embodiment. The specific steps of obtaining the behavioral-physiological regulation synergy map include:

[0201] Extract the synchronization offset values ​​corresponding to the time points of the psychological stress window from the two-dimensional synchronization offset map;

[0202] The weighting factor in the mapping process between the third-line data and the fourth-line physiological data is determined based on the synchronization offset value;

[0203] The basic correlation strength between the third behavioral data and the fourth physiological data was calculated using a multidimensional similarity metric.

[0204] Multiplying the weighting factor by the baseline correlation strength yields the modified correlation strength. This modified correlation strength is then mapped using the third behavioral data and the fourth physiological data to obtain a behavioral-physiological regulatory synergy map that represents the behavioral-physiological synergistic regulation pattern.

[0205] The weighting factor refers to a coefficient that is dynamically adjusted based on the synchronization offset value. Specifically, it can be implemented using a normalization function or a scaling function.

[0206] Among them, the multidimensional similarity measurement method refers to the method of calculating the correlation between data in different dimensions, which can be implemented by using cosine similarity, Pearson correlation coefficient or dynamic time warping algorithm.

[0207] Among them, the basic correlation strength refers to the set of original correlation index values ​​obtained by quantitatively analyzing the synchronicity, trend consistency and structural similarity of the third behavioral data and the fourth physiological data in multiple feature dimensions through multi-dimensional similarity measurement methods within the psychological stress window;

[0208] Among them, the corrected correlation strength refers to the correlation strength after adjustment by combining weighting factors, which can be achieved through linear weighting or nonlinear fusion methods.

[0209] The following section details a mapping between the third behavioral data and the fourth physiological data to obtain a behavioral-physiological regulatory synergy map representing the coordinated regulatory pattern of behavior and physiology, which will be explained in detail:

[0210] When constructing the behavior-physiological regulation synergy map, based on the previously calculated corrected correlation strength, the third behavioral data and the fourth physiological data are mapped to nodes and edges in the map.

[0211] The nodes include behavioral feature nodes and physiological feature nodes;

[0212] To represent the connection between behavioral feature nodes and physiological feature nodes;

[0213] The weight of an edge is determined by the strength of the modified correlation between the corresponding behavior and physiological characteristics. The larger the weight, the thicker the visual appearance of the edge, indicating a stronger coupling relationship between the two.

[0214] This scheme introduces a synchronization offset value to dynamically adjust the weighting factor and combines it with a multidimensional similarity measurement method to correct the correlation strength, which can more accurately capture the nonlinear synergistic relationship between behavioral and physiological data under psychological stress. Through the above technical solution, this application solves the problem of inaccurate mapping between behavioral and physiological data caused by ignoring the impact of psychological stress on data synchronization in the prior art. By dynamically adjusting the weights and correcting the correlation strength, the reliability of the behavioral-physiological regulation synergistic map is significantly improved, providing more accurate data support for generating personalized treatment adjustment plans.

[0215] The above describes the obtained behavioral-physiological regulation synergy map. The following section introduces the generation of treatment and adjustment plans, specifically including:

[0216] Extract psychological stress index, third physiological data, and behavior-physiological regulation synergy map;

[0217] The predefined decision rules are invoked to compare the psychological stress index with the preset stress grading threshold to determine the current psychological stress level of the pet.

[0218] Feature extraction is performed on the third physiological data to output physiological state parameters, and a joint representation feature vector is constructed by combining the corrected correlation strength in the behavior-physiological regulation synergy map.

[0219] Based on the psychological stress level and the joint representation feature vector, decision rules are retrieved, and treatment adjustment strategies that match the current state are selected.

[0220] Based on the treatment adjustment strategy, a personalized treatment adjustment plan is intelligently generated.

[0221] Among them, the stress level threshold refers to a set of numerical ranges set based on the psychological stress index;

[0222] The joint characterization feature vector refers to a multidimensional data set that integrates physiological state parameters and modified correlation strength.

[0223] This solution constructs a joint representation feature vector to dynamically link psychological stress levels with behavioral-physiological synergy patterns. Through the above technical solution, this application can dynamically generate personalized treatment plans based on the pet's real-time psychological-physiological interaction state, solving the problem of the single treatment strategy in the prior art. Through data-driven decision rule matching, it significantly improves the scientificity and adaptability of treatment adjustment plans.

[0224] The above describes the generated treatment adjustment plan. The following section will also cover:

[0225] Obtain the pet's physical data and combine it with the pet's species data to screen for suitability and fine-tune parameters of the treatment adjustment plan;

[0226] Treatment adjustment plan after adaptability screening and parameter fine-tuning;

[0227] Real-time data collection of pets during the treatment adjustment process following suitability screening and parameter fine-tuning;

[0228] The treatment plan is adjusted and revised in real time based on relevant data.

[0229] Among them, body data refers to the basic physiological parameters of a pet, such as weight, body length, and age, obtained through sensors or manual input.

[0230] Adaptability screening and parameter fine-tuning refers to the dynamic adjustment of parameters such as airflow rate and treatment duration based on species differences and individual characteristics;

[0231] The relevant data includes respiratory rate, activity level, and heart rate variability indicators monitored in real time during treatment;

[0232] Real-time correction refers to dynamically adjusting treatment parameters based on the deviation between real-time data and preset thresholds.

[0233] This solution achieves precise matching of treatment parameters by introducing a species database and a body parameter correlation model, and realizes dynamic optimization of treatment parameters through a closed-loop control system. Through the above technical solution, this application solves the problems of rigid treatment plans and lack of individual adaptability in the prior art, ensuring that the treatment intensity matches the pet's physiological tolerance. By utilizing real-time data acquisition and rapid response mechanisms, it can promptly correct abnormal physiological reactions that occur during treatment, prevent secondary stress damage caused by improper parameter settings, and significantly improve the safety and effectiveness of respiratory disease treatment.

[0234] Example 2:

[0235] Please see Figure 5 A synergistic physiological and psychological treatment system for pets, comprising:

[0236] The data acquisition module is used to continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window;

[0237] The data processing module is used to perform spatiotemporal variation analysis on the first row of data to obtain the second row of data that characterizes the complexity of the behavior.

[0238] Nonlinear calculations are performed on the first respiratory data and the second behavioral data to obtain the second respiratory data;

[0239] The phase data calculation module is used to perform phase transformation on the second line data and the second respiratory data respectively, and to calculate the difference between the phase transformation results to obtain the first phase data.

[0240] Fluctuation analysis is performed on the first phase data to obtain the second and third phase data;

[0241] The psychological stress index calculation module is used to determine whether the third phase data is greater than the preset abnormal threshold. If so, the time window is determined to be the psychological stress window.

[0242] The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window.

[0243] The regulation-coordination map generation module is used to perform cluster analysis on the second behavioral data and the first physiological data within the psychological stress window, and then perform mapping to obtain the behavior-physiological regulation-coordination map.

[0244] The treatment adjustment plan output module is used to call predefined decision rules, output treatment adjustment data based on psychological stress index and behavioral-physiological regulation synergy map, and then generate a treatment adjustment plan.

[0245] This embodiment has the same technical effects as Embodiment 1.

[0246] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0247] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A synergistic physiological and psychological treatment method for pets, applied to the synergistic physiological and psychological treatment of pets with respiratory diseases, characterized in that, Includes the following steps: Continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window; Spatiotemporal variation analysis is performed on the first behavioral data to obtain second behavioral data that characterizes the complexity of the behavior. The first respiratory data and the second behavioral data are subjected to nonlinear calculations to obtain the second respiratory data. Phase transformation is performed on the second behavioral data and the second respiratory data respectively, and the difference between the phase transformation results is calculated to obtain the first phase data; Fluctuation analysis is performed on the first phase data to obtain the second and third phase data; Determine whether the third phase data is greater than a preset abnormal threshold; if so, determine that the time window is a psychological stress window. The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window. Cluster analysis was performed on the second behavioral data and the first physiological data within the psychological stress window, and then mapping was performed to obtain a behavioral-physiological regulation synergy map; The system invokes predefined decision rules and outputs treatment adjustment data based on the psychological stress index and the behavioral-physiological regulation synergy map, thereby generating a treatment adjustment plan.

2. The synergistic treatment method for pet physiology and psychology according to claim 1, characterized in that: Before continuously acquiring the pet's first behavioral data, first respiratory data, and first physiological data within a time window, acquire the pet's first image data, specifically including: Acquire the pet's initial image data via camera; The first image data is subjected to image detection and contour extraction processing to obtain second image data representing the nose contour. The second image data is matched with preset cat nose feature templates and dog nose feature templates to output pet species data; The basic respiratory regulation airflow pattern was determined based on the pet species data. If it is a cat, then set the basic airflow mode to laminar flow mode and the airflow rate to 4L / min; If it is a dog, then the basic airflow mode should be set to turbulence mode and the airflow rate should be 6L / min.

3. The synergistic treatment method for pet physiology and psychology according to claim 1, characterized in that: The second respiratory data is obtained by performing nonlinear calculations on the first respiratory data and the second behavioral data, specifically including: Extract the first respiratory data and the second line data within the same time window; Calculate the correlation coefficient between the first respiratory data and the second behavioral data; Mutation detection was performed on the first respiratory data and the second behavioral data to obtain the first time point and the second time point; The difference between the first time point and the second time point is calculated to obtain the first delay time; If the first delay time is greater than a preset first time threshold, then the first respiratory data is processed in conjunction with the correlation coefficient to obtain second respiratory data characterizing respiratory stability. Otherwise, the first respiratory data is processed by combining the correlation coefficient and the first delay time to obtain second respiratory data characterizing respiratory stability.

4. The synergistic treatment method for pet physiology and psychology according to claim 1, characterized in that: Phase transformation is performed on the second behavioral data and the second respiratory data respectively, and the difference between the phase transformation results is calculated to obtain the first phase data, which specifically includes: Extract the second respiratory data and the second behavioral data within the same time window; The second respiratory data and the second behavioral data are filtered and noise and high-frequency interference are removed. The second respiratory data and the second behavioral data are analyzed by Hilbert transform to generate a first analytical signal and a second analytical signal. Calculate the instantaneous phases of the first analytic signal and the second analytic signal to obtain the first instantaneous phase and the second instantaneous phase accordingly; The first phase data is obtained by calculating the difference between the first instantaneous phase and the second instantaneous phase point by point.

5. The synergistic treatment method for pet physiology and psychology according to claim 3, characterized in that: Fluctuation analysis of the first phase data yields the second and third phase data, specifically including: The first phase data is subjected to phase unwrapping and noise reduction filtering. Calculate the statistical characteristics of the processed first phase data; the statistical characteristics include standard deviation, sample entropy, and mean. Nonlinear calculations are performed on the statistical characteristics to obtain second phase data that characterizes phase stability; The first phase data is differentiated by the first order to obtain the third phase data that characterizes the rate of phase change. The synchronization offset value is obtained by linearly superimposing the second phase data and the first phase data. Construct a two-dimensional synchronization offset graph containing an X-axis, a Y-axis, and an origin; where the X-axis represents the time series including the time window, the Y-axis represents the synchronization offset value, and the origin represents the 0 point.

6. The synergistic treatment method for pet physiology and psychology according to claim 5, characterized in that: Cluster analysis was performed on the second behavioral data and the first physiological data within the psychological stress window, specifically including: Within the psychological stress window, frequency domain features are extracted from the first physiological data to form a feature vector; Cluster analysis is performed on the feature vectors, and perturbation clusters are identified based on the cluster analysis results; The first physiological data corresponding to the perturbation cluster is used as the second physiological data; Cross-correlation analysis was performed on the second physiological data and the second respiratory data to obtain the cross-correlation analysis results; Determine whether the maximum value of the cross-correlation analysis result is greater than the preset perturbation threshold. If so, determine that the frequency corresponding to the maximum value of the cross-correlation analysis result is an abnormal frequency. Peak detection is performed on the first physiological data to output a third time point. The difference between the third time point and the second time point is calculated to obtain the second delay time. Based on the second delay time, the second physiological data corresponding to the abnormal frequency is time-corrected to obtain the third physiological data; Cluster analysis is performed on the third physiological data to output fourth physiological data that characterizes the physiological perturbation pattern; Cluster analysis is performed on the second behavioral data within the psychological stress window to output the third behavioral data representing the behavioral pattern.

7. The synergistic treatment method for pet physiology and psychology according to claim 6, characterized in that: Then, through mapping, a behavioral-physiological regulation synergy map is obtained, which specifically includes: Extract the synchronization offset values ​​corresponding to the time points of the psychological stress window from the two-dimensional synchronization offset map; The weighting factor in the mapping process between the third behavioral data and the fourth physiological data is determined based on the synchronization offset value; The basic correlation strength between the third behavioral data and the fourth physiological data was calculated using a multidimensional similarity metric. Multiplying the weighting factor by the baseline correlation strength yields the modified correlation strength, which is then mapped using the third behavioral data and the fourth physiological data to obtain a behavioral-physiological regulatory synergy map representing the behavioral-physiological synergistic regulation pattern.

8. The synergistic treatment method for pet physiology and psychology according to claim 6, characterized in that: By invoking predefined decision rules and based on the psychological stress index and behavioral-physiological regulation synergy map, treatment adjustment data is output, thereby generating a treatment adjustment plan, specifically including: Extract psychological stress index, third physiological data, and behavior-physiological regulation synergy map; The predefined decision rules are invoked to compare the psychological stress index with the preset stress grading threshold to determine the current psychological stress level of the pet. Feature extraction is performed on the third physiological data to output physiological state parameters, and a joint representation feature vector is constructed by combining the corrected correlation strength in the behavior-physiological regulation synergy map. Based on the psychological stress level and the joint representation feature vector, decision rules are retrieved, and treatment adjustment strategies that match the current state are selected. Based on the treatment adjustment strategy, a personalized treatment adjustment plan is intelligently generated.

9. The synergistic treatment method for pet physiology and psychology according to claim 2, characterized in that: The generated treatment adjustment plan also includes: Obtain the pet's physical data and combine it with the pet's species data to screen for suitability and fine-tune parameters of the treatment adjustment plan; Treatment adjustment plan after adaptability screening and parameter fine-tuning; Real-time data collection of pets during the treatment adjustment process following suitability screening and parameter fine-tuning; The treatment plan is adjusted in real time based on the relevant data.

10. A synergistic physiological and psychological treatment system for pets, characterized in that, include: The data acquisition module is used to continuously acquire the pet's first behavioral data, first respiratory data, and first physiological data within a time window; The data processing module is used to perform spatiotemporal variation analysis on the first behavioral data to obtain second behavioral data that characterizes the complexity of the behavior. The first respiratory data and the second behavioral data are subjected to nonlinear calculations to obtain the second respiratory data. The phase data calculation module is used to perform phase transformation on the second behavioral data and the second respiratory data respectively, and to calculate the difference between the phase transformation results to obtain the first phase data; Fluctuation analysis is performed on the first phase data to obtain the second and third phase data; The psychological stress index calculation module is used to determine whether the third phase data is greater than a preset abnormal threshold. If so, the time window is determined to be a psychological stress window. The psychological stress index is obtained by performing nonlinear calculations on the first phase data, second phase data, and third phase data within the psychological stress window. The regulation-coordination map generation module is used to perform cluster analysis on the second behavioral data and the first physiological data within the psychological stress window, and then perform mapping to obtain a behavior-physiological regulation-coordination map; The treatment adjustment plan output module is used to call predefined decision rules, output treatment adjustment data based on the psychological stress index and the behavior-physiological regulation synergy map, and then generate a treatment adjustment plan.

Images