Multi-dimensional collaborative evaluation method and system based on plantar pressure detection

Abstract

The invention relates to the technical field of plantar pressure detection, and discloses a plantar pressure detection-based multi-dimensional collaborative evaluation method and system, and the method comprises the steps: obtaining an original data flow which is transmitted by a pressure detection platform through a data collection interface and is synchronized through a timestamp, the original data stream comprises a pressure data frame sequence of the pressure sensor array; processing the original data stream to obtain a test data set of the tested user; and analyzing and processing the test data set to obtain a corresponding analysis result, and displaying the analysis result. According to the invention, a plurality of data sets are analyzed and processed to obtain corresponding analysis results, and the analysis results are displayed, so that the plantar pressure conditions of the tested user can be comprehensively evaluated from different dimensions. And the analysis results are displayed, so that the evaluation result is more intuitive and understandable, professional personnel can conveniently and quickly obtain key information, and then personalized intervention schemes and rehabilitation plans are formulated or targeted suggestions are provided for users.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of plantar pressure detection, and in particular to a multi-dimensional collaborative evaluation method and system based on plantar pressure detection. BACKGROUND

[0002] At present, the traditional plantar observation and pressing feedback detection method is used. This method relies on the subjective experience of the detection personnel, and the plantar morphology and skin state are observed by naked eyes, and feedback information is obtained by manually pressing different areas of the plantar, so as to judge the plantar pressure distribution. However, this method has obvious limitations. On the one hand, the subjective component accounts for a high proportion, and the detection result is easily affected by the experience and operation method of the detection personnel, so that the accuracy and repeatability are difficult to guarantee. On the other hand, the detection efficiency is low, and large-scale detection and real-time data acquisition cannot be realized, so it is difficult to meet the precise and efficient needs of plantar pressure analysis in various fields. Therefore, it has become a technical problem to be solved by the technical personnel in the field to design a scheme for objective detection and analysis. SUMMARY

[0003] In view of the defects, the embodiment of the present application discloses a multi-dimensional collaborative evaluation method based on plantar pressure detection, which can realize comprehensive evaluation of the user's plantar.

[0004] The first aspect of the embodiment of the present application discloses a multi-dimensional collaborative evaluation method based on plantar pressure detection, comprising: obtaining the original data stream transmitted by the pressure detection platform through the data acquisition interface and synchronized by the time stamp, wherein the original data stream includes a pressure data frame sequence of the pressure sensor array; processing the original data stream to obtain a test data set of the measured user, wherein the test data set includes a balance function data set, a plantar pressure data set, a standing posture data set and a stability limit data set; analyzing and processing the balance function data set, the plantar pressure data set, the standing posture data set and the stability limit data set to obtain corresponding analysis results, and displaying the analysis results.

[0005] As an optional implementation, in the first aspect of the embodiment of the present application, the balance function data set includes a proprioceptive index; the proprioceptive index includes total trajectory length, peripheral area, unit area trajectory length and unit time trajectory length; The proprioceptive index is calculated by the following method: receiving real-time pressure data frames from the pressure sensor array, wherein the pressure data frames include the pressure value of each sensing unit wherein, is the pressure value of the i th sensing unit; calculating total pressure of current data frame according to the pressure data frame ; calculating sum of moments of all pressure values in current data frame about first axis of preset coordinate system , wherein the calculation formula is: , is the coordinate of the i th sensing unit on the first axis; calculating sum of moments of all pressure values in current data frame about second axis of preset coordinate system , wherein the calculation formula is: , is the coordinate of the i th sensing unit on the second axis; calculating pressure center coordinate of corresponding data frame , and obtaining corresponding pressure center coordinate sequence wherein the calculation formula is: , ; inputting the pressure center coordinate sequence into total trajectory calculation formula to obtain corresponding total trajectory length, wherein the total trajectory calculation formula is: ; obtaining outer peripheral area by calculating the area of an ellipse covering preset percentage of pressure center data points; determining corresponding unit area trajectory length through total trajectory length and outer peripheral area; determining corresponding unit time trajectory length through total trajectory length and total test time. The balance function related somatosensory index is quantitatively evaluated from multiple dimensions.

[0006] As an optional implementation, in the first aspect of the embodiment of the present application, the balance function data set includes vestibular system index, visual system index, left-right side symmetry degree, gravity center trajectory data, and support surface index; the vestibular system index includes X-axis average gravity center deviation and Y-axis average gravity center deviation; the support surface index includes support surface size, support surface axis length, and support surface axis width; the support surface index is determined through pressure pixel points; the vestibular system index is calculated through the following steps: obtaining X-axis average gravity center deviation according to the difference between the X coordinate value of all pressure center coordinates and the average value of X coordinate during the whole test period; obtaining Y-axis average gravity center deviation according to the difference between the Y coordinate value of all pressure center coordinates and the average value of Y coordinate during the whole test period; the visual system index is calculated through the following steps: obtaining open-eye test index value and closed-eye test index value; According to the open-eye test index value and the closed-eye test index value, a Romberg rate is calculated, and the Romberg rate is a corresponding visual index. Rich and valuable data basis is provided for accurate and comprehensive evaluation of human balance ability.

[0007] As an optional implementation, in the first aspect of the embodiment of the present application, the plantar pressure data set is obtained by the following method: The pressure data frame is subjected to image processing to identify left and right foot contours and divide the foot regions of interest; For each of the regions of interest, a predefined calculation is performed to obtain an arch index, forefoot and hindfoot pressure distribution, region area and average pressure. This accurate region division avoids confusion of pressure data of different foot regions and provides an accurate basis for subsequent detailed analysis of each region.

[0008] As an optional implementation, in the first aspect of the embodiment of the present application, the standing posture data set is obtained by the following method: Left and right foot pressure data are determined; According to the left and right foot pressure data, a left and right foot pressure symmetry index is calculated; The stability limit data set is obtained by the following method: Trajectory analysis is performed on the data frame sequence collected in the dynamic balance test to calculate motion speed, maximum deviation, deviation angle and deviation area. This can improve evaluation accuracy.

[0009] As an optional implementation, in the first aspect of the embodiment of the present application, the balance function data set, the plantar pressure data set, the standing posture data set and the stability limit data set are analyzed and processed to obtain corresponding analysis results, and the analysis results are displayed, including: The balance function data set, the plantar pressure data set, the standing posture data set and the stability limit data set are logically compared to generate an abnormal biomechanics mode identifier; Based on a predefined rule base, the abnormal biomechanics mode identifier is associated with a physiological system defect type, and an association result data is generated; A trained neural network model is used for pattern recognition analysis of the test data set, and the neural network model is configured to receive index data from the core evaluation module and output a similarity probability of a biomechanics mode of the corresponding user and a predefined at least one pathological mode library; Generate corresponding evaluation report data, and generate user balance function and posture image according to the evaluation report data rendered in the user interface, the evaluation report data includes index data set, correlation result data and pattern recognition result. It can realize comprehensive data analysis.

[0010] As an optional implementation, in the first aspect of the embodiment of the application, the generation of the corresponding evaluation report data comprises: Retrieving historical evaluation data of the same user from the database; Performing data comparison and analysis to calculate the change difference and percentage of the current index data and the historical index data; Generating a data structure for visual rendering, the data structure including data sequences for drawing trajectory superimposed graphs, pressure distribution comparison graphs and index change trend graphs. It can provide more intuitive data display.

[0011] As an optional implementation, in the first aspect of the embodiment of the application, the pressure detection platform further comprises a mechanical sensor, and before the acquisition of the time-stamped original data stream transmitted by the pressure detection platform through the data acquisition interface, it further comprises: Acquiring calibration relationship data stored in the system calibration stage; For each real-time data acquisition period, using the calibration relationship data and the current acquisition of the mechanical sensor reading, calculating the real-time calibration coefficient; Using a spatial interpolation algorithm to process the real-time calibration coefficient to generate a two-dimensional calibration matrix covering the entire pressure sensor array; Point multiplication operation is performed on the two-dimensional calibration matrix and the corresponding pressure data frame to output the calibrated pressure data. It improves data accuracy, enhances system stability and ensures data consistency.

[0012] The second aspect of the embodiment of the application discloses a multi-dimensional cooperative evaluation system based on foot pressure detection, comprising: An acquisition module for acquiring time-stamped original data streams transmitted by a pressure detection platform through a data acquisition interface, the original data stream including a sequence of pressure data frames of a pressure sensor array; A processing module for processing the original data stream to obtain a test data set of the measured user, the test data set including a balance function data set, a foot pressure data set, a standing posture data set and a stability limit data set; An analysis module for analyzing and processing the balance function data set, the foot pressure data set, the standing posture data set and the stability limit data set to obtain corresponding analysis results, and displaying the analysis results.

[0013] The third aspect of the embodiment of the present application discloses an electronic device, comprising: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory, and is used for executing the multi-dimension collaborative evaluation method based on foot pressure detection disclosed in the first aspect of the embodiment of the present application.

[0014] The fourth aspect of the embodiment of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program enables a computer to execute the multi-dimension collaborative evaluation method based on foot pressure detection disclosed in the first aspect of the embodiment of the present application.

[0015] Compared with the prior art, the embodiment of the present application has the following beneficial effects: The method in the embodiment of the present application analyzes and processes a plurality of data sets to obtain corresponding analysis results and display the analysis results, so that the foot pressure conditions of the tested user can be comprehensively evaluated from different dimensions. The analysis results are displayed, so that the evaluation results are more intuitive and easy to understand, and professional personnel can quickly obtain key information, and then an individual intervention scheme, a rehabilitation plan or targeted suggestions are formulated for the user, so that the application value and practicality of the evaluation are improved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0017] Figure 1 is a flowchart of the multi-dimension collaborative evaluation method based on foot pressure detection disclosed in the embodiment of the present application; Figure 2 is a flowchart of data analysis and processing disclosed in the embodiment of the present application; Figure 3 is a flowchart of calibration disclosed in the embodiment of the present application; Figure 4 is a structural diagram of a multi-dimension collaborative evaluation system based on foot pressure detection provided by the embodiment of the present application; Figure 5 is a structural diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0018] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", "third", "fourth" and the like in the specification and claims of the present application are used to distinguish different objects, and are not used to describe a specific order. The terms "include" and "have" in the embodiments of the present application and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] Embodiment one

[0021] Please refer to Figure 1 , Figure 1 is a flowchart of the multi-dimensional cooperative evaluation method based on foot pressure detection disclosed in the embodiments of the present application. Wherein, the execution subject of the method described in the embodiments of the present application is composed of software or / and hardware, which can receive relevant information through wired or / and wireless mode, and can send certain instructions. Of course, it can also have certain processing function and storage function. The execution subject can control multiple devices, such as remote physical servers or cloud servers and related software, or local host or server and related software for related operation of devices placed in a certain place, etc. In some scenarios, it can also control multiple storage devices, which can be placed in the same place or different places. As Figure 1 shown, the multi-dimensional cooperative evaluation method based on foot pressure detection includes the following steps: S101: obtaining the original data stream synchronized by time stamp transmitted by the pressure detection platform through the data acquisition interface, the original data stream including the pressure data frame sequence of the pressure sensor array; S102: processing the original data stream to obtain the test data set of the measured user, the test data set including the balance function data set, the foot pressure data set, the standing posture data set and the stability limit data set; S103: analyzing and processing the balance function data set, the foot pressure data set, the standing posture data set and the stability limit data set to obtain the corresponding analysis results, and displaying the analysis results.

[0022] The scheme of the embodiment of the application ensures the consistency of the pressure data frame sequence of the pressure sensor array collected from the pressure detection platform in the time dimension by acquiring the timestamp-synchronized original data stream. This helps to accurately analyze the plantar pressure change at different times, provides a reliable data basis for comprehensively and accurately evaluating the plantar pressure related conditions of the tested user, and avoids data errors and analysis deviations caused by different time synchronization.

[0023] Specifically, the original data stream is processed to obtain a test data set containing a balance function data set, a plantar pressure data set, a standing posture data set and a stability limit data set, realizing the conversion from single original data to multi-dimensional key data. The integration of such multi-dimensional data can comprehensively reflect multiple important aspects of the plantar pressure related conditions of the tested user, providing rich and targeted data support for subsequent comprehensive evaluation, and helping to more deeply and carefully understand the plantar pressure characteristics and physical conditions of the user.

[0024] The analysis and processing of multiple data sets obtain corresponding analysis results and display, which can comprehensively evaluate the plantar pressure conditions of the tested user from different dimensions. For example, the balance function data set analysis can understand the user's body balance ability; the plantar pressure data set analysis can master the plantar pressure distribution; the standing posture data set analysis can judge whether the standing posture is correct; and the stability limit data set analysis can determine the boundary of the user's body stability. Displaying these analysis results makes the evaluation results more intuitive and easy to understand, facilitates professional personnel (such as doctors, rehabilitation therapists, etc.) to quickly obtain key information, and further formulates personalized intervention programs, rehabilitation plans or provides targeted suggestions for the user, improving the application value and practicality of the evaluation.

[0025] More preferably, the balance function data set includes a proprioceptive index; the proprioceptive index includes total trajectory length, peripheral area, unit area trajectory length and unit time trajectory length; The proprioceptive index is calculated by the following method: Receiving real-time pressure data frames from the pressure sensor array, the pressure data frames including the pressure value of each sensing unit , wherein, is the pressure value of the i th sensing unit; Calculating the total pressure of the current data frame according to the pressure data frame ; Calculating the sum of the moments of all pressure values in the current data frame about the first axis of the preset coordinate system , wherein the calculation formula is: , is the coordinate of the i th sensing unit on the first axis; sum of the moments of all pressure values in the current data frame about the second axis of the preset coordinate system , wherein the calculation formula is: , is the coordinate of the i-th sensing unit on the second axis; calculate the pressure center coordinates of the corresponding data frame , and obtain the corresponding pressure center coordinate sequence, wherein the calculation formula is: , ; input the pressure center coordinate sequence into the total trajectory calculation formula to obtain the corresponding total trajectory length, wherein the total trajectory calculation formula is: ; obtain the outer perimeter area by calculating the area of the ellipse covering the preset percentage of pressure center data points; determine the corresponding unit area trajectory length by the total trajectory length and the outer perimeter area; determine the corresponding unit time trajectory length by the total trajectory length and the total test time.

[0026] Specifically, real-time pressure data frames from the pressure sensor array are received, and the pressure value of each sensing unit is determined. This accurate way of obtaining the pressure value of each sensing unit provides accurate basic data for subsequent calculations based on pressure data, ensuring the reliability and accuracy of subsequent calculations, and can truly reflect the pressure situation at different positions of the foot bottom.

[0027] The total pressure of the current data frame is calculated according to the pressure data frame. The calculation of the total pressure is a quantification of the overall force on the foot bottom, which provides a key reference for subsequent calculations of moments, pressure center coordinates, etc., and helps to grasp the intensity and distribution characteristics of the foot bottom pressure as a whole. The sum of the moments of all pressure values in the current data frame about the first axis of the preset coordinate system and the sum of the moments about the second axis are calculated. The calculation of the moment can reflect the rotating effect of the foot bottom pressure in different directions, and the two moment values can further analyze the influence of foot bottom pressure distribution on body balance and posture, providing important mechanical parameters for evaluating the balance function of the body.

[0028] Based on the total pressure and the moment, the pressure center coordinates of the corresponding data frame are calculated, and the corresponding pressure center coordinate sequence is obtained. The pressure center coordinates are a concentrated reflection of the foot bottom pressure distribution, which reflects the projection position of the body's center of gravity on the foot bottom. By obtaining the pressure center coordinate sequence, the moving trajectory of the pressure center in the test process can be dynamically observed, providing intuitive and key data for analyzing the balance stability and posture change of the body.

[0029] The total trajectory length is calculated by inputting the sequence of pressure center coordinates into the total trajectory calculation formula. The total trajectory length reflects the total distance of the pressure center movement during the test, and it can intuitively represent the fluctuation degree of the pressure center in the process of maintaining balance. The longer the total trajectory length, the greater the range of pressure center movement of the body during the test, the more frequent the balance adjustment of the body, which may indicate that the balance function is relatively weak; on the contrary, it may indicate that the balance function is good.

[0030] In the embodiment of the present application, the outer peripheral area is obtained by calculating the area of the ellipse covering the preset percentage of pressure center data points. The outer peripheral area describes the distribution range of the pressure center during the test, which can reflect the stability and control ability of body balance. A larger outer peripheral area means that the pressure center is more dispersed, and the body may need a larger adjustment range when maintaining balance, which may indicate that there is a certain problem with the balance function; while a smaller outer peripheral area indicates that the pressure center is relatively concentrated, and the body balance control is more stable.

[0031] The unit area trajectory length is determined by the total trajectory length and the outer peripheral area. The unit area trajectory length combines the total trajectory length and the outer peripheral area, further refining the evaluation of balance function. It can more accurately reflect the movement efficiency of the pressure center within a certain pressure center distribution range, and help to more accurately judge the fine degree and effectiveness of body balance adjustment.

[0032] The unit time trajectory length is determined by the total trajectory length and the total test time. The unit time trajectory length takes into account the test time factor, and can reflect the movement speed of the pressure center in unit time. It can be used to evaluate the reaction speed and adjustment ability of the body in the process of dynamic balance, and has important significance for analyzing the changes of balance function of the body in different time scales.

[0033] Through the above series of accurate calculation steps, the proprioceptive indicators related to balance function are quantitatively evaluated from multiple dimensions. These indicators complement each other and can comprehensively and meticulously reflect the balance function status of the testee, including balance stability, adjustment ability, reaction speed, etc. It provides rich and accurate evaluation basis for doctors, rehabilitation therapists and other professionals, which helps them to develop more scientific individualized rehabilitation training programs and evaluate rehabilitation effect.

[0034] More preferably, the balance function data set includes vestibular system indicators, visual system indicators, left-right symmetry, center of gravity trajectory data, and support surface indicators; the vestibular system indicators include X-axis average center of gravity deviation and Y-axis average center of gravity deviation; the support surface indicators include support surface size, support surface axis length and support surface axis width; the support surface indicators are determined by pressure pixel points; The vestibular system indicators are calculated by the following steps: The X-axis average center of gravity deviation is calculated according to the difference between the X-coordinate values of all pressure center coordinates and the average value of the X-coordinate during the entire test period. The Y-axis average center of gravity deviation is calculated according to the difference between the Y-coordinate values of all pressure center coordinate points and the average value of the Y-coordinate during the entire test period. The visual system index is calculated by the following steps: Obtaining open-eye test index values and closed-eye test index values; The Romberg rate is calculated according to the open-eye test index values and closed-eye test index values, wherein the Romberg rate is the corresponding visual index.

[0035] The scheme of the embodiment of the application constructs a balance function data set from multiple key systems (vestibular system, visual system) and body posture characteristics (left-right symmetry, center of gravity trajectory, support surface), etc. Various factors affecting human balance function are comprehensively and meticulously covered, providing a rich and valuable data basis for accurate and comprehensive evaluation of human balance ability. Compared with single-dimensional evaluation, the balance status of individuals can be more truly and completely reflected.

[0036] The X-axis average center of gravity deviation and the Y-axis average center of gravity deviation are calculated as vestibular system indexes. The X-axis and Y-axis average center of gravity deviations respectively reflect the deviation degree of the center of gravity of the body in the horizontal direction (left and right, front and back) relative to the average position. The vestibular system is an important sensory organ for maintaining balance in the human body, responsible for sensing head movement and spatial position changes. These two indexes can directly quantify the influence of vestibular system dysfunction on body balance, and through the above indexes, such abnormalities can be intuitively found, providing an objective basis for the diagnosis and evaluation of vestibular system-related diseases.

[0037] The average center of gravity deviation is calculated based on the difference between the coordinate values of all pressure center coordinates and the average value of the coordinates during the entire test period. This calculation method considers the dynamic changes of the center of gravity position during the entire test process. It can capture the subtle changes of the vestibular system in balancing adjustment at different times and under different actions. It can not only be used to evaluate static balance function, but also can effectively analyze dynamic balance ability, which is helpful to more comprehensively understand the working condition of the vestibular system under different balance states.

[0038] In practice, the Romberg rate is calculated using both open-eye and closed-eye test index values ​​as a visual system indicator. The Romberg rate is a classic indicator used to assess the role of vision in maintaining balance. When eyes are open, the human body primarily relies on vision, vestibular sense, and proprioception to maintain balance; while when eyes are closed, visual input is removed, and the body mainly relies on vestibular sense and proprioception. By comparing the differences in the index (Romberg rate) between open-eye and closed-eye tests, the extent of the visual system's role in maintaining balance can be clearly identified. For example, a significantly increased Romberg rate indicates a greater contribution of vision to balance, potentially suggesting a problem with vestibular or proprioceptive sense, requiring further examination and evaluation. The open-eye and closed-eye test index values ​​can be the duration of standing or the total trajectory of the center of gravity movement in either the open-eye or closed-eye state.

[0039] This calculation method is relatively simple to operate. It only requires performing open-eye and closed-eye tests to obtain the corresponding index values, and then calculating the Romberg rate. This method can quickly and effectively provide a preliminary assessment of the impact of the visual system on balance function.

[0040] Specifically, support surface indicators, such as support surface size, support surface axial length, and support surface axial width, are determined using pressure pixel data. The support surface is the contact area between the body and a support surface (such as the ground), and its size and shape directly affect the body's balance stability. Support surface size reflects the available support range; a larger support surface generally indicates better balance stability. Support surface axial length and width further describe the shape characteristics of the support surface; different shapes of support surfaces have different mechanical properties when bearing body weight and resisting external forces. These indicators can objectively and accurately reflect the body's support state during testing, providing important geometric parameters for assessing balance function. Combined with other balance function indicators, support surface indicators can be used to analyze the strategies an individual employs to maintain balance. For example, when the support surface size decreases or its shape changes, it may mean that the individual is adjusting their body posture to adapt to different balance needs, or attempting to compensate for functional deficiencies in other sensory systems (such as the vestibular or visual systems). Analysis of support surface indicators can provide insights into an individual's behavioral patterns and strategy choices during balance regulation, providing a basis for developing personalized rehabilitation training programs.

[0041] More preferably, the plantar pressure dataset is obtained in the following manner: Image processing is performed on the pressure data frames to identify the contours of the left and right feet and to segment the regions of interest in the feet; For each region of interest, predefined calculations are performed to obtain information including arch index, forefoot and heel pressure distribution, area, and average pressure.

[0042] The pressure data frames are subjected to image processing to identify the left and right foot contours and divide the foot into regions of interest. Image processing techniques can accurately delineate the boundaries of the left and right feet, dividing the foot into different regions of interest such as the forefoot, arch, and rear heel. This precise region division avoids confusion of pressure data from different foot regions, providing an accurate basis for subsequent detailed analysis of each region, making the obtained plantar pressure data more targeted and reliable.

[0043] For each region of interest, predefined calculations are performed to obtain indicators such as the arch index, forefoot and rear heel pressure distribution, region area, and average pressure. The arch index can reflect the shape and elasticity of the arch, which is important for determining whether the foot has deformities such as flat feet or high arches; the forefoot and rear heel pressure distribution can reveal the force characteristics of the foot during standing or walking, and different distribution patterns may be related to foot diseases, exercise habits, etc.; the region area and average pressure further quantify the force on each foot region. These indicators comprehensively and meticulously describe the plantar pressure characteristics from multiple dimensions, providing rich data support for evaluating foot health, motor function, and developing personalized foot care or rehabilitation programs.

[0044] More preferably, the standing posture data set is obtained by the following method: Determine the left and right foot pressure data; Calculate the left and right foot pressure symmetry index based on the left and right foot pressure data; In specific implementation, the left and right foot pressure data are determined, and the left and right foot pressure symmetry index is calculated based on these data. The left and right foot pressure symmetry is one of the important indicators for evaluating the balance of the standing posture. In a normal standing posture, the pressure distribution of the left and right feet should be relatively symmetrical, and if there is significant asymmetry, it may indicate posture abnormalities, muscle strength imbalance, or skeletal structure problems in the body. By calculating the left and right foot pressure symmetry index, the symmetry of the standing posture can be objectively and quantitatively evaluated, providing a basis for discovering potential posture problems.

[0045] The stability limit data set is obtained by the following method: Perform trajectory analysis on the sequence of data frames collected during the dynamic balance test to calculate the movement speed, maximum deviation, deviation angle, and deviation area.

[0046] Specifically, the trajectory analysis is performed on the data frame sequence collected in the dynamic balance test, and the movement speed, maximum deviation, deviation angle, and deviation area are calculated. The dynamic balance test can simulate various dynamic scenarios in actual life, such as walking, turning, and avoiding obstacles. By analyzing the data frame sequence in the dynamic test, these indicators can comprehensively reflect the balance control ability of the human body in the dynamic process. The movement speed reflects the speed of body movement and the timeliness of balance adjustment; the maximum deviation, deviation angle, and deviation area describe the degree and direction of the body deviating from the balance position in the dynamic process, which can intuitively show the stability and control accuracy of body balance.

[0047] More preferably, as shown in Figure 2 The analysis and processing of the balance function data set, the plantar pressure data set, the standing posture data set, and the stability limit data set to obtain corresponding analysis results, and the display of the analysis results, include: S1031: logically comparing the balance function data set, the plantar pressure data set, the standing posture data set, and the stability limit data set to generate an abnormal biomechanics pattern identifier; S1032: based on a predefined rule base, associating the abnormal biomechanics pattern identifier with a physiological system defect type, and generating an association result data; S1033: using a trained neural network model to perform pattern recognition analysis on the test data set, the neural network model being configured to receive index data from the core evaluation module and output a similarity probability of the biomechanics pattern of the corresponding user and a predefined at least one pathological pattern library; S1034: generating a corresponding evaluation report data, and rendering a user balance function and posture portrait on a user interface according to the evaluation report data, the evaluation report data including an index data set, an association result data, and a pattern recognition result.

[0048] Specifically, the balance function data set, the plantar pressure data set, the standing posture data set, and the stability limit data set are logically compared. These data sets reflect the balance and posture information of the human body from different dimensions, for example, the balance function data set involves the vestibular, visual, and other system indicators, the plantar pressure data set reflects the foot force, the standing posture data set focuses on body symmetry, and the stability limit data set reflects the dynamic balance ability. Through logical comparison, multiple aspects of data can be comprehensively considered, avoiding the one-sidedness that may be caused by a single data source, so as to more accurately generate an abnormal biomechanics pattern identifier and discover potential abnormalities.

[0049] The logical comparison process in the embodiments of the present application not only simply compares data, but also mines potential correlations and rules between different data. For example, plantar pressure distribution abnormalities may be intrinsically linked to asymmetric standing posture or decreased balance function. Through this comprehensive analysis, some unobservable abnormal patterns can be found, providing more comprehensive clues for subsequent in-depth assessment and diagnosis.

[0050] Based on the predefined rule base, the abnormal biomechanical pattern identification is associated with the physiological system defect type. The rule base is a collection of experiences summarized through extensive research and clinical practice, which clearly identifies different abnormal patterns that may correspond to physiological system problems, such as vestibular system dysfunction, musculoskeletal system abnormalities, etc. This association can quickly convert complex biomechanical abnormalities into specific physiological system defect types, providing clear diagnostic directions for medical personnel and improving diagnostic efficiency and accuracy.

[0051] The generated association result data not only helps diagnosis, but also provides a basis for developing targeted intervention measures. For example, if the association result shows that the abnormal pattern is related to insufficient foot muscle strength, a corresponding foot muscle training program can be developed; if it is related to vestibular system problems, vestibular rehabilitation training can be considered. Such intervention measures based on specific physiological system defects are more targeted and effective.

[0052] Specifically, the trained neural network model is used for pattern recognition analysis of the test data set. The model can receive index data from the core evaluation module and output the similarity probability of the user's biomechanical pattern with the predefined at least one pathological pattern library. The neural network model has strong learning and pattern recognition capabilities. It can learn the biomechanical characteristics under different pathological patterns through a large amount of training data, so as to accurately judge the similarity of the user's biomechanical pattern with the known pathological pattern in actual application. This intelligent pattern matching can provide more scientific and objective basis for early detection and diagnosis of diseases. Compared with traditional subjective evaluation methods, the analysis results of the neural network model are more objective and consistent. It is not affected by the experience and subjective factors of the evaluators, and can evaluate all users based on unified standards to ensure the reliability and repeatability of the evaluation results. This is of great significance for large-scale population health evaluation and disease screening.

[0053] According to the evaluation report data, a user balance function and posture portrait is rendered in the user interface. This intuitive portrait display can present complex evaluation data in a graphical form, allowing users to more clearly understand their balance function and posture status. For example, different colors, shapes or icons are used to represent the normality of each index and the similarity with the pathological pattern, allowing users to see their strengths and weaknesses at a glance.

[0054] For example, the rule of associating foot pressure distribution abnormalities with foot deformities is as follows: if, in the foot pressure data set, it is found that the forefoot pressure is concentrated and accounts for more than the normal range, while the hindfoot pressure is significantly reduced, and the arch index is lower than the normal value (the normal arch index range varies slightly depending on the measurement method, and the arch index of flat feet is generally lower than a certain threshold), it is associated with the physiological system defect type of flat feet.

[0055] The rule of associating foot pressure asymmetry with lower limb inequality is as follows: when the standing posture data set shows that there is a significant asymmetry in the pressure distribution of the left and right feet, and the stability limit data set shows that the body's offset angle to one side during the dynamic balance test is consistently greater than the normal range (for example, the normal offset angle is within ±5°, and when the consistent offset is more than ±10°), and the foot pressure data set shows that the pressure on one side of the foot is abnormally increased, it is associated with the physiological system defect type of lower limb inequality.

[0056] The rule of associating standing posture asymmetry with scoliosis is as follows: if the standing posture data set shows that the height of the shoulders and pelvis on the left and right sides of the body is inconsistent, and there is a significant lateral curvature in the neutral position of the spine (for example, by measuring the angle of scoliosis, when the angle is more than 10°), and the balance function data set shows that the body's sway amplitude increases when standing statically, it is associated with the physiological system defect type of scoliosis. Because scoliosis can cause the body's center of gravity to shift, the body will unconsciously make compensatory adjustments, resulting in asymmetry in the shoulders, pelvis, and other parts. At the same time, scoliosis can affect the normal physiological curvature and stability of the spine, making it difficult for the body to maintain balance when standing statically, resulting in an increase in sway amplitude.

[0057] More preferably, the generation of the corresponding evaluation report data includes: Retrieving historical evaluation data of the same user from the database; Performing data comparison and analysis to calculate the change difference and percentage of the current index data and the historical index data; Generating a data structure for visual rendering, which includes data sequences for drawing trajectory overlay graphs, pressure distribution comparison graphs, and index change trend graphs.

[0058] In specific implementation, historical evaluation data of the same user is retrieved from the database and integrated with the index data obtained from the current evaluation. This integration breaks the limitations of a single evaluation and provides a comprehensive understanding of the user's balance function and posture at different time periods. For example, for a user who has been concerned about their balance ability for a long time, by comparing multiple evaluation data, the changes in their balance function at different stages can be clearly seen, whether it is gradually improving or showing a deterioration trend.

[0059] Perform data comparison analysis, calculate the change difference and percentage of current index data and historical index data. This accurate quantitative analysis can accurately capture the subtle changes in the user's health status. For example, in terms of plantar pressure data, if it is found that the pressure value of a certain area has been increasing continuously in the past period of time, and the change percentage exceeds a certain threshold, it may indicate that there are potential muscle fatigue, bone deformation or nerve dysfunction problems in that part, providing important clues for further diagnosis and treatment.

[0060] The data structure also supports drawing trajectory superimposition and pressure distribution comparison charts. Trajectory superimposition can superimpose the standing posture trajectory or motion trajectory of the user at different time periods, facilitating comparative analysis of the stability and changes of the posture. For example, during rehabilitation training, by comparing the trajectory superimposition charts before and after training, the improvement degree of the patient's standing posture can be intuitively seen. The pressure distribution comparison chart can compare the current and historical plantar pressure distribution, clearly show the change pattern of the pressure distribution, help judge whether there is an abnormal pressure concentration or dispersion, and provide a basis for adjusting the rehabilitation program or selecting appropriate insoles and other assistive devices.

[0061] The visual evaluation report presents complex health data in the form of intuitive graphs and charts, allowing users to easily understand their health status without professional medical knowledge. For example, through the colorfully displayed pressure distribution comparison chart, users can intuitively see which parts of their feet have excessive or insufficient pressure, and better understand the doctor's or health manager's suggestions. This intuitive display method can enhance users' trust in the evaluation results and improve users' enthusiasm and participation in health management.

[0062] More preferably, as shown in Figure 3 The pressure detection platform also includes a mechanical sensor before the original data stream synchronized by the timestamp transmitted by the pressure detection platform through the data acquisition interface. The pressure detection platform also includes: S100a: Obtain the calibration relationship data stored in the system calibration stage; S100b: For each real-time data acquisition period, use the calibration relationship data and the current acquired mechanical sensor readings to calculate the real-time calibration coefficient; S100c: Use a spatial interpolation algorithm to process the real-time calibration coefficient to generate a two-dimensional calibration matrix covering the entire pressure sensor array; S100d: Perform dot multiplication operation on the two-dimensional calibration matrix and the corresponding pressure data frame to output the calibrated pressure data.

[0063] On a large pressure detection platform, there are hundreds of pressure sensors distributed. If no calibration is performed, the measurement values of different sensors may have large deviations, resulting in a significant reduction in the data accuracy of the entire platform. After the above calibration processing, the measurement values of each sensor can more truly reflect the actual pressure situation.

[0064] In actual application, the pressure detection platform may face various dynamic changing scenes, such as rapid change of pressure distribution, unstable working state of sensors, etc. The spatial interpolation algorithm is adopted to process the real-time calibration coefficient, to generate a two-dimensional calibration matrix covering the entire pressure sensor array, which can make the calibration process more smooth and continuous, and adapt to the dynamically changing environment. Even if some sensors appear temporary abnormality or fluctuation, through the overall adjustment of the two-dimensional calibration matrix, the output data of the entire system can be kept relatively stable.

[0065] The positions of each sensor in the pressure sensor array are different, and the measured pressure regions may also have differences. By generating a two-dimensional calibration matrix and performing point multiplication operation with the corresponding pressure data frame, the measurement data of different sensors can be unified to the same reference standard, to ensure the consistency of the output data of the entire pressure sensor array. In this way, the pressure data collected at any position can have the same dimension and accuracy, facilitating subsequent data analysis and processing.

[0066] Specifically, the high-precision high-density sensor film in the embodiment of the present application is matched with a high-speed parallel data acquisition card, which can meet the data acquisition of 9600 pressure sensors. Meanwhile, four high-precision mechanical sensors are added for real-time dynamic calibration, solving the common problem of time drift of pressure distribution sensors, reducing the output error from about 10% in the industry to 2%, and making the data more accurate.

[0067] The method in the embodiment of the present application analyzes and processes a plurality of data sets to obtain corresponding analysis results and display them, which can comprehensively evaluate the plantar pressure condition of the measured user from different dimensions. Displaying these analysis results makes the evaluation results more intuitive and easy to understand, facilitating professional personnel to quickly obtain key information, and then formulating personalized intervention schemes, rehabilitation plans or providing targeted suggestions for the user, thereby improving the application value and practicality of the evaluation.

[0068] Embodiment two

[0069] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of the multi-dimensional collaborative evaluation system based on plantar pressure detection disclosed by the embodiment of the present application. As Figure 4 shown, the multi-dimensional collaborative evaluation system based on plantar pressure detection can include: The acquisition module 21 is configured to acquire a time-stamped original data stream transmitted by the pressure detection platform through a data acquisition interface, the original data stream comprising a sequence of pressure data frames of the pressure sensor array. The processing module 22 is configured to process the original data stream to obtain a test data set of the user under test, the test data set comprising a balance function data set, a plantar pressure data set, a standing posture data set and a stability limit data set. The analysis module 23 is configured to analyze and process the balance function data set, the plantar pressure data set, the standing posture data set and the stability limit data set to obtain corresponding analysis results, and display the analysis results.

[0070] The method in the embodiment of the present application analyzes and processes multiple data sets to obtain corresponding analysis results and displays the analysis results, which can comprehensively evaluate the plantar pressure condition of the user under test from different dimensions. Displaying the analysis results makes the evaluation results more intuitive and easy to understand, facilitates professional personnel to quickly obtain key information, and further formulates a personalized intervention scheme, a rehabilitation plan or provides targeted suggestions for the user, thereby improving the application value and practicality of the evaluation.

[0071] Embodiment three

[0072] Please refer to Figure 5 , Figure 5 is a structural schematic diagram of an electronic device disclosed by the embodiment of the present application. The electronic device can be a computer, a server and the like, and of course, under certain circumstances, can also be a mobile phone, a tablet computer, a smart monitoring terminal and the like, and an image acquisition device with processing function. As shown in Figure 5 , the electronic device can include: a memory 510 storing executable program codes; a processor 520 coupled with the memory 510; The processor 520 calls the executable program codes stored in the memory 510 to execute part or all of the steps of the multi-dimensional collaborative evaluation method based on plantar pressure detection in the embodiment one.

[0073] The embodiment of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program causes a computer to execute part or all of the steps of the multi-dimensional collaborative evaluation method based on plantar pressure detection in the embodiment one.

[0074] The embodiment of the present application further discloses a computer program product, wherein when the computer program product runs on a computer, the computer program product causes the computer to execute part or all of the steps of the multi-dimensional collaborative evaluation method based on plantar pressure detection in the embodiment one.

[0075] The application also discloses an application publishing platform, which is used for publishing the computer program product.

[0076] In various embodiments of the present application, it should be understood that the size of the serial number of the processes does not mean the inevitable sequence of execution, and the execution sequence of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0077] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0078] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0079] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-accessible memory. Based on such understanding, the technical solutions of the present application, essentially or the part that contributes to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of steps for causing a computer device (which can be a personal computer, a server or a network device, and specifically can be a processor in the computer device) to execute some or all of the steps of the method described in each embodiment of the present application.

[0080] In the embodiments provided by the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that the determination of B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0081] Those skilled in the art can understand that part or all of the steps in the various methods of the embodiments can be completed by instructing the relevant hardware by a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk memories, magnetic disk memories, magnetic tape memories, or any other computer readable medium capable of carrying or storing data.

[0082] The multi-dimensional collaborative evaluation method and system based on plantar pressure detection, the electronic device and the storage medium are described in detail above. The principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method and the core idea of the present application. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges can be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A multi-dimensional collaborative assessment method based on plantar pressure detection, characterized in that, include: The original data stream transmitted by the pressure detection platform through the data acquisition interface and synchronized with the timestamp is obtained. The original data stream includes a sequence of pressure data frames from the pressure sensor array. The raw data stream is processed to obtain a test dataset of the tested user, which includes a balance function dataset, a plantar pressure dataset, a standing posture dataset, and a stability limit dataset. The balance function dataset, plantar pressure dataset, standing posture dataset, and stability limit dataset are analyzed and processed to obtain corresponding analysis results, which are then displayed.

2. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 1, characterized in that, The balance function dataset includes proprioceptive indicators; the proprioceptive indicators include total trajectory length, peripheral area, trajectory length per unit area, and trajectory length per unit time. The proprioceptive index is calculated as follows: Receive real-time pressure data frames from the pressure sensor array, the pressure data frames including the pressure value of each sensing unit. ,in, Let be the pressure value of the i-th sensing unit; Calculate the total pressure of the current data frame based on the pressure data frame. ; Calculate the sum of the moments of all pressure values ​​in the current data frame about the first axis of the preset coordinate system. The calculation formula is as follows: , Let be the coordinate of the i-th sensing unit on the first axis; Calculate the sum of the moments of all pressure values ​​in the current data frame about the second axis of the preset coordinate system. The calculation formula is as follows: , Let be the coordinate of the i-th sensing unit on the second axis; Calculate the pressure center coordinates of the corresponding data frame And obtain the corresponding pressure center coordinate sequence, where the calculation formula is: , ; The pressure center coordinate sequence is input into the total trajectory calculation formula to calculate the corresponding total trajectory length. The total trajectory calculation formula is as follows: ; The outer perimeter area is obtained by calculating the area of ​​the ellipse covering the preset percentage pressure center data point; The corresponding unit area trajectory length is determined by the total trajectory length and the peripheral area; The corresponding unit time trajectory length is determined by the total trajectory length and the total test time.

3. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 2, characterized in that, The balance function dataset includes vestibular system indicators, visual system indicators, left and right symmetry, center of gravity trajectory data, and support surface indicators; the vestibular system indicators include average center of gravity offset along the X-axis and average center of gravity offset along the Y-axis; the support surface indicators include support surface size, support surface axial length, and support surface axial width; the support surface indicators are determined by pressure pixels; The vestibular system parameters are calculated through the following steps: The average centroid offset of the X-axis is obtained by comparing the X-coordinate values ​​of all pressure center coordinates with the average X-coordinate value during the entire test period. The average Y-axis centroid offset is obtained by comparing the Y-coordinate values ​​of all pressure center points with the average Y-coordinate value during the entire test period. The visual system metrics are calculated through the following steps: Obtain the values ​​of the open-eye test index and the closed-eye test index; The Romberg rate is calculated based on the open-eye test index value and the closed-eye test index value, where the Romberg rate is the corresponding visual index.

4. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 3, characterized in that, The plantar pressure dataset was obtained in the following manner: Image processing is performed on the pressure data frames to identify the contours of the left and right feet and to segment the regions of interest in the feet; For each region of interest, predefined calculations are performed to obtain information including arch index, forefoot and heel pressure distribution, area, and average pressure.

5. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 4, characterized in that, The standing posture dataset was obtained in the following way: Determine the pressure data for the left and right feet; Calculate the left and right foot pressure symmetry index based on the left and right foot pressure data; The stability limit dataset was obtained in the following manner: Trajectory analysis is performed on the data frame sequence collected during the dynamic balance test to calculate the motion speed, maximum offset, offset angle, and offset area.

6. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 5, characterized in that, The analysis and processing of the balance function dataset, plantar pressure dataset, standing posture dataset, and stability limit dataset to obtain corresponding analysis results, and the display of the analysis results, including: Logical comparisons are performed on the balance function dataset, plantar pressure dataset, standing posture dataset, and stability limit dataset to generate abnormal biomechanical pattern identifiers. Based on a predefined rule base, the abnormal biomechanical pattern identifiers are associated with physiological system defect types, and association result data is generated. The test dataset is subjected to pattern recognition analysis using a trained neural network model, which is configured to receive index data from the core evaluation module and output the similarity probability between the biomechanical pattern of the corresponding user and at least one predefined pathological pattern library. The system generates corresponding evaluation report data and renders a user balance function and posture profile on the user interface based on the evaluation report data. The evaluation report data includes an indicator dataset, related result data, and pattern recognition results.

7. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 6, characterized in that, The data for generating the corresponding evaluation report includes: Retrieve historical evaluation data for the same user from the database; Perform comparative analysis of the data to calculate the difference and percentage change between the current indicator data and the historical indicator data; Generate a data structure for visualization rendering, the data structure including a data sequence for drawing trajectory overlay plots, pressure distribution comparison plots, and indicator change trend plots.

8. The multi-dimensional collaborative assessment method based on plantar pressure detection as described in claim 1, characterized in that, The pressure detection platform also includes a mechanical sensor, and before acquiring the timestamped raw data stream transmitted by the pressure detection platform through the data acquisition interface, it further includes: Retrieve calibration relationship data stored during the system calibration phase; For each real-time data acquisition cycle, the real-time calibration coefficient is calculated using the calibration relationship data and the currently acquired mechanical sensor readings; The real-time calibration coefficients are processed using a spatial interpolation algorithm to generate a two-dimensional calibration matrix covering the entire pressure sensor array. The two-dimensional calibration matrix is ​​multiplied by the corresponding pressure data frame to output the calibrated pressure data.

9. A multi-dimensional collaborative assessment system based on plantar pressure detection, characterized in that, include: Acquisition module: used to acquire the raw data stream transmitted by the pressure detection platform through the data acquisition interface and synchronized with the timestamp, the raw data stream including the pressure data frame sequence of the pressure sensor array; Processing module: used to process the raw data stream to obtain the test dataset of the tested user, the test dataset including balance function dataset, plantar pressure dataset, standing posture dataset and stability limit dataset; Analysis module: Used to analyze and process the balance function dataset, plantar pressure dataset, standing posture dataset, and stability limit dataset to obtain corresponding analysis results, and to display the analysis results.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program causes a computer to perform the multi-dimensional collaborative evaluation method based on plantar pressure detection as described in any one of claims 1 to 7.

Images