Skin creep feature point recognition method and related device

Abstract

The application discloses a skin creep feature point recognition method and related equipment, and relates to the field of biological tissue mechanics testing. The method comprises the following steps: acquiring displacement-time sequence data of skin under the action of a step negative pressure load; performing twice difference calculation on the displacement-time sequence data by using a numerical differentiation method to obtain an acceleration-time sequence, wherein the twice difference calculation directly uses an original sampling interval of the displacement-time sequence as a difference step; positioning a global minimum extreme point in the acceleration-time sequence, and determining a displacement point corresponding to the extreme point as a creep starting point. The application realizes objective and automatic recognition of the creep starting point, does not need to preset parameters, has high recognition precision and good consistency, and is suitable for feature point positioning in skin viscoelasticity testing.

Description

Technical Field

[0001] This application relates to the field of biomechanical testing of tissues, specifically to a method and related equipment for identifying skin creep feature points. Background Technology

[0002] In skin viscoelasticity tests based on negative pressure attraction, a response curve showing the change in skin displacement over time can be obtained by applying a step negative pressure to the skin. This curve typically includes an instantaneous elastic response stage and a subsequent creep stage. Accurately identifying the creep initiation point (i.e., the moment when the skin transitions from the instantaneous elastic response to steady-state creep) is a prerequisite for subsequent calculations of mechanical parameters such as creep displacement and instantaneous elasticity.

[0003] In existing technologies, the identification of creep initiation points mainly adopts the following methods: manual interpretation relies on operators visually observing the inflection point of the curve, which is highly subjective and has poor repeatability; the fixed threshold method presets a fixed time point or displacement change as the starting point, which cannot adapt to the differences in skin response speed among different individuals and different parts; the first-order differential method finds the maximum value point of displacement velocity, but this point is usually a certain moment in the stress loading process, not the physical moment when the force loading is completed and enters steady-state creep, and is easily affected by signal glitches.

[0004] None of the above methods could accurately locate the creep initiation point from the perspective of physical mechanisms, resulting in systematic errors in the extracted creep displacement and instantaneous elastic parameters, which affected the reliability and comparability of the test results. Summary of the Invention

[0005] The purpose of this application is to provide a method and related equipment for identifying skin creep feature points, so as to overcome the technical problems of strong subjectivity and insufficient accuracy in feature point positioning caused by the lack of a precise positioning method based on physical mechanisms in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for identifying skin creep feature points, comprising: Acquire displacement-time series data of the skin under step negative pressure load; The displacement-time series data is subjected to a second difference calculation using a numerical differential method to obtain an acceleration-time series; wherein the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size. Locate the global minimum extreme point in the acceleration-time series, and determine the displacement point corresponding to the extreme point as the creep initiation point.

[0007] In one embodiment of the present invention, the quadratic difference calculation includes: The first derivative of the displacement-time series data is used to obtain the velocity-time series; The acceleration-time series is obtained by taking the first derivative of the velocity-time series.

[0008] In one embodiment of the present invention, locating the global minimum extreme point in the acceleration-time series includes: Traverse all data points in the acceleration-time series, compare the acceleration values ​​at each point, record the minimum value and its corresponding time index, and take the displacement point corresponding to the time index as the creep start point.

[0009] In one embodiment of the present invention, before employing the numerical differentiation method, the method further includes: The displacement-time series data is truncated to extract the displacement data from the start of the step negative pressure to the end of the test.

[0010] In one embodiment of the present invention, it further includes: Based on the creep initiation point, the start and end points of the displacement-time series, calculate at least one of the following skin mechanical characteristic parameters: Total displacement ,in This represents the displacement value at the end of the displacement-time series. This represents the displacement value at the starting point of the displacement-time series. creep displacement ,in This refers to the displacement value at the creep initiation point; Instantaneous elastic response ,in The absolute value of the applied step negative pressure.

[0011] In one embodiment of the present invention, the starting point is the displacement point corresponding to the moment when the step negative pressure is first applied, and the ending point is the displacement point corresponding to the moment when the test ends.

[0012] In one embodiment of the present invention, the displacement-time series data is acquired by a high-frequency displacement sensor, and the step negative pressure is applied by a negative pressure skin testing device.

[0013] Secondly, the present invention provides a skin creep feature point recognition system, comprising: The data acquisition module is used to acquire displacement-time series data of the skin under step negative pressure load; An acceleration calculation module is used to perform a second difference calculation on the displacement-time series data using a numerical differential method to obtain an acceleration-time series; wherein the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size; The feature point localization module is used to locate the global minimum extreme point in the acceleration-time series and determine the displacement point corresponding to the extreme point as the creep initiation point.

[0014] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the skin creep feature point recognition method as described above.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the skin creep feature point recognition method described above.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: Firstly, this invention provides a method for identifying skin creep feature points. It obtains the acceleration-time series by calculating the second derivative of the displacement-time series and uses the global minimum acceleration point as the creep initiation point. This minimum point physically corresponds to the transition moment when the step negative pressure loading is completed and the skin transitions from inertial response to viscous creep. By accurately locating feature points based on the physical mechanism, it avoids the subjectivity and insufficient accuracy problems of manual interpretation or fixed thresholds. The second-order difference calculation directly uses the original sampling interval as the difference step size, without the need for any preset parameters, achieving objective and adaptive automatic identification.

[0017] Secondly, this invention provides a skin creep feature point recognition system. The system acquires displacement-time series data through a data acquisition module, performs quadratic difference using numerical differentiation, and directly outputs the acceleration sequence with the original sampling interval as the step size. The feature point localization module searches for the global minimum point and determines it as the creep initiation point. These modules work collaboratively, embedding a physical mechanism-based recognition algorithm into the system, eliminating human intervention, and ensuring the stability of the recognition process and the consistency of the results. This overcomes the shortcomings of existing technologies, such as subjective localization and low accuracy.

[0018] Thirdly, the present invention provides a computer device that, through a processor executing a specific computer program, can efficiently implement the steps of the method of the present invention. When performing data processing tasks, the computer device can accurately perform numerical calculations and logical judgments, avoiding errors caused by human factors. At the same time, since the computer program has high stability and reliability, it can ensure the accuracy and consistency of the data processing results.

[0019] Fourthly, the present invention provides a computer-readable storage medium. By programming the steps of the method of the present invention into a computer program and storing it on the computer-readable storage medium, users can easily load these programs onto any compatible computer device and execute them without rewriting or converting the code, which greatly improves the convenience and flexibility of program execution. Attached Figure Description

[0020] Figure 1 This is a flowchart of the skin creep feature point recognition method in an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of the original skin displacement-time curve in an embodiment of the present invention.

[0022] Figure 3 This is a schematic diagram of the effective displacement-time data segment in an embodiment of the present invention.

[0023] Figure 4 This is a schematic diagram of the speed-time curve in an embodiment of the present invention.

[0024] Figure 5 This is a schematic diagram of the acceleration-time curve in an embodiment of the present invention.

[0025] Figure 6 This is a diagram showing the distribution of total displacement parameters in an embodiment of the present invention.

[0026] Figure 7 This is a distribution diagram of creep displacement parameters in an embodiment of the present invention.

[0027] Figure 8 This is a diagram showing the instantaneous elastic parameter distribution in an embodiment of the present invention.

[0028] Figure 9 This is a schematic diagram of the skin creep feature point recognition system in an embodiment of the present invention. Detailed Implementation

[0029] In skin viscoelasticity testing based on negative pressure attraction, the skin generates a displacement-time response curve under step negative pressure. Accurately identifying the creep initiation point is a prerequisite for calculating mechanical parameters such as creep displacement and instantaneous elasticity. Existing technologies rely on manual interpretation, fixed thresholds, or extreme velocity values ​​for localization, lacking precise localization methods based on physical mechanisms. This results in highly subjective and inaccurate feature point identification, failing to adapt to individual differences.

[0030] Based on the above background, this invention proposes a method and related equipment for identifying skin creep feature points. The acceleration-time series is obtained by calculating the second derivative of the displacement-time series. The global minimum point of acceleration is taken as the creep initiation point, which physically corresponds to the transition moment when the step negative pressure loading is completed and the skin transitions from inertial response to viscous creep. The quadratic difference calculation directly uses the original sampling interval as the step size, without the need for preset parameters, achieving objective and adaptive automatic identification, overcoming the problems of subjective positioning and low accuracy in existing technologies.

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Example 1 In this embodiment, a method for identifying skin creep feature points is provided, referring to... Figure 1 As shown, this method automatically locates the creep initiation point by numerical differentiation based on the displacement response data of the skin under step negative pressure load.

[0033] Specifically, the first step is to acquire displacement-time series data of the skin under a step negative pressure load. This data can be obtained using a negative pressure skin testing device in conjunction with a displacement sensor, reflecting the real-time deformation process of the skin under the applied load. Obtaining accurate displacement-time series data is the foundation for subsequent feature point identification.

[0034] After obtaining the displacement-time series data, a numerical differentiation method is used to perform a second-order difference calculation on the displacement-time series data to obtain the acceleration-time series. The second-order difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size, without the need for interpolation, filtering, or resampling of the data. The numerical differentiation method can extract acceleration information from discrete displacement data. Acceleration, as the second derivative of displacement, characterizes the rate of change of skin deformation velocity. Directly using the original sampling interval as the difference step size avoids subjective errors introduced by manually setting the step size or smoothing window, ensuring that the calculated acceleration-time series fully preserves the dynamic characteristics of the original displacement signal.

[0035] After obtaining the acceleration-time series, the global minimum extreme point in the acceleration-time series is located. The global minimum extreme point is the point with the smallest value in the acceleration series. This point physically corresponds precisely to the moment when the step negative pressure load is completed and the skin transitions from inertial-dominated rapid elastic deformation to viscous-dominated creep flow. The displacement point corresponding to this global minimum extreme point is determined as the creep initiation point, thus completing the automatic identification of skin creep characteristic points.

[0036] The skin creep feature point recognition method provided in this embodiment achieves objective localization based on physical mechanisms through a collaborative process of acquiring displacement-time series, performing quadratic difference calculation using numerical differentiation, locating the global minimum extremum point of acceleration, and determining it as the creep initiation point. The steps are logically progressive: displacement data is the raw input, quadratic difference calculation extracts acceleration information, and global extremum search locks the feature point. This method overcomes the technical problems of strong subjectivity and insufficient accuracy in existing technologies by eliminating the need for any preset parameters or manual interpretation.

[0037] Example 2 The skin creep feature point recognition method provided in this embodiment further explains the specific implementation of the second difference calculation based on the above embodiment 1.

[0038] After obtaining the displacement-time series data of the skin under a step negative pressure load, a quadratic difference calculation is performed. This quadratic difference calculation consists of two consecutive numerical differentiation steps.

[0039] First, the first derivative of the displacement-time series data is calculated to obtain the velocity-time series. The first derivative reflects the rate of change of skin elevation displacement over time, i.e., the skin elevation velocity. During numerical differentiation, the original sampling interval of the displacement-time series is directly used as the difference step size, and the instantaneous velocity at each discrete point is calculated using difference formulas in numerical differentiation (such as forward differencing or central differencing). Through this step, the original displacement data is converted into velocity data, and the velocity-time series clearly demonstrates the dynamic evolution of the skin velocity during the loading transient process, from zero to a peak value and then gradually decreasing.

[0040] Then, the first derivative of the obtained velocity-time series is calculated again to obtain the acceleration-time series. The second derivative reflects the rate of change of the skin bulge velocity, i.e., the skin bulge acceleration. Similarly, this step uses a numerical differentiation method, with the difference step size still directly using the original sampling interval, without the need for additional filtering or smoothing. Through two consecutive numerical differentiations, acceleration information is extracted from the original displacement data.

[0041] The first numerical differentiation of the displacement curve yields the velocity curve, which exhibits a pattern of rapid initial rise followed by gradual decline. The second numerical differentiation of the velocity curve yields the acceleration curve, which displays alternating positive and negative values, with the global minimum acceleration point appearing as a sharp negative peak. This acceleration minimum point precisely corresponds to the physical transition moment when the step negative pressure loading is completed, and the skin transitions from inertial-dominated rapid elastic deformation to viscous-dominated creep flow.

[0042] Both numerical differentiations directly utilize the original sampling interval as the difference step size, avoiding errors introduced by manually setting the difference step size or smoothing window. This ensures that the calculated acceleration-time series fully preserves the dynamic characteristics of the original displacement signal. Through the synergistic effect of the two differentiations, the implicit force loading state change information in the displacement signal is explicitly extracted, providing a reliable acceleration data foundation for the subsequent accurate location of the global minimum extreme point.

[0043] Example 3 The skin creep feature point recognition method provided in this embodiment further explains the specific method of locating the global minimum extreme point in the acceleration-time series based on the above embodiment 1.

[0044] After obtaining the acceleration-time series using numerical differentiation, it is necessary to locate the global minimum extremum point within the series. Specifically, a traversal search method is employed: traversing all data points in the acceleration-time series, comparing the acceleration values ​​at each point sequentially, and recording the currently encountered minimum value and its corresponding time index. After traversing all data points, the recorded minimum value is the global minimum extremum point of acceleration, and the recorded time index is the time when this extremum point occurred.

[0045] The displacement point in the displacement-time series corresponding to the time index is determined as the creep initiation point. This traversal search method is deterministic, does not rely on random algorithms or approximate estimations, and can uniquely determine the global minimum extreme point for any given acceleration sequence, ensuring the repeatability of the identification results.

[0046] By traversing and searching to locate the global minimum extreme point, the most significant negative peak in the acceleration curve can be accurately captured. This peak physically corresponds precisely to the moment when the step negative pressure loading is completed and the skin transitions from inertial response to viscous creep. By tracing the time index corresponding to the extreme point back to the displacement-time series, the creep initiation point with clear physical significance can be obtained, providing a reliable reference position for subsequent mechanical parameter calculations.

[0047] Example 4 The skin creep feature point recognition method provided in this embodiment further explains the data preprocessing steps based on the above embodiment 1.

[0048] After obtaining the displacement-time series data of the skin under step negative pressure load, before performing the second difference calculation using the numerical differentiation method, the effective segment of the displacement-time series data is first extracted.

[0049] Specifically, displacement data is extracted from the period from the application of the step negative pressure to the end of the test. The start time of the step negative pressure application can be determined based on the rising edge of the negative pressure control signal or the moment when the displacement signal begins to change significantly. The end time of the test is determined by the preset acquisition duration of the testing device or the end command set by the operator. Through this interception operation, the zero displacement segment before the start of the test and the noise segment after the end of the test are removed, retaining a complete and valid data segment that includes the transient process of load application and the steady-state holding phase.

[0050] Extracting the effective data segment reduces the amount of data required for subsequent numerical differentiation calculations, thus improving computational efficiency. Simultaneously, this step eliminates invalid data segments, preventing noise signals from the pre- and post-test stages from interfering with acceleration calculations and global extremum searches. This ensures that feature point identification is performed only within the effective data range, thereby improving the accuracy and robustness of the identification.

[0051] Example 5 The skin creep feature point recognition method provided in this embodiment further explains the calculation of skin mechanical feature parameters based on the above embodiment 1.

[0052] After identifying the creep initiation point, at least one of the following skin mechanical characteristic parameters is calculated by combining the start and end points of the displacement-time series.

[0053] The starting point is the displacement point corresponding to the moment the step negative pressure is applied, and the ending point is the displacement point corresponding to the moment the test ends. The starting and ending points together define the effective test interval, providing a benchmark reference position for parameter calculation.

[0054] The total displacement is based on the formula Calculation, where For the total displacement, This represents the displacement value at the end of the displacement-time series. This is the displacement value at the starting point of the displacement-time series. This parameter characterizes the total deformation of the skin during the entire test process, reflecting the overall response of the skin under a step negative pressure load.

[0055] Creep displacement is based on the formula Calculation, where This is creep displacement. This is the displacement value at the creep initiation point. This parameter characterizes the amount of viscous flow deformation of the skin under steady-state force loading, reflecting the skin's continuous deformation capacity from the end of the instantaneous elastic response to the end of the test, and is an important indicator for evaluating skin laxity characteristics.

[0056] Instantaneous elastic response according to the formula Calculation, where For instantaneous elastic response, This is the absolute value of the applied step negative pressure. This parameter characterizes the skin's ability to rapidly deform elastically at the moment of force loading. Its physical meaning is the pressure value borne per unit displacement change. The higher the value, the stronger the skin's resistance to deformation at the moment of loading, reflecting the skin's tightness.

[0057] The three parameters described above describe the mechanical behavior of the skin under a step negative pressure load from different dimensions: total displacement reflects the overall deformation amplitude, creep displacement reflects the viscous flow characteristics, and instantaneous elastic response reflects the rapid elastic capability. The calculation of each parameter is based on the precise location of the creep initiation point, and the accuracy of feature point identification directly determines the reliability of these parameters.

[0058] Example 6 The skin creep feature point identification method provided in this embodiment further explains the sources of displacement-time series data and step negative pressure based on the above embodiment 1.

[0059] Displacement-time series data were acquired by a high-frequency displacement sensor. The high-frequency displacement sensor can be any of a laser displacement sensor, an eddy current displacement sensor, or a linear variable differential transformer, with its sampling frequency set to fully capture the dynamic response of the skin during the loading transient process. High-frequency sampling ensures a sufficiently high temporal resolution of the displacement data, enabling subsequent numerical differentiation calculations to accurately extract acceleration information and preventing the omission or shifting of acceleration extrema due to insufficient sampling rate.

[0060] The step negative pressure is applied by a negative pressure skin testing device. This device includes a vacuum pump, a negative pressure chamber, and a pressure controller. The vacuum pump generates a negative pressure source, the pressure controller adjusts and maintains a preset negative pressure value, and the negative pressure chamber is fitted to the skin surface to transmit the negative pressure load. The opening size and shape of the negative pressure chamber can be selected according to the test site (such as cheek, arm, fingertip) to meet the skin testing needs of different areas.

[0061] A high-frequency displacement sensor works in conjunction with a negative pressure skin testing device: the negative pressure device applies a step negative pressure to the skin, and the sensor records the skin's bulge displacement in real time, generating displacement-time series data. Data acquisition and negative pressure application are triggered synchronously, ensuring time axis alignment and making the correspondence between displacement response and load application accurate and reliable. This hardware configuration provides a high-precision, highly synchronized raw data foundation for feature point recognition methods, guaranteeing the accuracy and repeatability of the recognition results.

[0062] Example 7 This embodiment applies the skin creep feature point recognition method provided in Embodiments 1 to 6 above to an actual skin test, and provides a complete description of the implementation process of the technical solution in conjunction with the accompanying drawings.

[0063] Reference Figure 1 The flowchart shown in this embodiment of the invention illustrates a method for identifying skin creep feature points. This method operates within a data processing unit (such as a host computer, embedded processor, or cloud server). The data source is a negative pressure skin testing device with rapid response capabilities. This device applies a preset step negative pressure to the skin surface, and a high-frequency displacement sensor records the skin response. This embodiment performs signal post-processing on the raw displacement curve generated by the above process.

[0064] Reference Figure 2 The diagram shown is a schematic representation of the original skin displacement-time curve in an embodiment of the present invention. The horizontal axis represents time (seconds), and the vertical axis represents the displacement of the skin bulge (millimeters). The original curve contains the complete displacement response from the start to the end of the test.

[0065] First, the effective segment of the original displacement-time series data is extracted. Displacement data is extracted from the period from the application of the step negative pressure to the end of the test. (Refer to...) Figure 3 The diagram shown is a schematic representation of the effective displacement-time data segment in an embodiment of the present invention. The starting displacement value of the displacement-time series is marked in the diagram. Creep initiation point displacement value and the final displacement value of the displacement-time series The starting point corresponds to the moment when the step negative pressure begins to be applied, and the ending point corresponds to the moment when the test ends.

[0066] Then, a numerical differential method is used to perform a second-order difference calculation on the effective displacement-time series data. (Refer to...) Figure 4 The illustrated velocity-time curve diagram in this embodiment of the invention shows that the velocity curve is obtained by taking the first derivative of the displacement curve. This curve exhibits a shape of first rising rapidly and then gradually decreasing. (Refer to...) Figure 5 The illustrated acceleration-time curve diagram in this embodiment of the invention shows that by taking the first derivative of the velocity curve again to obtain the acceleration curve, it can be clearly seen that the acceleration curve is obtained by taking the first derivative of the velocity curve. A sharp peak appears at this point, which is the global minimum of acceleration. Looking back at the effective displacement-time data segment diagram... The displacement point corresponding to that moment is defined as the creep initiation point. From a physical perspective, this extreme point precisely corresponds to the moment when the external step load is completed and the body enters a steady state, marking the formal transition of skin tissue from the inertia-dominated rapid elastic deformation stage to the viscosity-dominated creep flow stage.

[0067] In a specific numerical example, the negative pressure set for testing... The collected displacement values ​​are as follows: Displacement - Displacement value at the starting point of the time series ; Creep initiation point displacement ; Displacement - Displacement value at the end of the time series .

[0068] Calculated according to the formula in Example 5: Total displacement ; creep displacement ; Instantaneous elastic response .

[0069] These calculation results will be stored and output for direct evaluation or as input to downstream algorithms.

[0070] Multiple tests were conducted on different parts of the same human body (cheek, arm, and fingertips) to evaluate the ability of the characteristic parameters obtained by this method to characterize the mechanical properties of skin in different areas. The testing procedure was the same for each test, as described above. (Refer to...) Figure 6 The total displacement parameter distribution diagram shown in the embodiment of the present invention is as follows: Figure 7 The creep displacement parameter distribution diagram shown in the embodiment of the present invention and Figure 8 The instantaneous elastic parameter distribution diagram shown in the embodiment of the present invention indicates that, compared with the skin on the cheek, the fingertip has smaller total displacement and creep displacement, but a higher instantaneous elastic value. This demonstrates that the feature parameters extracted by this method can effectively distinguish the differences in mechanical properties of skin in different areas, verifying the effectiveness and reliability of this method in practical applications.

[0071] Example 8 Reference Figure 9 As shown, the present invention also provides a skin creep feature point recognition system, which includes a data acquisition module, an acceleration calculation module, and a feature point localization module.

[0072] The data acquisition module is used to acquire displacement-time series data of the skin under step negative pressure load. This module communicates with an external high-frequency displacement sensor and negative pressure skin testing device, receiving raw displacement response data collected by the sensor and providing accurate time series input for the entire system. The data acquisition module ensures the integrity and real-time nature of the data source, enabling subsequent processing modules to operate based on high-quality raw data.

[0073] The acceleration calculation module is connected to the data acquisition module and receives the displacement-time series data output by the data acquisition module. The acceleration calculation module uses a numerical differentiation method to perform a second-order difference calculation on the displacement-time series data to obtain the acceleration-time series. The second-order difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size, without the need for interpolation, filtering, or resampling. Through two consecutive numerical differentiations, this module extracts acceleration information from the displacement data, making the implicit force loading state changes explicit, and providing a physically meaningful criterion for feature point identification.

[0074] The feature point localization module is connected to the acceleration calculation module and receives the acceleration-time series output by the acceleration calculation module. The feature point localization module locates the global minimum extreme point in this acceleration-time series and determines the displacement point corresponding to this extreme point as the creep initiation point. This module uniquely determines the location of the minimum value in the acceleration sequence through traversal search or extreme value detection algorithms and maps it back to the original displacement sequence, thus completing the automatic identification of feature points.

[0075] The data acquisition module, acceleration calculation module, and feature point localization module are cascaded sequentially, forming a complete processing chain from raw data acquisition to feature point output. The data acquisition module provides raw displacement data, the acceleration calculation module converts it into acceleration information, and the feature point localization module extracts the global minimum extreme point as the creep initiation point. Each module has a clear division of labor and works collaboratively, embedding the physical mechanism-based recognition algorithm into the system, eliminating human intervention, and ensuring the stability of the recognition process and the consistency of the results. This overcomes the shortcomings of existing technologies, such as subjective positioning and low accuracy.

[0076] Example 9 In a specific embodiment of the present invention, a computer device is also provided. Specifically, the computer device includes a processor and a memory. The memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to realize the corresponding method flow or corresponding function. The processor described in this embodiment of the invention can be used to acquire displacement-time series data of skin under step negative pressure load; a numerical differentiation method is used to perform a second difference calculation on the displacement-time series data to obtain an acceleration-time series; wherein, the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size; the global minimum extreme point in the acceleration-time series is located, and the displacement point corresponding to the extreme point is determined as the creep initiation point.

[0077] Example 10 This invention also provides a storage medium, specifically a computer-readable storage medium, which is a memory device in a terminal device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and extended storage media supported by the terminal device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the methods in the above embodiments; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: acquiring displacement-time series data of skin under step negative pressure load; using a numerical differentiation method to perform a second difference calculation on the displacement-time series data to obtain an acceleration-time series; wherein the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size; locating the global minimum extreme point in the acceleration-time series, and determining the displacement point corresponding to the extreme point as the creep initiation point.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is not limited by the foregoing description. Thus, all changes falling within the meaning and scope of equivalents are intended to be included within the scope of the invention. No reference numerals in the drawings should be considered limiting.

[0083] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only for illustrating the technical concept of the present invention and should not be used to limit the scope of protection of the present invention. Any modifications made to the technical solutions based on the technical concept proposed in this invention fall within the scope of protection of this invention.

Claims

1. A method for identifying skin creep feature points, characterized in that, include: Acquire displacement-time series data of the skin under step negative pressure load; The displacement-time series data is subjected to a second difference calculation using a numerical differential method to obtain an acceleration-time series; wherein the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size. Locate the global minimum extreme point in the acceleration-time series, and determine the displacement point corresponding to the extreme point as the creep initiation point.

2. The method for identifying skin creep feature points according to claim 1, characterized in that, The quadratic difference calculation includes: The first derivative of the displacement-time series data is used to obtain the velocity-time series; The acceleration-time series is obtained by taking the first derivative of the velocity-time series.

3. The method for identifying skin creep feature points according to claim 1, characterized in that, The process of locating the global minimum extreme point in the acceleration-time series includes: Traverse all data points in the acceleration-time series, compare the acceleration values ​​at each point, record the minimum value and its corresponding time index, and take the displacement point corresponding to the time index as the creep start point.

4. The method for identifying skin creep feature points according to claim 1, characterized in that, Before employing the numerical differentiation method, the method further includes: The displacement-time series data is truncated to extract the displacement data from the start of the step negative pressure to the end of the test.

5. The method for identifying skin creep feature points according to claim 1, characterized in that, Also includes: Based on the creep initiation point, the start and end points of the displacement-time series, calculate at least one of the following skin mechanical characteristic parameters: Total displacement ,in For the total displacement, This represents the displacement value at the end of the displacement-time series. This represents the displacement value at the starting point of the displacement-time series. creep displacement ,in This is creep displacement. This refers to the displacement value at the creep initiation point; Instantaneous elastic response ,in For instantaneous elastic response, The absolute value of the applied step negative pressure.

6. The method for identifying skin creep feature points according to claim 5, characterized in that, The starting point is the displacement point corresponding to the moment when the step negative pressure is first applied, and the ending point is the displacement point corresponding to the moment when the test ends.

7. The method for identifying skin creep feature points according to claim 1, characterized in that, The displacement-time series data is acquired by a high-frequency displacement sensor, and the step negative pressure is applied by a negative pressure skin testing device.

8. A skin creep feature point recognition system, characterized in that, include: The data acquisition module is used to acquire displacement-time series data of the skin under step negative pressure load; An acceleration calculation module is used to perform a second difference calculation on the displacement-time series data using a numerical differential method to obtain an acceleration-time series; wherein the second difference calculation directly uses the original sampling interval of the displacement-time series as the difference step size; The feature point localization module is used to locate the global minimum extreme point in the acceleration-time series and determine the displacement point corresponding to the extreme point as the creep initiation point.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the skin creep feature point recognition method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the skin creep feature point recognition method as described in any one of claims 1 to 7.

Images