A postoperative patient safety support point intelligent identification and positioning method

Abstract

This invention relates to the field of medical auxiliary diagnosis and monitoring technology, and discloses a method for intelligent identification and positioning of postoperative patient safety support points. The method includes: acquiring postoperative posture data of the patient and support point data in the environment; extracting multi-dimensional stability features from the postoperative posture data to construct a stability assessment vector reflecting the patient's current balance state; performing a comprehensive multi-attribute safety analysis on the support point data using a biomechanical coupling model to generate a dynamic safety level assessment result for each support point; associating and matching the stability assessment vector with the dynamic safety level assessment result to calculate the matching degree between each support point and the patient's current state; determining the optimal safety support point based on the matching degree, and generating recommended data containing support point location information. This invention can improve the accuracy of intelligent identification and positioning of postoperative patient safety support points.

Description

Technical Field

[0001] This invention relates to the field of medical auxiliary diagnosis and monitoring technology, and in particular to a method for intelligent identification and positioning of postoperative patient safety support points. Background Technology

[0002] Postoperative patients need to use support points in the ward environment, such as bed rails, handrails, and wheelchair handles, to maintain their balance and prevent falls and secondary injuries when performing bedside activities or early rehabilitation training. However, existing support point identification and positioning methods mainly rely on static marking or manual designation, that is, nursing staff pre-determine the location of available support points in the ward based on experience, and patients find them themselves or are guided to the designated support points by nursing staff when needed.

[0003] The drawbacks of this approach are twofold: First, static marking methods cannot perceive real-time changes in the patient's postoperative condition, such as trunk tilt, pressure center shift trend, and lower limb joint stability. When the patient is at high risk of imbalance, the pre-marked support points may not be the optimal choice for the current condition. Second, existing technologies have a relatively singular assessment dimension for support point safety, typically focusing only on the support point's position coordinates or basic load-bearing capacity, without fully considering the support point's material characteristics, current load status, the accessible distance between the patient and the support point, and the mechanical coupling relationship between the patient's ergonomic parameters and the support point. This results in recommended support points that are insufficient in terms of safety, accessibility, and suitability. Therefore, how to intelligently identify and accurately locate the safest support point best suited to the patient's current condition based on the patient's real-time posture and the multi-dimensional attributes of environmental support points has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method for intelligent identification and positioning of postoperative patient safety support points to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for intelligent identification and positioning of postoperative patient safety support points, comprising:

[0006] S1, acquire the patient's postoperative posture data and the support point data in the environment;

[0007] S2, extract multi-dimensional stability features from the postoperative posture data to construct a stability assessment vector that reflects the patient's current balance state;

[0008] S3, A biomechanical coupling model is used to perform a comprehensive multi-attribute security analysis on the support point data, and a dynamic security level assessment result is generated for each support point.

[0009] S4, associate and match the stability assessment vector with the dynamic safety level assessment result, and calculate the matching degree between each support point and the patient's current state;

[0010] S5. Determine the optimal safety support point based on the matching degree, and generate recommended data containing support point location information.

[0011] Compared with the prior art, the present invention has the following beneficial effects:

[0012] 1. This invention constructs a patient posture stability assessment vector, transforming trunk tilt angle, pressure center offset, and joint angle data into multi-dimensional quantitative stability indicators. It then correlates and matches this stability assessment vector with the dynamic safety level assessment results of the support points, achieving dynamic adaptation between the support points and the patient's real-time state. Compared to existing technologies that use static marking or manual designation, this invention can recommend the most suitable support point in real time based on the patient's current balance state and imbalance risk type, significantly improving the accuracy and safety of support point identification and effectively reducing the risk of falls or secondary injuries due to improper support point selection.

[0013] 2. This invention constructs a four-dimensional attribute vector encompassing structural mechanical properties, surface contact properties, spatial accessibility properties, and load state properties. Combined with the patient's real-time ergonomic parameters, a biomechanical coupling model is used to conduct a multi-dimensional safety assessment of the support point. This biomechanical coupling model incorporates torque transmission constraints and contact surface stress distribution equations, comprehensively analyzing the support point's structural load-bearing capacity, support surface friction characteristics, contact stress distribution, load margin, and the spatial relationship between the patient and the support point. This achieves a refined, graded assessment of support point safety. Compared to existing technologies that only focus on support point location or basic load-bearing capacity, this invention provides more comprehensive and reliable support point safety level information, ensuring the structural stability and load-bearing reliability of recommended support points, and improving the safety of postoperative patients during mobility and rehabilitation training. Attached Figure Description

[0014] Figure 1 This is a flowchart illustrating a method for intelligent identification and positioning of postoperative patient safety support points according to an embodiment of the present invention.

[0015] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0016] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0017] This application provides a method for intelligent identification and positioning of postoperative patient safety support points. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for intelligent identification and positioning of postoperative patient safety support points can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0018] Reference Figure 1 The diagram shown is a flowchart illustrating a method for intelligent identification and positioning of postoperative patient safety support points according to an embodiment of the present invention. In this embodiment, the method for intelligent identification and positioning of postoperative patient safety support points includes:

[0019] S1, acquire the patient's postoperative posture data and the support point data in the environment;

[0020] In this embodiment of the invention, acquiring the patient's postoperative posture data and the support point data in the environment includes:

[0021] The patient's postoperative posture data was collected, including trunk tilt angle obtained by an inertial measurement unit, pressure center offset obtained by a plantar pressure sensor, and joint angle data obtained by a depth camera.

[0022] The data collected includes the location coordinates, material type, geometric dimensions, and current usage status of each support point.

[0023] It should be noted that acquiring the patient's postoperative posture data and the support point data in the environment are the original input data for subsequent patient stability assessment and support point safety analysis. Specifically: the inertial measurement unit is fixed at the center of the patient's sternum to collect the tilt angle of the patient's torso relative to the direction of gravity in real time; the plantar pressure sensor array is laid between the patient's foot and the support surface to capture instantaneous changes in plantar pressure distribution when the patient stands or moves, thereby calculating the pressure center offset; the depth camera is installed at a preset position on the ward ceiling to continuously track the three-dimensional spatial coordinates of the patient's key joints, calculating joint angle data through coordinate changes. The support point data is collected through RFID tags or QR code identifiers pre-deployed in the ward environment. Each support point corresponds to a unique identifier. By reading this identifier, the position coordinates, material type, and geometric dimensions of the support point are obtained. Simultaneously, the current usage status indicator of the support point is obtained through pressure sensing pads or contact sensors, including idle and occupied states.

[0024] It should be noted that the trunk tilt angle refers to the angle between the patient's trunk midline and the vertical direction, used to characterize the degree of tilt of the patient's upper body; the pressure center offset refers to the positional offset vector of the point of application of the resultant force of the patient's plantar pressure relative to the geometric center of the plantar support area, used to characterize the patient's overall balance shift trend; the joint angle data includes hip joint angle, knee joint angle, and ankle joint angle, used to characterize the flexion and extension state of each joint of the patient's lower limbs. Through the synchronous acquisition of the above multidimensional data, the postural characteristics and balance state of the patient during the postoperative rehabilitation process can be comprehensively reflected.

[0025] S2, extract multi-dimensional stability features from the postoperative posture data to construct a stability assessment vector that reflects the patient's current balance state;

[0026] In this embodiment of the invention, the step of extracting multi-dimensional stability features from the postoperative posture data and constructing a stability assessment vector reflecting the patient's current balance state includes:

[0027] Multidimensional stability structure analysis was performed on the postoperative posture data to obtain the first stability component, the second stability component, and the third stability component.

[0028] The first stability component, the second stability component, and the third stability component are combined to form the stability evaluation vector.

[0029] It should be noted that the multi-dimensional stability feature extraction of the postoperative posture data and the construction of a stability assessment vector reflecting the patient's current balance state are to transform the original multi-source posture data into a stability evaluation index that can be uniformly quantified and compared. Each component in the stability assessment vector corresponds to an independent posture stability assessment dimension, and the numerical range is normalized to between 0 and 1. The closer the value is to 1, the higher the risk of imbalance in that dimension.

[0030] Furthermore, the first stability component approaches 1, indicating a higher risk of upper body imbalance; when the real-time torso tilt angle is much smaller than the safety threshold angle, the first stability component approaches 0, indicating stable upper body posture.

[0031] The second stability component indicates that the greater the offset distance of the pressure center, the more severe the overall balance shift of the patient and the worse the stability.

[0032] The third stability component reflects the deviation of the real-time angle of each joint from the normal standard angle. The greater the deviation, the worse the stability of the patient's lower limb joints.

[0033] It should be noted that after obtaining the first stability component, the second stability component, and the third stability component, the three are combined in sequence to form the stability evaluation vector, the mathematical representation of which is as follows: The stability assessment vector comprehensively characterizes the patient's stability status in three dimensions: upper body posture, overall balance, and lower limb joints, providing a quantitative basis for subsequent correlation and matching with the safety level of support points.

[0034] In this embodiment of the invention, the step of performing multi-dimensional stability structure analysis on the postoperative posture data to obtain a first stability component, a second stability component, and a third stability component includes:

[0035] The torso tilt angle is normalized and mapped to obtain the first stability component that characterizes the risk of upper body imbalance.

[0036] The offset distance is calculated based on the pressure center offset to obtain a second stability component that characterizes the degree of overall balance offset.

[0037] The deviation of the joint angle data is analyzed to obtain the third stability component characterizing the stability of the lower limb joints.

[0038] It should be noted that the torso tilt angle is normalized and mapped to obtain the first stability component, which represents the risk of upper body imbalance. Its calculation expression is as follows:

[0039]

[0040] In the formula, As the first stability component, The torso tilt angle is collected in real time. The preset safe threshold angle for torso tilt. This is the preset mapping sensitivity coefficient;

[0041] The preset mapping sensitivity coefficient is used to control the steepness of the normalization curve. The preset mapping sensitivity coefficient is 2.0. This value ensures that when the real-time trunk tilt angle reaches the safe threshold angle, the value of the first stability component is 0.86, which can effectively distinguish the risk level under different tilt degrees. The safe threshold angle of trunk tilt is set according to the postoperative patient's recovery stage. It is set to 15 degrees for patients in the early postoperative period and 25 degrees for patients in the postoperative recovery period.

[0042] Furthermore, based on the pressure center offset, the offset distance is calculated to obtain a second stability component characterizing the degree of overall balance offset, and its calculation expression is as follows:

[0043]

[0044] In the formula, This is the second stability component. The modulus of the pressure center offset is the Euclidean distance between the pressure center and the geometric center of the foot support area. This is the preset maximum allowable offset radius for the plantar support area. The real-time three-dimensional spatial coordinates of the pressure center. The three-dimensional spatial coordinates of the geometric center of the foot support area;

[0045] When the magnitude of the pressure center offset is greater than the preset maximum allowable offset radius of the foot support area, the second stability component is assigned a value of 1;

[0046] The preset maximum allowable offset radius of the foot support area is set according to the patient's foot size, specifically 30% of the patient's foot length, and is usually set to 60 mm for adult patients.

[0047] Furthermore, a deviation analysis is performed on the joint angle data to obtain the third stability component characterizing the stability of the lower limb joints. Its calculation expression is as follows:

[0048]

[0049] In the formula, This is the third stability component. These are the serial numbers of the lower limb joints, corresponding to the hip, knee, and ankle joints, respectively. For the first Real-time angle of each joint For the first The standard angles of each joint in a normal standing position. For the first The maximum permissible angular deviation of each joint;

[0050] The standard angle of the hip joint is 0 degrees, the standard angle of the knee joint is 0 degrees, and the standard angle of the ankle joint is 90 degrees. The maximum permissible deviation of the hip joint is 20 degrees, the maximum permissible deviation of the knee joint is 15 degrees, and the maximum permissible deviation of the ankle joint is 10 degrees.

[0051] S3, A biomechanical coupling model is used to perform a comprehensive multi-attribute security analysis on the support point data, and a dynamic security level assessment result is generated for each support point.

[0052] In this embodiment of the invention, the step of using a biomechanical coupling model to perform a comprehensive multi-attribute security analysis on the support point data and generating dynamic security level assessment results for each support point includes:

[0053] The patient's real-time ergonomic parameters are obtained, including the patient's weight, upper limb length, and current trunk tilt angle.

[0054] For each support point, a four-dimensional attribute vector is constructed, which includes structural mechanical properties, surface contact properties, spatial reachability properties, and load state properties.

[0055] Based on the four-dimensional attribute vector and the ergonomic parameters, the dynamic safety factor of each support point is calculated using a biomechanical coupling model. The biomechanical coupling model includes the torque transmission constraint conditions between the support point and the patient and the stress distribution equation of the contact surface.

[0056] The dynamic safety coefficients are sorted and graded according to their values ​​to generate dynamic safety level assessment results for each support point.

[0057] It should be noted that the ergonomic parameters include patient weight, upper limb length, and current trunk tilt angle. The patient weight is obtained from a pre-entered patient basic information database, and the upper limb length is calculated from the spatial distance between the shoulder and wrist joints measured by a depth camera.

[0058] Furthermore, for each support point, a four-dimensional attribute vector is constructed, comprising structural mechanical properties, surface contact properties, spatial accessibility properties, and load state properties, as follows: The structural mechanical properties include the structural stiffness coefficient and ultimate bearing capacity of the support point. The structural stiffness coefficient is obtained by looking up a table based on the material type and geometric dimensions of the support point. The surface contact properties include the friction coefficient and contact stiffness of the support surface, with the contact stiffness characterizing the deformation characteristics of the support surface under compression. The spatial accessibility properties include the position coordinates of the support point and the orientation angle of the support surface. The load state properties include the current load mass and the maximum design load mass of the support point. The mathematical representation of the four-dimensional attribute vector is as follows:

[0059]

[0060] In the formula, As a support point A four-dimensional attribute vector, As a support point The structural stiffness coefficient, As a support point Ultimate bearing capacity, As a support point The coefficient of friction of the supporting surface, As a support point Contact stiffness, As a support point The three-dimensional position coordinate vector, As a support point The angle of the supporting surface represents the angle between the direction of the normal to the supporting surface and the horizontal plane. As a support point Current load quality, As a support point Maximum design load capacity.

[0061] It should be noted that after obtaining the dynamic safety coefficient of each support point, the dynamic safety coefficients of all support points are sorted from largest to smallest, and the sorting results are divided into four levels: the top 25% of support points are classified as Level 1 safety, the top 25% to 50% as Level 2 safety, the top 50% to 75% as Level 3 safety, and the bottom 25% as Level 4 safety. The dynamic safety coefficients and their corresponding safety levels of all support points are then organized according to the spatial distribution of the support points to generate the dynamic safety level assessment results.

[0062] In this embodiment of the invention, the mathematical expression of the biomechanical coupling model is as follows:

[0063] ;

[0064] In the formula, For the patient's support point Demand torque, For the patient's weight, It is the acceleration due to gravity. For the length of the patient's upper limb, The torso tilt angle is collected in real time. As a support point Maximum contact stress on the contact surface As a support point index, Apply support to the patient through the upper limbs The estimated load, As a support point The equivalent elastic modulus, As a support point The equivalent radius of curvature of the supporting surface, As a support point Available load-bearing capacity As a support point Ultimate bearing capacity, As a support point Current load quality, As a support point The angle of the supporting surface As a support point The ultimate bending moment of the structure As a support point The dynamic safety factor, The patient's current location and support points The straight-line distance between them As a support point Orientation adaptation factor, The angle between the direction of the force applied by the patient's upper limb relative to the point of support and the horizontal plane.

[0065] It should be noted that the calculation of the dynamic safety factor for each support point using a biomechanical coupling model includes the following sub-steps:

[0066] Sub-step 1: Establish torque transmission constraints;

[0067] When a patient applies a supporting force to a support point through their upper limbs, the support point needs to provide sufficient reaction torque to maintain the patient's balance. Considering the influence of the patient's current trunk tilt angle on the direction of the force applied by the upper limbs, a torque transmission constraint for the support point is established to obtain the torque demanded by the patient on the support point. This constraint equation reflects the patient's body center of gravity shift. The greater the patient's trunk tilt angle, the more severe the body center of gravity shift, and the greater the torque demand generated by the upper limb support point.

[0068] Sub-step 2: Establish the stress distribution equation at the contact surface;

[0069] When the patient's upper limb comes into contact with the support point surface, the support surface generates contact stress under the force applied by the patient. Based on Hertz contact theory, the stress distribution on the contact surface of the support point is analyzed to obtain the maximum contact stress on the contact surface of the support point. The estimated load applied by the patient's upper limb to the support point is calculated by the patient's weight and the proportion of the load shared by the support point. The equivalent radius of curvature of the support surface of the support point is calculated based on the geometric dimensions of the support point.

[0070] The greater the estimated load, the greater the equivalent elastic modulus, and the smaller the equivalent radius of curvature, the greater the maximum contact stress on the contact surface. Excessive contact stress can lead to local plastic deformation of the support surface or discomfort for the patient. Therefore, the contact stress should be controlled within a safe range.

[0071] Sub-step 3: Calculate the available load-bearing capacity of the support points;

[0072] The available load margin of the support point is calculated by considering the ultimate bearing capacity of the support point, the current load mass, and the required moment of the patient. The structural ultimate bending moment of the support point is obtained by referring to a table based on the material type and geometric dimensions of the support point. The available load margin takes into account both the vertical bearing limit and the bending limit of the support point, and takes the smaller constraint value of the two as the available load margin to ensure the structural safety of the support point.

[0073] Sub-step four: Combining the spatial relationship between the patient and the support point, after obtaining the available load-bearing capacity and contact stress distribution of the support point, and combining the reachable distance and orientation relationship between the patient's current position and the support point, calculate the dynamic safety factor of the support point.

[0074] Furthermore, the greater the available load-bearing capacity of the support point, the smaller the contact stress, the closer it is to the patient, and the more the orientation of the support surface matches the direction of the force applied by the patient, the higher the dynamic safety factor and the better the safety of the support point in the current state.

[0075] Furthermore, the angle between the direction of the force applied by the patient's upper limb relative to the support point and the horizontal plane is calculated using the arctangent function based on the ratio of the vertical height difference of the patient's force application position to the horizontal projection length.

[0076] It should be noted that the estimated load applied by the patient to the support point through the upper limbs is calculated based on the patient's current posture and weight distribution model. When the patient's torso tilts, the body's center of gravity shifts, and part of the weight is transferred to the support point through the upper limbs to maintain balance. First, the product of the patient's weight and gravitational acceleration is calculated to obtain the gravity value experienced by the patient. Then, the sine value of the current torso tilt angle is calculated. The gravity value is multiplied by the sine value of the torso tilt angle to obtain the imbalance component of the patient in the tilt direction. Finally, the imbalance component is multiplied by the load sharing coefficient of the support point to obtain the estimated load applied by the patient to the support point through the upper limbs.

[0077] Furthermore, the load-sharing coefficient is allocated based on the relative spatial position between the patient and the support point, as well as the number of support points currently used by the patient. When the patient uses only a single support point, the load-sharing coefficient for that support point is 1, meaning that all additional loads generated by the patient's tilt are borne independently by that support point. When the patient uses two support points simultaneously, the load-sharing coefficient for each support point is allocated based on the angle between the projection direction of the patient's trunk axis on the horizontal plane and the direction vector of each support point relative to the center of the patient's trunk. The specific allocation process is as follows: calculate the cosine value of the angle between each support point and the projection direction of the trunk axis; divide the cosine value corresponding to each support point by the sum of the cosine values ​​of all support points to obtain the load-sharing coefficient for that support point. The basis for this allocation method is that when the support point is located on the same side as the patient's trunk tilt direction, it bears a larger load and has a higher load-sharing coefficient; when it is located on the opposite side, it bears a smaller load and has a lower load-sharing coefficient.

[0078] It should be noted that the equivalent radius of curvature of the support surface is determined based on the geometry of the contact area between the support point and the patient's upper limb. Different support point structures have different contact surface geometric characteristics. The specific calculation method is as follows: For support structures with a circular cross-section, such as cylindrical handrails or circular bed rails, the equivalent radius of curvature of the support surface is directly taken as the radius of the circular cross-section, which is obtained directly from the geometric dimension data of the support point. For support structures with a rectangular or square cross-section, such as rectangular handrails or square bed rails, the equivalent radius of curvature of the support surface is calculated based on the width and height of the rectangular cross-section. The specific calculation process is as follows: multiply the width and height of the rectangular cross-section to obtain the product; then add the width and height to obtain the sum; finally, divide the product by the sum to obtain the equivalent radius of curvature of the rectangular support surface. The calculation of the equivalent radius of curvature implies that the rectangular cross-section is approximated as an equivalent semi-cylindrical surface, and the width and height determine the curvature of the equivalent cylinder.

[0079] For planar support structures, such as wall supports or planar shelves, the equivalent radius of curvature of the support surface is set to a preset large value to characterize the relatively uniform distribution of contact stress when in planar contact.

[0080] Furthermore, when the patient's upper limb contacts the support point, the actual contact area is not the entire support surface, but a local contact area between the upper limb and the support surface. For a circular cross-section support structure, the contact area is an approximately rectangular strip-shaped region with a width equal to the width of the support surface and a length equal to the arc length of the contact between the upper limb and the support surface. For a rectangular cross-section support structure, the contact area is a local planar region of the support surface. In the stress distribution equation of the contact surface, the equivalent radius of curvature is used to describe the local geometric characteristics of the contact area. The smaller the equivalent radius of curvature, the more concentrated the contact stress and the greater the local stress value.

[0081] S4, associate and match the stability assessment vector with the dynamic safety level assessment result, and calculate the matching degree between each support point and the patient's current state;

[0082] In this embodiment of the invention, the step of associating and matching the stability assessment vector with the dynamic safety level assessment result, and calculating the matching degree between each support point and the patient's current state, includes:

[0083] Each component in the stability assessment vector is mapped to a different security attribute dimension of the support point, and an attribute weight allocation table based on the type of imbalance risk is constructed.

[0084] Calculate the load-bearing capacity score, spatial accessibility score, and surface contact stability score for each support point;

[0085] Based on the attribute weight allocation table, the three scores of each support point are weighted and corrected to obtain the dimension adaptation coefficient of each support point.

[0086] Based on the ratio of the overall norm of the stability assessment vector to the dimensional adaptation coefficient, the matching degree between each support point and the patient's current state is calculated.

[0087] It should be noted that the process of associating and matching the stability assessment vector with the dynamic safety level assessment result, and calculating the matching degree between each support point and the patient's current state, is to address the adaptation problem between the patient's current imbalance state and the safety attributes of the support points. Different patients may have different types of imbalance risks at the same time; for example, some patients may primarily have upper body tilt, while others may primarily have lower limb joint instability. Different types of imbalance risks have different requirements for the safety attributes of the support points. This technical solution achieves accurate matching between the patient's imbalance type and the safety attributes of the support points by constructing the dimensional adaptation model.

[0088] Furthermore, the process of mapping each component of the stability assessment vector to different safety attribute dimensions of the support point and constructing an attribute weight allocation table based on the type of imbalance risk is as follows: The stability assessment vector contains three components, corresponding to upper body imbalance risk, overall balance shift risk, and lower limb joint imbalance risk, respectively. The above three risk dimensions are mapped to the three core safety attribute dimensions of the support point, wherein: upper body imbalance risk is mapped to the load-bearing support requirement dimension of the support point, that is, the higher the upper body imbalance risk, the higher the load-bearing capacity requirement of the support point; overall balance shift risk is mapped to the spatial accessibility requirement dimension of the support point, that is, the more severe the overall balance shift, the higher the spatial accessibility requirement between the support point and the patient; lower limb joint imbalance risk is mapped to the surface contact stability requirement dimension of the support point, that is, the worse the lower limb joint stability, the higher the requirements for the friction coefficient and contact stability of the support point.

[0089] It should be noted that the specific process of weighting and correcting the three scores of each support point according to the attribute weight allocation table is as follows: For the load-bearing capacity score, spatial accessibility score and surface contact stability score of each support point; multiply the three weight values ​​in the attribute weight allocation table by the score value of the corresponding dimension of the support point, and then add the three products to obtain the dimension adaptation coefficient of the support point.

[0090] The calculation process of the dimensional adaptation coefficient is as follows: The dimensional adaptation coefficient is equal to the first weight value multiplied by the load-bearing capacity score of the support point, plus the second weight value multiplied by the spatial accessibility score of the support point, plus the third weight value multiplied by the surface contact stability score of the support point; wherein the first weight value is the value of the first stability component, the second weight value is the value of the second stability component, and the third weight value is the value of the third stability component.

[0091] The load-bearing capacity score of the support point is determined based on the ratio of the ultimate load-bearing capacity of the support point to the patient's weight; the larger the ratio, the higher the score. The spatial accessibility score of the support point is determined based on the straight-line distance between the support point and the patient; the closer the distance, the higher the score. The surface contact stability score of the support point is determined based on the friction coefficient of the support surface; the larger the friction coefficient, the higher the score. All scores are normalized to the range of 0 to 1.

[0092] It should be noted that the process of calculating the matching degree between each support point and the patient's current state based on the ratio of the overall norm of the stability assessment vector to the dimensional adaptation coefficient is as follows: First, the overall norm of the stability assessment vector is calculated. The overall norm is calculated by adding the squares of the three components and then taking the square root. The overall norm represents the severity of the patient's overall imbalance risk. The larger the overall norm, the worse the patient's overall stability.

[0093] For each support point, the dimension adaptation coefficient of the support point is divided by the global norm of the stability evaluation vector to obtain the initial matching degree of the support point; then the initial matching degrees of all support points are normalized so that the sum of the matching degrees of all support points is equal to one, and the final matching degree of each support point is obtained.

[0094] When the overall imbalance risk of the patient is low, the difference in matching degree between each support point is mainly determined by the properties of the support point itself. When the overall imbalance risk of the patient is high, the overall norm of the stability assessment vector is large, and the overall matching degree decreases. At this time, only support points with sufficiently high dimension fit coefficients can obtain a high matching degree, thereby ensuring that the support points most suitable for the patient's imbalance type are recommended first under the high imbalance risk state.

[0095] In this embodiment of the invention, the construction rules for the attribute weight allocation table include:

[0096] The value of the first stability component is directly used as the weight value of the load-bearing support requirement dimension;

[0097] The value of the second stability component is directly used as the weight value of the spatial reachability requirement dimension;

[0098] The value of the third stability component is directly used as the weight value of the surface contact stability requirement dimension.

[0099] It should be noted that the values ​​of each component in the stability evaluation vector are used as the weight benchmarks for the corresponding security attribute dimensions. The larger the value of each component, the higher the weight of the corresponding dimension. This results in the attribute weight allocation table, and the sum of the three weight values ​​in the attribute weight allocation table is equal to the sum of the values ​​of each component in the stability evaluation vector.

[0100] In this embodiment of the invention, the calculation of the load-bearing capacity score, spatial accessibility score, and surface contact stability score for each support point includes:

[0101] The load-bearing capacity score, spatial accessibility score, and surface contact stability score of each support point are calculated using a preset three-dimensional scoring equation set. The mathematical expression of the preset three-dimensional scoring equation set is as follows:

[0102] ;

[0103] In the formula, As a support point The load-bearing capacity score As a support point Ultimate bearing capacity, For the patient's weight, It is the acceleration due to gravity. As a support point Spatial accessibility score The patient's current location and support points The straight-line distance between them The preset maximum reachable distance, As a support point Surface contact stability rating As a support point The coefficient of friction of the supporting surface, It is the highest coefficient of friction of the support surface among all support points.

[0104] It should be noted that when the ultimate load-bearing capacity of the support point is greater than or equal to the patient's weight, the load-bearing capacity score is 1, indicating that the support point fully meets the patient's needs in terms of load-bearing capacity.

[0105] The preset maximum reachable distance is set based on the patient's upper limb length, and is set to 1.5 times the patient's upper limb length. When the support point is more than the maximum reachable distance from the patient, the spatial reachability score is 0, indicating that the support point is currently unreachable.

[0106] S5. Determine the optimal safety support point based on the matching degree, and generate recommended data containing support point location information.

[0107] In this embodiment of the invention, determining the optimal safety support point based on the matching degree and generating recommended data containing support point location information includes:

[0108] Select the support point with the maximum matching degree from all support points as the candidate optimal safe support point;

[0109] Determine whether the matching degree of the candidate optimal security support point is greater than the preset matching degree threshold. If it is greater, determine the candidate optimal security support point as the target optimal security support point. Otherwise, trigger the re-collection instruction and return to step S1.

[0110] Obtain the location coordinates and attribute information of the optimal safety support point of the target, and generate recommended data including support point identifier, positioning guidance path and usage safety tips.

[0111] It should be noted that the step of determining the optimal safety support point based on the matching degree and generating recommended data containing support point location information is to transform the matching degree calculated in the aforementioned steps into support point recommendation information that can be directly used by patients or caregivers. This step also includes a reliability verification mechanism for the matching degree results to avoid outputting incorrect recommendation information in the event of abnormal data collection or sudden changes in patient status.

[0112] Furthermore, the support point with the maximum matching degree among all support points is selected as the candidate optimal safe support point; when there are multiple support points with equal matching degrees and all of them being the maximum value, the support point with the highest dynamic safety coefficient is selected as the candidate optimal safe support point.

[0113] It should be noted that the preset matching threshold is set to 0.3, which is used to characterize the minimum reliability requirement for the support point recommendation. When the matching degree of the candidate optimal safety support point is greater than 0.3, it indicates that the support point meets the recommendation requirements for the current state of the patient, and the support point is determined as the target optimal safety support point. When the matching degree of the candidate optimal safety support point is less than or equal to 0.3, it indicates that the current support points are poorly adapted to the patient's state, which may be due to abnormal patient posture data acquisition, sudden changes in support point state, or the patient's position being outside the support point coverage area. In this case, a re-acquisition command is triggered to notify each sensor module to re-execute the data acquisition and return to step S1 to start execution again.

[0114] It should be noted that the process of obtaining the location coordinates and attribute information of the target optimal safety support point, generating recommended data including support point identifiers, positioning guidance paths, and usage safety prompts, involves extracting the location coordinates and attribute information of the target optimal safety support point from the support point data. The location coordinates are the coordinate values ​​of the support point in the three-dimensional space of the ward; the attribute information includes the name, type, and material of the support point.

[0115] The recommended data comprises three components: the first part is the support point identifier, including the unique identifier and name of the support point, used to clearly inform the patient or caregiver which support point is recommended in the visual interface or voice prompts; the second part is the positioning guidance path, which calculates the optimal movement path from the patient's current position to the support point based on the coordinates of the patient's current position and the coordinates of the target optimal safety support point. The positioning guidance path is presented in a step-by-step directional guidance manner, for example, first instructing the patient to move a certain number of meters forward, then a certain number of meters to the left, and finally reaching out to grasp the support point; the third part is the usage safety prompts, which are based on the target optimal... The dynamic safety coefficient and safety level of the safety support point generate corresponding usage precautions. When the safety level of the support point is Level 1, the safety reminder is "This support point is safe and reliable, and can be used with confidence"; when the safety level of the support point is Level 2, the safety reminder is "This support point is of good safety, but apply force slowly when using it"; when the safety level of the support point is Level 3, the safety reminder is "This support point is of average safety, and it is recommended to use it only for auxiliary balance and avoid complete reliance"; when the safety level of the support point is Level 4, the safety reminder is "This support point is of low safety, and it is recommended to choose other support points or use it with the assistance of caregivers."

[0116] Furthermore, the recommended data is presented to patients or caregivers through a visual interface. The visual interface uses a 3D map of the ward as a background and marks the patient's current location, the location of the target optimal safety support point, and arrows indicating the positioning guidance path. At the same time, the voice broadcast module synchronously broadcasts the support point name and the hierarchical guidance information of the positioning guidance path.

[0117] In the several embodiments provided by this invention, it should be understood that the disclosed method can be implemented in other ways.

[0118] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0119] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, and technology that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for intelligent identification and positioning of postoperative patient safety support points, characterized in that, The method includes: S1, acquire the patient's postoperative posture data and the support point data in the environment; S2, extract multi-dimensional stability features from the postoperative posture data to construct a stability assessment vector that reflects the patient's current balance state; S3, A biomechanical coupling model is used to perform a comprehensive multi-attribute security analysis on the support point data, and a dynamic security level assessment result is generated for each support point. S4, associate and match the stability assessment vector with the dynamic safety level assessment result, and calculate the matching degree between each support point and the patient's current state; S5. Determine the optimal safety support point based on the matching degree, and generate recommended data containing support point location information.

2. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 1, characterized in that, The acquisition of the patient's postoperative posture data and the support point data in the environment includes: Collect postoperative posture data of the patient, including trunk tilt angle obtained by inertial measurement unit, pressure center offset obtained by plantar pressure sensor and joint angle data obtained by depth camera; The data collected includes the location coordinates, material type, geometric dimensions, and current usage status of each support point.

3. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 1, characterized in that, The step of extracting multi-dimensional stability features from the postoperative posture data to construct a stability assessment vector reflecting the patient's current balance state includes: Multidimensional stability structure analysis was performed on the postoperative posture data to obtain the first stability component, the second stability component, and the third stability component. The first stability component, the second stability component, and the third stability component are combined to form the stability evaluation vector.

4. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 3, characterized in that, The multi-dimensional stability structure analysis of the postoperative posture data yields a first stability component, a second stability component, and a third stability component, including: The torso tilt angle is normalized and mapped to obtain the first stability component that characterizes the risk of upper body imbalance. The offset distance is calculated based on the pressure center offset to obtain a second stability component that characterizes the degree of overall balance offset. The deviation of the joint angle data is analyzed to obtain the third stability component characterizing the stability of the lower limb joints.

5. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 1, characterized in that, The biomechanical coupling model is used to perform a comprehensive multi-attribute security analysis on the support point data, generating dynamic security level assessment results for each support point, including: The patient's real-time ergonomic parameters are obtained, including the patient's weight, upper limb length, and current trunk tilt angle. For each support point, a four-dimensional attribute vector is constructed, which includes structural mechanical properties, surface contact properties, spatial reachability properties, and load state properties. Based on the four-dimensional attribute vector and the ergonomic parameters, the dynamic safety factor of each support point is calculated using a biomechanical coupling model. The biomechanical coupling model includes the torque transmission constraint conditions between the support point and the patient and the stress distribution equation of the contact surface. The dynamic safety coefficients are sorted and graded according to their values ​​to generate dynamic safety level assessment results for each support point.

6. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 5, characterized in that, The mathematical expression of the biomechanical coupling model is as follows: ； In the formula, For the patient's support point Demand torque, For the patient's weight, It is the acceleration due to gravity. For the length of the patient's upper limb, The torso tilt angle is collected in real time. As a support point Maximum contact stress on the contact surface As a support point index, Apply support to the patient through the upper limbs The estimated load, As a support point The equivalent elastic modulus, As a support point The equivalent radius of curvature of the supporting surface, As a support point Available load-bearing capacity As a support point Ultimate bearing capacity, As a support point Current load quality, As a support point The angle of the supporting surface As a support point The ultimate bending moment of the structure As a support point The dynamic safety factor, The patient's current location and support points The straight-line distance between them As a support point Orientation adaptation factor, The angle between the direction of the force applied by the patient's upper limb relative to the point of support and the horizontal plane.

7. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 1, characterized in that, The step of associating and matching the stability assessment vector with the dynamic safety level assessment result, and calculating the matching degree between each support point and the patient's current state, includes: Each component in the stability assessment vector is mapped to a different security attribute dimension of the support point, and an attribute weight allocation table based on the type of imbalance risk is constructed. Calculate the load-bearing capacity score, spatial accessibility score, and surface contact stability score for each support point; Based on the attribute weight allocation table, the three scores of each support point are weighted and corrected to obtain the dimension adaptation coefficient of each support point. Based on the ratio of the overall norm of the stability assessment vector to the dimensional adaptation coefficient, the matching degree between each support point and the patient's current state is calculated.

8. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 7, characterized in that, The construction rules for the attribute weight allocation table include: The value of the first stability component is directly used as the weight value of the load-bearing support requirement dimension; The value of the second stability component is directly used as the weight value of the spatial reachability requirement dimension; The value of the third stability component is directly used as the weight value of the surface contact stability requirement dimension.

9. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 7, characterized in that, The calculation of the load-bearing capacity score, spatial accessibility score, and surface contact stability score for each support point includes: The load-bearing capacity score, spatial accessibility score, and surface contact stability score of each support point are calculated using a preset three-dimensional scoring equation set. The mathematical expression of the preset three-dimensional scoring equation set is as follows: ； In the formula, As a support point The load-bearing capacity rating As a support point Ultimate bearing capacity, For the patient's weight, It is the acceleration due to gravity. As a support point Spatial accessibility score, The patient's current location and support points The straight-line distance between them The preset maximum reachable distance, As a support point Surface contact stability rating As a support point The coefficient of friction of the supporting surface, It is the highest coefficient of friction of the support surface among all support points.

10. The method for intelligent identification and positioning of postoperative patient safety support points as described in claim 1, characterized in that, The step of determining the optimal safety support point based on the matching degree and generating recommended data containing support point location information includes: Select the support point with the maximum matching degree from all support points as the candidate optimal safe support point; Determine whether the matching degree of the candidate optimal security support point is greater than the preset matching degree threshold. If it is greater, determine the candidate optimal security support point as the target optimal security support point. Otherwise, trigger the re-collection instruction and return to step S1. Obtain the location coordinates and attribute information of the optimal safety support point of the target, and generate recommended data including support point identifier, positioning guidance path and usage safety tips.

Images