Orthopedic surgery robot navigation positioning processing method and system

Abstract

The invention discloses an orthopedic surgery robot navigation positioning processing method and system, and relates to the technical field of medical instruments, and the technical scheme is characterized by comprising the following steps: obtaining preoperative planning data and intraoperative real-time sensing data of an orthopedic surgery site, the preoperative planning data and the intraoperative real-time sensing data are judged, and a key positioning data set is generated; acquiring curvature parameters of planned paths in the key positioning data sets, signal features of the real-time sensing data and deviation adaptation states of the curvature parameters and the signal features, and performing path calibration judgment on the at least two groups of key positioning data sets to generate a to-be-positioned calibration data set; the deviation compensation parameter of the planned path in the to-be-positioned calibration data set and the real-time sensing signal stability parameter are collected, so that the deviation difference of the data collected in different time periods can be effectively identified, the effective data conforming to the calibration threshold value is screened out to form the to-be-positioned calibration data set, the positioning deviation caused by the data difference is avoided, and the positioning accuracy is improved. And the uniformity and reliability of the positioning data are improved.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and more specifically, to a navigation and positioning processing method and system for orthopedic surgical robots. Background Technology

[0002] In orthopedic surgery, precise navigation and positioning are crucial for ensuring surgical safety and effectiveness. This is especially true in complex procedures such as spinal surgery, joint replacement, and minimally invasive fracture fixation, where navigation accuracy directly impacts surgical trauma, postoperative recovery time, and complication rates. Traditional orthopedic surgery relies on manual manipulation based on surgeon experience. However, the complexity of human anatomy, obstructed surgical views, and surgeon fatigue can lead to path deviations, resulting in risks such as improper placement of internal fixation devices and damage to surrounding nerves and blood vessels, failing to meet the demands of precision medicine. With the rapid development of medical robotics, orthopedic surgical robots are increasingly being applied clinically. By combining preoperative planning with intraoperative navigation, these robots assist surgeons in completing surgical procedures, effectively improving surgical precision.

[0003] However, existing orthopedic surgical robot navigation and positioning systems mostly rely on preoperative CT / MRI images to construct anatomical models and plan surgical paths, then collect real-time data through intraoperative sensors to match the planned path with the actual surgical site. In actual surgery, the validity verification mechanisms for preoperative planning data and intraoperative real-time sensor data are inadequate. They fail to adequately consider data integrity, coordinate system consistency, and sampling frequency compliance, directly using raw data for positioning matching, which easily introduces invalid data, leading to positioning deviations. Furthermore, there is a lack of consistency calibration processing for multiple sets of positioning data. When differences exist in positioning data collected at different times, it is impossible to effectively identify the source of data deviation, making it difficult to generate a reliable calibration dataset for positioning. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a navigation and positioning processing method and system for orthopedic surgical robots.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A navigation and positioning processing method for orthopedic surgical robots, the method comprising the following steps: Step S1: Acquire preoperative planning data and intraoperative real-time sensor data of the orthopedic surgical site; Step S2: Compare the preoperative planning data with the intraoperative real-time sensor data and generate a key localization dataset; Step S3: Obtain the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two. Perform path calibration judgment on at least two sets of key positioning datasets to generate a positioning calibration dataset. Step S4: Collect the deviation compensation parameters of the planned path in the calibration dataset to be located and the signal stability parameters of the real-time sensor. Step S5: Determine whether there are interference signal features in the dataset to be positioned and calibrated that could cause positioning inaccuracies based on the curvature parameter distribution and the number of deviation adaptation state types. Step S6: If there are no interference signal features in the calibration dataset that would cause positioning inaccuracy, determine the first adaptation of navigation and positioning based on the deviation compensation parameter and the signal stability parameter. Step S7: If there are interference signal features in the dataset to be positioned and calibrated that cause positioning inaccuracy, determine the second adaptation situation of navigation and positioning when interference signal features are present based on the deviation compensation parameter and the signal stability parameter. Step S8: Determine whether the navigation and positioning meet the path execution requirements of orthopedic surgery based on the first or second adaptation situation.

[0006] Preferably, step S2 specifically includes the following steps: Extract the anatomical feature reference points of the surgical area from the preoperative planning data and the corresponding anatomical feature reference points from the real-time intraoperative sensing data. Adapt and associate the coordinates of the anatomical feature reference points of the surgical area with the coordinates of the corresponding anatomical feature reference points to form a dual-track navigation dataset. Based on the dual-track navigation dataset, feature dimensions are mapped between preoperative planning data and intraoperative real-time sensing data, and key positioning data are formed by filtering planned path feature data and real-time sensing feedback feature data.

[0007] Preferably, step S3 specifically includes the following steps: Obtain the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two. Based on the curvature parameters and the deviation and adaptation status, determine whether path calibration processing is required for at least two sets of key positioning datasets. The complete curvature parameters and deviation adaptation status of the planned paths in the same group are judged and processed to obtain the calibration dataset to be located and the segmented positioning data units. Based on the curvature parameters of the planned path, path-related nodes in each segmented positioning data unit are identified. The path parameters of each segmented positioning data unit are calibrated and integrated to form a positioning calibration dataset based on the path-related nodes.

[0008] Preferably, the path parameters of each segmented positioning data unit are calibrated according to the path association nodes and then integrated to form a positioning calibration dataset, specifically including the following steps: Determine whether there is a coordinate overlap between path-related nodes in at least two segmented positioning data units to obtain the positioning calibration dataset.

[0009] Preferably, step S5 specifically includes the following steps: If there is only one type of deviation adaptation state in the dataset to be positioned and calibrated, it is determined that there are no interference signal features in the dataset to be positioned and calibrated that would cause positioning inaccuracy. If there are at least two types of deviation adaptation states in the dataset to be located and calibrated, then the distribution of curvature parameters is used to determine whether there is a signal conflict relationship between the different adaptation state types. Determine whether there is a signal conflict relationship between different adaptation state types and identify the characteristics of interference signals.

[0010] Preferably, step S6 specifically includes the following steps: By comparing the deviation compensation parameters and corresponding signal stability parameters of each planned path node with the deviation, stability, and adaptation table, the first adaptation level and first adaptation value of each node are obtained; the first adaptation level of each planned path node is divided into the optimal adaptation level and the first qualified adaptation level. Determine whether there is any overlap in the threshold ranges between the optimal adaptation level and the first qualified adaptation level; The first fit or comprehensive fit value is obtained based on whether there is interval overlap. The first adaptation case is formed by combining the comprehensive adaptation value with the first adaptation values ​​of the other planned path nodes.

[0011] Preferably, determining the second adaptation scenario for navigation and positioning when interference signal characteristics exist based on deviation compensation parameters and signal stability parameters specifically includes the following steps: Determine the conflict intensity and affected frequency band of the interference signal characteristics in the dataset to be located and calibrated; The second adaptation value, second adaptation level, third adaptation value, and third adaptation level are obtained based on the interference information characteristics in the calibration data to be located. The second adaptation value, the second adaptation level, and / or the third adaptation value and the third adaptation level are combined to form the second adaptation case.

[0012] Preferably, step S8 specifically includes the following steps: Determine whether the characteristics of interference signals from high-intensity collisions exceed the accuracy correction threshold; The second adaptation level is determined based on whether it exceeds the correction threshold.

[0013] Preferably, the adaptation parameters are optimized based on the frequency band analysis results and signal stability parameters to obtain the third adaptation value and the third adaptation level, specifically including the following steps: The frequency band affected by the interference signal characteristics of the wide frequency band is divided into frequency bands. The weight coefficients of the signal stability parameters are assigned according to the frequency division results. The navigation and positioning adaptation parameters are optimized based on the weight coefficients. The third adaptation level and the third adaptation value are obtained by referring to the deviation, stability and adaptation table.

[0014] A navigation and positioning processing system for an orthopedic surgical robot, comprising: Data acquisition module: Acquires preoperative planning data and intraoperative real-time sensor data of orthopedic surgical sites, judges the preoperative planning data and intraoperative real-time sensor data, and generates key positioning dataset; Positioning calibration module: acquires the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two, and performs path calibration judgment on at least two sets of key positioning datasets to generate a positioning calibration dataset. Parameter acquisition module: Acquires deviation compensation parameters of the planned path in the calibration dataset to be located and the signal stability parameters of real-time sensing; Interference detection module: Determines whether there are interference signal characteristics in the dataset to be located and calibrated that could lead to positioning inaccuracy based on the curvature parameter distribution and the number of deviation adaptation state types. Precise Adaptation Module 1: If there are no interference signal features in the dataset to be positioned and calibrated that would cause positioning inaccuracy, the first adaptation situation of navigation and positioning is determined based on the deviation compensation parameters and signal stability parameters. Precise Adaptation Module 2: If there are interference signal features in the dataset to be positioned and calibrated that cause positioning inaccuracies, the second adaptation situation of navigation and positioning is determined based on the deviation compensation parameters and signal stability parameters when interference signal features are present. Navigation and positioning module: Determines whether the navigation and positioning meets the path execution requirements of orthopedic surgery based on the first or second adaptation condition.

[0015] Compared with existing technologies, this invention has the following advantages: By generating a key positioning dataset after validating preoperative planning data and intraoperative real-time sensing data, the validity verification mechanism can be improved, avoiding positioning deviations caused by invalid data. By achieving consistency calibration of multiple sets of positioning data, a high-quality positioning calibration dataset is generated, which can improve the consistency calibration of multiple sets of data and be used to identify the source of deviation. By extracting curvature parameters, signal features, and deviation adaptation states, path consistency calibration judgment is performed on at least two sets of key positioning datasets, which can effectively identify deviation differences in data collected at different times, screen out valid data that meets the calibration threshold to form a positioning calibration dataset, avoid positioning deviations caused by data differences, and improve the uniformity and reliability of positioning data. Through comprehensive analysis of curvature parameter distribution characteristics and the number of deviation adaptation state types, accurate determination of the characteristics of positioning inaccuracy interference signals can be achieved, which can effectively distinguish interference signals generated by intraoperative bone movement, soft tissue occlusion, and sensor signal fluctuations, providing a basis for subsequent differential adaptation judgment, avoiding positioning inaccuracies caused by interference signals, and ensuring the stability of navigation and positioning in complex surgical scenarios. Attached Figure Description

[0016] Figure 1 This invention provides a schematic diagram of the steps involved in a navigation and positioning process for an orthopedic surgical robot, as illustrated in an embodiment of the present invention. Figure 2 This is a schematic diagram illustrating the steps of forming a calibration dataset to be positioned in a navigation and positioning processing method for an orthopedic surgical robot, as provided in an embodiment of the present invention. Figure 3 This invention provides a module diagram of a navigation and positioning processing system for an orthopedic surgical robot. Detailed Implementation

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0018] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0020] Reference Figures 1-3 As shown.

[0021] This embodiment further illustrates the navigation and positioning processing method and system for orthopedic surgical robots proposed in this invention.

[0022] A navigation and positioning processing method for orthopedic surgical robots, the method comprising the following steps: Step S1: Acquire preoperative planning data and intraoperative real-time sensor data of the orthopedic surgical site; Step S2: Compare the preoperative planning data with the intraoperative real-time sensor data and generate a key localization dataset.

[0023] Preoperative planning data for orthopedic surgical sites is acquired, including the preset coordinates of the surgical path and the positioning parameters of the target lesion. During the surgery, real-time intraoperative sensing data of the surgical site is collected in real time by sensors mounted on the robot, covering the current position data of surgical instruments and the spatial pose data of the tissues surrounding the lesion. To ensure the usability and correlation of the two types of data, consistency judgment is performed on the preoperative planning data and the intraoperative real-time sensing data. Specific judgment dimensions include data format verification, spatial coordinate matching verification, and timestamp synchronization verification. After the above consistency judgment, invalid, excessively biased, or out-of-synchronization data are eliminated, and a key positioning dataset that accurately reflects the correspondence between the surgical plan and the actual intraoperative state is finally generated.

[0024] Step S3: Obtain the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two. Perform path calibration judgment on at least two sets of key positioning datasets to generate a positioning calibration dataset. Step S4: Collect the deviation compensation parameters of the planned path in the calibration dataset to be located and the signal stability parameters of the real-time sensing.

[0025] The system collects deviation compensation parameters for the planned path in the calibration dataset to be positioned and signal stability parameters for real-time sensor data. Deviation compensation parameters are calculated based on the deviation between the planned path and the intraoperative data selected in the early stage, and are used to make targeted corrections to the positioning deviation in the future. Signal stability parameters include signal fluctuation amplitude, fluctuation frequency, and stable duration. Signal stability parameters can directly reflect the working status of the sensing device. If the signal stability is insufficient, it will directly affect the reliability of the positioning results. By accurately collecting these two types of parameters, the core parameter basis supporting the subsequent positioning accuracy judgment is formed.

[0026] Step S5: Determine whether there are interference signal features in the dataset to be positioned and calibrated that could cause positioning inaccuracies based on the curvature parameter distribution and the number of deviation adaptation state types. Step S6: If there are no interference signal features in the calibration dataset that would cause positioning inaccuracy, determine the first adaptation of navigation and positioning based on the deviation compensation parameter and the signal stability parameter. Step S7: If there are interference signal features in the dataset to be positioned and calibrated that cause positioning inaccuracy, determine the second adaptation situation of navigation and positioning when interference signal features are present based on the deviation compensation parameter and the signal stability parameter. Step S8: Determine whether the navigation and positioning meet the path execution requirements of orthopedic surgery based on the first or second adaptation situation.

[0027] Path execution compliance is the final verification step in the entire navigation and positioning process. Its core is to determine whether the navigation and positioning results, after the aforementioned processing, meet the actual execution requirements of orthopedic surgery. First, a comprehensive verification is conducted against the path execution requirements of orthopedic surgery, taking into account both the first and / or second adaptation scenarios (i.e., referring to the first adaptation scenario when there is no interference, and referring to the second adaptation scenario when there is interference). Key execution requirements include: a positioning error of no more than 0.5mm to ensure surgical instruments accurately reach the target location and avoid damage to surrounding normal tissues; a path tracking response time of no more than 100ms to ensure navigation and positioning can follow the surgical operation rhythm in real time and avoid dynamic positioning lag; and a continuous positioning stability duration of no less than the surgical execution duration to ensure consistent and stable positioning results throughout the entire surgical process without sudden inaccuracies. If the verification results meet the above execution requirements, the navigation and positioning are considered qualified and can guide the orthopedic surgical robot to perform the surgery according to the current positioning results. If not, it is necessary to return to the previous steps to recalibrate data, suppress interference, or adjust parameters until the positioning results meet the execution requirements, forming a complete closed-loop control to ensure the safety and accuracy of the surgery.

[0028] Step S2 specifically includes the following steps: Extract the anatomical feature reference points of the surgical area from the preoperative planning data and the corresponding anatomical feature reference points from the real-time intraoperative sensing data. Adapt and associate the coordinates of the anatomical feature reference points of the surgical area with the coordinates of the corresponding anatomical feature reference points to form a dual-track navigation dataset. Based on the dual-track navigation dataset, feature dimensions are mapped between preoperative planning data and intraoperative real-time sensing data, and key positioning data are formed by filtering planned path feature data and real-time sensing feedback feature data.

[0029] Starting with the adaptation and association of anatomical feature reference points, this method extracts anatomical feature reference points for the surgical area in advance from the preoperative planning data. These reference points are typically structures with clear anatomical markers within the surgical area, such as the apex of articular surfaces of bones or distinctive cortical protrusions. Their coordinates are determined through medical imaging such as CT and MRI, serving as a spatial reference for surgical path planning. Simultaneously, during the operation, corresponding anatomical feature reference points are acquired in real-time using intraoperative sensing devices. These reference points represent the spatial localization results of the actual anatomical structures in the current surgical area. The coordinates of the preoperatively planned anatomical feature reference points are then adapted and associated with the coordinates of the corresponding intraoperatively acquired reference points. Through spatial coordinate matching and alignment, the two sets of reference points are bound into a one-to-one spatial reference pair, ultimately forming a dual-track navigation dataset. This dataset contains both the ideal spatial information from preoperative planning and the actual real-time spatial information from the operation, providing a unified spatial reference for subsequent data mapping and filtering.

[0030] Based on a dual-track navigation dataset, feature dimensions were mapped between preoperative planning data and intraoperative real-time sensing data. These feature dimensions encompass multiple key pieces of information about the surgical path, such as the spatial orientation of the path, the coordinate accuracy of each node along the path, the planned data features of the pre-set posture of surgical instruments, and the real-time data features of the actual instrument posture, real-time displacement of anatomical structures, and intensity of sensor signals fed back by intraoperative sensing devices. Each feature dimension of the planning data was mapped one-to-one with the corresponding feature dimension in the real-time data, ensuring that the two types of data could be compared and correlated under the same feature dimensions. After completing the feature dimension mapping, the planned path feature data and real-time sensing feedback feature data were further filtered out. The core content directly related to navigation and positioning, such as the coordinates of key nodes in the planned path and the instrument position deviations from real-time sensing feedback, was selected. Redundant data irrelevant to positioning was eliminated, ultimately forming key positioning data. This provides accurate and focused basic data support for subsequent path calibration and interference assessment.

[0031] Step S3 specifically includes the following steps: Obtain the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two. Based on the curvature parameters and the deviation and adaptation status, determine whether path calibration processing is required for at least two sets of key positioning datasets. The complete curvature parameters and deviation adaptation status of the planned paths in the same group are judged and processed to obtain the calibration dataset to be located and the segmented positioning data units. If the complete curvature parameters and deviation adaptation status of the planned path in the same group appear in the same key positioning dataset, then mark the key positioning dataset as the dataset to be positioned and calibrated. If the complete curvature parameters and deviation adaptation status of the planned path in the same group are scattered across at least two sets of key positioning datasets, then the corresponding key positioning datasets will be processed into path segmentation to form segmented positioning data units containing a single path segment. Based on the curvature parameters of the planned path, path-related nodes in each segmented positioning data unit are identified. The path parameters of each segmented positioning data unit are calibrated and integrated to form a positioning calibration dataset based on the path-related nodes.

[0032] The curvature parameters of the planned path, signal features of real-time sensor data, and the deviation fit between the two are extracted from the key localization dataset. The curvature parameters of the planned path reflect the degree of curvature of the surgical planning path, such as whether the path is a smooth straight section or a curved section with multiple inflections. Different curvature parameters correspond to different localization difficulties; the greater the curvature and the more inflections, the higher the requirement for localization accuracy. The signal features of the real-time sensor data cover the signal transmission stability and the continuity of data feedback. These features directly affect the reliability of the real-time data. The more stable the signal features, the higher the fit between the real-time data and the actual surgical state. The deviation fit between the planned path data and the real-time sensor data reflects the degree of agreement between the two in dimensions such as spatial coordinates and path direction. The better the fit, the closer the current localization result is to the planned target. After extracting this information, combined with the curvature parameters and the deviation fit, it is determined whether path calibration processing is required for at least two sets of key localization datasets. If the path complexity corresponding to the curvature parameters is high and the deviation fit is poor, it indicates that the accuracy of the current localization data is insufficient, and the calibration process needs to be initiated.

[0033] Based on the information distribution in the key localization dataset, the data is classified. If the complete curvature parameters and deviation adaptation status of the planned paths in the same group are concentrated in the same key localization dataset, it means that this set of data can independently reflect the localization deviation of the path. In this case, the key localization dataset is directly marked as the dataset to be calibrated. Calibration operations can then be performed separately on this dataset. For example, if a dataset completely records all curvature parameters of the implanted path segment A and clearly indicates that the deviation adaptation status of that segment is "fit," then this dataset is directly marked as the dataset to be calibrated without additional processing. If the complete curvature parameters and deviation adaptation status of the planned paths in the same group are concentrated in the same key localization dataset, it means that this set of data can independently reflect the localization deviation of the path. In this case, the key localization dataset is directly marked as the dataset to be calibrated without additional processing. If the complete curvature parameters and deviation adaptation status of the path are scattered across at least two sets of key positioning datasets, it indicates that a single dataset cannot fully cover the positioning information of the path. In this case, the system will perform path segmentation processing on these key positioning datasets. Based on the curvature change nodes of the planned path, the complete path will be divided into multiple single path segments. Each segment corresponds to a segmented positioning data unit. Each unit only contains the curvature parameters, signal characteristics, and deviation adaptation status of that path segment. For example, if the curvature parameters of the implanted path segment B are scattered across two sets of data, the system will divide the path into segments B1 and B2, forming two segmented positioning data units respectively.

[0034] The segmented positioning data units are integrated, and path-related nodes in each segment are identified based on the curvature parameters of the planned path. These nodes are usually the connection points between path segments. For example, the curvature parameter of the end point of segment B1 is consistent with the curvature parameter of the starting point of segment B2. The position corresponding to this parameter is the connection node between the two. Then, the path parameters of each segment positioning data unit are calibrated to ensure that the parameters of each segment are consistent with the planning target. Finally, the calibrated segment units are integrated according to the order of the path-related nodes to form a positioning calibration dataset covering the complete planned path, providing complete and calibrated basic data for subsequent positioning accuracy adaptation judgment.

[0035] After calibrating the path parameters of each segmented positioning data unit based on the path association nodes, the data is integrated to form a positioning calibration dataset, which specifically includes the following steps: Determine whether there is a coordinate overlap relationship between path-related nodes in at least two segmented positioning data units to obtain the positioning calibration dataset; Determine whether there is a coordinate overlap relationship between path-related nodes in at least two segmented positioning data units; If the path association nodes in at least two segmented positioning data units have a coordinate overlap relationship, the corresponding segmented positioning data units are marked as track matching data units. Based on the path association nodes corresponding to the overlapping coordinates, the corresponding track matching data units are integrated and processed to form a positioning calibration dataset. If the path association nodes in each segmented positioning data unit do not have a coordinate overlap relationship, then the path association nodes in each segmented positioning data unit will be interpolated and associated. If the path-related nodes form a continuous planned path trajectory after interpolation, the corresponding segmented positioning data units are then processed for path calibration and integration to form a positioning calibration dataset. If the path-related nodes do not form a continuous planned path trajectory after interpolation, the preoperative three-dimensional anatomical model data and intraoperative real-time image supplementary data corresponding to the planned path are obtained, and the path auxiliary positioning nodes in the supplementary data are extracted. The path auxiliary positioning nodes are fused with the interpolated path-related nodes to complete the continuous planned path trajectory. The corresponding segmented positioning data units are calibrated and integrated to form the positioning calibration dataset.

[0036] The coordinate relationship of the path association nodes of at least two segmented positioning data units is determined. These path association nodes are the connection points between the segmented units. For example, the end node of segment B1 and the start node of segment B2 are the path association nodes of these two units. The core of the determination is to confirm whether the spatial coordinates of these nodes are completely consistent.

[0037] If these path-related nodes have overlapping coordinates, such as the endpoint coordinates of segment B1 being exactly the same as the starting coordinates of segment B2, these two segment units are marked as track-matching data units. Then, using the path-related node corresponding to the overlapping coordinates as the core, the path parameters of the two units are directly integrated to form a calibration dataset covering segments B1 and B2.

[0038] If the path-related nodes of each segment unit do not have overlapping coordinates, for example, the endpoint coordinates of segment B1 are (2, 3, 1) and the starting coordinates of segment B2 are (4, 5, 3), then interpolation is performed on these nodes. Interpolation is a process of calculating multiple intermediate transition coordinate points based on the coordinate differences between nodes and according to the preset trend of the planned path. Specifically, the coordinate differences between two nodes are first determined, for example, the difference on the x-axis is 2, the difference on the y-axis is 2, and the difference on the z-axis is 2. Then, the density of interpolation is determined according to the curvature parameters of the path. If the curvature of the path is high, the number of interpolation points will be increased to ensure smooth connection; if the curvature is low, the number of interpolation points will be reduced appropriately. For example, the system may insert a transition point (3, 4, 2) between two nodes, so that the discrete coordinates form a continuous coordinate sequence of (2, 3, 1), (3, 4, 2), and (4, 5, 3). At the same time, the coordinates of these interpolation points will match the curvature characteristics of the planned path to avoid abrupt connections that do not match the path trend.

[0039] After completing the interpolation association, it is necessary to check whether these nodes form a continuous planned path trajectory. If the interpolated node sequence can be connected into a continuous curve that conforms to the original path trend, such as the coordinates of segment B1, the interpolation point and segment B2 can be connected into a smooth implantation path, the system will calibrate the path parameters of the two segment units based on this continuous trajectory and then integrate them into a calibration dataset to be located.

[0040] If the interpolated nodes still cannot form a continuous trajectory, such as due to coordinate discontinuities at the junctions, the system will retrieve the preoperative 3D anatomical model data and intraoperative real-time image data corresponding to the path. From this data, path-aiding localization nodes will be extracted, such as skeletal feature points along the path in the preoperative model and path markers in the intraoperative images. These auxiliary nodes will then be fused and interpolated a second time with the previously associated path nodes and interpolation points to fill in the discontinuous areas and form a complete and continuous path trajectory. Finally, based on this trajectory, the segmented units will be calibrated and integrated to generate a calibration dataset for localization. For different node coordinate states, precise interpolation processing, combined with supplementary data, can achieve continuous integration of dispersed segmented units, providing accurate path data support for surgical navigation.

[0041] Step S5 specifically includes the following steps: If there is only one type of deviation adaptation state in the dataset to be positioned and calibrated, it is determined that there are no interference signal features in the dataset to be positioned and calibrated that would cause positioning inaccuracy. If there are at least two types of deviation adaptation states in the dataset to be located and calibrated, then the distribution of curvature parameters is used to determine whether there is a signal conflict relationship between the different adaptation state types. Determine whether there is a signal conflict relationship between different adaptation state types and identify the characteristics of interference signals; If there is no signal conflict between different adaptation state types, it is determined that there are no interference signal features in the data set to be located and calibrated that would cause positioning inaccuracy. If there is a signal conflict between different adaptation state types, it is determined that there are at least two interference signal features in the dataset to be located and calibrated that cause positioning inaccuracy.

[0042] First, the number of deviation adaptation state types in the calibration dataset to be positioned is counted. Deviation adaptation state refers to the matching state between the planned path and the real-time sensor data. Common types include mild deviation and severe deviation. Taking the calibration dataset for implanted path segment B as an example, if the deviation adaptation state corresponding to all path segments in this dataset is only mild deviation, the system will directly determine that there are no interference signal features in the calibration dataset to be positioned that would cause positioning inaccuracy. Because the adaptation state is singular, the matching of the data is stable, and no conflicting signal interference occurs.

[0043] If there are at least two types of deviation adaptation states in the dataset to be located and calibrated, such as mild deviation and severe deviation appearing simultaneously in the dataset of implantation path segment B, then the curvature parameter distribution is further combined to determine whether there is a signal conflict relationship between these different adaptation state types. The curvature parameter distribution refers to the curvature parameter characteristics of each segment of the path, while the signal conflict relationship refers to the situation where the curvature parameter characteristics of the path segment corresponding to different adaptation states do not match the state type. For example, the curvature parameter of the path shows that its trend is gentle, and the corresponding deviation adaptation state should be mild deviation, but in fact, severe deviation occurs. The mismatch between these two states and the curvature characteristics belongs to signal conflict.

[0044] If there is no signal conflict between different adaptation state types, such as a slight deviation corresponding to a path segment with gentle curvature and a severe deviation corresponding to a path segment with steep curvature, and the two states are consistent with the curvature parameter characteristics of their respective path segments, it indicates that the state difference is caused by the characteristics of the path itself and not by signal interference. The system will determine that there are no interference signal characteristics in the dataset.

[0045] If there are signal conflicts between different adaptation state types, such as a path segment with gentle curvature showing both slight and severe deviation states, and the real-time sensing signal characteristics corresponding to these two states are inconsistent, it indicates that there are contradictory signal inputs in the data. The system will determine that there are at least two interference signal characteristics in the dataset to be positioned and calibrated that cause positioning inaccuracy.

[0046] By making hierarchical judgments based on the number of state types and the matching of curvature parameters, interference signals in the calibration data to be positioned can be accurately identified, providing a reliable preliminary basis for accurate adaptation judgments in subsequent navigation and positioning.

[0047] Step S6 specifically includes the following steps: By comparing the deviation compensation parameters and corresponding signal stability parameters of each planned path node with the deviation, stability, and adaptation table, the first adaptation level and first adaptation value of each node are obtained; the first adaptation level of each planned path node is divided into the optimal adaptation level and the first qualified adaptation level. Determine whether there is any overlap in the threshold ranges between the optimal adaptation level and the first qualified adaptation level; The first fit or comprehensive fit value is obtained based on whether there is interval overlap. If there is no interval overlap, the first adaptation level and the corresponding first adaptation value of each planned path node are combined to form the first adaptation situation; If there is an overlap in the range, the optimal adaptation level and the first adaptation value of the first qualified adaptation level are fused together according to the weight ratio of the adaptation standard threshold to obtain the comprehensive adaptation value. The first adaptation case is formed by combining the comprehensive adaptation value with the first adaptation values ​​of the other planned path nodes.

[0048] For each planned path node in implantation path segment B, corresponding deviation compensation parameters and signal stability parameters are extracted. Deviation compensation parameters are values ​​used to correct the deviation between the planned and actual paths; for example, the node's position deviation compensation is 0.2 mm. Signal stability parameters are indicators reflecting the reliability of real-time sensing signals; for example, the signal-to-noise ratio (SNR) of this node is 35 dB. Subsequently, these two parameters are compared with a preset deviation stability adaptation table to obtain the first adaptation level and first adaptation value for each node. The adaptation table classifies levels based on the parameter's numerical range. For example, when the deviation compensation is less than 0.3 mm and the SNR is greater than 30 dB, the adaptation level is the optimal adaptation level, with an adaptation value of 95; when the deviation compensation is between 0.3 and 0.5 mm and the SNR is between 25 and 30 dB, the adaptation level is the first qualified adaptation level, with an adaptation value of 80. Taking the three nodes of the implantation path B segment as an example, node 1 has the best adaptation level and an adaptation value of 95, node 2 has the best adaptation level and an adaptation value of 92, and node 3 has the first qualified adaptation level and an adaptation value of 80.

[0049] The optimal adaptation level and the first qualified adaptation level are divided into adaptation standard threshold ranges, and then it is determined whether these two ranges overlap. The adaptation standard threshold range is the parameter value range corresponding to the adaptation level. For example, the deviation compensation range of the optimal adaptation level is 0 to 0.3 mm, and the range of the first qualified adaptation level is 0.3 to 0.5 mm. The critical value of these two ranges is 0.3 mm. If the range is set to optimal adaptation ≤ 0.3 and qualified adaptation ≥ 0.3, then the 0.3 mm position will overlap; if it is set to optimal adaptation < 0.3 and qualified adaptation ≥ 0.3, then the ranges will not overlap.

[0050] If the threshold ranges of the two adaptation standards do not overlap, for example, the deviation compensation range of the optimal adaptation level is 0 to 0.29 mm, and the first qualified adaptation level is 0.3 to 0.5 mm, the system will directly combine the first adaptation level of each node with the corresponding first adaptation value to form the first adaptation situation. For example, the result of implanting path segment B is that node 1 is the optimal adaptation of 95, node 2 is the optimal adaptation of 92, and node 3 is the qualified adaptation of 80.

[0051] If the intervals overlap, for example, if the deviation compensation interval for the optimal adaptation level includes 0.3 mm and the first qualified adaptation level also includes 0.3 mm, the first adaptation values ​​of the optimal adaptation level and the first qualified adaptation level are fused according to the weight ratio of the adaptation standard threshold to obtain a comprehensive adaptation value. The weight ratio is set according to the proportion of the overlapping part of the intervals. For example, if the overlapping part accounts for 10% of the optimal adaptation interval and 20% of the qualified adaptation interval, then the weight of the optimal adaptation value is 2 and the weight of the qualified adaptation value is 1. If a node is in the overlapping interval, its optimal adaptation value is 95 and its qualified adaptation value is 80, and the comprehensive adaptation value is (95×2+80×1)÷3=90. Subsequently, the comprehensive adaptation value is combined with the first adaptation values ​​of the remaining nodes to form the final first adaptation status. Through hierarchical matching, interval verification, and fusion calculation, the adaptation status of each path node can be comprehensively and accurately evaluated, ultimately obtaining the first adaptation status that reflects the reliability of navigation and positioning.

[0052] The second adaptation scenario for navigation and positioning when interference signal characteristics are present is determined based on deviation compensation parameters and signal stability parameters, specifically including the following steps: Determine the conflict intensity and affected frequency band of the interference signal characteristics in the dataset to be located and calibrated; The second adaptation value, second adaptation level, third adaptation value, and third adaptation level are obtained based on the interference information characteristics in the calibration data to be located. If there are high-intensity conflict interference signal characteristics in the dataset to be located and calibrated, the second adaptation value and the second adaptation level are obtained by accuracy correction calculation based on the conflict intensity quantification value and deviation compensation parameter. If the dataset to be located and calibrated contains interference signal characteristics with wide frequency band influence, the third adaptation value and the third adaptation level are obtained by optimizing the adaptation parameters based on the analysis results of the influencing frequency band and the signal stability parameters. The second adaptation value, the second adaptation level, and / or the third adaptation value and the third adaptation level are combined to form the second adaptation case.

[0053] To determine the conflict intensity and influence frequency band of interference signals in the dataset to be located and calibrated, the conflict intensity refers to the severity of the deviation between the planned path and the sensor data caused by the interference signal. For example, if both slight and severe deviations occur simultaneously on the same path segment, and the difference in deviation exceeds 0.5 mm, it is considered a high-intensity conflict. The influence frequency band refers to the range of the path affected by the interference signal. For example, if the interference signal only affects a certain segment of the path, it is considered a narrow-band influence. Taking implantation path segment B as an example, if both slight and severe deviations occur simultaneously in the middle segment of the path, and the difference in deviation reaches 0.6 mm, it belongs to the characteristics of a high-intensity conflict interference signal; if the interference only affects the first 2 cm segment of the path, it belongs to the characteristics of a narrow-band influence interference signal.

[0054] If the dataset contains interference signals with high-intensity conflict, the conflict intensity is first quantified into a specific value. For example, a deviation difference of 0.6 mm corresponds to a quantization value of 8. The higher the quantization value, the stronger the conflict. Then, the accuracy correction calculation is performed in conjunction with the deviation compensation parameters of that path segment. Specifically, based on the baseline accuracy without interference, the accuracy is reduced according to the quantized conflict intensity value, and the adaptation level is adjusted accordingly. For example, if the baseline accuracy of implantation path segment B is 90, and the correction coefficient corresponding to the conflict quantization value of 8 is 0.8, then the corrected second adaptation value is 90 × 0.8 = 72, and the second adaptation level is adjusted to a qualified adaptation level.

[0055] If the dataset contains interference signal characteristics affecting a narrow frequency band, the system will first analyze the affected frequency band to determine the specific path segment range of the interference, and then optimize the adaptation parameters based on the signal stability parameters within that frequency band. For example, if the first 2 cm segment of the implantation path B is affected by interference, its signal-to-noise ratio drops from 35 dB to 28 dB. The system will optimize the weight of the signal stability parameters for that frequency band to increase the proportion of effective signals, ultimately obtaining a third adaptation value. For instance, after optimization, the accuracy of this segment may be adjusted from 85 to 80. The third adaptation level corresponds to the basic adaptation level.

[0056] The processed second adaptation value and second adaptation level, and / or third adaptation value and third adaptation level are combined to form the second adaptation situation of the implantation path segment B. For example, if the path has both high-intensity conflict and narrow-band interference, the final combination result is that the middle segment has a second accuracy of 72 and a qualified adaptation level, the starting segment has a third accuracy of 80 and a basic adaptation level, and the remaining segments maintain the original adaptation state.

[0057] By processing different types of interference differently, the adaptation status of navigation and positioning can be accurately assessed in the presence of interference signals, providing a more realistic basis for judgment in the execution of surgical paths.

[0058] Step S8 specifically includes the following steps: Determine whether the characteristics of interference signals from high-intensity collisions exceed the accuracy correction threshold; If the correction threshold is exceeded, dynamic conflict trend data of the interference signal characteristics are obtained, and the corrected second adaptation value is calculated in combination with the deviation compensation parameters. The second adaptation level is determined by comparing the deviation, stability, and adaptation table. The second adaptation level is determined based on whether it exceeds the correction threshold; If the correction threshold is not exceeded, the basic adaptation value is obtained by linearly superimposing the conflict intensity quantification value and the deviation compensation parameter. The basic adaptation value is marked as the second adaptation value. The second adaptation level is determined by comparing the deviation, stability and adaptation table with the second adaptation value.

[0059] First, determine the accuracy correction threshold. The accuracy correction threshold is a critical value that distinguishes whether interference exceeds the normal correction range. For example, for orthopedic surgical pathways, the conflict intensity quantization value corresponding to the accuracy correction threshold is set to 7. Then, determine whether the quantization value corresponding to the interference signal characteristics of the current high-intensity conflict exceeds the threshold. Taking implantation pathway segment B as an example, its conflict intensity quantization value is 8, which is greater than the threshold of 7, meaning it exceeds the correction threshold.

[0060] If the characteristics of the interference signal exceed the correction threshold, the system will first acquire the dynamic conflict trend data of the interference. This dynamic conflict trend data represents the changes in the interference signal over time or along its path. For example, the conflict intensity quantization value of the intermediate segment might gradually increase from 6 to 8, showing a continuously strengthening trend. Next, the system will combine this with the deviation compensation parameter of 0.6 mm for this segment to perform accuracy correction calculations. The specific formula is: Corrected second adaptation value = Baseline adaptation value - (Conflict intensity quantization value × Dynamic trend coefficient + Deviation compensation parameter × Compensation coefficient). Here, the base adaptation value is the accuracy of the segment without interference, for example, 90. The dynamic trend coefficient is set according to the trend slope; for example, a continuously strengthening trend corresponds to a coefficient of 1.2. The compensation coefficient is set to 10. Therefore, the corrected second adaptation value = 90 - (8 × 1.2 + 0.6 × 10) = 74.4. Afterward, the system will compare the corrected adaptation value with the deviation stability adaptation table to determine the corresponding second adaptation level. For example, levels 70 to 80 in the adaptation table correspond to a qualified adaptation level; therefore, the second adaptation level for this segment is a qualified adaptation level.

[0061] If the characteristics of the interference signal do not exceed the correction threshold, for example, if the conflict intensity quantization value of a certain sub-segment of the implantation path B is 6, which is less than the threshold 7, and the deviation compensation parameter is 0.4 mm, the system will directly perform linear superposition calculation on these two parameters. The formula is: Basic adaptation value = Baseline adaptation value - (Conflict intensity quantization value + Deviation compensation parameter × 10). After substituting the parameters, the basic adaptation value is: 90 - (6 + 0.4 × 10) = 80. Then, the basic adaptation value is marked as the second adaptation value. Then, by referring to the deviation stability adaptation table, the corresponding second adaptation level is determined. For example, the level corresponding to 80 in the adaptation table is the good adaptation level. Therefore, the second adaptation level of this sub-segment is the good adaptation level.

[0062] By using differentiated calculations based on thresholds, the adaptation values ​​of path segments can be accurately corrected for high-intensity conflict interference of varying severity, while matching the corresponding adaptation level to ensure the rationality and accuracy of the adaptation assessment.

[0063] Based on the analysis results of the influencing frequency bands and signal stability parameters, the adaptation parameters are optimized to obtain the third adaptation value and the third adaptation level. The specific steps include: The frequency band affected by the interference signal characteristics of the wide frequency band is divided into frequency bands. The weight coefficients of the signal stability parameters are assigned according to the frequency division results. The navigation and positioning adaptation parameters are optimized based on the weight coefficients. The third adaptation level and the third adaptation value are obtained by referring to the deviation, stability and adaptation table.

[0064] First, the affected frequency bands of the wideband interference signal are divided into sub-bands. Wideband interference refers to interference signals covering a continuous and large area along the path. Sub-band processing divides this area into multiple sub-bands according to the intensity of the interference. For example, in the 2-5 cm wideband interference area of ​​the implanted path B, the signal fluctuation variance of the 2-3 cm segment is 0.8, indicating strong interference, while the signal fluctuation variance of the 3-5 cm segment is 0.4, indicating weak interference. The system will divide this area into these two independent sub-bands accordingly to ensure that the interference intensity in each sub-segment is relatively uniform.

[0065] Then, based on the frequency division results, weight coefficients are assigned to the signal stability parameters of each sub-segment. These parameters include signal-to-noise ratio (SNR), signal fluctuation variance, and signal continuous acquisition success rate. The magnitude of the weight coefficient is inversely proportional to the interference intensity of the sub-segment; that is, the stronger the interference, the lower the weight of the corresponding signal stability parameter, thus weakening the parameter influence in areas with strong interference. For example, the 2cm to 3cm sub-segment has strong interference, so a weight coefficient of 0.7 is assigned to its signal stability parameter; the 3cm to 5cm sub-segment has weak interference, so a weight coefficient of 1.3 is assigned. Taking signal-to-noise ratio as an example, the SNR of the 2cm to 3cm sub-segment is 27 dB, and that of the 3cm to 5cm sub-segment is 32 dB.

[0066] Subsequently, the system optimizes the navigation and positioning adaptation parameters based on weighted coefficients. Specifically, the signal stability parameter of each sub-segment is multiplied by the corresponding weighted coefficient to obtain the weighted signal stability parameter. That is, the weighted signal-to-noise ratio of the 2 cm to 3 cm sub-segment is 27 × 0.7 = 18.9, and that of the 3 cm to 5 cm sub-segment is 32 × 1.3 = 41.6. At the same time, the system combines the deviation compensation parameters of each sub-segment, such as 0.4 mm for the 2 cm to 3 cm segment and 0.2 mm for the 3 cm to 5 cm segment, and integrates the weighted signal stability parameter with the deviation compensation parameter to form the optimized adaptation parameter combination.

[0067] Finally, the system compares the optimized adaptation parameter combination with a preset deviation stability adaptation table to obtain the third adaptation level and third adaptation value for each sub-segment. For example, in the adaptation table, when the weighted signal-to-noise ratio is ≥40 and the deviation compensation parameter is ≤0.2 mm, the adaptation value is 90 and the adaptation level is good; when the weighted signal-to-noise ratio is between 18 and 25 and the deviation compensation parameter is between 0.3 and 0.5 mm, the adaptation value is 70 and the adaptation level is basic. Corresponding to the sub-segments of implantation path B, the weighted signal-to-noise ratio of the 3 cm to 5 cm sub-segment is 41.6 and the deviation compensation parameter is 0.2 mm, corresponding to a third adaptation value of 90 and a third adaptation level of good; the weighted signal-to-noise ratio of the 2 cm to 3 cm sub-segment is 18.9 and the deviation compensation parameter is 0.4 mm, corresponding to a third adaptation value of 70 and a third adaptation level of basic.

[0068] By frequency division, weight allocation, and parameter optimization, the unevenness of wideband interference can be addressed in a targeted manner, making the final third adaptation value and third adaptation level more consistent with the actual signal state of each path segment, thereby improving the accuracy of navigation and positioning adaptation evaluation.

[0069] A navigation and positioning processing system for an orthopedic surgical robot, comprising: Data acquisition module: Acquires preoperative planning data and intraoperative real-time sensor data of orthopedic surgical sites, judges the preoperative planning data and intraoperative real-time sensor data, and generates key positioning dataset; Positioning calibration module: acquires the curvature parameters of the planned path in the key positioning dataset, the signal characteristics of the real-time sensor data, and the deviation and adaptation status of the two, and performs path calibration judgment on at least two sets of key positioning datasets to generate a positioning calibration dataset. Parameter acquisition module: Acquires deviation compensation parameters of the planned path in the calibration dataset to be located and the signal stability parameters of real-time sensing; Interference detection module: Determines whether there are interference signal characteristics in the dataset to be located and calibrated that could lead to positioning inaccuracy based on the curvature parameter distribution and the number of deviation adaptation state types. Precise Adaptation Module 1: If there are no interference signal features in the dataset to be positioned and calibrated that would cause positioning inaccuracy, the first adaptation situation of navigation and positioning is determined based on the deviation compensation parameters and signal stability parameters. Precise Adaptation Module 2: If there are interference signal features in the dataset to be positioned and calibrated that cause positioning inaccuracies, the second adaptation situation of navigation and positioning is determined based on the deviation compensation parameters and signal stability parameters when interference signal features are present. Navigation and positioning module: Determines whether the navigation and positioning meets the path execution requirements of orthopedic surgery based on the first or second adaptation condition.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An orthopedic surgery robot navigation positioning processing method, characterized in that, The method comprises the following steps: Step S1: obtaining preoperative planning data and intraoperative real-time sensing data of an orthopedic surgery site; Step S2: judging the preoperative planning data and the intraoperative real-time sensing data and generating a key positioning data set; Step S3: obtaining a curvature parameter of a planned path in the key positioning data set, a signal feature of real-time sensing data, and a deviation adaptation state of the two, performing path calibration judgment on at least two groups of key positioning data sets to generate a to-be-positioned calibration data set; Step S4: collecting a deviation compensation parameter of the planned path in the to-be-positioned calibration data set and a signal stability parameter of real-time sensing; Step S5: judging whether there is an interference signal feature causing positioning misalignment in the to-be-positioned calibration data set according to the curvature parameter distribution and the number of deviation adaptation state types; Step S6: if there is no interference signal feature causing positioning misalignment in the to-be-positioned calibration data set, judging a first adaptation condition of navigation positioning according to the deviation compensation parameter and the signal stability parameter; Step S7: if there is an interference signal feature causing positioning misalignment in the to-be-positioned calibration data set, judging a second adaptation condition of navigation positioning when the interference signal feature exists according to the deviation compensation parameter and the signal stability parameter; Step S8: judging whether the navigation positioning meets the path execution requirements of the orthopedic surgery according to the first adaptation condition or the second adaptation condition.

2. The orthopedic surgery robot navigation positioning processing method according to claim 1, characterized in that, Step S2 specifically comprises the following steps: Extracting a corresponding anatomic feature reference point of the intraoperative real-time sensing data from an anatomic feature reference point in the preoperative planning data, and adaptively associating the coordinates of the anatomic feature reference point of the surgical region with the coordinates of the corresponding anatomic feature reference point to form a double-track navigation data set; Based on the double-track navigation data set, the feature dimension mapping of the preoperative planning data and the intraoperative real-time sensing data is performed, and the planned path feature data and the real-time sensing feedback feature data are screened to form key positioning data.

3. The orthopedic surgery robot navigation positioning processing method according to claim 2, characterized in that, Step S3 specifically comprises the following steps: Obtaining a curvature parameter of a planned path in the key positioning data set, a signal feature of real-time sensing data, and a deviation adaptation state of the two, and judging whether path calibration processing is needed for at least two groups of key positioning data sets according to the curvature parameter and the deviation adaptation state; Judging and processing the complete curvature parameter and the deviation adaptation state of the same group of planned paths to obtain a to-be-positioned calibration data set and a segmented positioning data unit; According to the curvature parameter of the planned path, identifying the path association nodes in each segmented positioning data unit, and integrating the path parameters of each segmented positioning data unit after calibration according to the path association nodes to form the to-be-positioned calibration data set.

4. The orthopedic surgery robot navigation positioning processing method according to claim 3, characterized in that, According to the path association nodes, the path parameters of each segmented positioning data unit are calibrated and integrated to form the to-be-positioned calibration data set, specifically comprising: Judging whether there is a coordinate coincidence relationship between the path association nodes in at least two segmented positioning data units to obtain the to-be-positioned calibration data set.

5. The orthopedic surgery robot navigation positioning processing method according to claim 4, characterized in that, Step S5 specifically comprises the following steps: If there is only one type of deviation adaptation state in the to-be-positioned calibration data set, it is determined that there is no interference signal feature causing positioning misalignment in the to-be-positioned calibration data set; If there are at least two bias adaptation state types in the to-be-positioned calibration data set, whether there is a signal conflict relationship between different adaptation state types is determined according to the curvature parameter distribution; Whether there is a signal conflict relationship between different adaptation state types is determined, and the interference signal characteristics are determined.

6. The orthopedic surgery robot navigation positioning processing method according to claim 5, characterized in that, Step S6 specifically includes the following steps: The bias compensation parameters and the corresponding signal stability parameters of each planned path node are matched with the bias, stability and adaptation table to obtain the first adaptation level and the first adaptation value corresponding to each node; the first adaptation level of each planned path node is divided into an optimal adaptation level and a first qualified adaptation level; Whether there is interval overlap of the adaptation standard threshold of the optimal adaptation level and the first qualified adaptation level is determined; The first adaptation situation or the comprehensive adaptation value is obtained according to whether there is interval overlap; The comprehensive adaptation value and the first adaptation value of the remaining planned path nodes are combined to form the first adaptation situation.

7. The orthopedic surgery robot navigation positioning processing method according to claim 6, characterized in that, The second adaptation situation of navigation positioning when the interference signal characteristics exist is determined according to the bias compensation parameters and the signal stability parameters, specifically including the following steps: The conflict strength and the influence frequency band of the interference signal characteristics in the to-be-positioned calibration data set are determined; The second adaptation value, the second adaptation level, the third adaptation value and the third adaptation level are obtained according to the interference information characteristics in the to-be-positioned calibration data set; The second adaptation value, the second adaptation level and / or the third adaptation value, the third adaptation level are combined to form the second adaptation situation.

8. The orthopedic surgery robot navigation positioning processing method of claim 7, wherein, Step S8 specifically includes the following steps: Whether the high-intensity conflict interference signal characteristics exceed the precision correction threshold is determined; The second adaptation level is determined according to whether the correction threshold is exceeded.

9. The orthopedic surgery robot navigation positioning processing method of claim 8, wherein, The third adaptation value and the third adaptation level are obtained by optimizing the adaptation parameters according to the influence frequency band analysis result and the signal stability parameters, specifically including the following steps: The influence frequency band of the interference signal characteristics with wide frequency band influence is processed by frequency division, the weight coefficient of the signal stability parameter is allocated according to the frequency division result, the navigation positioning adaptation parameters are optimized based on the weight coefficient, and the third adaptation level and the third adaptation value are obtained by matching the bias, stability and adaptation table.

10. An orthopedic surgery robot navigation positioning processing system applied to the orthopedic surgery robot navigation positioning processing method in claims 1-9, characterized in that, It includes: A data acquisition module: acquires preoperative planning data and intraoperative real-time sensing data of an orthopedic surgery site, judges the preoperative planning data and the intraoperative real-time sensing data, and generates a key positioning data set; A positioning calibration module: acquires the curvature parameters of the planned path, the signal characteristics of the real-time sensing data and the bias adaptation state of the two in the key positioning data set, judges the path calibration of at least two key positioning data sets, and generates a to-be-positioned calibration data set; A parameter acquisition module: acquires the bias compensation parameters of the planned path in the to-be-positioned calibration data set and the signal stability parameters of the real-time sensing data; An interference judgment module: determines whether there is an interference signal characteristic causing positioning error in the to-be-positioned calibration data set according to the curvature parameter distribution and the number of bias adaptation state types; A precise adaptation module one: if there is no interference signal characteristic causing positioning error in the to-be-positioned calibration data set, the first adaptation situation of navigation positioning is determined according to the bias compensation parameters and the signal stability parameters; The precise fitting module two: if there is an interference signal feature in the pending positioning calibration data set that causes positioning misalignment, the second fitting condition of navigation positioning when the interference signal feature exists is judged according to the deviation compensation parameter and the signal stability parameter; The navigation positioning module: whether the navigation positioning meets the path execution requirements of the orthopedic surgery is judged according to the first fitting condition or the second fitting condition.

Images