Intelligent decision-making method and system for perioperative multi-source data fusion based on internet of things

Abstract

This invention provides an intelligent decision-making method and system for multi-source data fusion during the surgical period based on the Internet of Things (IoT). It relates to the field of surgical data fusion technology, and includes: acquiring multi-source heterogeneous data streams during the surgical period through an IoT sensing layer; identifying cross-source response events and extracting surgical event anchor points; calculating time phase differences and performing reverse compensation to generate a surgical period dataset with a unified time reference; constructing a causal dependency topology by performing conditional independence tests on this dataset; identifying causal shielding nodes through causal blocking tests to generate causal decoupling surgical period features; constructing a surgical safety decision space including intervention and damage boundaries based on the surgical progress; projecting the features and generating decision instructions through constrained gradient search and transmitting them to the surgical equipment control unit; and dynamically updating boundary parameters. This invention achieves time synchronization and causal decoupling of multi-source data, improving the accuracy and safety of surgical decisions.

Description

Technical Field

[0001] This invention relates to the field of surgical data fusion technology, and in particular to an intelligent decision-making method and system based on Internet of Things (IoT) for multi-source data fusion during the surgical period. Background Technology

[0002] Surgical decision-making methods typically rely on real-time analysis of a single data source (such as vital signs monitoring or imaging data), triggering alarms or intervention commands through preset thresholds or rule bases. Common practices include collecting data on physiological parameters (such as heart rate and blood pressure), equipment status (such as electrosurgical power), and depth of anesthesia during surgery; extracting features using a sliding window based on time series data; and then combining this with expert experience or machine learning models to generate decision recommendations. These methods are widely used in clinical practice, especially for the auxiliary monitoring of standardized surgical procedures.

[0003] However, conventional methods have significant drawbacks. Inconsistent time bases in multi-source data acquisition lead to time misalignments during data fusion. For example, the operational signals of surgical instruments (such as electrosurgical initiation) and changes in physiological parameters (such as heart rate fluctuations) may exhibit millisecond-level phase differences due to variations in sampling frequencies, transmission delays, or system clock differences between different sensors. This time deviation distorts the determination of causal relationships between events, causing decision-making models to mistakenly identify asynchronous data as related events, resulting in false alarms or delayed interventions. Furthermore, there is the issue of redundant coupling between data sources. Different sensors (such as ECG and blood pressure) often exhibit statistical dependence in surgical events, but existing methods typically fuse all features directly, neglecting the decoupling of causal relationships. This makes it difficult for models to distinguish between direct causal relationships (such as changes in tissue impedance caused by electrosurgical cutting) and indirect correlations (such as a drop in blood pressure caused by anesthetic drugs), thereby reducing the accuracy of decision-making instructions. This can lead to unnecessary interventions or overlooking critical risks, especially in complex surgical procedures. Summary of the Invention

[0004] This invention provides an intelligent decision-making method and system based on IoT-based multi-source data fusion during the surgical period, which can solve the problems in the prior art.

[0005] A first aspect of this invention provides an intelligent decision-making method for multi-source data fusion during surgery based on the Internet of Things, comprising:

[0006] Acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer;

[0007] In a multi-source heterogeneous data stream, cross-source response events triggered by the same surgical operation are identified, the peak time of the cross-source response events is extracted as the surgical event anchor point, the time phase difference between the surgical event anchor points of different data sources is calculated, and the collection timestamps of each data source are reversed based on the time phase difference to generate a surgical period dataset with a unified time reference.

[0008] Conditional independence tests are performed on the surgical dataset, and a causal dependency topology between the data sources is constructed based on the test results. Causal blocking tests are used to identify causal blocking nodes in the causal dependency topology, and causal decoupling surgical features are generated based on the causal blocking nodes.

[0009] Based on the current stage of the surgical procedure, a surgical safety decision space containing intervention and damage boundaries is constructed. The causal decoupled surgical period features are projected onto the surgical safety decision space. Within the surgical safety decision space, decision instructions that meet the surgical objectives are generated through constrained gradient search.

[0010] The decision-making instructions are transmitted to the surgical equipment control unit for execution, and the boundary parameters of the surgical safety decision space are dynamically updated by collecting surgical feedback data after execution.

[0011] In one optional embodiment, cross-source response events triggered by the same surgical operation are identified in multi-source heterogeneous data streams. The peak time of the cross-source response events is extracted as the surgical event anchor point. The time phase difference between the surgical event anchor points of different data sources is calculated. Based on the time phase difference, reverse compensation is performed on the collection timestamps of each data source to generate a surgical period dataset with a unified time reference, including:

[0012] An adaptive sliding window scan is performed on the multi-source heterogeneous data stream. The energy change rate of each data source signal is calculated within the adaptive sliding window. When the energy change rate exceeds a preset dynamic threshold, it is marked as a potential response point. Waveform segments before and after the potential response point are extracted to construct a response waveform library.

[0013] Morphological feature extraction is performed on waveform segments in the response waveform library. The kurtosis, skewness, and temporal envelope area of ​​the waveform segments are calculated as morphological feature vectors. By matching the morphological feature vectors across data sources, cross-source response events triggered by the same surgical operation are identified, and the successfully matched waveform segments are grouped into response event groups.

[0014] Extract the maximum amplitude moment of each data source waveform segment from the response event group, mark the surgical event anchor point, construct a time series correlation graph with the surgical event anchor point of each data source as the node, and calculate the time offset of the surgical event anchor point relative to the surgical event anchor point of the reference data source in the time series correlation graph as the time phase difference.

[0015] Establish time mapping relationships between various data sources based on time phase differences, apply a time offset opposite to the time phase difference to the collection timestamps of each data source to perform reverse compensation, and rearrange the multi-source heterogeneous data streams of each data source according to a unified time axis to generate a surgical period dataset.

[0016] In one optional embodiment, performing a conditional independence test between data sources on the surgical dataset and constructing a causal dependency topology between data sources based on the test results includes:

[0017] Extract data state snapshots of each data source at the moment of surgical instrument action from the surgical period dataset, and construct a surgical data source graph structure with data sources as nodes and data state snapshots as node attributes;

[0018] Two data source nodes are selected from the surgical data source graph structure as the node pair to be tested, and the other data source nodes are selected as condition variable nodes in turn.

[0019] For each condition variable node, calculate the conditional mutual information of the node pair to be tested under the condition variable node. When the conditional mutual information is lower than the preset independence threshold, determine that the node pair to be tested is conditionally independent under the condition variable node. Record all condition variable nodes that make the node pair to be tested conditionally independent to form an intermediate transmission node set.

[0020] When the intermediate transmission node set is empty, causal dependency edges are established between the pairs of nodes to be tested. When the intermediate transmission node set is not empty, the condition variable nodes in the intermediate transmission node set are marked as causal transmission path nodes between the pairs of nodes to be tested.

[0021] Perform the above conditional independence test on all data source node pairs in the surgical data source graph structure, and combine all data source nodes and the causal dependency edges established between them to construct the causal dependency topology between data sources.

[0022] In one optional embodiment, causal blocking nodes are identified in the causal dependency topology through a causal blocking test, and causal decoupling operation-phase features are generated based on the causal blocking nodes, including:

[0023] In the causal dependency topology, identify the target data source node corresponding to the surgical decision target and the source data source node corresponding to the surgical instrument control command. Starting from the target data source node, perform a reverse breadth-first search along the causal dependency edge to the source data source node, record all data source nodes traversed by the reverse breadth-first search, and construct a set of causal transmission nodes.

[0024] For each data source node in the causal transmission node set, perform a causal blocking test, temporarily remove the data source node and its connected causal dependency edges from the causal dependency topology, re-execute the causal path search from the source data source node to the target data source node, and when the causal path search fails, mark the data source node as a causal blocking node, and combine the causal blocking node and its connected causal dependency edges to form a causal backbone path.

[0025] In the causal dependency topology, data source nodes that are not causal shielding nodes are marked as bypass coupling nodes, and bypass coupling nodes and their connected causal dependency edges are combined to form bypass coupling paths.

[0026] Extract the data state snapshot corresponding to the causal shielding node as the causal decoupling operation period feature.

[0027] In one optional embodiment, constructing a surgical safety decision space that includes intervention and damage boundaries based on the current stage of the surgical procedure includes:

[0028] Obtain the standard surgical operation sequence corresponding to the current stage of the surgical process from the surgical procedure database, analyze the instrument movement type and tissue contact range corresponding to each surgical operation step in the standard surgical operation sequence, and map the instrument movement type and tissue contact range to the three-dimensional coordinate system of the surgical scene to form a standard operation space area.

[0029] Based on the causal decoupling of the surgical period features, the physiological state deviation of each anatomical structure in the current surgical scene is calculated. Anatomical structures whose physiological state deviation exceeds the preset safety threshold are marked as high-risk tissue areas. The spatial boundary of the high-risk tissue area is marked in the three-dimensional coordinate system of the surgical scene to construct the damage boundary.

[0030] Based on the standard operating space area, a preset safe distance is extended outward in the three-dimensional coordinate system of the surgical scene to form an operating allowable space area. The space area between the operating allowable space area and the damage boundary is defined as the intervention boundary.

[0031] The spatial region enclosed by the intervention boundary and the damage boundary in the three-dimensional coordinate system of the surgical scene is defined as the surgical safety decision space.

[0032] In one optional embodiment, projecting causal decoupled perioperative features onto a surgical safety decision space, and generating decision instructions that satisfy surgical objectives within the surgical safety decision space through constrained gradient search, includes:

[0033] Extract the data state snapshots corresponding to each causal shielding node from the causal decoupling surgical period features, convert the instrument space coordinates and tissue deformation displacement in the data state snapshots into state point coordinates in the surgical safety decision space, and establish the mapping relationship between causal shielding nodes and state points in the surgical safety decision space.

[0034] Based on the intervention boundary and the damage boundary, a boundary normal vector field is constructed, the intervention normal distance and the damage normal distance of the state point are calculated, and a constraint potential energy field is generated by nonlinear weighted fusion.

[0035] Starting from the target state point corresponding to the surgical target, gradient descent iteration is performed along the negative gradient direction of the constraint potential energy field. In each iteration, the constraint potential energy gradient vector of the current iteration point is calculated, and the preset step size is moved to the next iteration point in the opposite direction of the constraint potential energy gradient vector. The sequence of iteration points passed during the iteration process constitutes the constraint guidance trajectory.

[0036] The coordinates of the state points corresponding to each iteration point in the constraint-guided trajectory are reverse-mapped to the causal shielding node, and the instrument control parameters corresponding to the causal shielding node are extracted to generate decision instructions.

[0037] In one optional embodiment, a boundary normal vector field is constructed based on the intervention boundary and the damage boundary. The intervention normal distance and the damage normal distance of the state point are calculated. A constraint potential energy field is generated by nonlinear weighted fusion, including:

[0038] Extract the boundary surface mesh nodes of the intervention boundary and the damage boundary, and calculate the unit normal vectors of each boundary surface mesh node pointing into the surgical safety decision space to construct the boundary normal vector field;

[0039] In the surgical safety decision space, the state points obtained by mapping the causal shielding nodes are calculated, and the Euclidean distance from the state point to the nearest grid node of the intervention boundary is calculated to determine the intervention normal distance. The Euclidean distance from the state point to the nearest grid node of the damage boundary is also calculated to determine the damage normal distance.

[0040] The intervention potential energy vector is obtained by performing a scalar multiplication operation between the intervention normal distance and the unit normal vector of the corresponding intervention boundary grid node, and the damage potential energy vector is obtained by performing a scalar multiplication operation between the damage normal distance and the unit normal vector of the corresponding damage boundary grid node. The intervention potential energy vector and the damage potential energy vector are then subjected to nonlinear weighted fusion to generate the constraint potential energy vector.

[0041] The constraint potential vectors of all state points constitute the constraint potential field.

[0042] A second aspect of this invention provides an intelligent decision-making system based on Internet of Things (IoT) for fusion of multi-source data during surgery, comprising:

[0043] The data synchronization unit is used to acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer.

[0044] The causal analysis unit is used to identify cross-source response events triggered by the same surgical operation in multi-source heterogeneous data streams, extract the peak time of the cross-source response events as the surgical event anchor point, calculate the time phase difference between surgical event anchor points from different data sources, perform reverse compensation on the collection timestamps of each data source based on the time phase difference, and generate a surgical period dataset with a unified time reference.

[0045] The decision generation unit is used to perform conditional independence tests between data sources on the surgical dataset, construct a causal dependency topology between data sources based on the test results, identify causal blocking nodes in the causal dependency topology through causal blocking tests, and generate causal decoupling surgical features based on the causal blocking nodes.

[0046] The feedback update unit is used to construct a surgical safety decision space containing intervention and damage boundaries based on the current surgical process stage, project the causal decoupled surgical period features onto the surgical safety decision space, and generate decision instructions that meet the surgical objectives through constrained gradient search within the surgical safety decision space.

[0047] The processing unit is used to transmit decision instructions to the surgical equipment control unit for execution, and to collect surgical feedback data after execution to dynamically update the boundary parameters of the surgical safety decision space.

[0048] A third aspect of the present invention provides an electronic device, comprising:

[0049] processor;

[0050] Memory used to store processor-executable instructions;

[0051] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0052] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0053] In this embodiment of the invention, based on the multi-source heterogeneous data stream acquired by the IoT sensing layer, by identifying cross-source response events and extracting surgical event anchor points, the time deviation introduced by the asynchronous acquisition time between different data sources can be eliminated, generating a surgical period dataset with a unified time benchmark, significantly improving the alignment accuracy of multi-source data in the time dimension; performing conditional independence tests on the unified dataset and constructing a causal dependency topology, and identifying causal blocking nodes through causal blocking tests, can effectively remove redundant correlations and interference factors between data sources, generating surgical period features with causal decoupling characteristics, greatly reducing feature dimensionality and enhancing feature interpretability; constructing a surgical safety decision space containing intervention and damage boundaries according to the current surgical process stage, projecting causal decoupling features into this space, and generating decision instructions that meet surgical objectives through constrained gradient search, can ensure that decision actions are always within a safe and controllable range, avoiding exceeding the physical or physiological limits of surgical operations, while optimizing surgical efficiency and patient safety; collecting surgical feedback data after execution to dynamically update the boundary parameters of the surgical safety decision space, forming a closed-loop adaptive adjustment mechanism, enabling the decision system to respond in real time to changes in the surgical process and fluctuations in patient status, continuously improving the robustness and accuracy of decision-making. Attached Figure Description

[0054] Figure 1 This is a flowchart illustrating an intelligent decision-making method based on IoT-based multi-source data fusion during the surgical period. Figure 2 This is a flowchart of causal dependency topology analysis and feature extraction. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0057] Figure 1 This is a flowchart illustrating the intelligent decision-making method for multi-source data fusion during surgery based on the Internet of Things, as described in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0058] Acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer;

[0059] In a multi-source heterogeneous data stream, cross-source response events triggered by the same surgical operation are identified, the peak time of the cross-source response events is extracted as the surgical event anchor point, the time phase difference between the surgical event anchor points of different data sources is calculated, and the collection timestamps of each data source are reversed based on the time phase difference to generate a surgical period dataset with a unified time reference.

[0060] Conditional independence tests are performed on the surgical dataset, and a causal dependency topology between the data sources is constructed based on the test results. Causal blocking tests are used to identify causal blocking nodes in the causal dependency topology, and causal decoupling surgical features are generated based on the causal blocking nodes.

[0061] Based on the current stage of the surgical procedure, a surgical safety decision space containing intervention and damage boundaries is constructed. The causal decoupled surgical period features are projected onto the surgical safety decision space. Within the surgical safety decision space, decision instructions that meet the surgical objectives are generated through constrained gradient search.

[0062] The decision-making instructions are transmitted to the surgical equipment control unit for execution, and the boundary parameters of the surgical safety decision space are dynamically updated by collecting surgical feedback data after execution.

[0063] In one optional embodiment, cross-source response events triggered by the same surgical operation are identified in multi-source heterogeneous data streams. The peak time of the cross-source response events is extracted as the surgical event anchor point. The time phase difference between the surgical event anchor points of different data sources is calculated. Based on the time phase difference, reverse compensation is performed on the collection timestamps of each data source to generate a surgical period dataset with a unified time reference, including:

[0064] An adaptive sliding window scan is performed on the multi-source heterogeneous data stream. The energy change rate of each data source signal is calculated within the adaptive sliding window. When the energy change rate exceeds a preset dynamic threshold, it is marked as a potential response point. Waveform segments before and after the potential response point are extracted to construct a response waveform library.

[0065] Morphological feature extraction is performed on waveform segments in the response waveform library. The kurtosis, skewness, and temporal envelope area of ​​the waveform segments are calculated as morphological feature vectors. By matching the morphological feature vectors across data sources, cross-source response events triggered by the same surgical operation are identified, and the successfully matched waveform segments are grouped into response event groups.

[0066] Extract the maximum amplitude moment of each data source waveform segment from the response event group, mark the surgical event anchor point, construct a time series correlation graph with the surgical event anchor point of each data source as the node, and calculate the time offset of the surgical event anchor point relative to the surgical event anchor point of the reference data source in the time series correlation graph as the time phase difference.

[0067] Establish time mapping relationships between various data sources based on time phase differences, apply a time offset opposite to the time phase difference to the collection timestamps of each data source to perform reverse compensation, and rearrange the multi-source heterogeneous data streams of each data source according to a unified time axis to generate a surgical period dataset.

[0068] In one specific implementation, when performing adaptive sliding window scanning on multi-source heterogeneous data streams, the window length is not fixed but dynamically adjusted according to the signal frequency characteristics of each data source. For high-frequency physiological signals (such as EEG and EMG), the window length is relatively short to capture rapidly changing transient responses; for low-frequency device status signals (such as instrument pressure and temperature), the window length is appropriately extended to ensure sufficient energy accumulation period. Within each sliding window, the ratio of the signal energy of the current window to that of the previous window is calculated to obtain the energy change rate. Its calculation method is the ratio of the sum of the squares of the amplitudes of all sampling points within the current window to the corresponding value in the previous window. When Exceeding the preset dynamic threshold At that moment, the potential response point is marked. Dynamic threshold. Instead of a globally fixed value, it is adaptively estimated based on the historical baseline noise level of signals from each data source. Specifically, the average energy change rate of several recent windows plus several times the standard deviation is used as the current threshold, thereby effectively suppressing false alarms caused by electromagnetic interference in the surgical environment or slight equipment vibration.

[0069] After identifying potential response points, waveform segments within a certain time range before and after these points are extracted to construct a response waveform library. The forward truncation length of the waveform segments covers the rising edge of the response, and the backward truncation length covers the complete process of the response decaying to the baseline. For different data sources, the truncation length is independently set according to the typical response duration of their respective signals, ensuring that the waveform segments completely reflect the response process triggered by a single surgical operation. The response waveform library is organized and stored in the form of a triplet of data source identifier, potential response point time, and waveform segment, providing a unified data input for subsequent cross-source matching.

[0070] Perform morphological feature extraction on each waveform segment in the response waveform library and select kurtosis. skewness and temporal envelope area The three components of the morphological feature vector: kurtosis. Reflects the sharpness and skewness of the waveform amplitude distribution. Describes the asymmetry of waveform amplitude distribution, time-domain envelope area. This is obtained by integrating the absolute value of the waveform segment amplitude, reflecting the total response energy. These three factors together constitute the morphological feature vector. It can characterize the overall shape of a waveform from different dimensions, so that even if the data sources come from different physical dimensions, their response waveforms are still comparable in shape.

[0071] Cross-data source morphological feature vector similarity matching employs a normalized Euclidean distance metric. Before matching, z-score normalization is performed on the morphological feature vectors of each data source according to the historical statistical distribution of their respective feature components to eliminate scale differences caused by different physical dimensions. After normalization, the Euclidean distance between the morphological feature vectors of waveform segments from different data sources is calculated. ,when Below the matching similarity threshold When two waveform segments are determined to be triggered by the same surgical operation, they are grouped into the same response event group. The matching process employs a greedy strategy to progressively expand the response event group: using a potential response point from a certain baseline data source as a seed, it sequentially searches for candidate segments in other data sources that have the highest similarity to the seed waveform segment and satisfy the distance constraint, until all participating data sources are covered or no candidate segments satisfy the conditions are found. Potential response points that fail to match are considered local noise responses and are not included in the subsequent time alignment process.

[0072] The maximum amplitude moment of each data source waveform segment is extracted from each response event group and marked as the surgical event anchor point of that data source in this response event. The extraction of the maximum amplitude moment is based on the sampling point accuracy, and sub-sampling accuracy anchor point positioning is achieved by performing quadratic curve fitting on the waveform segment near the peak, thereby reducing the anchor point discretization error caused by sampling rate differences. Using the surgical event anchor points of all participating data sources as nodes, a time series correlation graph is constructed. Each edge in the graph connects anchor point nodes from different data sources, and the weight of the edge is the difference between the corresponding anchor point moments of the two nodes, i.e., the time phase difference. .

[0073] In the timing correlation diagram, a data source is designated as the baseline data source (usually the one with the highest sampling rate and best clock stability). The time offset of the surgical event anchor point of each of the other data sources relative to the surgical event anchor point of the baseline data source is calculated, and this offset is taken as the time phase difference of each data source. subscript Identify the specific data source number. When the same data source participates in matching in multiple response event groups, the result from multiple calculations is used. The median is used as the final time phase difference estimate to improve the robustness of the estimate and avoid time alignment deviations caused by individual abnormal response events.

[0074] Based on the time phase difference of each data source Establish time mapping relationships between various data sources. Each collection timestamp Perform reverse compensation to correct it to This means applying a time offset of equal magnitude and opposite direction to the time phase difference to the original timestamp. The physical meaning of reverse compensation is: if the response event anchor point of a data source lags behind the reference data source... Then all timestamps of the data source need to be shifted forward as a whole. This aligns the timeline with the baseline data source. The compensation operation acts directly on the timestamp field without modifying the signal amplitude, ensuring the integrity of the original physiological and equipment signal amplitudes.

[0075] After completing the reverse timestamp compensation for each data source, the multi-source heterogeneous data streams from all data sources are rearranged along a unified timeline. The rearrangement process uses the compensated timestamps as keys to perform a global sort on the data points of each data source, and then performs equal-interval resampling on the timeline. Data points missing from each data source are filled using linear interpolation, ultimately generating a surgical dataset with a unified time reference. In this dataset, the signals from each data source are strictly aligned in the time dimension, eliminating time deviations introduced by device clock drift, signal transmission delays, and sampling rate differences. This provides a reliable time synchronization foundation for subsequent conditional independence tests and causal dependency topology construction among data sources. The surgical dataset uses a unified timeline as an index, retains the original physical quantity identifiers of each data source, supports flexible retrieval by time interval and data source type, and meets the input format requirements for subsequent multi-source fusion analysis.

[0076] In one optional embodiment, performing a conditional independence test between data sources on the surgical dataset and constructing a causal dependency topology between data sources based on the test results includes:

[0077] Extract data state snapshots of each data source at the moment of surgical instrument action from the surgical period dataset, and construct a surgical data source graph structure with data sources as nodes and data state snapshots as node attributes;

[0078] Two data source nodes are selected from the surgical data source graph structure as the node pair to be tested, and the other data source nodes are selected as condition variable nodes in turn.

[0079] For each condition variable node, calculate the conditional mutual information of the node pair to be tested under the condition variable node. When the conditional mutual information is lower than the preset independence threshold, determine that the node pair to be tested is conditionally independent under the condition variable node. Record all condition variable nodes that make the node pair to be tested conditionally independent to form an intermediate transmission node set.

[0080] When the intermediate transmission node set is empty, causal dependency edges are established between the pairs of nodes to be tested. When the intermediate transmission node set is not empty, the condition variable nodes in the intermediate transmission node set are marked as causal transmission path nodes between the pairs of nodes to be tested.

[0081] Perform the above conditional independence test on all data source node pairs in the surgical data source graph structure, and combine all data source nodes and the causal dependency edges established between them to construct the causal dependency topology between data sources.

[0082] In one specific implementation, extracting data state snapshots of each data source at the moment of surgical instrument action triggering from the surgical dataset is the starting point for constructing the causal dependency topology. The moment of surgical instrument action triggering corresponds to a unified time reference node after the surgical event anchor point is aligned. At this moment, the state information of each data source, such as signal amplitude, frequency distribution, and statistical moments, is fully preserved, forming a set of high-dimensional state vectors. Each data source is regarded as a node in a graph structure, and its corresponding data state snapshot is used as the attribute vector of that node, thereby constructing the surgical data source graph structure. The number of nodes in this graph structure is equal to the total number of data sources participating in the fusion, and the attribute dimension of the nodes is determined by the number of features in the state snapshot. In the initial state, there are no edge connections between the nodes in the graph. The subsequent conditional independence test process will gradually fill in the causal dependencies between the nodes.

[0083] After establishing the surgical data source graph structure, two nodes are selected from all data source nodes to form a pair of nodes to be tested, and the remaining data source nodes are sequentially set as condition variable nodes. Let the pairs of nodes to be tested correspond to the data sources respectively. and data source The current condition variable node corresponds to the data source. Then it is necessary to calculate in the given Under the conditions and Conditional mutual information between Conditional mutual information measures the degree of residual statistical dependence between two data sources, given information from a third-party data source. If... and The relationship between them is entirely determined by The intermediary, then in the given Under certain conditions, the two tend to become conditionally independent. The value will approach zero. The calculation of conditional mutual information is based on the joint probability distribution and marginal probability distribution estimation of state snapshots from each data source, using kernel density estimation or based on... The nearest neighbor nonparametric estimation method approximates the probability density to avoid strong constraints on the form of data distribution.

[0084] Let the preset independence threshold be... When the calculated conditional mutual information satisfy At that time, determine the data source With data source In condition variables Conditional independence under given conditions. Threshold. The settings need to comprehensively consider the data sampling volume, the dimension of the state snapshot, and the tolerance of the surgical scenario for misjudgment. They are typically calibrated using permutation tests or statistical significance tests based on asymptotic distributions to ensure the reliability of the independence determination. For the current node pair to be tested... Iterate through all condition variable nodes and perform the conditional mutual information calculation and independence determination on each one. Summarize all condition variable nodes that satisfy the conditional independence determination to form a set of intermediate transit nodes for that node pair. .

[0085] intermediate transmission node set The state directly determines how the causal relationship between the pairs of nodes to be tested is modeled. When it is an empty set, it means that no matter what third-party data source is introduced as a condition, and The consistent statistical dependence between them indicates a direct causal relationship, which is reflected in the nodes of the surgical data source graph structure. With nodes Establish causal dependencies between them. The directionality of this edge can be further determined through subsequent temporal relationships or intervention experiment results. In the initial graph construction stage, bidirectional dependencies can be represented by undirected edges. When not empty, it means and The statistical dependency between them can be explained by one or more condition variable nodes in the set. The relationship between them is not a direct causal one, but rather transmitted through the set of intermediate nodes. The nodes in the process are passed. At this point, [the process will be...]. All condition variable nodes are marked as nodes With nodes The nodes in the causal transmission path between these nodes will be used as important structural information in subsequent causal shielding analysis.

[0086] Conditional independence tests are performed sequentially on all data source node pairs in the surgical data source graph structure according to the above procedure. The traversal order of node pairs follows the principle of no repeated enumeration, and the total number of tests is [number missing]. ,in This represents the total number of data source nodes. After each node pair is tested, a causal dependency edge is added between the node pairs based on the state of the intermediate transmission node set, and the corresponding transmission path node information is recorded. After all node pairs are tested, all data source nodes and all causal dependency edges established during the testing process are integrated to form a complete causal dependency topology between data sources. This topology visually represents the direct causal relationship structure between data sources in graph form. Node pairs connected by causal dependency edges indicate a direct physiological or operational causal effect, while node pairs connected only through transmission path nodes indicate that their relationship is mediated by a specific intermediate data source.

[0087] In real-world surgical scenarios, causal relationships between different data sources often have significant physiological implications. For example, there might be a direct causal dependency between surgical force sensor data and tissue impedance data, while the correlation between surgical instrument position data and patient vital signs data may require intermediate transmission nodes such as surgical force to explain. Constructing a causal dependency topology provides a structured graph theory foundation for subsequent identification of causal shielding nodes, avoiding the interference of spurious associations introduced by relying solely on correlation analysis. Furthermore, the conditional mutual information-based testing method makes relatively relaxed assumptions about data distribution, effectively handling the non-Gaussian and non-linear statistical dependency structures commonly found in multi-source data during surgery, thus improving the accuracy and robustness of the causal dependency topology.

[0088] In real-time surgical scenarios with limited computing resources, the above-mentioned inspection process can be accelerated through tiered processing. Priority is given to cases where the absolute value of the Pearson correlation coefficient between state snapshots exceeds a preset screening threshold. The nodes perform a full conditional mutual information test, and for those with a correlation coefficient lower than 1, the test is performed. Node pairs are directly determined to be conditionally independent and detailed checks are skipped, thus significantly reducing computational overhead while maintaining the integrity of the main causal structure. Screening threshold. The values ​​of need to be pre-calibrated based on the statistical characteristics of historical surgical data to ensure that key causal dependencies are not overlooked. The final constructed causal dependency topology will serve as a structural prior for causal decoupling of surgical feature extraction, supporting accurate modeling of the subsequent surgical safety decision space.

[0089] like Figure 2 The diagram shows the flowchart of causal dependency topology analysis and feature extraction.

[0090] In one optional embodiment, causal blocking nodes are identified in the causal dependency topology through a causal blocking test, and causal decoupling operation-phase features are generated based on the causal blocking nodes, including:

[0091] In the causal dependency topology, identify the target data source node corresponding to the surgical decision target and the source data source node corresponding to the surgical instrument control command. Starting from the target data source node, perform a reverse breadth-first search along the causal dependency edge to the source data source node, record all data source nodes traversed by the reverse breadth-first search, and construct a set of causal transmission nodes.

[0092] For each data source node in the causal transmission node set, perform a causal blocking test, temporarily remove the data source node and its connected causal dependency edges from the causal dependency topology, re-execute the causal path search from the source data source node to the target data source node, and when the causal path search fails, mark the data source node as a causal blocking node, and combine the causal blocking node and its connected causal dependency edges to form a causal backbone path.

[0093] In the causal dependency topology, data source nodes that are not causal shielding nodes are marked as bypass coupling nodes, and bypass coupling nodes and their connected causal dependency edges are combined to form bypass coupling paths.

[0094] Extract the data state snapshot corresponding to the causal shielding node as the causal decoupling operation period feature.

[0095] In one specific implementation, after constructing the causal dependency topology between data sources, it is necessary to accurately locate the nodes that play a key role in transmitting surgical decisions within this topology, and generate causal decoupling surgical features based on these nodes, removing redundant coupling information. The entire process consists of four stages: constructing a set of causal transmission nodes, identifying causal shielding nodes, stripping bypass coupling paths, and feature extraction. Each stage is logically progressive and interconnected.

[0096] In the causal dependency topology, the semantic positioning of two types of key nodes is first clarified. The target data source node corresponding to the surgical decision objective represents the final output end that needs to be predicted or evaluated in the topology, such as an intraoperative tissue damage risk score or a patient's comprehensive vital signs status node. The source data source node corresponding to the surgical instrument control command represents the input end that applies intervention in the topology, such as an ultrasonic scalpel power command node or a robotic arm pose command node. Starting from the target data source node, a reverse breadth-first search is performed along the directed causal dependency edges in the causal dependency topology, tracing upwards layer by layer until the source data source node is reached or a leaf node cannot be extended further. During the search, all intermediate data source nodes traversed are uniformly included in the causal transmission node set. The reverse breadth-first search is implemented using a queue structure. Each time, a node is taken from the queue, and all its predecessor nodes (i.e., nodes in the directed graph that point to that node) are traversed. If a predecessor node has not been visited and is not a node specified by the search termination condition, it is added to the queue and recorded. Finally, It includes all data source nodes that may be involved in causal transmission from the source to the target, forming a candidate set for subsequent causal blocking tests.

[0097] right Each data source node in the process is subjected to a causal blocking test in sequence. The test process adopts a three-step operation paradigm of "temporary removal - re-search - restoration". Specifically, for The first in A candidate node is temporarily removed from the causal dependency topology, along with all causal dependency edges connected to it, forming a reduced temporary topology. A causal path search from the source data node to the target data node is then re-executed on this temporary topology. If the search result indicates that the path does not exist (i.e., the source node and the target node are no longer connected in the temporary topology), it means that the node... The existence of a causal link is a necessary condition for maintaining the source-target causal transmission link. It is marked as a causal shielding node and added to the causal shielding node set. If the search results show that the path still exists, it means that even if the node is removed... Even if a causal signal can still propagate from the source to the target through other paths, this node is not indispensable for the causal backbone propagation and is not marked as a causal shielding node. After each test, the temporarily removed node and its edges are immediately restored to the topology to ensure that subsequent node tests are performed on the complete topology structure, avoiding test bias caused by cumulative removal. After testing all candidate nodes is completed, the... The combination of all causal shielding nodes and their causal dependencies forms the causal backbone path. . This represents the most critical information transmission backbone between surgical instrument control commands and surgical decision-making goals; the absence of any node in this backbone will lead to the breakage of the causal link.

[0098] In the causal dependency topology, belonging to But not belonging to The data source nodes are marked as bypass coupling nodes, and these bypass coupling nodes and the causal dependency edges they connect to form bypass coupling paths. While nodes in bypass coupling paths have directed connections to trunk nodes in the causal dependency topology, they are not indispensable for source-target causal transmission. They primarily reflect covariant relationships or indirect associations between data sources, rather than true causal trunk transmission. In surgical decision-making scenarios, bypass coupling paths often correspond to equipment noise propagation links, indirect reflection pathways of patient physiological parameters, or diffusion paths of surgical environment interference. Extracting information from these bypass coupling nodes from decision features helps eliminate the interference of confounding variables on the decision model, improving the causal interpretability and clinical reliability of decision instructions.

[0099] After completing the causal shielding node set After identification, targeting For each causal masking node, a data state snapshot corresponding to it in the unified surgical dataset based on the current time benchmark is extracted. The data state snapshot extraction uses the time-synchronized acquisition timestamp as an index, extracting a data segment within a fixed time window centered on the current surgical event anchor point, covering all sampled values ​​from the data source corresponding to that node within that time window. For continuous data source nodes (such as vital sign waveforms, instrument torque sensor signals), the data state snapshot is a time series segment; for discrete data source nodes (such as surgical stage labels, instrument status codes), the data state snapshot is a category encoding vector. Data state snapshots of all causal shielding nodes are concatenated in node number order to form a causal decoupling surgical feature vector. .because It contains only information on key nodes on the main causal path, while eliminating redundant coupling components introduced by bypass coupling nodes. It has a stronger causal explanation ability for surgical decision objectives and is more robust to surgical environment noise and individual equipment differences.

[0100] In real-world surgical scenarios, the structure of causal dependency topology may undergo local changes as the surgical process transitions between different stages. For example, the correspondence between source data source nodes and target data source nodes may adjust between the suturing and resection stages, leading to changes in the set of causal propagation nodes. The composition differs. Therefore, whenever the surgical procedure changes, the reverse breadth-first search and causal blocking test must be re-executed, and the results dynamically updated. and causal decoupling of surgical feature vectors The structure ensures that the features remain consistent with the causal structure of the current surgical stage. Furthermore, when surgical feedback data triggers an update of the boundary parameters of the surgical safety decision space, if the weight of a causal dependency edge in the causal dependency topology changes significantly, the causal blocking test must be re-executed on the affected nodes to verify whether their shielded node status still holds, thus ensuring the continued effectiveness of the causal decoupling features during the surgical period.

[0101] In one optional embodiment, constructing a surgical safety decision space that includes intervention and damage boundaries based on the current stage of the surgical procedure includes:

[0102] Obtain the standard surgical operation sequence corresponding to the current stage of the surgical process from the surgical procedure database, analyze the instrument movement type and tissue contact range corresponding to each surgical operation step in the standard surgical operation sequence, and map the instrument movement type and tissue contact range to the three-dimensional coordinate system of the surgical scene to form a standard operation space area.

[0103] Based on the causal decoupling of the surgical period features, the physiological state deviation of each anatomical structure in the current surgical scene is calculated. Anatomical structures whose physiological state deviation exceeds the preset safety threshold are marked as high-risk tissue areas. The spatial boundary of the high-risk tissue area is marked in the three-dimensional coordinate system of the surgical scene to construct the damage boundary.

[0104] Based on the standard operating space area, a preset safe distance is extended outward in the three-dimensional coordinate system of the surgical scene to form an operating allowable space area. The space area between the operating allowable space area and the damage boundary is defined as the intervention boundary.

[0105] The spatial region enclosed by the intervention boundary and the damage boundary in the three-dimensional coordinate system of the surgical scene is defined as the surgical safety decision space.

[0106] In one specific implementation, when retrieving a standard surgical operation sequence matching the current surgical stage from a surgical procedure database, it is necessary to determine the current surgical stage identifier based on preoperative planning information and real-time surgical process identification results, and then use this identifier as an index to retrieve the corresponding standard operation sequence record from the database. The standard surgical operation sequence contains several ordered surgical operation steps, each associated with an instrument action type field and a tissue contact range field. The instrument action type describes the movement pattern of the surgical instrument in that step, such as cutting, suturing, electrocoagulation, traction, etc.; the tissue contact range describes the tissue area that the instrument tip is expected to contact in the anatomical space, usually given as a three-dimensional coordinate range with reference to anatomical landmarks. By jointly mapping these two types of information to the three-dimensional coordinate system of the surgical scene, the standard operation space area for that surgical stage can be obtained. Specifically, for each surgical operation step... The type of instrument movement determines the set of motion direction constraints for this step in the three-dimensional coordinate system, while the tissue contact range determines the set of spatial position constraints for this step. The intersection of the two constitutes the step. Standard operation sub-region The union of the standard operation sub-regions of all steps constitutes the complete standard operation space region. ,Right now .

[0107] Based on the generated causal decoupling surgical period feature vector This involves quantitatively assessing the current physiological state of various anatomical structures within the surgical setting. For structures numbered... Anatomical structure, from Extract physiological indicator subvectors related to this structure. It also retrieves the standard physiological state reference vector of the anatomical structure at the current surgical stage from the surgical procedure database. Deviance of physiological state Defined as the weighted distance between the current physiological indicator subvector and the standard reference vector, i.e. ,in For anatomical structure A physiological indicator weight matrix is ​​used to highlight physiological indicator dimensions that have a greater impact on the structural safety. Let the preset safety threshold be... ,when At that time, the anatomical structure The area is marked as high-risk tissue. The spatial boundary of the high-risk tissue area is obtained by applying an expansion operation to the three-dimensional anatomical model of this structure; the expansion radius is... Deviation from physiological state A positive correlation exists; the higher the deviation, the larger the boundary range, ensuring that the protection margin for high-risk areas dynamically increases with the degree of risk. The spatial boundaries of all high-risk tissue areas are merged in the three-dimensional coordinate system of the surgical scene to form the damage boundary. The space inside the damage boundary is a prohibited area where instruments are absolutely forbidden to enter.

[0108] With standard operating space area Based on this, along the three-dimensional coordinate system of the surgical scene The outer normal direction expands uniformly outward at a preset safety distance. Obtain the permitted operating space area Preset safe distance The value is determined based on the operational precision requirements of the current surgical stage and the error range for controlling the position of the instrument tip, and is usually on the order of millimeters. For delicate operations, it can be appropriately reduced to maintain operational precision, while for large-area traction operations, it can be appropriately increased to accommodate instrument movement fluctuations. (Operational allowable space area) This represents the maximum permissible range of operational deviation from standard operating procedures; movement of the instrument outside this range will trigger a warning response. Intervention Boundary Defined as the operational allowable space region outer boundary and damage boundary The spatial region between, i.e. The outer boundary surface is used to characterize the buffer zone for the transition of instrument movement from the safe zone to the danger zone. When the instrument tip enters the spatial area corresponding to the intervention boundary, an early warning intervention command is triggered, prompting the operator to adjust the direction or amplitude of instrument movement to avoid further approaching the damage boundary.

[0109] Intervention boundaries and damage boundary The enclosed spatial region bounded by the three-dimensional coordinates of the surgical scene is defined as the surgical safety decision space. Surgical safety decision space In a physical sense, this represents the three-dimensional spatial range within which the instrument tip can move safely during the current surgical phase, and its internal boundaries are subject to intervention. It is further divided into two levels: a core safety zone and a buffer warning zone. The core safety zone corresponds to the standard operating space area. Within and around this area, when the device moves within this area, the decision-making instructions maintain the current operation; the buffer warning area corresponds to... Outer boundary to intervention boundary Within the designated area, when the device enters this area, corrective decision instructions are generated to guide the device back to the core safety zone; when the device exceeds the intervention boundary... And the damage boundary has not yet been reached. When an emergency stop command is generated, it is triggered; when the instrument reaches the damage boundary. At that time, the highest priority forced rollback command is triggered. The three-dimensional geometric representation of the surgical safety decision space is stored using a signed distance field. For any point in the three-dimensional coordinate system of the surgical scene... Define its signed distance field value This is the signed distance from the point to the nearest boundary surface. The point indicates that it is located inside the safe zone. The point indicates that it is located inside the prohibited area. The corresponding boundary surface location. In the subsequent constraint gradient search process, this will be directly utilized. The gradient information guides the direction of decision command generation, ensuring that the generated decision commands always meet the spatial constraints of the surgical safety decision space.

[0110] In practical applications, the establishment of a three-dimensional coordinate system for the surgical scene relies on the registration results of intraoperative image navigation data and instrument tracking data. The origin of the three-dimensional coordinate system is usually set at an anatomical reference point in the surgical area, and the coordinate axes are aligned with the patient's body axis to ensure that the spatial description of the anatomical structures has clear clinical significance. Standard operating space area Damage boundary and intervention boundaries All data is constructed and stored within this unified coordinate system, ensuring consistent processing and decision inference of spatial information from different data sources within the same reference framework. Each time a surgical stage changes, the aforementioned boundary parameters are recalculated based on the standard operating sequence corresponding to the new stage and the current causal decoupling surgical period characteristics, achieving dynamic adaptive updating of the surgical safety decision space as the surgical progresses.

[0111] In one optional embodiment, projecting causal decoupled perioperative features onto a surgical safety decision space, and generating decision instructions that satisfy surgical objectives within the surgical safety decision space through constrained gradient search, includes:

[0112] Extract the data state snapshots corresponding to each causal shielding node from the causal decoupling surgical period features, convert the instrument space coordinates and tissue deformation displacement in the data state snapshots into state point coordinates in the surgical safety decision space, and establish the mapping relationship between causal shielding nodes and state points in the surgical safety decision space.

[0113] Based on the intervention boundary and the damage boundary, a boundary normal vector field is constructed, the intervention normal distance and the damage normal distance of the state point are calculated, and a constraint potential energy field is generated by nonlinear weighted fusion.

[0114] Starting from the target state point corresponding to the surgical target, gradient descent iteration is performed along the negative gradient direction of the constraint potential energy field. In each iteration, the constraint potential energy gradient vector of the current iteration point is calculated, and the preset step size is moved to the next iteration point in the opposite direction of the constraint potential energy gradient vector. The sequence of iteration points passed during the iteration process constitutes the constraint guidance trajectory.

[0115] The coordinates of the state points corresponding to each iteration point in the constraint-guided trajectory are reverse-mapped to the causal shielding node, and the instrument control parameters corresponding to the causal shielding node are extracted to generate decision instructions.

[0116] In one specific implementation, the causal decoupling of the surgical period feature vector is derived from... In this process, for each causal shielding node, a snapshot of its data state at the current moment is extracted. The data state snapshot contains two core types of information: instrument spatial coordinates and tissue deformation displacement. The instrument spatial coordinates are derived from the pose sensor data of the surgical robot's end effector and are represented in a three-dimensional Cartesian coordinate system; the tissue deformation displacement is derived from the real-time tracking results of soft tissue deformation by intraoperative ultrasound or optical coherence tomography. The instrument spatial coordinates are denoted as... The deformation displacement vector of the tissue is denoted as The two are combined to form the coordinates of the state point. This completes the transformation from the feature space of causal shielding nodes to the surgical safety decision space. Mapping of state points. This mapping relationship is achieved through a pre-calibrated coordinate transformation matrix. To ensure consistency between the sensor's physical coordinate system and the decision space coordinate system, a corresponding state point is established for each causal shielding node, forming a set of state points. Subsequent constraint potential field construction and gradient search are carried out on this set of state points.

[0117] In the surgical safety decision space In China, based on intervention boundaries and damage boundary Construct the corresponding boundary normal vector fields for each. For any state point in space... Using signed distance fields The gradient direction determines the boundary normal vector: Intervention boundary normal vector Defined as Pointing to The unit normal vector on the outer side, the normal vector of the damage boundary. Defined as Pointing to The unit normal vector on the outer side. Intervention normal distance. State point along Direction to Signed distance, damage normal distance State point along Direction to The signed distance. When the state point is located within the operational allowable space. Inside the system, both types of normal distances are positive; when a state point crosses the corresponding boundary, the corresponding normal distance takes a negative value, indicating a violation of safety constraints.

[0118] Constrained potential energy field The interference potential energy component is generated by nonlinearly weighted fusion of the intervention potential energy component and the damage potential energy component. Using the definition of an exponential repulsive potential function, when the state point approaches... The potential energy increases rapidly, preventing the instrument from exceeding its permissible operating range; damage potential energy component A steeper exponential repulsive potential function is used to define the hard constraint characteristics of damage risk. The weights for nonlinear weighted fusion are... and The risk priority is determined by the current stage of the surgical procedure, and the damage boundary weight is determined during high-precision operations. Higher values ​​are assigned to enhance the protection of key anatomical structures. The fused constraint potential field is expressed as... The potential energy field is A continuously differentiable scalar field is formed within it, and its gradient... Each state point has a clear physical meaning: it points in the direction of increasing potential energy, that is, the direction away from the safe region.

[0119] Constrained gradient search starts from the target state point corresponding to the surgical objective. Starting from the negative gradient direction of the constrained potential field, perform iterative descent. In the... In this iteration, the current iteration point is denoted as... Calculate the constraint potential gradient vector at that point. The iterative update rule is as follows: ,in A preset step size controls the movement amplitude in each iteration. To prevent state points from crossing boundaries and entering prohibited regions during iteration, a feasibility projection is performed after each iteration update: if... Falling Otherwise, project it back. The closest feasible point on the boundary. Iteration termination conditions fall into two categories: one is the displacement norm between adjacent iteration points. Below the convergence threshold This indicates that the search has converged to a local stable point; secondly, the number of iterations has reached the preset maximum iteration limit. This prevents the search from getting stuck in an infinite loop. Records from... The sequence of all iteration points passed to the convergence point This sequence constitutes a constrained guiding trajectory. This represents the optimal path starting from the target state while satisfying both the intervention boundary and the damage boundary constraints.

[0120] Constrained Guiding Trajectory The coordinates of the state points at each iteration point are transformed by the coordinate transformation matrix. The inverse transformation maps back to the physical feature space corresponding to the causal shielding node. For each iteration point... The instrument space coordinate components Directly corresponds to the target pose of the surgical instrument end effector, tissue deformation displacement components This is used to verify whether the current tissue deformation is within the expected range. The instrument control parameters corresponding to each iteration point are extracted from the causal shielding node, including the joint angle command sequence. ( (Joint degrees of freedom) and end effector force control parameters and instrument opening / closing status indicators The above control parameters are arranged according to the trajectory timing and encapsulated into structured decision instructions. This decision instruction sequence comprehensively describes the instrument motion control strategy from the current surgical state to the target state, satisfying both the surgical operation objectives and strictly adhering to the safety constraints of intervention and damage boundaries. After the decision instructions are generated, they are transmitted to the surgical equipment control unit, which executes the instrument actions step by step in sequence, continuously collecting feedback data during execution for dynamic updates of subsequent boundary parameters.

[0121] In one optional embodiment, a boundary normal vector field is constructed based on the intervention boundary and the damage boundary. The intervention normal distance and the damage normal distance of the state point are calculated. A constraint potential energy field is generated by nonlinear weighted fusion, including:

[0122] Extract the boundary surface mesh nodes of the intervention boundary and the damage boundary, and calculate the unit normal vectors of each boundary surface mesh node pointing into the surgical safety decision space to construct the boundary normal vector field;

[0123] In the surgical safety decision space, the state points obtained by mapping the causal shielding nodes are calculated, and the Euclidean distance from the state point to the nearest grid node of the intervention boundary is calculated to determine the intervention normal distance. The Euclidean distance from the state point to the nearest grid node of the damage boundary is also calculated to determine the damage normal distance.

[0124] The intervention potential energy vector is obtained by performing a scalar multiplication operation between the intervention normal distance and the unit normal vector of the corresponding intervention boundary grid node, and the damage potential energy vector is obtained by performing a scalar multiplication operation between the damage normal distance and the unit normal vector of the corresponding damage boundary grid node. The intervention potential energy vector and the damage potential energy vector are then subjected to nonlinear weighted fusion to generate the constraint potential energy vector.

[0125] The constraint potential vectors of all state points constitute the constraint potential field.

[0126] In one specific implementation, extracting the boundary surface mesh nodes of the intervention boundary and damage boundary is the starting point for constructing the boundary normal vector field. Intervention boundary With damage boundary Geometrically, all surfaces are discretized and stored as triangular mesh surfaces, each consisting of several mesh nodes and their connections. For the intervention boundary surface, all its triangular faces are traversed, and the cross product direction of the three edge vectors of each triangular face is used as the original normal vector of that face. This normal vector is then normalized to a unit vector, and its orientation towards the surgical safety decision space is verified. Internal directional consistency—if the cross product points outwards, it is inverted. For each grid node, the unit normal vectors of all its adjacent triangular faces are weighted and averaged (weights are the areas of each face), and then the mean vector is normalized to obtain the unit normal vector at that grid node. Damage boundary The same process is used to create normal vector index tables for all grid nodes of both the intervention and damage boundaries, thereby constructing the boundary normal vector field. This normal vector field is stored in discrete form and retrieved in subsequent calculations using spatial nearest neighbor queries.

[0127] In the surgical safety decision space In the context of causal decoupling, the feature vector during the surgical period... via calibration coordinate transformation matrix After projection, the corresponding state points are obtained. For each state point At the intervention boundary Mesh node set and damage boundary Perform a nearest neighbor search within the set of grid nodes. For the intervention boundary, calculate... The Euclidean distance between all grid nodes on the intervention boundary is used to determine the grid node with the minimum Euclidean distance on the intervention boundary. This minimum Euclidean distance is then denoted as the intervention normal distance. Simultaneously, record the unit normal vector at the nearest grid node. Similarly, performing the same operation on the damage boundary yields the damage normal distance. and the unit normal vector at the nearest mesh node of the damage boundary To improve the efficiency of nearest neighbor search, KD-tree index structures are pre-built for the grid nodes of intervention and damage boundaries, reducing the time complexity of each query from linear to logarithmic, thus meeting the stringent requirements of real-time surgical decision-making for response speed.

[0128] Obtain the normal distance of the intervention and damage normal distance After obtaining the corresponding unit normal vector, scalar multiplication is performed to generate the potential energy vector. Intervention potential energy vector Intervention normal distance The unit normal vector of the nearest grid node to the intervention boundary Multiplying them together yields the result, i.e. Damage potential vector Damage normal distance The unit normal vector of the nearest mesh node to the damage boundary Multiplying them together yields the result, i.e. The physical meaning of the above scalar multiplication is that distance information is encoded into the direction vector, so that the potential energy vector simultaneously carries the proximity of the state point to the boundary and the direction information of the constraint to be applied. When the state point is closer to the boundary, the magnitude of the potential energy vector is smaller, and the corresponding constraint guidance effect is stronger; when the state point is farther from the boundary, the magnitude of the potential energy vector increases, and the constraint guidance tends to be gentler.

[0129] Intervention potential vector and damage potential vector Perform nonlinear weighted fusion to generate a constraint potential vector. The core of nonlinear weighting lies in the two sets of weight coefficients. and These all change dynamically with the distance between the state point and the corresponding boundary, rather than being a fixed constant. Specifically, Follow The decrease rather than the nonlinear increase reflects the sensitivity to the approaching response to the intervention boundary; Follow The decrease exhibits a steeper nonlinear increase, reflecting the priority given to protecting the damage boundary. The fusion result is... ,in and The nonlinear form can be implemented using an inverse proportional function or an exponentially decaying function, ensuring that the weights approach infinity as the distance approaches zero, thus generating a sufficiently strong constraint repulsive force near the boundary to prevent state points from crossing the boundary. In practical implementations, to avoid numerical singularities where the denominator is zero, [the following is omitted as it is not explicitly stated in the original text]. and Each variable is regularized by introducing a small positive bias.

[0130] The final construction of the confined potential field is achieved through the surgical safety decision space. The above process is repeated for all state points. The intervention potential vector is calculated independently for each state point. and damage potential vector And generate the corresponding constraint potential vector according to the above nonlinear weighted fusion rule. The constraint potential energy vectors of all state points are aggregated to form a constraint potential energy field covering the entire surgical safety decision space. This potential energy field is stored in the form of a vector field, where each state point corresponds to a three-dimensional constraint potential energy vector, reflecting the comprehensive guiding direction and intensity of that point under the dual constraints of the intervention boundary and the damage boundary. During the constraint gradient search phase, the constraint gradient at each step of the gradient descent iteration is queried from this potential energy field or calculated in real time, driving the trajectory of the state point to remain within the constraints while satisfying the surgical objectives. Within the safe zone.

[0131] This constraint potential field construction scheme exhibits excellent geometric adaptability, capable of handling situations where the shapes of the intervention and damage boundaries are complex and where local curvature changes drastically. Since the normal vector field is established based on discrete nodes of the actual mesh surface, its directional information remains consistent with the geometric relationships of the real anatomical structure and instrument motion space, avoiding directional deviations caused by simplified geometric assumptions. Simultaneously, the nonlinear weighted fusion mechanism ensures that the constraint weight of the damage boundary is never lower than that of the intervention boundary under any circumstances, thereby prioritizing surgical safety at the decision-making level.

[0132] A second aspect of this invention provides an intelligent decision-making system based on Internet of Things (IoT) for fusion of multi-source data during surgery, comprising:

[0133] The data synchronization unit is used to acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer.

[0134] The causal analysis unit is used to identify cross-source response events triggered by the same surgical operation in multi-source heterogeneous data streams, extract the peak time of the cross-source response events as the surgical event anchor point, calculate the time phase difference between surgical event anchor points from different data sources, perform reverse compensation on the collection timestamps of each data source based on the time phase difference, and generate a surgical period dataset with a unified time reference.

[0135] The decision generation unit is used to perform conditional independence tests between data sources on the surgical dataset, construct a causal dependency topology between data sources based on the test results, identify causal blocking nodes in the causal dependency topology through causal blocking tests, and generate causal decoupling surgical features based on the causal blocking nodes.

[0136] The feedback update unit is used to construct a surgical safety decision space containing intervention and damage boundaries based on the current surgical process stage, project the causal decoupled surgical period features onto the surgical safety decision space, and generate decision instructions that meet the surgical objectives through constrained gradient search within the surgical safety decision space.

[0137] The processing unit is used to transmit decision instructions to the surgical equipment control unit for execution, and to collect surgical feedback data after execution to dynamically update the boundary parameters of the surgical safety decision space.

[0138] A third aspect of the present invention provides an electronic device, comprising:

[0139] processor;

[0140] Memory used to store processor-executable instructions;

[0141] The processor is configured to invoke instructions stored in the memory to execute the aforementioned method.

[0142] A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the aforementioned method.

[0143] This invention can be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the invention.

[0144] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent decision-making method based on multi-source data fusion during the surgical period using the Internet of Things, characterized in that, include: Acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer; In a multi-source heterogeneous data stream, cross-source response events triggered by the same surgical operation are identified, the peak time of the cross-source response events is extracted as the surgical event anchor point, the time phase difference between the surgical event anchor points of different data sources is calculated, and the collection timestamps of each data source are reversed based on the time phase difference to generate a surgical period dataset with a unified time reference. Conditional independence tests are performed on the surgical dataset, and a causal dependency topology between the data sources is constructed based on the test results. Causal blocking tests are used to identify causal blocking nodes in the causal dependency topology, and causal decoupling surgical features are generated based on the causal blocking nodes. Based on the current stage of the surgical procedure, a surgical safety decision space containing intervention and damage boundaries is constructed. The causal decoupled surgical period features are projected onto the surgical safety decision space. Within the surgical safety decision space, decision instructions that meet the surgical objectives are generated through constrained gradient search. The decision-making instructions are transmitted to the surgical equipment control unit for execution, and the boundary parameters of the surgical safety decision space are dynamically updated by collecting surgical feedback data after execution.

2. The method according to claim 1, characterized in that, In multi-source heterogeneous data streams, cross-source response events triggered by the same surgical operation are identified. The peak time of these cross-source response events is extracted as the surgical event anchor point. The time phase difference between surgical event anchor points from different data sources is calculated. Based on the time phase difference, reverse compensation is performed on the acquisition timestamps of each data source to generate a surgical period dataset with a unified time reference, including: An adaptive sliding window scan is performed on the multi-source heterogeneous data stream. The energy change rate of each data source signal is calculated within the adaptive sliding window. When the energy change rate exceeds a preset dynamic threshold, it is marked as a potential response point. Waveform segments before and after the potential response point are extracted to construct a response waveform library. Morphological feature extraction is performed on waveform segments in the response waveform library. The kurtosis, skewness, and temporal envelope area of ​​the waveform segments are calculated as morphological feature vectors. By matching the morphological feature vectors across data sources, cross-source response events triggered by the same surgical operation are identified, and the successfully matched waveform segments are grouped into response event groups. Extract the maximum amplitude moment of each data source waveform segment from the response event group, mark the surgical event anchor point, construct a time series correlation graph with the surgical event anchor point of each data source as the node, and calculate the time offset of the surgical event anchor point relative to the surgical event anchor point of the reference data source in the time series correlation graph as the time phase difference. Establish time mapping relationships between various data sources based on time phase differences, apply a time offset opposite to the time phase difference to the collection timestamps of each data source to perform reverse compensation, and rearrange the multi-source heterogeneous data streams of each data source according to a unified time axis to generate a surgical period dataset.

3. The method according to claim 1, characterized in that, Perform conditional independence tests between data sources on the surgical dataset, and construct a causal dependency topology among the data sources based on the test results, including: Extract data state snapshots of each data source at the moment of surgical instrument action from the surgical period dataset, and construct a surgical data source graph structure with data sources as nodes and data state snapshots as node attributes; Two data source nodes are selected from the surgical data source graph structure as the node pair to be tested, and the other data source nodes are selected as condition variable nodes in turn. For each condition variable node, calculate the conditional mutual information of the node pair to be tested under the condition variable node. When the conditional mutual information is lower than the preset independence threshold, determine that the node pair to be tested is conditionally independent under the condition variable node. Record all condition variable nodes that make the node pair to be tested conditionally independent to form an intermediate transmission node set. When the intermediate transmission node set is empty, causal dependency edges are established between the pairs of nodes to be tested. When the intermediate transmission node set is not empty, the condition variable nodes in the intermediate transmission node set are marked as causal transmission path nodes between the pairs of nodes to be tested. Perform the above conditional independence test on all data source node pairs in the surgical data source graph structure, and combine all data source nodes and the causal dependency edges established between them to construct the causal dependency topology between data sources.

4. The method according to claim 3, characterized in that, Causal shielding nodes are identified in causal dependency topologies through causal blocking tests. Based on these causal shielding nodes, causal decoupling features are generated during the operative period, including: In the causal dependency topology, identify the target data source node corresponding to the surgical decision target and the source data source node corresponding to the surgical instrument control command. Starting from the target data source node, perform a reverse breadth-first search along the causal dependency edge to the source data source node, record all data source nodes traversed by the reverse breadth-first search, and construct a set of causal transmission nodes. For each data source node in the causal transmission node set, perform a causal blocking test, temporarily remove the data source node and its connected causal dependency edges from the causal dependency topology, re-execute the causal path search from the source data source node to the target data source node, and when the causal path search fails, mark the data source node as a causal blocking node, and combine the causal blocking node and its connected causal dependency edges to form a causal backbone path. In the causal dependency topology, data source nodes that are not causal shielding nodes are marked as bypass coupling nodes, and bypass coupling nodes and their connected causal dependency edges are combined to form bypass coupling paths. Extract the data state snapshot corresponding to the causal shielding node as the causal decoupling operation period feature.

5. The method according to claim 1, characterized in that, The surgical safety decision space, which includes intervention and damage boundaries, is constructed based on the current stage of the surgical procedure. Obtain the standard surgical operation sequence corresponding to the current stage of the surgical process from the surgical procedure database, analyze the instrument movement type and tissue contact range corresponding to each surgical operation step in the standard surgical operation sequence, and map the instrument movement type and tissue contact range to the three-dimensional coordinate system of the surgical scene to form a standard operation space area. Based on the causal decoupling of the surgical period features, the physiological state deviation of each anatomical structure in the current surgical scene is calculated. Anatomical structures whose physiological state deviation exceeds the preset safety threshold are marked as high-risk tissue areas. The spatial boundary of the high-risk tissue area is marked in the three-dimensional coordinate system of the surgical scene to construct the damage boundary. Based on the standard operating space area, a preset safe distance is extended outward in the three-dimensional coordinate system of the surgical scene to form an operating allowable space area. The space area between the operating allowable space area and the damage boundary is defined as the intervention boundary. The spatial region enclosed by the intervention boundary and the damage boundary in the three-dimensional coordinate system of the surgical scene is defined as the surgical safety decision space.

6. The method according to claim 1, characterized in that, Projecting causal decoupling of perioperative features onto the surgical safety decision space, and generating decision instructions that satisfy surgical objectives through constrained gradient search within the surgical safety decision space, including: Extract the data state snapshots corresponding to each causal shielding node from the causal decoupling surgical period features, convert the instrument space coordinates and tissue deformation displacement in the data state snapshots into state point coordinates in the surgical safety decision space, and establish the mapping relationship between causal shielding nodes and state points in the surgical safety decision space. Based on the intervention boundary and the damage boundary, a boundary normal vector field is constructed, the intervention normal distance and the damage normal distance of the state point are calculated, and a constraint potential energy field is generated by nonlinear weighted fusion. Starting from the target state point corresponding to the surgical target, gradient descent iteration is performed along the negative gradient direction of the constraint potential energy field. In each iteration, the constraint potential energy gradient vector of the current iteration point is calculated, and the preset step size is moved to the next iteration point in the opposite direction of the constraint potential energy gradient vector. The sequence of iteration points passed during the iteration process constitutes the constraint guidance trajectory. The coordinates of the state points corresponding to each iteration point in the constraint-guided trajectory are reverse-mapped to the causal shielding node, and the instrument control parameters corresponding to the causal shielding node are extracted to generate decision instructions.

7. The method according to claim 6, characterized in that, Based on the intervention boundary and damage boundary, a boundary normal vector field is constructed. The intervention normal distance and damage normal distance of the state point are calculated. The constraint potential energy field is generated through nonlinear weighted fusion, including: Extract the boundary surface mesh nodes of the intervention boundary and the damage boundary, and calculate the unit normal vectors of each boundary surface mesh node pointing into the surgical safety decision space to construct the boundary normal vector field; In the surgical safety decision space, the state points obtained by mapping the causal shielding nodes are calculated, and the Euclidean distance from the state point to the nearest grid node of the intervention boundary is calculated to determine the intervention normal distance. The Euclidean distance from the state point to the nearest grid node of the damage boundary is also calculated to determine the damage normal distance. The intervention potential energy vector is obtained by performing a scalar multiplication operation between the intervention normal distance and the unit normal vector of the corresponding intervention boundary grid node, and the damage potential energy vector is obtained by performing a scalar multiplication operation between the damage normal distance and the unit normal vector of the corresponding damage boundary grid node. The intervention potential energy vector and the damage potential energy vector are then subjected to nonlinear weighted fusion to generate the constraint potential energy vector. The constraint potential vectors of all state points constitute the constraint potential field.

8. An IoT-based intelligent decision-making system for multi-source data fusion during surgery, used to implement the method as described in any one of claims 1-7, characterized in that, include: The data synchronization unit is used to acquire multi-source heterogeneous data streams during the surgical period through the IoT sensing layer. The causal analysis unit is used to identify cross-source response events triggered by the same surgical operation in multi-source heterogeneous data streams, extract the peak time of the cross-source response events as the surgical event anchor point, calculate the time phase difference between surgical event anchor points from different data sources, perform reverse compensation on the collection timestamps of each data source based on the time phase difference, and generate a surgical period dataset with a unified time reference. The decision generation unit is used to perform conditional independence tests between data sources on the surgical dataset, construct a causal dependency topology between data sources based on the test results, identify causal blocking nodes in the causal dependency topology through causal blocking tests, and generate causal decoupling surgical features based on the causal blocking nodes. The feedback update unit is used to construct a surgical safety decision space containing intervention and damage boundaries based on the current surgical process stage, project the causal decoupled surgical period features onto the surgical safety decision space, and generate decision instructions that meet the surgical objectives through constrained gradient search within the surgical safety decision space. The processing unit is used to transmit decision instructions to the surgical equipment control unit for execution, and to collect surgical feedback data after execution to dynamically update the boundary parameters of the surgical safety decision space.

9. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images