Virtual operation demonstration management system and method based on 3D modeling

Abstract

The invention discloses a virtual operation demonstration management system and method based on 3D modeling, and relates to the technical field of virtual operation demonstration management. The system comprises a data acquisition and processing module, a knowledge graph construction module, a key node identification module, a reference knowledge graph generation module and a comprehensive demonstration scheme matching module. The data acquisition and feature extraction module retrieves virtual surgical cases and historical demonstration schemes thereof from a database, extracts key features and constructs a case set; the knowledge graph construction module generates a knowledge graph by using the extracted key features and the numbers of the 3D modeling objects; the key node identification module analyzes the knowledge graph and identifies key nodes and connection paths thereof; the reference knowledge graph generation module is used for extracting global nodes from all knowledge graphs, establishing a reference knowledge graph and generating a demonstration scheme; and the comprehensive demonstration scheme matching module is used for matching the reference demonstration scheme according to the target characteristics of the comprehensive virtual surgical case so as to obtain a comprehensive demonstration scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual surgery demonstration management, and in particular to a virtual surgery demonstration management system and method based on 3D modeling. Background Art

[0002] In the current field of medical education and training, the teaching of surgical skills often relies on traditional physical models and on-site operations. However, this method has many limitations. First, it is difficult for physical models to fully replicate the complex structure and dynamic changes of the human body, which limits the trainees' understanding and mastery of real surgical situations. Secondly, on-site operations are not only costly, but also have high risks, especially for beginners, incorrect operations may lead to serious consequences. In addition, with the rapid development of medical technology, new surgical methods and instruments are constantly emerging, and traditional training methods are difficult to keep up with the pace of technological updates.

[0003] In recent years, virtual surgery demonstration methods based on 3D modeling have gradually emerged, providing an innovative solution to address the limitations of traditional training methods. This method uses advanced computer technology and virtual reality technology to create a highly simulated surgical environment and operation experience, thereby significantly improving the training effect and the trainees' operation skills. However, in practical applications, the existing virtual surgery demonstration management system still has shortcomings. Specifically, although the existing virtual surgery demonstration method based on 3D modeling has brought significant improvements to medical training through a highly simulated surgical environment and operation experience, the automation and intelligence of the management system still need to be strengthened. The existing system is usually able to generate a demonstration plan for a single virtual surgical case that has been preset, but when faced with a comprehensive virtual surgical case composed of more than one preset surgical case, the system often cannot make full use of the connection between different cases to automatically generate a corresponding comprehensive demonstration plan. This results in the need for professionals to manually perform a lot of configuration and adjustment work when facing a comprehensive virtual surgical case, thereby reducing overall efficiency and flexibility. Summary of the invention

[0004] The purpose of the present invention is to provide a virtual surgery demonstration management system and method based on 3D modeling to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: A virtual surgery demonstration management method based on 3D modeling includes the following steps: Step S100. Obtain historical demonstration plans of preset virtual surgical cases from the database, extract key features from the historical demonstration plans, and construct a preset virtual surgical case set; combine the historical demonstration plans of the preset virtual surgical cases, and generate a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set; Step S200. Based on the knowledge graph of the 3D modeling object, the connection paths of all nodes in the knowledge graph are obtained, and the key nodes in the knowledge graph of the 3D modeling object are identified by analyzing the knowledge graph in combination with the preset virtual surgery case set, and the key nodes and the corresponding connection paths are stored in correspondence; Step S300. According to the key nodes and the corresponding connection paths, the knowledge graphs of the 3D modeling objects of different preset virtual surgery cases are subjected to association analysis, and a reference knowledge graph of the reference virtual surgery case and the corresponding 3D modeling object is generated according to the result of the association analysis, and a reference demonstration plan is generated according to the reference knowledge graph of the 3D modeling object; Step S400. Input the target features of the comprehensive virtual surgical case, analyze the target features with the key features in the preset virtual surgical case set, and match the corresponding reference demonstration plan according to the analysis results; output the reference demonstration plan to relevant personnel, who will analyze and process it accordingly to obtain a comprehensive demonstration plan for the comprehensive virtual surgical case.

[0006] Furthermore, step S100 includes: S101. Retrieve all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extract key features from the historical demonstration plans, and one preset virtual surgical case corresponds to multiple different historical demonstration plans; the key features include information such as operation steps, tool use, surgical site and surgical environment; correspond the extracted key features to the corresponding historical demonstration plan numbers, and extract the corresponding 3D modeling object numbers from the historical demonstration plans, and construct a preset virtual surgical case set Av for each preset virtual surgical case, and Av={av1,av2,...,avn}, wherein av1 represents a data group consisting of the first historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, a2 represents a data group consisting of the second historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and so on, an represents a data group consisting of the nth historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and n represents the number of historical demonstration plans of the vth preset virtual surgical case; S102. Combined with the historical demonstration scheme of the preset virtual surgical case, for each element in the preset virtual surgical case set, according to the extracted key features and the corresponding 3D modeling object number, a knowledge graph of the corresponding 3D modeling object is generated, and the knowledge graph of the 3D modeling object uses the key features and the 3D modeling object as nodes, and the edges represent the relationship between different nodes. For example, there is an edge between node A (operation step 1) and node B (surgical site A), indicating that operation step 1 involves surgical site A; and the 3D modeling object number provided in the historical demonstration scheme is associated with its corresponding feature (such as tool use, operation step, etc.), and the knowledge graph of the 3D modeling object is filled, so as to generate a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set. For example, if the historical demonstration scheme number 1 uses tool A for operation step B, then in the knowledge graph, an edge should be established between the node "tool A" and the node "operation step B", indicating that "tool A" is used for "operation step B".

[0007] Further, step S200 includes: S201. For each preset virtual surgery case, extract all nodes and edges from the knowledge graph of the corresponding 3D modeling object, record the node set U and the edge set E, and the knowledge graph of the 3D modeling object is represented as a graph G=(U,E); use a graph traversal algorithm to traverse all nodes and edges in the knowledge graph of the 3D modeling object, so as to obtain all connection paths P from any node to other nodes, and the connection path P is represented as a node sequence, specifically: P=[u1,u2,...,uk], where u1 is the starting node, uk is the ending node, and u2 and subsequent other nodes are intermediate nodes; S202. Calculate the node occurrence frequency I corresponding to each preset virtual surgery case, and I=Mu / NP, where Mu represents the number of times node u appears in all connection paths P in the preset virtual surgery case, and NP represents the number of connection paths P corresponding to the preset virtual surgery case; analyze in combination with the preset virtual surgery case set, calculate the complexity F of the connection path P of the node corresponding to each preset virtual surgery case, and the specific calculation formula is: F(P)=(NuP+NeP) / NP, where NuP represents the total number of connection paths P corresponding to node u in the preset virtual surgery case, and NeP represents the total number of edges of the connection path P corresponding to node u in the preset virtual surgery case; combine the node occurrence frequency I and complexity F, and comprehensively calculate the node importance evaluation index R, and R=w1×I+w2×F, and w1 and w2 represent weight coefficients, and w1+w2=1; S203. Obtain the importance evaluation index R of all nodes corresponding to the preset virtual surgical case, and sort the nodes in descending order according to the importance evaluation index R, select the first m nodes as key nodes, and summarize and store the key nodes and the corresponding connection paths P.

[0008] Furthermore, step S300 includes: S301. Extract all unique nodes from the knowledge graph of 3D modeling objects of all preset virtual surgical cases to form a global node set N_global; for any two nodes ni and nj in the global node set, combine the knowledge graph of the 3D modeling objects of the corresponding preset virtual surgical cases to calculate the node attribute similarity S(ni,nj) between the two, and Sa(ni,nj)=(Ai·Aj) / |Ai|||Aj|, ​​where Ai and Aj represent the attribute vectors of nodes ni and nj respectively; based on the global node set N_glob The node co-occurrence similarity Sc(ni,nj) is calculated based on the co-occurrence of each node in al in different cases, and Sc(ni,nj)=Cij / (Ci·Cj)^(1 / 2), where Cij represents the number of times nodes ni and nj appear at the same time, and Ci and Cj represent the total number of times nodes ni and nj appear respectively; the node similarity S(ni,nj) is calculated based on the comprehensive attribute similarity and co-occurrence similarity, and S(ni,nj)=α·Sa(ni,nj)+(1-α)·Sc(ni,nj), where α represents the weight coefficient; S302. Use a clustering algorithm to cluster the global node set, classify nodes with equal similarity into a cluster class, and mark the central node of each cluster; for the nodes in each cluster, find their corresponding nodes in different preset virtual surgical cases and establish a mapping relationship; initialize an empty reference knowledge graph Gref, for each cluster, copy the nodes and their connection relationships contained in it from the knowledge graph G of the corresponding 3D modeling object to the reference knowledge graph Gref, and add new edges En by calculating the similarity of cross-case nodes, and the corresponding judgment expression is: En=(ni,nj)|S(ni,nj)>S0, where S0 represents the corresponding similarity threshold; if there are two or more nodes from different virtual surgical cases mapped to the same position in the reference knowledge graph Gref, they are merged according to the importance evaluation index R in step S202; S303. Use a graph search algorithm to find several optimal paths from the starting node to the target node in the reference knowledge graph, and extract relevant operation steps, tool usage and 3D modeling object information from the reference knowledge graph, generate detailed demonstration content for each step, including text descriptions, pictures, animations and possible interactive elements, and integrate all steps into several coherent reference demonstration plans, and the reference demonstration plan is composed of several different preset virtual surgical case demonstration plans; for each reference demonstration plan, obtain the key nodes and corresponding connection paths P in the demonstration plan of the relevant preset virtual surgical case, and search the key nodes and the corresponding connection paths P in the reference demonstration plan. If the key nodes and the corresponding connection paths P can be found in the reference demonstration plan, save this reference demonstration plan, otherwise filter out this reference demonstration plan.

[0009] Furthermore, step S400 includes: S401. Input the target feature T of the comprehensive virtual surgery case, extract the corresponding key feature L from the reference demonstration plan, calculate the similarity S(T, L) between the target feature T and the key feature L, and screen out the matching reference demonstration plans according to the similarity S(T, L) and the similarity threshold S1, and output the matching reference demonstration plans in descending order according to the similarity S(T, L), so as to obtain a reference demonstration plan list; S402. The relevant personnel receive a list of matching reference demonstration plans, and select a reference demonstration plan and determine whether the selected reference demonstration plan meets the requirements. If so, the reference demonstration plan will be used as a comprehensive demonstration plan. If not, the relevant personnel will make corresponding adjustments and use the adjusted reference demonstration plan as a comprehensive demonstration plan.

[0010] Although the present invention can automatically generate reference demonstration plans, the system also provides a flexible adjustment mechanism. Relevant personnel can adjust the selected reference demonstration plan according to actual needs to ensure that the final comprehensive demonstration plan fully meets the requirements of the actual surgical scene. This flexibility makes the system more adaptable to complex and changing surgical training needs.

[0011] A virtual surgery demonstration management system based on 3D modeling, the system includes: a data acquisition and processing module, a knowledge graph construction module, a key node identification module, a reference knowledge graph generation module and a comprehensive demonstration plan matching module; The data acquisition and feature extraction module retrieves preset virtual surgical cases and their historical demonstration plans from the database, extracts key features, and constructs a set of preset virtual surgical cases; the knowledge graph construction module generates a 3D modeling object knowledge graph for each preset virtual surgical case based on the extracted key features and 3D modeling object numbers, and establishes associations between nodes and edges; the key node identification module analyzes the knowledge graph of 3D modeling objects, identifies key nodes and their connection paths, calculates the importance evaluation index based on the node occurrence frequency and path complexity, and screens out key nodes; the reference knowledge graph generation module extracts global nodes from the knowledge graphs of all preset virtual surgical cases, calculates the similarity between nodes, uses a clustering algorithm to establish a reference knowledge graph, and generates a reference demonstration plan; the comprehensive demonstration plan matching module inputs the target features of the comprehensive virtual surgical cases, matches the reference demonstration plans, screens and sorts them according to the similarity, and generates a reference demonstration plan list for relevant personnel to select and adjust.

[0012] Further, the data acquisition and processing module includes a data retrieval unit, a feature extraction unit, and a 3D modeling object number association unit; The data retrieval unit retrieves all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extracts key features and 3D modeling object numbers, and constructs a preset virtual surgical case set; the feature extraction unit extracts key features from the historical demonstration plans and associates them with the corresponding historical demonstration plan numbers; the 3D modeling object number association unit associates the extracted key features with the 3D modeling object numbers to generate a preset virtual surgical case set; The knowledge graph construction module includes a knowledge graph generation unit and a knowledge graph filling unit; The knowledge graph generation unit generates a knowledge graph of the 3D modeling object based on the extracted key features and the 3D modeling object number; the knowledge graph filling unit fills the knowledge graph and establishes edges between nodes based on the features and 3D modeling object numbers provided in the historical demonstration plan.

[0013] Further, the key node identification module includes a node frequency calculation unit, an importance evaluation index calculation unit and a key node screening unit; The node frequency calculation unit calculates the frequency of occurrence of each node in the preset virtual surgical case; the importance evaluation index calculation unit calculates the connection path complexity of each node and comprehensively calculates the importance evaluation index of the node; the key node screening unit screens out the key nodes according to the importance evaluation index of the node, and summarizes and stores the key nodes and the corresponding connection paths.

[0014] Furthermore, the reference knowledge graph generation module includes a node similarity calculation unit, a node clustering unit, a reference knowledge graph construction unit, and a reference demonstration solution generation unit; The node similarity calculation unit calculates the attribute similarity and co-occurrence similarity between nodes in the global node set, and comprehensively calculates the node similarity; the node clustering unit clusters the global node set, marks the central node of each cluster, and establishes a mapping relationship between the nodes; the reference knowledge graph construction unit extracts nodes and connection relationships from the 3D modeling object knowledge graph of each preset virtual surgical case, generates a reference knowledge graph, calculates the similarity between nodes, adds new edges, and merges them according to the importance evaluation index; the reference demonstration plan generation unit finds the optimal path from the starting node to the target node in the reference knowledge graph, generates detailed demonstration content, and integrates demonstration plans for different virtual surgical cases.

[0015] Further, the comprehensive demonstration scheme matching module includes a feature matching unit, a reference demonstration scheme sorting unit, and a scheme selection and adjustment unit; The feature matching unit inputs the target features of the comprehensive virtual surgical case, calculates the similarity between the target features and the key features in the reference demonstration plan, and screens the matching reference demonstration plans; the reference demonstration plan sorting unit sorts the matching reference demonstration plans according to the similarity and generates a reference demonstration plan list; the relevant personnel of the plan selection and adjustment unit receive the reference demonstration plan list and select the plan that meets the requirements; if it does not meet the requirements, corresponding adjustments are made to form the final comprehensive demonstration plan.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention automatically extracts historical demonstration plans of preset virtual surgical cases from the database, constructs a knowledge graph, and then automatically associates and analyzes and generates reference demonstration plans, which greatly reduces the workload of manual configuration and adjustment, and improves the automation and intelligence level of the system; this enables faster and more accurate generation of demonstration plans when facing comprehensive virtual surgical cases, thereby improving overall efficiency and flexibility. When facing comprehensive virtual surgical cases, traditional systems often fail to fully utilize the connections between different cases to automatically generate comprehensive demonstration plans; however, the present invention can automatically generate demonstration plans that adapt to comprehensive surgical cases through cross-case node association analysis and knowledge graph fusion, without the need for manual configuration by professionals, thereby improving the adaptability and practicality of the system. The present invention automatically identifies key nodes in the knowledge graph of 3D modeling objects by calculating the importance evaluation index of the nodes, and stores the key nodes and corresponding connection paths; this method can accurately capture the core elements and key steps in the surgical case, providing an important basis for subsequent analysis and demonstration. After inputting the target features of the comprehensive virtual surgical case, the present invention can accurately match the corresponding reference demonstration plan based on similarity calculation, and arrange the output from large to small according to the similarity to help relevant personnel quickly find the most suitable demonstration plan. This matching mechanism improves the accuracy of the system and the user experience. In the association analysis process, the present invention not only considers the attribute similarity of the nodes, but also combines the node co-occurrence similarity to comprehensively calculate the node similarity; this comprehensive calculation method can more accurately reflect the similarity and degree of association between nodes, and provide a reliable basis for subsequent knowledge graph fusion and demonstration plan generation. By clustering the global node set through a clustering algorithm and adding new edges to the reference knowledge graph according to the node similarity, the present invention realizes the effective fusion of cross-case knowledge graphs; this fusion method can make full use of the similarities and differences between different cases to generate a richer and more complete reference knowledge graph. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of a module of a virtual surgery demonstration management system based on 3D modeling of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 , the present invention provides a technical solution: A virtual surgery demonstration management system based on 3D modeling, the system includes: a data acquisition and processing module, a knowledge graph construction module, a key node identification module, a reference knowledge graph generation module and a comprehensive demonstration plan matching module; The data acquisition and feature extraction module retrieves preset virtual surgical cases and their historical demonstration plans from the database, extracts key features, and constructs a set of preset virtual surgical cases; the knowledge graph construction module generates a 3D modeling object knowledge graph for each preset virtual surgical case based on the extracted key features and 3D modeling object numbers, and establishes associations between nodes and edges; the key node identification module analyzes the knowledge graph of 3D modeling objects, identifies key nodes and their connection paths, calculates the importance evaluation index based on the node occurrence frequency and path complexity, and screens out key nodes; the reference knowledge graph generation module extracts global nodes from the knowledge graphs of all preset virtual surgical cases, calculates the similarity between nodes, uses a clustering algorithm to establish a reference knowledge graph, and generates a reference demonstration plan; the comprehensive demonstration plan matching module inputs the target features of the comprehensive virtual surgical cases, matches the reference demonstration plans, screens and sorts them according to the similarity, and generates a reference demonstration plan list for relevant personnel to select and adjust.

[0020] The data acquisition and processing module includes a data retrieval unit, a feature extraction unit, and a 3D modeling object number association unit; The data retrieval unit retrieves all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extracts key features and 3D modeling object numbers, and constructs a preset virtual surgical case set; the feature extraction unit extracts key features from the historical demonstration plans and associates them with the corresponding historical demonstration plan numbers; the 3D modeling object number association unit associates the extracted key features with the 3D modeling object numbers to generate a preset virtual surgical case set; The knowledge graph construction module includes a knowledge graph generation unit and a knowledge graph filling unit; The knowledge graph generation unit generates a knowledge graph of the 3D modeling object based on the extracted key features and the 3D modeling object number; the knowledge graph filling unit fills the knowledge graph and establishes edges between nodes based on the features and 3D modeling object numbers provided in the historical demonstration plan.

[0021] The key node identification module includes a node frequency calculation unit, an importance evaluation index calculation unit and a key node screening unit; The node frequency calculation unit calculates the frequency of occurrence of each node in the preset virtual surgical case; the importance evaluation index calculation unit calculates the connection path complexity of each node and comprehensively calculates the importance evaluation index of the node; the key node screening unit screens out the key nodes according to the importance evaluation index of the node, and summarizes and stores the key nodes and the corresponding connection paths.

[0022] The reference knowledge graph generation module includes a node similarity calculation unit, a node clustering unit, a reference knowledge graph construction unit, and a reference demonstration solution generation unit; The node similarity calculation unit calculates the attribute similarity and co-occurrence similarity between nodes in the global node set, and comprehensively calculates the node similarity; the node clustering unit clusters the global node set, marks the central node of each cluster, and establishes a mapping relationship between the nodes; the reference knowledge graph construction unit extracts nodes and connection relationships from the 3D modeling object knowledge graph of each preset virtual surgical case, generates a reference knowledge graph, calculates the similarity between nodes, adds new edges, and merges them according to the importance evaluation index; the reference demonstration plan generation unit finds the optimal path from the starting node to the target node in the reference knowledge graph, generates detailed demonstration content, and integrates demonstration plans for different virtual surgical cases.

[0023] The comprehensive demonstration scheme matching module includes a feature matching unit, a reference demonstration scheme sorting unit, and a scheme selection and adjustment unit; The feature matching unit inputs the target features of the comprehensive virtual surgical case, calculates the similarity between the target features and the key features in the reference demonstration plan, and screens the matching reference demonstration plans; the reference demonstration plan sorting unit sorts the matching reference demonstration plans according to the similarity and generates a reference demonstration plan list; the relevant personnel of the plan selection and adjustment unit receive the reference demonstration plan list and select the plan that meets the requirements; if it does not meet the requirements, corresponding adjustments are made to form the final comprehensive demonstration plan.

[0024] A virtual surgery demonstration management method based on 3D modeling includes the following steps: Step S100. Obtain historical demonstration plans of preset virtual surgical cases from the database, extract key features from the historical demonstration plans, and construct a preset virtual surgical case set; combine the historical demonstration plans of the preset virtual surgical cases, and generate a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set; Step S200. Based on the knowledge graph of the 3D modeling object, the connection paths of all nodes in the knowledge graph are obtained, and the key nodes in the knowledge graph of the 3D modeling object are identified by analyzing the knowledge graph in combination with the preset virtual surgery case set, and the key nodes and the corresponding connection paths are stored in correspondence; Step S300. According to the key nodes and the corresponding connection paths, the knowledge graphs of the 3D modeling objects of different preset virtual surgery cases are subjected to association analysis, and a reference knowledge graph of the reference virtual surgery case and the corresponding 3D modeling object is generated according to the result of the association analysis, and a reference demonstration plan is generated according to the reference knowledge graph of the 3D modeling object; Step S400. Input the target features of the comprehensive virtual surgical case, analyze the target features with the key features in the preset virtual surgical case set, and match the corresponding reference demonstration plan according to the analysis results; output the reference demonstration plan to relevant personnel, who will analyze and process it accordingly to obtain a comprehensive demonstration plan for the comprehensive virtual surgical case.

[0025] Step S100 includes: S101. Retrieve all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extract key features from the historical demonstration plans, and one preset virtual surgical case corresponds to multiple different historical demonstration plans; the key features include information such as operation steps, tool use, surgical site and surgical environment; correspond the extracted key features to the corresponding historical demonstration plan numbers, and extract the corresponding 3D modeling object numbers from the historical demonstration plans, and construct a preset virtual surgical case set Av for each preset virtual surgical case, and Av={av1,av2,...,avn}, wherein av1 represents a data group consisting of the first historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, a2 represents a data group consisting of the second historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and so on, an represents a data group consisting of the nth historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and n represents the number of historical demonstration plans of the vth preset virtual surgical case; S102. Combined with the historical demonstration scheme of the preset virtual surgical case, for each element in the preset virtual surgical case set, according to the extracted key features and the corresponding 3D modeling object number, a knowledge graph of the corresponding 3D modeling object is generated, and the knowledge graph of the 3D modeling object uses the key features and the 3D modeling object as nodes, and the edges represent the relationship between different nodes. For example, there is an edge between node A (operation step 1) and node B (surgical site A), indicating that operation step 1 involves surgical site A; and the 3D modeling object number provided in the historical demonstration scheme is associated with its corresponding feature (such as tool use, operation step, etc.), and the knowledge graph of the 3D modeling object is filled, so as to generate a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set. For example, if the historical demonstration scheme number 1 uses tool A for operation step B, then in the knowledge graph, an edge should be established between the node "tool A" and the node "operation step B", indicating that "tool A" is used for "operation step B".

[0026] Step S200 includes: S201. For each preset virtual surgery case, extract all nodes and edges from the knowledge graph of the corresponding 3D modeling object, record the node set U and the edge set E, and the knowledge graph of the 3D modeling object is represented as a graph G=(U,E); use a graph traversal algorithm to traverse all nodes and edges in the knowledge graph of the 3D modeling object, so as to obtain all connection paths P from any node to other nodes, and the connection path P is represented as a node sequence, specifically: P=[u1,u2,...,uk], where u1 is the starting node, uk is the ending node, and u2 and subsequent other nodes are intermediate nodes; S202. Calculate the node occurrence frequency I corresponding to each preset virtual surgery case, and I=Mu / NP, where Mu represents the number of times node u appears in all connection paths P in the preset virtual surgery case, and NP represents the number of connection paths P corresponding to the preset virtual surgery case; analyze in combination with the preset virtual surgery case set, calculate the complexity F of the connection path P of the node corresponding to each preset virtual surgery case, and the specific calculation formula is: F(P)=(NuP+NeP) / NP, where NuP represents the total number of connection paths P corresponding to node u in the preset virtual surgery case, and NeP represents the total number of edges of the connection path P corresponding to node u in the preset virtual surgery case; combine the node occurrence frequency I and complexity F, and comprehensively calculate the node importance evaluation index R, and R=w1×I+w2×F, and w1 and w2 represent weight coefficients, and w1+w2=1; S203. Obtain the importance evaluation index R of all nodes corresponding to the preset virtual surgical case, and sort the nodes in descending order according to the importance evaluation index R, select the first m nodes as key nodes, and summarize and store the key nodes and the corresponding connection paths P.

[0027] Step S300 includes: S301. Extract all unique nodes from the knowledge graph of 3D modeling objects of all preset virtual surgical cases to form a global node set N_global; for any two nodes ni and nj in the global node set, combine the knowledge graph of the 3D modeling objects of the corresponding preset virtual surgical cases to calculate the node attribute similarity S(ni,nj) between the two, and Sa(ni,nj)=(Ai·Aj) / |Ai|||Aj|, ​​where Ai and Aj represent the attribute vectors of nodes ni and nj respectively; based on the global node set N_glob The node co-occurrence similarity Sc(ni,nj) is calculated based on the co-occurrence of each node in al in different cases, and Sc(ni,nj)=Cij / (Ci·Cj)^(1 / 2), where Cij represents the number of times nodes ni and nj appear at the same time, and Ci and Cj represent the total number of times nodes ni and nj appear respectively; the node similarity S(ni,nj) is calculated based on the comprehensive attribute similarity and co-occurrence similarity, and S(ni,nj)=α·Sa(ni,nj)+(1-α)·Sc(ni,nj), where α represents the weight coefficient; In this embodiment, the acquisition process of Ai and Aj is as follows: extract the attributes of the nodes from the 3D modeling object knowledge graph of each preset virtual surgical case. These attributes may include the category, function, position, shape, size, etc. of the node; create an attribute vector Ai and Aj for each node; the attribute vector can be a numerical vector, in which each element corresponds to a certain characteristic value or attribute of the node; if the attribute of the node is discrete (such as a category label), it can be represented by one-hot encoding; if the attribute is continuous (such as size), the value can be used directly; the attribute vector is standardized to ensure that the scale of all attributes is consistent, and normalization (such as minimum-maximum normalization) or standardization (such as z-score normalization) can be used.

[0028] S302. Use a clustering algorithm to cluster the global node set, classify nodes with equal similarity into a cluster class, and mark the central node of each cluster; for the nodes in each cluster, find their corresponding nodes in different preset virtual surgical cases and establish a mapping relationship; initialize an empty reference knowledge graph Gref, for each cluster, copy the nodes and their connection relationships contained in it from the knowledge graph G of the corresponding 3D modeling object to the reference knowledge graph Gref, and add new edges En by calculating the similarity of cross-case nodes, and the corresponding judgment expression is: En=(ni,nj)|S(ni,nj)>S0, where S0 represents the corresponding similarity threshold; if there are two or more nodes from different virtual surgical cases mapped to the same position in the reference knowledge graph Gref, they are merged according to the importance evaluation index R in step S202; S303. Use a graph search algorithm to find several optimal paths from the starting node to the target node in the reference knowledge graph, and extract relevant operation steps, tool usage and 3D modeling object information from the reference knowledge graph, generate detailed demonstration content for each step, including text descriptions, pictures, animations and possible interactive elements, and integrate all steps into several coherent reference demonstration plans, and the reference demonstration plan is composed of several different preset virtual surgical case demonstration plans; for each reference demonstration plan, obtain the key nodes and corresponding connection paths P in the demonstration plan of the relevant preset virtual surgical case, and search the key nodes and the corresponding connection paths P in the reference demonstration plan. If the key nodes and the corresponding connection paths P can be found in the reference demonstration plan, save this reference demonstration plan, otherwise filter out this reference demonstration plan.

[0029] Step S400 includes: S401. Input the target feature T of the comprehensive virtual surgery case, extract the corresponding key feature L from the reference demonstration plan, calculate the similarity S(T, L) between the target feature T and the key feature L, and screen out the matching reference demonstration plans according to the similarity S(T, L) and the similarity threshold S1, and output the matching reference demonstration plans in descending order according to the similarity S(T, L), so as to obtain a reference demonstration plan list; S402. The relevant personnel receive a list of matching reference demonstration plans, and select a reference demonstration plan and determine whether the selected reference demonstration plan meets the requirements. If so, the reference demonstration plan will be used as a comprehensive demonstration plan. If not, the relevant personnel will make corresponding adjustments and use the adjusted reference demonstration plan as a comprehensive demonstration plan.

[0030] Although the present invention can automatically generate reference demonstration plans, the system also provides a flexible adjustment mechanism. Relevant personnel can adjust the selected reference demonstration plan according to actual needs to ensure that the final comprehensive demonstration plan fully meets the requirements of the actual surgical scene. This flexibility makes the system more adaptable to complex and changing surgical training needs.

[0031] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0032] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A virtual surgery demonstration management method based on 3D modeling, characterized by: The method comprises the following steps: Step S100. Obtain historical demonstration plans of preset virtual surgical cases from the database, extract key features from the historical demonstration plans, and construct a preset virtual surgical case set; combine the historical demonstration plans of the preset virtual surgical cases, and generate a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set; Step S200. Based on the knowledge graph of the 3D modeling object, the connection paths of all nodes in the knowledge graph are obtained, and the key nodes in the knowledge graph of the 3D modeling object are identified by analyzing the knowledge graph in combination with the preset virtual surgery case set, and the key nodes and the corresponding connection paths are stored in correspondence; Step S300. According to the key nodes and the corresponding connection paths, the knowledge graphs of the 3D modeling objects of different preset virtual surgery cases are subjected to association analysis, and a reference knowledge graph of the reference virtual surgery case and the corresponding 3D modeling object is generated according to the result of the association analysis, and a reference demonstration plan is generated according to the reference knowledge graph of the 3D modeling object; Step S400. Input the target features of the comprehensive virtual surgical case, analyze the target features with the key features in the preset virtual surgical case set, and match the corresponding reference demonstration plan according to the analysis results; output the reference demonstration plan to relevant personnel, who will analyze and process it accordingly to obtain a comprehensive demonstration plan for the comprehensive virtual surgical case.

2. The method for managing virtual surgery demonstration based on 3D modeling according to claim 1, characterized in that: The step S100 includes: S101. Retrieve all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extract key features from the historical demonstration plans, and one preset virtual surgical case corresponds to multiple different historical demonstration plans; correspond the extracted key features to the corresponding historical demonstration plan numbers, and extract the corresponding 3D modeling object numbers from the historical demonstration plans, and construct a preset virtual surgical case set Av for each preset virtual surgical case, and Av={av1,av2,...,avn}, wherein av1 represents a data group consisting of the first historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, a2 represents a data group consisting of the second historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and so on, an represents a data group consisting of the nth historical demonstration plan number, the corresponding key features and the 3D modeling object number of the vth preset virtual surgical case, and n represents the number of historical demonstration plans for the vth preset virtual surgical case; S102. In combination with the historical demonstration plan of the preset virtual surgical case, for each element in the preset virtual surgical case set, a knowledge graph of the corresponding 3D modeling object is generated according to the extracted key features and the corresponding 3D modeling object numbers, and the knowledge graph of the 3D modeling object uses the key features and the 3D modeling objects as nodes, and the edges represent the relationship between different nodes. The 3D modeling object numbers provided in the historical demonstration plan are associated with their corresponding features, and the knowledge graph of the 3D modeling object is filled, thereby generating a knowledge graph of the corresponding 3D modeling object for each element in the preset virtual surgical case set.

3. The method for managing virtual surgery demonstration based on 3D modeling according to claim 1, characterized in that: The step S200 includes: S201. For each preset virtual surgery case, extract all nodes and edges from the knowledge graph of the corresponding 3D modeling object, record the node set U and the edge set E, and the knowledge graph of the 3D modeling object is represented as a graph G=(U,E); use a graph traversal algorithm to traverse all nodes and edges in the knowledge graph of the 3D modeling object, so as to obtain all connection paths P from any node to other nodes, and the connection path P is represented as a node sequence, specifically: P=[u1,u2,...,uk], where u1 is the starting node, uk is the ending node, and u2 and subsequent other nodes are intermediate nodes; S202. Calculate the node occurrence frequency I corresponding to each preset virtual surgery case, and I=Mu / NP, where Mu represents the number of times node u appears in all connection paths P in the preset virtual surgery case, and NP represents the number of connection paths P corresponding to the preset virtual surgery case; analyze in combination with the preset virtual surgery case set, calculate the complexity F of the connection path P of the node corresponding to each preset virtual surgery case, and the specific calculation formula is: F(P)=(NuP+NeP) / NP, where NuP represents the total number of connection paths P corresponding to node u in the preset virtual surgery case, and NeP represents the total number of edges of the connection path P corresponding to node u in the preset virtual surgery case; combine the node occurrence frequency I and complexity F, and comprehensively calculate the node importance evaluation index R, and R=w1×I+w2×F, and w1 and w2 represent weight coefficients, and w1+w2=1; S203. Obtain the importance evaluation index R of all nodes corresponding to the preset virtual surgical case, and sort the nodes in descending order according to the importance evaluation index R, select the first m nodes as key nodes, and summarize and store the key nodes and the corresponding connection paths P.

4. The method for managing virtual surgery demonstration based on 3D modeling according to claim 3, characterized in that: The step S300 includes: S301. Extract all unique nodes from the knowledge graph of 3D modeling objects of all preset virtual surgical cases to form a global node set N_global; for any two nodes ni and nj in the global node set, combine the knowledge graph of the 3D modeling objects of the corresponding preset virtual surgical cases to calculate the node attribute similarity S(ni,nj) between the two, and Sa(ni,nj)=(Ai·Aj) / |Ai|||Aj|, ​​where Ai and Aj represent the attribute vectors of nodes ni and nj respectively; based on the global node set N_glob The node co-occurrence similarity Sc(ni,nj) is calculated based on the co-occurrence of each node in al in different cases, and Sc(ni,nj)=Cij / (Ci·Cj)^(1 / 2), where Cij represents the number of times nodes ni and nj appear at the same time, and Ci and Cj represent the total number of times nodes ni and nj appear respectively; the node similarity S(ni,nj) is calculated based on the comprehensive attribute similarity and co-occurrence similarity, and S(ni,nj)=α·Sa(ni,nj)+(1-α)·Sc(ni,nj), where α represents the weight coefficient; S302. Use a clustering algorithm to cluster the global node set, classify nodes with equal similarity into a cluster class, and mark the central node of each cluster; for the nodes in each cluster, find their corresponding nodes in different preset virtual surgical cases and establish a mapping relationship; initialize an empty reference knowledge graph Gref, for each cluster, copy the nodes and their connection relationships contained in it from the knowledge graph G of the corresponding 3D modeling object to the reference knowledge graph Gref, and add new edges En by calculating the similarity of cross-case nodes, and the corresponding judgment expression is: En=(ni,nj)|S(ni,nj)>S0, where S0 represents the corresponding similarity threshold; if there are two or more nodes from different virtual surgical cases mapped to the same position in the reference knowledge graph Gref, they are merged according to the importance evaluation index R in step S202; S303. Use a graph search algorithm to find several optimal paths from the starting node to the target node in the reference knowledge graph, and extract relevant operation steps, tool usage and 3D modeling object information from the reference knowledge graph, generate detailed demonstration content for each step, and integrate all steps into several coherent reference demonstration plans, and the reference demonstration plan is composed of several different preset virtual surgical case demonstration plans; for each reference demonstration plan, obtain the key nodes and corresponding connection paths P in the demonstration plan of the relevant preset virtual surgical case, and search the key nodes and the corresponding connection paths P in the reference demonstration plan. If the key nodes and the corresponding connection paths P can be found in the reference demonstration plan, save this reference demonstration plan, otherwise filter out this reference demonstration plan.

5. The method for managing virtual surgery demonstration based on 3D modeling according to claim 1, characterized in that: The step S400 includes: S401. Input the target feature T of the comprehensive virtual surgery case, extract the corresponding key feature L from the reference demonstration plan, calculate the similarity S(T, L) between the target feature T and the key feature L, and screen out the matching reference demonstration plans according to the similarity S(T, L) and the similarity threshold S1, and output the matching reference demonstration plans in descending order according to the similarity S(T, L), so as to obtain a reference demonstration plan list; S402. The relevant personnel receive a list of matching reference demonstration plans, and select a reference demonstration plan and determine whether the selected reference demonstration plan meets the requirements. If so, the reference demonstration plan will be used as a comprehensive demonstration plan. If not, the relevant personnel will make corresponding adjustments and use the adjusted reference demonstration plan as a comprehensive demonstration plan.

6. A virtual surgery demonstration management system based on 3D modeling, applied to a virtual surgery demonstration management method based on 3D modeling as claimed in any one of claims 1 to 5, characterized in that: The system includes: a data collection and processing module, a knowledge graph construction module, a key node identification module, a reference knowledge graph generation module and a comprehensive demonstration solution matching module; The data acquisition and feature extraction module retrieves preset virtual surgical cases and their historical demonstration plans from the database, extracts key features, and constructs a set of preset virtual surgical cases; the knowledge graph construction module generates a 3D modeling object knowledge graph for each preset virtual surgical case based on the extracted key features and 3D modeling object numbers, and establishes associations between nodes and edges; the key node identification module analyzes the knowledge graph of the 3D modeling object, identifies key nodes and their connection paths, calculates the importance evaluation index based on the node occurrence frequency and path complexity, and filters out key nodes; the reference knowledge graph generation module extracts global nodes from the knowledge graphs of all preset virtual surgical cases, calculates the similarity between nodes, uses a clustering algorithm to establish a reference knowledge graph, and generates a reference demonstration plan; the comprehensive demonstration plan matching module inputs the target features of the comprehensive virtual surgical case, matches the reference demonstration plan, filters and sorts according to the similarity, and generates a reference demonstration plan list for relevant personnel to select and adjust.

7. The virtual surgery demonstration management system based on 3D modeling according to claim 6, characterized in that: The data acquisition and processing module includes a data retrieval unit, a feature extraction unit, and a 3D modeling object number association unit; The data retrieval unit retrieves all preset virtual surgical cases and their corresponding historical demonstration plans from the database, extracts key features and 3D modeling object numbers, and constructs a preset virtual surgical case set; the feature extraction unit extracts key features from the historical demonstration plans and associates them with the corresponding historical demonstration plan numbers; the 3D modeling object number association unit associates the extracted key features with the 3D modeling object numbers to generate a preset virtual surgical case set; The knowledge graph construction module includes a knowledge graph generation unit and a knowledge graph filling unit; The knowledge graph generation unit generates a knowledge graph of the 3D modeling object based on the extracted key features and the 3D modeling object number; the knowledge graph filling unit fills the knowledge graph and establishes edges between nodes based on the features and 3D modeling object numbers provided in the historical demonstration plan.

8. The virtual surgery demonstration management system based on 3D modeling according to claim 6, characterized in that: The key node identification module includes a node frequency calculation unit, an importance evaluation index calculation unit and a key node screening unit; The node frequency calculation unit calculates the frequency of occurrence of each node in a preset virtual surgery case; the importance evaluation index calculation unit calculates the connection path complexity of each node and comprehensively calculates the importance evaluation index of the node; The key node screening unit screens out key nodes according to the node importance evaluation index, and summarizes and stores the key nodes and corresponding connection paths.

9. The virtual surgery demonstration management system based on 3D modeling according to claim 1, characterized in that: The reference knowledge graph generation module includes a node similarity calculation unit, a node clustering unit, a reference knowledge graph construction unit and a reference demonstration solution generation unit; The node similarity calculation unit calculates the attribute similarity and co-occurrence similarity between the nodes in the global node set, and comprehensively calculates the node similarity; the node clustering unit clusters the global node set, marks the central node of each cluster, and establishes a mapping relationship between the nodes; The reference knowledge graph construction unit extracts nodes and connection relationships from the 3D modeling object knowledge graph of each preset virtual surgical case, generates a reference knowledge graph, calculates the similarity between nodes, adds new edges, and merges them according to the importance evaluation index; the reference demonstration plan generation unit finds the optimal path from the starting node to the target node in the reference knowledge graph, generates detailed demonstration content, and integrates demonstration plans of different virtual surgical cases.

10. The virtual surgery demonstration management system based on 3D modeling according to claim 1, characterized in that: The comprehensive demonstration scheme matching module includes a feature matching unit, a reference demonstration scheme sorting unit, and a scheme selection and adjustment unit; The feature matching unit inputs the target features of the comprehensive virtual surgery case, calculates the similarity between the target features and the key features in the reference demonstration scheme, and screens the matching reference demonstration scheme; The reference demonstration scheme sorting unit sorts the matched reference demonstration schemes according to the similarity and generates a reference demonstration scheme list; the relevant personnel of the scheme selection and adjustment unit receive the reference demonstration scheme list and select a scheme that meets the requirements; If it does not meet the requirements, corresponding adjustments will be made to form a final comprehensive demonstration plan.

Images