Medical diagnosis guide method and system based on knowledge graph

Abstract

The invention provides a medical diagnosis guide method and system based on a knowledge graph. According to the method, physical sign data of emergency orthopedic patients and processing precision data of orthopedic implants are obtained, the physical sign data and the processing precision data comprise dimensional tolerance, surface roughness, material strength and other parameters, the physical sign data and the processing precision data are subjected to multi-modal association according to fracture types, and a dynamic knowledge graph containing patient skeleton features, implant processing precision and inventory state nodes is constructed; and a dynamic priority queue is set. And based on the dynamic knowledge graph, matching the fracture characteristics of the patient with the precision requirement of the implant, and generating a hospital guide path set covering the surgical plan compatibility, the resource topological relation and the postoperative risk prediction. And when the implant processing precision or the inventory state changes, the system triggers priority queue reconstruction, and the hospital guide path set information is updated in real time. According to the technical scheme provided by the invention, the efficiency and precision of medical diagnosis guide can be improved.

Description

Technical Field

[0001] This application relates to the technical field of medical guidance, and particularly to a medical guidance method and system based on a knowledge graph. Background Art

[0002] In the field of emergency orthopedics, it is crucial to quickly and accurately develop personalized surgical plans for patients. Due to the high individual differences in physical sign data such as fracture types and skeletal geometric features of each patient, and the fact that the processing precision of orthopedic implants (such as dimensional tolerances, surface roughness, and material strength) directly affects the surgical effect and postoperative recovery, a method that can comprehensively consider the above factors is needed. By obtaining and analyzing the physical sign data of patients and the processing precision data of implants, and performing multimodal association of this information according to fracture types, a dynamic knowledge graph can be generated. This not only helps doctors comprehensively understand the patient's condition, but also enables them to optimize the surgical plan based on real-time updated data, improve the treatment effect, and reduce the risk of postoperative complications.

[0003] Currently, in emergency orthopedics, traditional methods based on experience are usually adopted to select suitable orthopedic implants for patients and develop surgical plans, combining imaging examinations and doctors' professional judgments to select appropriate treatment plans and orthopedic implants. This method first obtains information on the patient's fracture type and skeletal geometric features through imaging techniques such as X-rays and computed tomography scans, and then doctors decide on the most suitable surgical method and implant based on this information and their own experience. In addition, some advanced medical institutions have begun to use electronic health record systems to assist this process, which can integrate multi-source data such as the patient's medical records and test results to provide doctors with more comprehensive information support. At the same time, some hospitals have also introduced preliminary decision support tools that use algorithms to analyze this data and make suggestions to help doctors develop reasonable surgical plans more quickly. These measures have improved the diagnosis and treatment efficiency and accuracy, enabling patients to receive more precise treatment.

[0004] The existing solutions mainly have three deficiencies: First, the traditional decision-making method relies too much on doctors' personal experience and judgment, resulting in large differences in the selection of treatment plans among different doctors, which affects the consistency and quality of treatment; Second, the existing systems and decision support tools have not fully integrated the processing precision data of orthopedic implants, limiting their effectiveness in developing personalized surgical plans; Finally, due to the lack of a dynamic adjustment mechanism, the existing solutions are difficult to update the recommended treatment path in a timely manner according to the latest inventory status or changes in the processing precision of implants, which may lead to resource waste or delay in the best treatment opportunity. These problems urgently require a more intelligent and dynamically adjustable solution to overcome. Summary of the Invention

[0005] An embodiment of the present application provides a medical guidance method and system based on a knowledge graph to solve the problems of low efficiency and poor accuracy in medical guidance in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a medical guidance method based on a knowledge graph, including:

[0007] Obtain the physical sign data of emergency orthopedic patients and the processing precision data of orthopedic implants. The processing precision data of orthopedic implants includes a dynamically updated dimensional tolerance sequence, surface roughness distribution, and material strength fluctuation parameters;

[0008] Perform multimodal association on the physical sign data of the emergency orthopedic patients and the processing precision data of the orthopedic implants according to the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph. The emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and construct a dynamic priority queue between the nodes;

[0009] Traverse the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, match the intersection range of the patient's fracture characteristics and the implant processing precision constraint nodes, and generate a set of guidance paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters;

[0010] According to the fluctuations in the processing precision data of orthopedic implants collected in real time and the changes in the status of the emergency inventory nodes, trigger the reconstruction mechanism of the dynamic priority queue, and synchronously update the surgical plan compatibility parameters and alternative resource topological relationships in the set of guidance paths.

[0011] Optionally, the traversing the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, matching the intersection range of the patient's fracture characteristics and the implant processing precision constraint nodes, and generating a set of guidance paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters includes:

[0012] Perform multi-level traversal on the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue to identify the spatial matching pattern between the patient bone geometric feature nodes and the implant processing precision constraint nodes;

[0013] Calculate the surgical plan compatibility parameters according to the spatial matching pattern. The surgical plan compatibility parameters include implant dimensional tolerance coverage, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient;

[0014] Construct an alternative resource topological relationship based on the inventory availability status nodes. The alternative resource topological relationship includes a cross-hospital inventory distribution map and a real-time production capacity link of processing equipment;

[0015] Integrate the surgical plan compatibility parameters with the alternative resource topological relationship to generate a set of guiding diagnosis paths including the prediction of postoperative fretting wear probability and infection risk correlation factors.

[0016] Optionally, the calculation of the surgical plan compatibility parameters according to the spatial matching mode includes:

[0017] Based on the spatial matching mode, evaluate the geometric matching degree of the implant size tolerance coverage, and the geometric matching degree evaluation includes the curvature adaptation parameter of the bone contact surface and the alignment deviation parameter of the implant edge;

[0018] Generate a surface roughness tolerance threshold according to the curvature adaptation parameter of the bone contact surface, and the surface roughness tolerance threshold is evaluated multi-dimensionally through the dynamic contact surface friction coefficient and the fretting displacement tolerance range;

[0019] Combine the implant edge alignment deviation parameter with the dynamic contact surface friction coefficient to calculate the material strength fluctuation adaptation coefficient, and the material strength fluctuation adaptation coefficient includes the stress distribution uniformity parameter and the fatigue life attenuation correlation factor;

[0020] Take the geometric matching degree evaluation, the surface roughness tolerance threshold, and the material strength fluctuation adaptation coefficient as the surgical plan compatibility parameters.

[0021] Optionally, the multi-modal association of the emergency orthopedic patient sign data and the orthopedic implant processing accuracy data in the dimension of fracture type to generate an emergency orthopedic dynamic knowledge graph, the emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing accuracy constraint nodes, and inventory availability status nodes, and construct a dynamic priority queue between nodes, including:

[0022] Input the emergency orthopedic patient sign data into a deep learning model to extract bone geometric features, and generate a multi-dimensional feature vector including fracture type classification labels, bone morphology parameters, and biomechanical properties;

[0023] Construct an implant parameter map through the orthopedic implant processing accuracy data, and the orthopedic implant processing accuracy data includes size tolerance sequences, surface roughness distributions, and material strength fluctuation parameters;

[0024] Align the multi-dimensional feature vector with the implant parameter map through the fracture type classification label, and use a graph neural network to establish an emergency orthopedic dynamic knowledge graph including patient bone geometric feature nodes, implant processing accuracy constraint nodes, and inventory availability status nodes;

[0025] Construct a priority queue among nodes based on dynamic weight parameters, where the dynamic weight parameters include the weight of the patient's bone geometry feature nodes, the weight of the implant processing precision constraint nodes, and the weight of the inventory availability status nodes.

[0026] Optionally, constructing the implant parameter atlas through the orthopedic implant processing precision data includes:

[0027] Input the orthopedic implant processing precision data into a multi-modal feature parsing module to generate a processing precision feature set including a tolerance constraint vector and a roughness distribution matrix;

[0028] Based on a graph embedding algorithm, perform topological modeling on the processing precision feature set to construct an initial parameter atlas including tolerance constraint nodes and roughness distribution nodes, where the tolerance constraint nodes establish edge connection relationships through the similarity of tolerance fluctuation patterns, and the roughness distribution nodes establish edge connection relationships through the correlation of spatial gradient features;

[0029] Use a dynamic atlas optimization module to iteratively update the initial parameter atlas, perform tolerance constraint grouping based on a hierarchical clustering algorithm, and perform roughness distribution partitioning based on a region growing algorithm;

[0030] Based on the updated initial parameter atlas, generate an implant parameter atlas including a tolerance constraint rule chain and a roughness matching rule tree through a knowledge graph rule engine, where the tolerance constraint rule chain includes the allowable deviation thresholds of the tolerance constraint grouping, and the roughness matching rule tree includes the adaptation relationship between the roughness distribution partitioning and the implant contact surface.

[0031] Optionally, according to the fluctuations in the orthopedic implant processing precision data collected in real time and the changes in the emergency inventory node status, trigger the reconstruction mechanism of the dynamic priority queue, and synchronously update the surgical plan compatibility parameters and the alternative resource topological relationship in the navigation path set, including:

[0032] Use a streaming data processing engine to capture the fluctuations in the orthopedic implant processing precision data and the changes in the emergency inventory node status in real time, and generate a real-time feature set including a tolerance fluctuation index, a roughness offset matrix, and an inventory decay factor;

[0033] Based on an event-driven model, perform anomaly detection on the real-time feature set. When the tolerance fluctuation index exceeds a preset threshold, the gradient change rate of the roughness offset matrix exceeds a critical value, or the inventory decay factor triggers a warning line, activate the reconstruction mechanism of the dynamic priority queue;

[0034] According to the reconstruction mechanism, the node weights of the dynamic priority queue are updated using an adaptive weight allocation algorithm, the priority weights of the orthopedic implant processing precision constraint nodes are adjusted according to the tolerance fluctuation index, the spatial correlation degree of the inventory availability status nodes is corrected based on the gradient direction of the roughness offset matrix, and the biomechanical adaptability of the patient bone geometric feature nodes is dynamically attenuated and compensated in combination with the inventory decay factor;

[0035] The updated dynamic priority queue is mapped to the emergency orthopedics dynamic knowledge graph, and the surgical plan compatibility parameters and alternative resource topological relationships in the navigation path set are synchronously updated.

[0036] Optionally, according to the reconstruction mechanism, the node weights of the dynamic priority queue are updated using an adaptive weight allocation algorithm, the priority weights of the orthopedic implant processing precision constraint nodes are adjusted according to the tolerance fluctuation index, the spatial correlation degree of the inventory availability status nodes is corrected based on the gradient direction of the roughness offset matrix, and the biomechanical adaptability of the patient bone geometric feature nodes is dynamically attenuated and compensated in combination with the inventory decay factor, including:

[0037] Based on the reconstruction mechanism, the tolerance fluctuation index, roughness offset matrix, and inventory decay factor are loaded through a multimodal weight initialization module to generate a dynamic parameter set;

[0038] The orthopedic implant processing precision constraint nodes in the dynamic parameter set are grouped according to tolerance fluctuations, and the offset of the priority weight base value is adjusted according to the range distribution of the tolerance fluctuation index within the tolerance fluctuation group to generate a dynamic weight sequence of the orthopedic implant processing precision constraint nodes;

[0039] The spatial correlation degree of the inventory availability status nodes is gradient-corrected, a spatial correlation degree correction coefficient is generated according to the gradient direction of the roughness offset matrix, and an association degree compensation threshold is generated in combination with the time-series attenuation mode of the inventory decay factor;

[0040] The biomechanical adaptability of the patient bone geometric feature nodes is iteratively updated through a dynamic attenuation compensation model to generate biomechanical adaptability parameters including dynamic attenuation compensation values;

[0041] The dynamic weight sequence, association degree compensation threshold, and biomechanical adaptability parameters are synchronously input into the dynamic priority queue to update the node weights of the dynamic priority queue.

[0042] In a second aspect, an embodiment of the present application provides a medical navigation system based on a knowledge graph, including:

[0043] An acquisition module that acquires the physical sign data of emergency orthopedic patients and the orthopedic implant processing precision data, where the orthopedic implant processing precision data includes a dynamically updated dimensional tolerance sequence, a surface roughness distribution, and a material strength fluctuation parameter;

[0044] An association module that multimodally associates the physical sign data of the emergency orthopedic patients with the orthopedic implant processing precision data according to the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph. The emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and constructs a dynamic priority queue among the nodes;

[0045] A matching module that traverses the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue to match the intersection range between the patient's fracture features and the implant processing precision constraint nodes, and generates a set of guiding paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters;

[0046] An update module that triggers the reconstruction mechanism of the dynamic priority queue according to the fluctuations of the orthopedic implant processing precision data collected in real time and the changes in the status of the emergency inventory nodes, and synchronously updates the surgical plan compatibility parameters and alternative resource topological relationships in the set of guiding paths.

[0047] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a medical guiding method based on a knowledge graph as described in the first aspect above.

[0048] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements a medical guiding method based on a knowledge graph as described in the first aspect.

[0049] In the embodiments of the present application, the physical sign data of emergency orthopedic patients and the processing precision data of orthopedic implants are obtained. The processing precision data of orthopedic implants includes a dynamically updated dimensional tolerance sequence, a surface roughness distribution, and a material strength fluctuation parameter. The physical sign data of the emergency orthopedic patients and the processing precision data of the orthopedic implants are multi-modally associated according to the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph. The emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and a dynamic priority queue between the nodes is constructed. Based on the dynamic priority queue, the emergency orthopedic dynamic knowledge graph is traversed to match the intersection range between the patient fracture characteristics and the implant processing precision constraint nodes, and a set of guiding paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters is generated. According to the fluctuations in the processing precision data of orthopedic implants collected in real time and the changes in the status of the emergency inventory nodes, the reconstruction mechanism of the dynamic priority queue is triggered, and the surgical plan compatibility parameters and alternative resource topological relationships in the set of guiding paths are synchronously updated.

[0050] The technical solution of the present application has the following beneficial effects:

[0051] In the present application, by obtaining the physical sign data of emergency orthopedic patients and the processing precision data of orthopedic implants, and performing multi-modal association based on the fracture type, a dynamic knowledge graph is generated. This approach not only greatly improves the accuracy and efficiency of surgical plan formulation but also provides personalized treatment suggestions according to the specific conditions of patients. This method integrates information such as patient bone geometric features, implant processing precision, and inventory status within a framework, achieving effective allocation and utilization of resources. In addition, the construction of a dynamic priority queue enables the system to quickly respond to changes and update the set of guiding paths in a timely manner, ensuring the continuity and efficiency of medical services. This not only improves patient satisfaction but also reduces the workload of medical staff.

[0052] Furthermore, through multi-level traversal of the emergency orthopedic dynamic knowledge graph, the spatial matching pattern between the patient bone geometric features and the implant processing precision constraint nodes is identified, thereby accurately calculating the surgical plan compatibility parameters. This method takes into account multiple key factors such as implant dimensional tolerance coverage, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient, providing detailed data support for doctors and helping to improve the success rate of surgery. At the same time, the establishment of alternative resource topological relationships not only covers the cross-hospital inventory distribution but also includes the real-time production capacity link of processing equipment, ensuring the optimal allocation of resources. Combining the above analysis, a set of guiding paths including postoperative risk prediction is finally generated, effectively reducing the surgical risk and optimizing the patient treatment process.

[0053] Furthermore, when calculating the surgical plan compatibility parameters, this method deeply analyzes the geometric matching degree evaluation, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient under the spatial matching mode. By carefully considering factors such as the curvature adaptation parameter of the bone contact surface and the alignment deviation parameter of the implant edge, as well as their interactions, this method can accurately evaluate the fitting degree between the implant and the patient's bone. This method not only takes into account static geometric matching but also introduces variables such as dynamic friction coefficient and micro-movement displacement tolerance range, making the evaluation results closer to the actual situation. Therefore, it provides a solid theoretical basis for the selection of surgical plans, significantly improves the safety and effectiveness of surgeries, and also enhances the patient's confidence in the surgical results.

[0054] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0056] Figure 1 Shows a flowchart of a medical guidance method based on a knowledge graph provided by the present application;

[0057] Figure 2 Shows a schematic structural diagram of a medical guidance system based on a knowledge graph provided by the present application;

[0058] Figure 3 Shows a schematic structural diagram of a computing device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0060] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations can be performed not in the order in which they appear herein or in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations can be performed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0061] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0062] Figure 1 The flowchart of a medical guidance method based on a knowledge graph provided for an embodiment of the present application is as Figure 1 shown, and the method includes:

[0063] 101. Obtain the physical sign data of emergency orthopedic patients and the processing precision data of orthopedic implants. The processing precision data of the orthopedic implants includes a dynamically updated dimensional tolerance sequence, surface roughness distribution, and material strength fluctuation parameters;

[0064] In this step, obtaining the physical sign data of emergency orthopedic patients and the processing precision data of orthopedic implants is the first step of this method. Here, the physical sign data of the patient includes information such as fracture type and bone geometric characteristics, which is used to comprehensively understand the patient's health status and specific needs. The processing precision data of the orthopedic implants includes dimensional tolerance sequence, surface roughness distribution, material strength fluctuation parameters, etc. These data reflect the quality and applicability of the implants, ensuring the selection of the most suitable implants for the patient.

[0065] In an embodiment of the application, a patient with a complex fracture caused by a traffic accident is sent to the emergency room. The doctor quickly arranges a computed tomography scan and uploads the results to the system. At the same time, the system also automatically synchronizes the latest processing precision data of relevant implants in the hospital inventory, providing detailed basic information for the subsequent steps.

[0066] 102. Multimodally correlate the physical sign data of the emergency orthopedic patients with the processing precision data of the orthopedic implants in terms of the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph. The emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and construct a dynamic priority queue among the nodes;

[0067] In this step, the physical sign data of the patient is multimodally correlated with the implant processing precision data in terms of the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph. This graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and constructs a dynamic priority queue among these nodes to facilitate quickly finding the optimal solution.

[0068] In the application embodiment, based on previous cases, the system analyzed the patient's fracture type and matched it with the implants in the existing inventory. The results showed that a specific type of titanium alloy plate not only met the patient's bone geometric features, but also its latest processing precision was within the acceptable range. Subsequently, the system automatically generated a priority list and recommended several most suitable surgical plans.

[0069] 103. Traverse the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, match the intersection range of the patient's fracture features and the implant processing precision constraint nodes, and generate a set of guiding diagnosis paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters;

[0070] In this step, traverse the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, match the intersection range of the patient's fracture features and the implant processing precision constraint nodes, thereby generating a set of guiding diagnosis paths. This set includes surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters, providing a basis for formulating the final surgical plan.

[0071] In the application embodiment, continuing from the previous case, the system analyzed several recommended implants in detail according to the priority queue, and determined a plan that could meet the patient's fracture repair needs and ensure long-term stability. In addition, the system also considered the inventory situation of other hospitals and proposed alternative plans for cross-hospital deployment to ensure the smooth progress of the surgery.

[0072] 104. According to the fluctuations of the orthopedic implant processing precision data collected in real time and the changes in the status of the emergency inventory nodes, trigger the reconstruction mechanism of the dynamic priority queue, and synchronously update the surgical plan compatibility parameters and alternative resource topological relationships in the set of guiding diagnosis paths.

[0073] In this step, according to the fluctuations in the processing accuracy data of orthopedic implants collected in real time and the changes in the status of emergency inventory nodes, a reconstruction mechanism for the dynamic priority queue is triggered, and the surgical plan compatibility parameters and the topological relationship of alternative resources in the navigation path set are updated synchronously. This step ensures the flexibility and response speed of the entire system, enabling medical services to always maintain high efficiency and accuracy.

[0074] In the application example, on the eve of the surgery, the system detected that the inventory of a certain recommended implant was about to run out, so it automatically triggered the reconstruction of the priority queue. After re-evaluation, the system recommended another substitute with sufficient inventory and notified the medical team in a timely manner, avoiding the risk of surgical delay.

[0075] In summary, through the above steps 101 to 105, the method not only significantly improves the accuracy and efficiency of formulating emergency orthopedic surgery plans, but also realizes the optimal allocation and utilization of resources. It enables doctors to obtain the most suitable treatment plan in a short time and adjust strategies according to real-time data, thereby improving the surgical success rate and the patient's recovery rate. At the same time, this method also promotes the rational distribution of medical resources, reduces waste, and enhances the overall effectiveness of medical services.

[0076] Optionally, in step 103, traversing the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, matching the intersection range of the patient's fracture characteristics and the implant processing accuracy constraint nodes, and generating a navigation path set including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters, includes:

[0077] Performing multi-level traversal of the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue to identify the spatial matching pattern between the patient's bone geometric feature nodes and the implant processing accuracy constraint nodes; calculating the surgical plan compatibility parameters according to the spatial matching pattern, where the surgical plan compatibility parameters include the implant size tolerance coverage, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient; constructing the topological relationship of alternative resources based on the inventory availability status nodes, where the topological relationship of alternative resources includes the cross-hospital inventory distribution map and the real-time production capacity link of processing equipment; fusing the surgical plan compatibility parameters and the topological relationship of alternative resources to generate a navigation path set including the prediction of postoperative fretting wear probability and the infection risk correlation factor.

[0078] Optionally, calculating the surgical plan compatibility parameters according to the spatial matching pattern includes:

[0079] Perform geometric matching degree evaluation on the implant size tolerance coverage based on the spatial matching pattern, where the geometric matching degree evaluation includes the curvature adaptation parameter of the bone contact surface and the alignment deviation parameter of the implant edge; generate a surface roughness tolerance threshold according to the curvature adaptation parameter of the bone contact surface, and the surface roughness tolerance threshold is evaluated multi-dimensionally through the dynamic contact surface friction coefficient and the fretting displacement tolerance range; combine the alignment deviation parameter of the implant edge and the dynamic contact surface friction coefficient to calculate the material strength fluctuation adaptation coefficient, and the material strength fluctuation adaptation coefficient includes the stress distribution uniformity parameter and the fatigue life attenuation correlation factor; use the geometric matching degree evaluation, the surface roughness tolerance threshold, and the material strength fluctuation adaptation coefficient as the surgical plan compatibility parameters.

[0080] In this embodiment, perform multi-level traversal on the emergency orthopedics dynamic knowledge graph based on the dynamic priority queue to identify the spatial matching pattern between the patient's bone geometric feature nodes and the implant processing precision constraint nodes. The surgical plan compatibility parameters include key indicators such as implant size tolerance coverage, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient, which are used to evaluate whether a specific implant is suitable for the patient's fracture repair needs. In addition, the alternative resource topological relationship constructed based on the inventory availability status node not only considers the cross-hospital inventory distribution map but also includes the real-time production capacity link of the processing equipment to ensure that the best solution can be found under limited resources. The finally generated set of guiding diagnosis paths not only includes the surgical plan compatibility parameters but also covers the prediction of the probability of postoperative fretting wear and the infection risk correlation factor, providing comprehensive data support for doctors.

[0081] In the embodiment of the present application, first, the system performs multi-level traversal on the emergency orthopedics dynamic knowledge graph according to the dynamic priority queue, and calculates the surgical plan compatibility parameters by analyzing the spatial matching pattern between the patient's bone geometry and the implant processing precision constraint nodes. These parameters include geometric matching degree evaluation (such as the curvature adaptation parameter of the bone contact surface and the alignment deviation parameter of the implant edge), surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient. Next, the system constructs an alternative resource topological relationship based on the inventory availability status node, comprehensively considering the cross-hospital inventory distribution and the real-time production capacity of the processing equipment. Finally, all the above information is integrated to generate a set of guiding diagnosis paths including the prediction of the probability of postoperative fretting wear and the infection risk correlation factor. This process ensures the scientificity and feasibility of the surgical plan and maximally utilizes the existing medical resources.

[0082] After a patient with complex fractures caused by a traffic accident was sent to the emergency room, based on the dynamic priority queue and parameter knowledge graph generated in step 102, the system quickly performed a computed tomography scan on the patient in step 103 and uploaded the data. Subsequently, the system began to traverse the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, identifying the implants most suitable for the patient's fracture type and their machining precision requirements. After a detailed analysis of the spatial matching pattern, the system determined a titanium alloy plate as the preferred implant and calculated the evaluation results of its geometric matching degree, including the curvature adaptation parameter of the bone contact surface and the alignment deviation parameter of the implant edge. Further analysis showed that both the surface roughness tolerance threshold and the material strength fluctuation adaptation coefficient of this implant met the requirements. Considering the insufficient inventory in the current hospital, the system recommended transferring from a neighboring hospital and provided a real-time production capacity link of the processing equipment to ensure timely supply. Finally, the system generated a detailed set of guidance paths, including surgical plan compatibility parameters, cross-hospital resource allocation plans, and postoperative risk predictions, helping the medical team to efficiently formulate a treatment strategy and successfully perform the surgery. This process demonstrates how to improve the success rate and efficiency of emergency orthopedic surgeries through advanced data analysis and resource integration.

[0083] Optionally, in step 102, the multi-modal association of the emergency orthopedic patient's physical sign data and the orthopedic implant machining precision data in the dimension of fracture type generates an emergency orthopedic dynamic knowledge graph, which includes patient bone geometric feature nodes, implant machining precision constraint nodes, and inventory availability status nodes, and constructs a dynamic priority queue between the nodes, including:

[0084] Input the emergency orthopedic patient's physical sign data into a deep learning model to extract bone geometric features, generating a multi-dimensional feature vector including fracture type classification labels, bone morphology parameters, and biomechanical properties; construct an implant parameter map through the orthopedic implant machining precision data, which includes dimensional tolerance sequences, surface roughness distributions, and material strength fluctuation parameters; perform multi-modal alignment of the multi-dimensional feature vector and the implant parameter map through the fracture type classification label, and use a graph neural network to establish an emergency orthopedic dynamic knowledge graph including patient bone geometric feature nodes, implant machining precision constraint nodes, and inventory availability status nodes; construct a priority queue between the nodes based on dynamic weight parameters, and the dynamic weight parameters include the weights of the patient bone geometric feature nodes, the weights of the implant machining precision constraint nodes, and the weights of the inventory availability status nodes.

[0085] Optionally, the construction of the implant parameter map through the orthopedic implant machining precision data includes:

[0086] Input the orthopedic implant processing precision data into the multimodal feature analysis module to generate a processing precision feature set containing a tolerance constraint vector and a roughness distribution matrix; perform topological modeling on the processing precision feature set based on the graph embedding algorithm to construct an initial parameter graph containing tolerance constraint nodes and roughness distribution nodes, where the tolerance constraint nodes establish edge connection relationships through the similarity of tolerance fluctuation patterns, and the roughness distribution nodes establish edge connection relationships through the correlation of spatial gradient features; use the dynamic graph optimization module to iteratively update the initial parameter graph, perform tolerance constraint grouping based on the hierarchical clustering algorithm, and perform roughness distribution partitioning based on the region growing algorithm; based on the updated initial parameter graph, generate an implant parameter graph containing a tolerance constraint rule chain and a roughness matching rule tree through the knowledge graph rule engine, where the tolerance constraint rule chain contains the allowable deviation thresholds of the tolerance constraint grouping, and the roughness matching rule tree contains the adaptation relationship between the roughness distribution partitioning and the implant contact surface.

[0087] In this embodiment, by inputting the physical sign data of emergency orthopedic patients into a deep learning model, a multi-dimensional feature vector containing fracture type classification labels, bone morphology parameters, and biomechanical characteristics is extracted. At the same time, an implant parameter graph is constructed using the orthopedic implant processing precision data, which contains information such as dimensional tolerance sequences, surface roughness distributions, and material strength fluctuation parameters, and is used to evaluate the applicability of the implant. Through the fracture type classification label, the system can achieve multimodal alignment, that is, match the patient's bone geometric features with the appropriate implant processing precision requirements, and use a graph neural network to establish a comprehensive emergency orthopedic dynamic knowledge graph. In addition, a priority queue is constructed between nodes based on dynamic weight parameters to ensure that a reasonable weight is assigned to each node on the basis of considering the patient's bone geometric features, implant processing precision, and inventory status, thereby optimizing the selection process of the treatment plan.

[0088] In the embodiment of the present application, first, the physical sign data of the patient is input into a deep learning model to generate a multi-dimensional feature vector containing fracture type classification labels and detailed bone features. Then, the processing precision data of the orthopedic implant is processed by a multimodal feature analysis module to generate a processing precision feature set containing a tolerance constraint vector and a roughness distribution matrix. These feature sets are then topologically modeled through the graph embedding algorithm to construct an initial parameter graph, and the dynamic graph optimization module is used for iterative update to finally form an implant parameter graph. On this basis, the system aligns the patient's feature vector with the implant parameter graph using the fracture type classification label to create an emergency orthopedic dynamic knowledge graph containing all key nodes. Finally, dynamic weight parameters are set according to the importance of each node to construct a priority queue to guide the selection of subsequent surgical plans.

[0089] To further improve the efficiency of medical guidance, a patient with complex fractures caused by a traffic accident was sent to the emergency room. The doctor quickly arranged for a computed tomography scan and uploaded the results to the system. The system first analyzed the computed tomography images through a deep learning model, extracted the patient's fracture type, bone morphology parameters, and biomechanical characteristics, and generated a multi-dimensional feature vector. At the same time, the system processed the machining precision data of relevant implants in the hospital inventory and established an implant parameter atlas. Through the fracture type classification label, the system successfully matched the patient's bone characteristics with the implant parameters, forming an emergency orthopedic dynamic knowledge graph. Next, the system set the dynamic weight parameters of each node according to the patient's specific situation, the machining precision of the implant, and the current inventory status, and constructed a priority queue. This enabled the medical team to quickly identify the most suitable treatment plan for the patient and, considering the possibility of cross-hospital resource allocation, ensured the efficient progress of the surgical preparation work. This process not only improved the accuracy of the surgical plan but also optimized the resource allocation, demonstrating the great potential of advanced technology in emergency orthopedics.

[0090] Optionally, according to the fluctuations in the machining precision data of orthopedic implants collected in real time and the changes in the status of emergency inventory nodes in step 104, triggering the reconstruction mechanism of the dynamic priority queue, and synchronously updating the surgical plan compatibility parameters and alternative resource topological relationships in the guidance path set, including:

[0091] Real-time capture of fluctuations in the machining precision data of orthopedic implants and changes in the status of emergency inventory nodes through a streaming data processing engine, generating a real-time feature set including a tolerance fluctuation index, a roughness offset matrix, and an inventory decay factor; performing anomaly detection on the real-time feature set based on an event-driven model, and activating the reconstruction mechanism of the dynamic priority queue when the tolerance fluctuation index exceeds a preset threshold, the gradient change rate of the roughness offset matrix exceeds a critical value, or the inventory decay factor triggers a warning line; according to the reconstruction mechanism, using an adaptive weight allocation algorithm to update the node weights of the dynamic priority queue, adjusting the priority weights of the orthopedic implant machining precision constraint nodes according to the tolerance fluctuation index, correcting the spatial correlation degree of the inventory availability status nodes based on the gradient direction of the roughness offset matrix, and dynamically attenuating and compensating the biomechanical adaptability of the patient's bone geometry feature nodes in combination with the inventory decay factor; mapping the updated dynamic priority queue to the emergency orthopedic dynamic knowledge graph, and synchronously updating the surgical plan compatibility parameters and alternative resource topological relationships in the guidance path set.

[0092] Optionally, according to the reconstruction mechanism, the node weights of the dynamic priority queue are updated using an adaptive weight allocation algorithm, the priority weights of the orthopedic implant processing precision constraint nodes are adjusted according to the tolerance fluctuation index, the spatial correlation degree of the inventory availability status nodes is corrected based on the gradient direction of the roughness offset matrix, and the biomechanical adaptability of the patient bone geometric feature nodes is dynamically attenuated and compensated in combination with the inventory decay factor, including:

[0093] Based on the reconstruction mechanism, the tolerance fluctuation index, the roughness offset matrix, and the inventory decay factor are loaded through a multimodal weight initialization module to generate a dynamic parameter set; the orthopedic implant processing precision constraint nodes in the dynamic parameter set are grouped according to tolerance fluctuations, and the offset of the priority weight base value is adjusted according to the range distribution of the tolerance fluctuation index within the tolerance fluctuation group to generate the dynamic weight sequence of the orthopedic implant processing precision constraint nodes; the spatial correlation degree of the inventory availability status nodes is gradient-corrected, a spatial correlation degree correction coefficient is generated according to the gradient direction of the roughness offset matrix, and an association degree compensation threshold is generated in combination with the time-series attenuation mode of the inventory decay factor; the biomechanical adaptability of the patient bone geometric feature nodes is iteratively updated through a dynamic attenuation compensation model to generate biomechanical adaptability parameters including dynamic attenuation compensation values; the dynamic weight sequence, the association degree compensation threshold, and the biomechanical adaptability parameters are synchronously input into the dynamic priority queue to update the node weights of the dynamic priority queue.

[0094] In this embodiment, the fluctuations in the orthopedic implant processing precision data and the changes in the emergency inventory node status are monitored in real time to trigger the reconstruction mechanism of the dynamic priority queue. The data captured by the streaming data processing engine includes the tolerance fluctuation index, the roughness offset matrix, and the inventory decay factor, etc., which are used to evaluate the implant quality and its matching degree with the patient's needs. The event-driven model is used to detect anomalies in these feature sets. Once a change exceeding the set threshold is found, the reconstruction mechanism is activated to adjust the dynamic priority queue. The adaptive weight allocation algorithm updates the weights of each node according to the new parameters, ensuring that reasonable priorities are assigned to each node based on considering tolerance fluctuations, roughness changes, and inventory status. This process not only optimizes the selection of surgical plans but also improves the resource utilization efficiency, making medical decisions more accurate.

[0095] In the embodiments of the present application, first, the system uses a streaming data processing engine to capture in real time the fluctuations in the processing accuracy data of orthopedic implants and the status changes of the emergency inventory nodes, generating a set of multiple real-time features. When any of these feature indicators exceeds a preset threshold, the system starts an anomaly detection mechanism based on an event-driven model and activates the reconstruction of the dynamic priority queue. Then, an adaptive weight allocation algorithm is used to update the weights of each node. Specifically, the priority of the orthopedic implant processing accuracy constraint node is adjusted according to the tolerance fluctuation index, the spatial correlation degree of the inventory availability status node is corrected based on the gradient direction of the roughness offset matrix, and the biomechanical adaptability of the patient bone geometric feature node is compensated in combination with the inventory decay factor. Finally, the updated dynamic priority queue is mapped to the emergency orthopedic dynamic knowledge graph, and the surgical plan compatibility parameters and alternative resource topological relationships in the navigation path set are updated synchronously, so as to achieve the optimization of resource allocation.

[0096] A patient with a complex fracture caused by a traffic accident is sent to the emergency room, and the doctor decides to use a specific orthopedic implant for treatment. As the surgical preparation progresses, the system continuously monitors the processing accuracy data of the implant and the hospital inventory status. Suddenly, the system detects that the tolerance fluctuation index of a certain batch of implants exceeds the normal range, and at the same time, it is found that the decay factor of the relevant materials in the inventory is approaching the warning line. At this time, the system immediately triggers the reconstruction mechanism of the dynamic priority queue, recalculates and adjusts the priority weights of the orthopedic implant processing accuracy constraint node, corrects the spatial correlation degree of the inventory availability status node, and dynamically compensates the biomechanical adaptability of the patient bone geometric feature node. The results show that the originally selected implant is no longer the optimal choice, and the system recommends replacing it with another batch of implants with higher accuracy and more in line with the current inventory status, and provides updated surgical plan compatibility and resource allocation suggestions. This not only ensures the safety and success rate of the surgery, but also effectively manages limited medical resources.

[0097] Figure 2 The structure diagram of a medical navigation system based on a knowledge graph is provided for the embodiments of the present application, as Figure 2 shown, the device includes:

[0098] An acquisition module 21, which acquires the physical sign data of emergency orthopedic patients and the processing accuracy data of orthopedic implants, and the processing accuracy data of the orthopedic implants includes a dynamically updated dimensional tolerance sequence, a surface roughness distribution, and material strength fluctuation parameters;

[0099] The association module 22 multi - modally associates the physical sign data of the emergency orthopedic patients with the processing precision data of the orthopedic implants in terms of the fracture type dimension, generates an emergency orthopedic dynamic knowledge graph. The emergency orthopedic dynamic knowledge graph includes patient bone geometric feature nodes, implant processing precision constraint nodes, and inventory availability status nodes, and constructs a dynamic priority queue among the nodes.

[0100] The matching module 23 traverses the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, matches the intersection range between the patient fracture features and the implant processing precision constraint nodes, and generates a set of guiding paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters.

[0101] The update module 24 triggers the reconstruction mechanism of the dynamic priority queue according to the fluctuations of the orthopedic implant processing precision data collected in real - time and the changes in the status of the emergency inventory nodes, and synchronously updates the surgical plan compatibility parameters and alternative resource topological relationships in the set of guiding paths.

[0102] Figure 2 The described medical guiding system based on a knowledge graph can execute Figure 1 the medical guiding method based on a knowledge graph as described in the embodiments shown. Its implementation principle and technical effects will not be elaborated further. For the medical guiding system based on a knowledge graph in the above - mentioned embodiments, the specific ways for each module and unit to perform operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0103] In a possible design, Figure 2 the medical guiding system based on a knowledge graph in the embodiments shown can be implemented as a computing device. As Figure 3 shown, the computing device may include a storage component 31 and a processing component 32;

[0104] The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0105] The processing component 32 is used for the medical guiding method based on a knowledge graph in the above - mentioned Figure 1 embodiments.

[0106] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above methods. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above methods.

[0107] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0108] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0109] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0110] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0111] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0112] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of a medical guidance method based on a knowledge graph.

[0113] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0114] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative work.

[0115] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A medical guidance method based on knowledge graph, characterized in that: include: Obtaining emergency orthopedic patient vital sign data and orthopedic implant processing accuracy data, wherein the orthopedic implant processing accuracy data includes dynamically updated dimensional tolerance sequence, surface roughness distribution, and material strength fluctuation parameters; The emergency orthopedic patient vital sign data and the orthopedic implant processing accuracy data are multimodally associated according to the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph, wherein the emergency orthopedic dynamic knowledge graph includes patient bone geometry feature nodes, implant processing accuracy constraint nodes, and inventory availability status nodes, and a dynamic priority queue between nodes is constructed; Based on the dynamic priority queue, the emergency orthopedic dynamic knowledge graph is traversed to match the intersection range of the patient's fracture characteristics and the implant processing accuracy constraint nodes, and a guidance path set including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters is generated; According to the real-time collected orthopedic implant processing accuracy data fluctuations and emergency inventory node status changes, the reconstruction mechanism of the dynamic priority queue is triggered, and the surgical plan compatibility parameters and the alternative resource topological relationship in the guidance path set are synchronously updated.

2. The method according to claim 1, characterized in that The method traverses the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, matches the intersection range of the patient's fracture characteristics and the implant processing accuracy constraint nodes, and generates a set of guidance paths including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters, including: Based on the dynamic priority queue, the emergency orthopedics dynamic knowledge graph is traversed at multiple levels to identify the spatial matching pattern between the patient's bone geometry feature nodes and the implant processing accuracy constraint nodes; Calculating the compatibility parameters of the surgical plan according to the spatial matching mode, wherein the compatibility parameters of the surgical plan include implant size tolerance coverage, surface roughness tolerance threshold, and material strength fluctuation adaptation coefficient; Building a candidate resource topology relationship based on the inventory availability status node, wherein the candidate resource topology relationship includes a cross-campus inventory distribution map and a real-time capacity link of processing equipment; The compatibility parameters of the surgical plan and the topological relationship of the candidate resources are integrated to generate a set of guidance paths including postoperative micro-wear probability prediction and infection risk correlation factors.

3. The method according to claim 2, characterized in that Calculating the compatibility parameters of the surgical plan according to the spatial matching pattern includes: Performing a geometric matching evaluation on the implant size tolerance coverage based on the spatial matching mode, wherein the geometric matching evaluation includes a bone contact surface curvature adaptation parameter and an implant edge alignment deviation parameter; Generate a surface roughness tolerance threshold according to the bone contact surface curvature adaptation parameter, and the surface roughness tolerance threshold is evaluated in multiple dimensions through the dynamic contact surface friction coefficient and the micro-displacement tolerance range; Calculating a material strength fluctuation adaptation coefficient by combining the implant edge alignment deviation parameter with the dynamic contact surface friction coefficient, wherein the material strength fluctuation adaptation coefficient includes a stress distribution uniformity parameter and a fatigue life attenuation correlation factor; The geometric matching evaluation, surface roughness tolerance threshold and material strength fluctuation adaptation coefficient are used as surgical plan compatibility parameters.

4. The method according to claim 1, characterized in that: The emergency orthopedic patient vital sign data and the orthopedic implant processing accuracy data are multimodally associated according to the fracture type dimension to generate an emergency orthopedic dynamic knowledge graph, which includes patient bone geometry feature nodes, implant processing accuracy constraint nodes, and inventory availability status nodes, and constructs a dynamic priority queue between nodes, including: Inputting the emergency orthopedic patient's physical sign data into a deep learning model to extract bone geometric features, and generate a multidimensional feature vector including fracture type classification labels, bone morphological parameters, and biomechanical properties; Constructing an implant parameter map through the orthopedic implant processing accuracy data, wherein the orthopedic implant processing accuracy data includes a size tolerance sequence, a surface roughness distribution, and a material strength fluctuation parameter; The multi-dimensional feature vector is multimodally aligned with the implant parameter map through the fracture type classification label, and a graph neural network is used to establish an emergency orthopedic dynamic knowledge map including patient bone geometry feature nodes, implant processing accuracy constraint nodes, and inventory availability status nodes; A priority queue between nodes based on dynamic weight parameters is constructed, wherein the dynamic weight parameters include the weight of the patient's bone geometry feature node, the weight of the implant processing accuracy constraint node, and the weight of the inventory availability status node.

5. The method according to claim 4, characterized in that The step of constructing an implant parameter map using the orthopedic implant processing accuracy data comprises: Inputting the orthopedic implant processing accuracy data into a multimodal feature analysis module to generate a processing accuracy feature set including a tolerance constraint vector and a roughness distribution matrix; Based on the graph embedding algorithm, topological modeling is performed on the machining accuracy feature set to construct an initial parameter map including tolerance constraint nodes and roughness distribution nodes, wherein the tolerance constraint nodes are connected by edge through the similarity of tolerance fluctuation patterns, and the roughness distribution nodes are connected by edge through the correlation of spatial gradient features; The initial parameter map is iteratively updated using a dynamic map optimization module, tolerance constraints are grouped based on a hierarchical clustering algorithm, and roughness distribution is partitioned based on a region growing algorithm; Based on the updated initial parameter map, an implant parameter map including a tolerance constraint rule chain and a roughness matching rule tree is generated through a knowledge graph rule engine, wherein the tolerance constraint rule chain includes the allowable deviation threshold of the tolerance constraint grouping, and the roughness matching rule tree includes the adaptation relationship between the roughness distribution partition and the implant contact surface.

6. The method according to claim 1, characterized in that According to the real-time collected orthopedic implant processing accuracy data fluctuations and emergency inventory node status changes, the dynamic priority queue reconstruction mechanism is triggered, and the surgical plan compatibility parameters and the alternative resource topological relationship in the guidance path set are synchronously updated, including: The streaming data processing engine is used to capture the fluctuation of orthopedic implant processing accuracy data and the changes in the status of emergency inventory nodes in real time, and generate a real-time feature set including tolerance fluctuation index, roughness offset matrix and inventory attenuation factor; Anomaly detection is performed on the real-time feature set based on an event-driven model, and when the tolerance fluctuation index exceeds a preset threshold, the gradient change rate of the roughness offset matrix exceeds a critical value, or the inventory attenuation factor triggers a warning line, a reconstruction mechanism of the dynamic priority queue is activated; According to the reconstruction mechanism, the node weights of the dynamic priority queue are updated using an adaptive weight allocation algorithm, the priority weights of the orthopedic implant processing accuracy constraint nodes are adjusted according to the tolerance fluctuation index, the spatial correlation of the inventory availability status nodes is corrected based on the gradient direction of the roughness offset matrix, and the biomechanical adaptability of the patient's bone geometry feature nodes is dynamically attenuated and compensated in combination with the inventory attenuation factor; The updated dynamic priority queue is mapped to the emergency orthopedic dynamic knowledge graph, and the surgical plan compatibility parameters and the alternative resource topological relationship in the guidance path set are synchronously updated.

7. The method according to claim 6, characterized in that The method comprises: updating the node weights of the dynamic priority queue using an adaptive weight allocation algorithm according to the reconstruction mechanism, adjusting the priority weights of the orthopedic implant processing accuracy constraint nodes according to the tolerance fluctuation index, correcting the spatial correlation of the inventory availability status nodes based on the gradient direction of the roughness offset matrix, and dynamically performing attenuation compensation on the biomechanical adaptability of the patient's bone geometry feature nodes in combination with the inventory attenuation factor, including: Based on the reconstruction mechanism, the tolerance fluctuation index, the roughness offset matrix and the inventory attenuation factor are loaded through a multimodal weight initialization module to generate a dynamic parameter set; Grouping the orthopedic implant machining precision constraint nodes in the dynamic parameter set according to tolerance fluctuations, adjusting the offset of the priority weight base value according to the extreme difference distribution of the tolerance fluctuation index in the tolerance fluctuation group, and generating a dynamic weight sequence of the orthopedic implant machining precision constraint nodes; Performing gradient correction on the spatial correlation of the inventory availability status node, generating a spatial correlation correction coefficient according to the gradient direction of the roughness offset matrix, and generating a correlation compensation threshold in combination with the temporal attenuation mode of the inventory attenuation factor; Iteratively update the biomechanical adaptability of the patient's bone geometry feature nodes through a dynamic attenuation compensation model to generate biomechanical adaptability parameters including dynamic attenuation compensation values; The dynamic weight sequence, correlation compensation threshold and biomechanical adaptability parameter are synchronously input into the dynamic priority queue to update the node weight of the dynamic priority queue.

8. A medical guidance method based on knowledge graph, characterized in that: include: An acquisition module is used to acquire the vital sign data of emergency orthopedic patients and the processing accuracy data of orthopedic implants, wherein the processing accuracy data of orthopedic implants includes a dynamically updated dimensional tolerance sequence, surface roughness distribution, and material strength fluctuation parameters; An association module performs multimodal association between the emergency orthopedic patient's vital sign data and the orthopedic implant processing accuracy data according to the fracture type dimension, generates an emergency orthopedic dynamic knowledge graph, and the emergency orthopedic dynamic knowledge graph includes patient bone geometry feature nodes, implant processing accuracy constraint nodes and inventory availability status nodes, and constructs a dynamic priority queue between nodes; A matching module, which traverses the emergency orthopedic dynamic knowledge graph based on the dynamic priority queue, matches the intersection range of the patient's fracture characteristics and the implant processing accuracy constraint nodes, and generates a guidance path set including surgical plan compatibility parameters, alternative resource topological relationships, and postoperative risk prediction parameters; The update module triggers the reconstruction mechanism of the dynamic priority queue according to the real-time collected orthopedic implant processing accuracy data fluctuations and emergency inventory node status changes, and synchronously updates the surgical plan compatibility parameters and alternative resource topological relationships in the guidance path set.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a medical guidance method based on a knowledge graph as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a medical guidance method based on a knowledge graph as described in any one of claims 1 to 7 is implemented.

Images