Method and system for fusing medical knowledge maps of urology department and medium

Abstract

The invention relates to the technical field of knowledge graph fusion, in particular to a fusion method and system for medical knowledge graphs of the urology department and a medium. The method comprises the following steps: acquiring urology department historical medical record data and a lesion part CT image, and carrying out image region segmentation to obtain a lesion part CT segmentation image; then, performing lesion trend synchronous intersection identification on the CT segmented image according to the medical record data to obtain lesion trend synchronous intersection data, and performing implicit association deduction to obtain lesion trend causal implicit association data; and processing the causal implicit association data by using a knowledge graph representation learning method to obtain graph association structure learning data, and performing graph fusion logic adjustment. And finally, designing a lesion map fusion logic strategy based on the adjusted data, and sending the strategy to the cloud platform for execution. According to the method, the knowledge graph fusion technology is optimized, so that the knowledge graph fusion technology is more perfect.

Description

Technical Field

[0001] The present invention relates to the field of knowledge graph fusion technology, and in particular to a fusion method, system and medium for urology medical knowledge graph. Background Art

[0002] The fusion method of urology medical knowledge graph aims to provide comprehensive and accurate knowledge support for clinical diagnosis, treatment planning and scientific research innovation by integrating and associating multi-source heterogeneous urology medical data. Urology covers a wide range of disease types and complex pathological mechanisms, including urinary tract infections, urinary tumors, urinary tract stones, etc. The diagnosis and treatment of various diseases often involve data sources from multiple disciplines, such as patient electronic medical records (EHRs), laboratory test results, imaging data, genomic information, clinical guidelines and literature. However, these data are usually scattered in different systems, showing differences in data format, semantic definition and storage structure, which makes it difficult to fully and comprehensively utilize them, limiting the potential of intelligent clinical decision-making. As a new type of data management and knowledge expression technology, knowledge graph can effectively express the complex relationships between entities by modeling data as semantic networks, providing an innovative path for the organization, storage and utilization of medical knowledge. The construction and fusion of urology medical knowledge graphs need to address multiple challenges, including semantic inconsistency of different data sources, differences in data quality and the requirement for dynamic updating of medical knowledge. However, the traditional fusion method of urology medical knowledge graph has the problems of large errors in deducing the relationship between pathological principles and low correlation of knowledge graph fusion. Summary of the invention

[0003] Based on this, it is necessary to provide a fusion method, system and medium for urology medical knowledge graph to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for integrating urology medical knowledge graphs is provided, the method comprising the following steps: Step S1: Acquire the historical medical records of the urology department and the CT image of the lesion; perform image region segmentation on the CT image of the lesion according to the historical medical records of the urology department to obtain a CT segmented image of the lesion; Step S2: performing synchronous intersection recognition of lesion trends on the CT segmented images of the lesion site according to the historical medical records of the urology department to obtain synchronous intersection data of lesion trends; performing implicit association deduction on the synchronous intersection data of lesion trends to obtain causal implicit association data of lesion trends; Step S3: Perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; Step S4: Design a logic strategy based on the lesion map fusion logic adjustment data to obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

[0005] The present invention first collects the historical medical records of urology patients, combines the patient's condition background, previous medical records and clinical symptoms, and obtains detailed medical information. Then, by analyzing the CT image of the lesion site, the CT image is processed using image segmentation technology to extract the specific area of ​​the lesion site. This process automatically segments the CT image by using medical image processing algorithms (such as convolutional neural networks, CNN, etc.), so that the lesion area can be accurately located, thereby providing a high-quality data basis for subsequent disease analysis and prediction. By analyzing the patient's historical medical records and the CT segmented images of the lesion site, the synchronous intersection identification of the lesion trend is performed. This means that by comparing and analyzing the CT images of the lesion site at different time points, the laws and trends of lesion progression can be identified. These data can help identify potential associations in the development of lesions and reveal potential causal relationships between lesions. Implicit association deduction technology plays an important role here. It derives the causal relationship of lesions through mathematical models and machine learning algorithms, and generates lesion trend causal implicit association data to provide support for disease prediction and treatment decisions. The lesion trend causal implicit association data is converted into a knowledge graph representation, and a lesion knowledge graph is constructed through graph representation learning technology. This process presents the different attributes, types, development trends and relationships of lesions in the form of graphs by structurally processing the lesion data. Then, the graph fusion technology is used to fuse and logically adjust the data in the graph to optimize the graph structure and relationship. This process optimizes the reasoning path and logical deduction of lesion trends by adjusting the connection mode of each node and edge in the graph, making the prediction model of lesions more accurate and helping to further discover potential disease patterns and treatment plans. Based on the lesion graph fusion logic adjustment data obtained in step S3, a set of logical strategies for lesion trends is designed. These strategies are intended to provide a systematic guidance to help medical professionals make more scientific and reasonable decisions during diagnosis and treatment. Finally, the lesion graph fusion logic strategy will be sent to the cloud platform for execution, and the fusion method of the urology medical knowledge graph will be implemented through the computing and processing capabilities of the cloud platform. This not only enhances the data processing and reasoning capabilities, but also enables knowledge sharing and dynamic updating through the cloud platform, thereby providing clinicians with real-time and accurate medical advice and auxiliary decision-making, and improving the efficiency and quality of medical services. Therefore, the present invention optimizes the traditional fusion method of urology medical knowledge graphs, solves the problems of large errors in the deduction of lesion principle relationships and low correlation of knowledge graph fusion in the traditional fusion method of urology medical knowledge graphs, reduces the error in the deduction of lesion principle relationships, and improves the correlation of knowledge graph fusion.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire the historical medical records of the urology department and the CT images of the lesion site; Step S12: performing data desensitization processing on the historical medical record data of the urology department to obtain desensitized data of the historical medical record data; Step S13: Performing logical description analysis on the desensitized data of historical medical records to obtain logical description data of the medical records; Step S14: performing image region segmentation on the CT image of the lesion site according to the logical description data of the medical history to obtain a CT segmented image of the lesion site.

[0007] The present invention first collects the historical medical records of urology patients and CT images of lesions. These data include the patient's basic information, medical records, condition description, diagnosis and treatment process and examination results, and the CT image provides visual information of the lesion for further analysis. By fully acquiring the patient's historical medical records and imaging data, it can be ensured that there is sufficient data support for subsequent processing and analysis, and that the disease trend and development changes are accurately tracked. The obtained CT image can provide an important basis for subsequent image segmentation and trend prediction. The historical medical records of urology are desensitized to protect the privacy and data security of the patient. The desensitization process includes removing the patient's personal identity information (such as name, ID number, etc.) to prevent the patient's sensitive information from being leaked. This step is a key step in medical data processing, which complies with relevant laws and regulations and ensures that the data can be used for scientific research and analysis without infringing on the patient's privacy. Through the desensitized data, it is guaranteed that the data protection standards can be followed in the process of medical data analysis and machine learning, and the data can be widely used in technical research and clinical decision support. By performing logical description and analysis on the desensitized historical medical records data, key information is extracted and structured. This process uses natural language processing (NLP) technology to convert the descriptive language in the medical record data into clear logical relationships and diagnosis and treatment processes. For example, the patient's medical history, symptom description, diagnosis conclusion, treatment plan and its effect are analyzed and converted into logical description data that can be understood by the machine. Through this step, the core diagnosis and treatment information in the medical record can be extracted, providing more clear data support and background knowledge for the subsequent analysis of the trend of the lesion and the formulation of the treatment plan. According to the logical description data obtained from the historical medical records, combined with the patient's specific condition and lesion site, the CT image area is accurately segmented. This step uses machine learning, image processing algorithms, and deep learning models (such as convolutional neural networks CNN) to automatically mark and segment the lesion site. By combining the description of the condition in the medical record, the system can identify the specific location and type of the lesion and accurately mark it in the CT image. This image segmentation technology can greatly improve the positioning accuracy of the lesion area, providing important image data support for subsequent lesion analysis, trend prediction, and treatment plan formulation.

[0008] Preferably, step S2 comprises the following steps: Step S21: performing structural morphological analysis on the CT segmented image of the lesion to obtain structural morphological data of the lesion; Step S22: performing synchronous intersection recognition of lesion trends on the lesion site structure morphology data and the lesion site CT segmentation image according to the historical medical record data of the urology department to obtain synchronous intersection data of the lesion trend; Step S23: performing causal correlation analysis on the lesion trend synchronization intersection data to obtain lesion trend synchronization causal data; Step S24: perform implicit correlation deduction based on the synchronous causal data of the lesion trend to obtain causal implicit correlation data of the lesion trend.

[0009] The present invention can identify and extract the geometric morphology and spatial distribution characteristics of the lesion area by performing structural morphological analysis on the CT segmentation image of the lesion. This process uses image processing techniques, such as morphological analysis, edge detection, etc., to deeply explore the structural characteristics of the lesion area, including shape, size, boundary clarity and its relationship with surrounding tissues. Through these structural features, the development mode and evolution trend of the lesion can be better understood, providing reliable data support for lesion prediction and treatment plan design. The extraction of structural morphological data can reveal the complexity of the lesion and make more accurate judgments in the diagnosis process. By combining the historical medical record data of the urology department and the structural morphological data of the lesion and the CT segmentation image, the trend of the lesion is synchronously identified. This means that by comparing the time series of the changes in the patient's historical medical records and combining the characteristics of the lesion area in the CT image, the system can identify the progression trend of the lesion and its evolution pattern at different time nodes. This step realizes the vertical integration of lesion data, helps to reveal the potential development path of the lesion, and helps to predict the future trend of the disease, thereby providing a more personalized and accurate basis for clinical treatment decisions. Causal correlation analysis is performed on the synchronous intersection data of the lesion trend to explore the potential causal relationship of the development of the lesion. By establishing a causal reasoning model, we can analyze the relationship between changes in the lesion area and the patient's medical history, symptoms, and treatment measures, identify the factors that lead to lesion progression, and explore the causal chain between these factors. Causal association analysis can help doctors understand the root causes of lesion development and reveal the evolution path of the disease under different conditions. This can not only provide a basis for individualized treatment, but also provide scientific guidance for the prediction and preventive measures of similar cases in the future. Implicit association deduction based on lesion trend synchronization causal data means exploring deeper implicit associations between lesions through advanced data mining and machine learning techniques. This process uses algorithms to automatically discover unmanifested lesion factors and their potential causal relationships, and deduce implicit patterns in lesion progression. Implicit association deduction can identify potential risk factors for lesion development, even early, imperceptible change trends. The resulting lesion trend causal implicit association data.

[0010] Preferably, step S22 includes the following steps: Step S221: Perform spatial domain analysis on the lesion site structure morphology data to obtain lesion location distribution data; Step S222: performing a descriptive trend comparison on the lesion location distribution data according to the historical medical records of the urology department to obtain descriptive trend comparison data of the lesion distribution; Step S223: simulating the lesion boundary tissue density similarity difference on the lesion location distribution data and the lesion site CT segmentation image based on the lesion distribution descriptive trend comparison data to obtain the lesion boundary tissue density similarity difference; Step S224: performing boundary transition density difference analysis on the lesion position distribution data according to the boundary tissue density similarity difference to obtain the lesion tissue boundary transition density difference; Step S225: Perform lesion trend synchronization intersection identification on the lesion site structure morphology data according to the lesion boundary tissue density similarity difference and the lesion tissue boundary transition density difference to obtain lesion trend synchronization intersection data.

[0011] The present invention can further refine the spatial distribution and morphological characteristics of the lesion by performing spatial domain analysis on the structural morphological data of the lesion site, and obtain the lesion location distribution data. This analysis method uses spatial analysis techniques, such as regional growth, heat map generation, etc., to spatially locate the lesion area in the CT image, identify the specific location of the lesion site in the body and its relative distribution. By comparing the descriptive trend of the historical medical record data of the urology department with the lesion location distribution data, the evolution law of the lesion is excavated. The historical medical record data contains the lesion information, treatment records, examination results, etc. of the patient in different time periods, while the lesion location distribution data provides the spatial changes of the lesion site. By comparing and analyzing these two types of data, the temporal and spatial evolution trend of the lesion can be revealed, and the change pattern of the lesion area over time can be identified. Based on the descriptive trend comparison data of the lesion distribution, combined with the lesion location distribution data and the CT segmentation image of the lesion site, the tissue density of the lesion boundary is simulated by similarity difference. This process uses density analysis technology to compare the density difference between the lesion boundary area and the surrounding normal tissue, and then simulates the boundary characteristics of the lesion tissue. In this way, the difference in density between the lesion area and the healthy tissue can be identified, revealing the morphological characteristics of the lesion and its transition area with the normal tissue. According to the aforementioned tissue density similarity difference, the boundary transition density difference analysis is performed on the lesion location distribution data. This step focuses on the transition area between the lesion area and the normal tissue, analyzes the density difference in these areas, and reveals the fuzzy area of ​​the lesion boundary. Through this analysis, the specific scope of the lesion can be more clearly delineated, helping doctors determine the expansion trend of the lesion, evaluate the relationship between the lesion and the surrounding tissue, especially how to distinguish it from healthy tissue at the boundary of the lesion. This density difference analysis helps to improve the accuracy of CT image segmentation and reduce misjudgment and missed judgment. Combining the data of the lesion boundary tissue density similarity difference and the lesion tissue boundary transition density difference, the lesion trend synchronization intersection identification is performed on the lesion site structural morphology data. Through the intersection analysis of these two types of density difference data, the system can identify the synchronization trend in the development of the lesion, that is, the morphological changes of the lesion area at different stages and the transition law between it and the normal tissue. This process helps to identify the synchronization pattern of lesion progression from multiple dimensions, providing accurate support for the early detection, positioning and treatment intervention of lesions. At the same time, the synchronous intersection data of lesion trends can be used for subsequent lesion prediction.

[0012] Preferably, step S223 includes the following steps: Perform multi-scale spatial coordinate transformation on the lesion location distribution data to obtain multi-scale lesion area calibration data; According to the descriptive trend comparison data of lesion distribution, multi-point neighboring density distribution analysis is performed on the multi-scale lesion area calibration data and the CT segmentation image of the lesion part to obtain multi-point neighboring density distribution data; Perform layered density fitting on multi-point adjacent density distribution data to obtain layered lesion boundary density data; Based on the layered lesion boundary density data, position density trend deviation analysis is performed to obtain position density trend deviation data; According to the layered lesion boundary density data and the position density trend deviation data, the lesion position distribution data and the CT segmentation image of the lesion site are simulated to obtain the lesion boundary tissue density similarity difference.

[0013] The present invention can calibrate the lesion area at different scale levels by performing multi-scale spatial coordinate transformation on the lesion position distribution data. In this process, the spatial coordinate system of the lesion is converted into a representation method at multiple scales, which can help reveal the performance and distribution characteristics of the lesion at different scales (such as micro and macro scales). This multi-scale analysis method is particularly effective for complex lesion areas because it can take into account local details and overall trends at the same time, ensuring that the calibration of the lesion area is more accurate and comprehensive, thereby providing more detailed data support for subsequent lesion analysis. By combining the descriptive trend comparison data of the lesion distribution, a multi-point neighboring density distribution analysis is performed to reveal the density changes between different points in the lesion area. This analysis not only focuses on the characteristics of a single lesion position, but also analyzes the density distribution laws of these points by considering multiple points around the lesion site. In this way, the density differences and change trends of lesions at different positions can be identified, further improving the accuracy of lesion detection and segmentation. The purpose of this process is to clarify the spatial organizational structure of the lesion. By performing layered density fitting on the multi-point neighboring density distribution data, the density characteristics of the lesion boundary can be modeled at different levels. The hierarchical density fitting method divides the lesion area into several sub-areas according to different density levels to more accurately describe the changes in the lesion boundary. The fitting results of each layer reflect the density change trend of the lesion area, which can help doctors identify the boundary of the lesion, the difference in tissue density and its expansion pattern. This hierarchical analysis method can more clearly reveal the complexity of the lesion boundary. By performing position density trend deviation analysis on the layered lesion boundary density data, the abnormality of the density change trend of the lesion area at different spatial locations is revealed. This analysis method can identify the deviation between the density changes of each layer inside the lesion area and the normal tissue, thereby revealing the nature and evolution direction of the lesion. The position density trend deviation data can reflect the spatial inhomogeneity of the lesion area and the abnormal pattern of density change. By combining the layered lesion boundary density data and the position density trend deviation data, the lesion boundary tissue density similarity difference simulation can be performed to quantify the density difference between the lesion boundary and the surrounding normal tissue. This simulation reveals the characteristics of the lesion boundary and the expansion trend by comparing the density similarity between the lesion area and its adjacent normal tissue. The density similarity difference simulation helps to identify the relationship between the specific boundary of the lesion and the surrounding tissue.

[0014] Preferably, step S24 comprises the following steps: Step S241: performing structured classification processing on the lesion trend synchronization causal data to obtain lesion development stage division data; Step S242: performing stage trigger factor deduction according to the lesion development stage division data to obtain lesion stage trigger factor deduction data; Step S243: performing layer-by-layer factor event simulation analysis on the lesion stage trigger factor deduction data to obtain layer-by-layer factor event analysis data; Step S244: perform implicit association deduction based on the layer-by-layer factor event analysis data and the lesion stage trigger factor deduction data to obtain lesion trend causal implicit association data.

[0015] The present invention first needs to carry out detailed structured arrangement of lesion trends and related causal data. By classifying, labeling and categorizing the data of lesion trends, different types of lesions and their respective development stages can be effectively identified. For example, according to factors such as symptoms, manifestations, progression speed and treatment response of the lesions, they can be divided into different stages such as early, middle and late stages. Through structured classification processing, it is helpful to more accurately analyze the lesion stage and identify trigger factors in the subsequent steps, and provide clear basic data for subsequent causal deduction and analysis. According to the data of different development stages of the lesions, the key trigger factors affecting the lesion process are deduced. At each stage, the development of the lesion is not only affected by biological factors, but also by factors such as environment, living habits, and external interference. By conducting in-depth analysis of the lesion data at each stage, it is possible to identify which factors play a key role in a specific stage. These factors include physiological changes of the disease, fluctuations in immune response, the effect of drug treatment, etc. The deduced stage trigger factors provide data support for in-depth analysis of the development of the lesion and provide an important basis for formulating personalized treatment plans. By simulating and analyzing the interaction between each trigger factor and the lesion event layer by layer. Each layer of factors will have its unique mechanism of action and will be intertwined with the previous factors. In this process, by gradually analyzing the specific role of each layer of factors, simulating their impact on the progression of the disease, and revealing the internal connection between different factors. This process can help clarify which factors play a role in promoting or inhibiting the disease at different stages, and provide an important reference for further precise adjustment of treatment strategies and disease management. By comprehensively analyzing the layer-by-layer factor event analysis data and the lesion stage trigger factor deduction data, the implicit correlation between the various factors of the disease can be further explored and deduced. Different factors have complex interactions at different stages of the disease, and some seemingly unrelated factors are also associated due to changes in specific conditions. Through implicit correlation deduction, potential causal chains can be discovered, which are difficult to directly reveal through traditional analysis methods. The results of implicit correlation deduction provide a deeper understanding of the development trend of the disease, and also provide a more scientific and accurate basis for the formulation of prevention and control strategies.

[0016] Preferably, step S3 comprises the following steps: Step S31: constructing a graph relationship for the lesion trend causal implicit correlation data to obtain a lesion causal trend relationship graph; Step S32: Perform knowledge graph representation learning on the lesion causal trend relationship graph to obtain graph association structure learning data; Step S33: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the graph association structure learning data to obtain lesion graph fusion logic adjustment data.

[0017] The present invention constructs a lesion causal trend relationship map by converting the lesion trend causal implicit association data into a graph relationship. The map establishes nodes (lesion factors) and edges (causal relationships between them) based on the interaction and influence between different lesion factors. The graph relationship construction can not only show the dynamic changes of the lesions at various stages, but also reveal the relationship and dependency of different lesion factors at different development stages. This process helps to clarify the lesion causal chain, find out the potential lesion triggering factors and their mutual influence, and provide a clear graph structure for subsequent analysis. By applying knowledge graph representation learning, deep learning analysis is performed on the nodes and edges in the lesion causal trend relationship map, so as to extract more complex association patterns and structures. This learning process helps to automatically identify the potential relationships, similarities and influence paths between various lesion factors in the map. Through the learning of the knowledge graph, the correlation and potential causal relationship between certain factors can be found, especially in the case of large data volume and complex relationships, some deep information that is difficult to identify through manual analysis can be revealed. This process improves the intelligence and adaptability of the map. By combining the data obtained by learning the graph association structure, the graph fusion logic is adjusted to further optimize the lesion causal trend relationship map. Through logical adjustments, the relationship and correlation strength between lesion factors can be dynamically corrected and updated based on the original atlas structure. For example, it is found that the causal effect of some factors is more significant than expected, or the impact path of some factors changes at different stages. Through these logical adjustments, the atlas more accurately reflects the true development process and internal mechanism of the lesion.

[0018] Preferably, step S33 includes the following steps: Step S331: performing a topological correlation density analysis on the lesion causal trend relationship graph according to the graph correlation structure learning data to obtain topological correlation density data; Step S332: Based on the topological association density data, the relative centrality of the nodes in the lesion causal trend relationship map is evaluated to obtain the relative centrality of the nodes in the map; Step S333: performing multi-stage weight adjustment on the nodes of the lesion causal trend relationship map according to the topological association density data and the relative centrality of the map nodes to obtain multi-stage weight adjustment data for the nodes; Step S334: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the topological association density data, the graph node relative centrality and the node multi-stage weight adjustment data to obtain the lesion graph fusion logic adjustment data.

[0019] The present invention first performs a topological association density analysis on the lesion causal trend relationship map. The topological association density reflects the distribution characteristics of nodes and edges in the map and the degree of interconnection between them. By analyzing the topological structure of the map, it is possible to identify which lesion factors or nodes have a closer relationship, and these factors play a more important role in the spread and progression of the lesion. The topological association density data reveals the closeness of the association between various lesion factors and provides a basis for the analysis and adjustment of subsequent steps. For example, some nodes show a high degree of aggregation, indicating that these factors play a key role in the process of the lesion. Based on the topological association density data, the nodes in the map are evaluated for relative centrality. The centrality of a node refers to the importance and influence of a node in the entire map structure, which is usually measured by the strength of its connection with other nodes. A higher centrality value means that the node has an important position in the lesion causal chain and is a key lesion triggering factor or a key path node. By evaluating the relative centrality of the map nodes, it can help identify the most influential factors in the lesion process. According to the topological association density data and the relative centrality of the nodes, the weight of the nodes is adjusted in multiple stages. This process can dynamically adjust the weight of each node at different lesion stages. For example, in some stages, certain lesion factors become the main influencing factors, while in other stages, the role of these factors weakens and other factors become more important. Through multi-stage weight adjustment, the role strength of each node in the lesion causal map at different times can be more accurately reflected, thereby helping to identify and track the key stages of lesion development. By combining topological association density data, node relative centrality and node multi-stage weight adjustment data, a comprehensive graph fusion logic adjustment is performed on the lesion causal trend relationship map. This adjustment process involves re-optimizing the entire graph structure, aiming to more accurately reflect the causal relationship and influence path between different nodes and edges. The fusion logic adjustment will not only further strengthen the role of important nodes, but also balance the weights of factors at each stage.

[0020] Preferably, the present invention further provides a fusion system of urology medical knowledge graphs, which is used to execute the fusion method of urology medical knowledge graphs as described above. The fusion system of urology medical knowledge graphs includes: The image region segmentation module is used to obtain the historical medical records of the urology department and the CT image of the lesion site; the image region of the CT image of the lesion site is segmented according to the historical medical records of the urology department to obtain the CT segmentation image of the lesion site; The association analysis module is used to identify the synchronous intersection of lesion trends on the CT segmented images of the lesion parts according to the historical medical records of the urology department, and obtain the synchronous intersection data of lesion trends; perform implicit association deduction on the synchronous intersection data of lesion trends, and obtain the causal implicit association data of lesion trends; The graph fusion logic adjustment module is used to perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; The logic strategy design module is used to design the logic strategy based on the lesion map fusion logic adjustment data, obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

[0021] Preferably, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed, the method for fusing the urology medical knowledge graph as described in any one of the above is implemented.

[0022] The beneficial effects of the present invention are as follows: first, by collecting the historical medical records of urology patients, combined with the patient's condition background, previous medical records and clinical symptoms, detailed medical information is obtained. Then, by analyzing the CT image of the lesion site, the CT image is processed using image segmentation technology to extract the specific area of ​​the lesion site. This process automatically segments the CT image using a medical image processing algorithm (such as a convolutional neural network, CNN, etc.), so that the lesion area can be accurately located, thereby providing a high-quality data basis for subsequent disease analysis and prediction. By analyzing the patient's historical medical records and the CT segmented images of the lesion site, the synchronous intersection identification of the lesion trend is performed. This means that by comparing and analyzing the CT images of the lesion site at different time points, the laws and trends of lesion progression can be identified. These data can help identify potential associations in the development of lesions and reveal potential causal relationships between lesions. Implicit association deduction technology plays an important role here. It derives the causal relationship of lesions through mathematical models and machine learning algorithms, and generates lesion trend causal implicit association data to provide support for disease prediction and treatment decisions. The causal implicit association data of lesion trends are converted into knowledge graph representation, and the lesion knowledge graph is constructed through graph representation learning technology. This process presents the different attributes, types, development trends and relationships between lesions in the form of graphs by structurally processing the lesion data. Then, the graph fusion technology is used to fuse and logically adjust the data in the graph to optimize the graph structure and relationship. This process optimizes the reasoning path and logical deduction of lesion trends by adjusting the connection mode of each node and edge in the graph, making the prediction model of lesions more accurate and helping to further discover potential disease patterns and treatment plans. Based on the lesion graph fusion logic adjustment data obtained in step S3, a set of logical strategies for lesion trends are designed. These strategies are intended to provide a systematic guidance to help medical professionals make more scientific and reasonable decisions during diagnosis and treatment. Finally, the lesion graph fusion logic strategy will be sent to the cloud platform for execution, and the fusion method of the urology medical knowledge graph will be implemented through the computing and processing capabilities of the cloud platform. This not only enhances data processing and reasoning capabilities, but also enables knowledge sharing and dynamic updating through the cloud platform, thereby providing clinicians with real-time, accurate medical advice and decision support, and improving the efficiency and quality of medical services. Therefore, the present invention is an optimization of a traditional fusion method of urology medical knowledge graphs, which solves the problem that the traditional fusion method of urology medical knowledge graphs has large errors in the deduction of lesion principle relationships and low correlation of knowledge graph fusion, reduces the error in the deduction of lesion principle relationships, and improves the correlation of knowledge graph fusion. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1A schematic diagram of the steps of a fusion method of urology medical knowledge graph; Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0024] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figure 1 to Figure 2 , a fusion method of urology medical knowledge graph, the method comprising the following steps: Step S1: Acquire the historical medical records of the urology department and the CT image of the lesion; perform image region segmentation on the CT image of the lesion according to the historical medical records of the urology department to obtain a CT segmented image of the lesion; Step S2: performing synchronous intersection recognition of lesion trends on the CT segmented images of the lesion site according to the historical medical records of the urology department to obtain synchronous intersection data of lesion trends; performing implicit association deduction on the synchronous intersection data of lesion trends to obtain causal implicit association data of lesion trends; Step S3: Perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; Step S4: Design a logic strategy based on the lesion map fusion logic adjustment data to obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

[0029] In the embodiment of the present invention, reference Figure 1 As shown, it is a schematic diagram of the steps of a fusion method of a urology medical knowledge graph of the present invention. In this example, the fusion method of the urology medical knowledge graph includes the following steps: Step S1: Acquire the historical medical records of the urology department and the CT image of the lesion; perform image region segmentation on the CT image of the lesion according to the historical medical records of the urology department to obtain a CT segmented image of the lesion; In the embodiment of the present invention, in the process of obtaining the historical medical record data of the urology department and the CT image of the lesion, the medical record data is first preprocessed to ensure that the personal information and sensitive data therein are desensitized. The historical medical record data includes the patient's basic information, symptom description, diagnosis record, treatment process and examination results. Data is extracted from the hospital electronic medical record system through a standardized interface and structured conversion is performed to ensure the uniformity of the data format. The CT image of the lesion is obtained from the hospital's medical imaging management system. The image data is usually in DICOM format. The format conversion and size must be unified to ensure that the resolution and grayscale value of all images are consistent. Next, the image processing algorithm based on deep learning is used to segment the image region of the CT image of the lesion. Specifically, an image segmentation algorithm based on a convolutional neural network (CNN) is used. The input image is first preprocessed, and the image quality is improved by image enhancement techniques (such as contrast adjustment and edge sharpening), and then the trained model is used for regional segmentation. The goal of image segmentation is to accurately delineate the lesion site, exclude irrelevant areas, and generate a CT segmentation image of the lesion site. This process can accurately extract the target area for subsequent analysis.

[0030] Step S2: performing synchronous intersection recognition of lesion trends on the CT segmented images of the lesion site according to the historical medical records of the urology department to obtain synchronous intersection data of lesion trends; performing implicit association deduction on the synchronous intersection data of lesion trends to obtain causal implicit association data of lesion trends; In an embodiment of the present invention, synchronous intersection identification of lesion trends is performed based on the historical medical records of urology and the CT segmented images of the lesion site. First, the disease history, symptom changes, treatment process and other information in the medical record data are deeply analyzed to extract the patient's disease progression trend. On the CT image, image processing technology is used to extract different morphological features of the lesion area, such as the edge, shape, size and position of the lesion area. These image features are combined with the clinical information in the historical medical record data, and the evolution trend of the lesion is analyzed through a specific algorithm (such as a decision tree or a support vector machine SVM), and synchronous intersection identification of lesion trends is performed. By comparing the CT segmented images at different time points with the records in the medical record data, the trend of lesion development can be identified to form synchronous intersection data of lesion trends. Further, the synchronous intersection data of lesion trends is implicitly deduced, and an association rule mining method, such as an Apriori algorithm or an FP-growth algorithm, is used to find out the potential causal relationship. These causal relationships help to infer the implicit factors of lesion trends and provide a basis for the subsequent knowledge graph construction. During the deduction process, the algorithm calculates the dependencies between events in the progression of the lesion, generates causal implicit correlation data of the lesion trend, and reveals the potential connections between different lesion factors.

[0031] Step S3: Perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; In an embodiment of the present invention, the causal implicit association data of the lesion trend will be used for knowledge graph representation learning. First, the causal implicit association data of the lesion trend is converted into graph structure data, that is, the nodes represent different lesion factors or pathological states, and the edges represent the causal relationship between these factors or states. Then, the nodes and edges in the graph are represented and learned using graph embedding technology. The specific method adopts a graph embedding algorithm based on random walks, such as DeepWalk or Node2Vec. These methods learn the low-dimensional representation of nodes by simulating the random walk path in the graph, so that similar nodes have similar vector representations in the embedding space. By performing graph representation learning on the causal implicit association data of the lesion trend, a structured representation of the lesion causal relationship can be obtained, that is, graph association structure learning data. These learned node representations are further used for graph fusion. Specifically, the graph fusion logic adjustment is adjusted according to the graph association structure learning data. The graph alignment method is used in the adjustment process. First, the node correspondence in different lesion graphs is determined by graph isomorphism matching, and then multiple representations of the same lesion node are unified to obtain the lesion graph fusion logic adjustment data.

[0032] Step S4: Design a logic strategy based on the lesion map fusion logic adjustment data to obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

[0033] In an embodiment of the present invention, a fusion logic strategy of the lesion map is designed based on the fusion logic adjustment data of the lesion map. First, by analyzing the fusion logic adjustment data of the lesion map, the important causal nodes and their interrelationships in the lesion development process are identified and converted into executable logic strategies. When designing the logic strategy, the decision tree algorithm is used to divide different lesion development paths, and different intervention measures are selected according to different lesion stages. The design of the logic strategy not only takes into account the time progression of the lesion, but also combines the individual differences of the patients, such as age, gender, genetic background and other factors. After multiple simulations and adjustments, a lesion map fusion logic strategy suitable for clinical application is finally designed. After the design is completed, this strategy is sent to the cloud platform through the system interface. The cloud platform is responsible for executing the strategy, and continuously optimizes the strategy execution effect through a real-time data feedback mechanism to ensure the efficiency and accuracy of the fusion method of the urology medical knowledge map in practical applications.

[0034] Preferably, step S1 comprises the following steps: Step S11: Acquire the historical medical records of the urology department and the CT images of the lesion site; Step S12: performing data desensitization processing on the historical medical record data of the urology department to obtain desensitized data of the historical medical record data; Step S13: Performing logical description analysis on the desensitized data of historical medical records to obtain logical description data of the medical records; Step S14: performing image region segmentation on the CT image of the lesion site according to the logical description data of the medical history to obtain a CT segmented image of the lesion site.

[0035] In the embodiment of the present invention, it starts with obtaining the medical record data of the urology department and the CT image of the lesion. First, the medical record data of the urology department is extracted from the electronic medical record management system of the hospital. The medical record data includes the patient's medical history, symptom description, diagnosis results, treatment process and examination records. The data extraction adopts a standardized interface to ensure the accurate transmission of the data. For the CT image of the lesion, the image data is usually saved in DICOM format and extracted from the medical image management system. These CT image data contain the lesion scan results of the patient at different time points, and usually record the image information of the lesion. Through the image data management system, all CT images are identified and stored according to the patient ID, and the correctness and integrity of the image data are ensured. The data sources of the medical record data and the CT image are the medical information system and the image storage management system, respectively. During the extraction process, the data will be subjected to a preliminary quality check to ensure that the data is not missing or formatted incorrectly. The data of the historical medical record data of the urology department is desensitized. The purpose of desensitization is to protect the privacy of patients while maintaining the availability of data. First, all personal identity information is removed from the historical medical record data, including the patient's name, ID number, contact information and other information. These personal sensitive information is replaced with irrelevant identifiers or random codes. In addition, it is necessary to perform data fuzzification on specific areas involved in the medical history description, for example, standardize the names of diseases, treatment plans and drug names, and adopt a unified coding system (such as the ICD-10 coding system). For non-public information in other medical records, encryption is adopted to ensure the security of data transmission. In the process of data desensitization, it is necessary to ensure that the desensitized data will not affect the accuracy of subsequent analysis. Therefore, the desensitization process replaces or masks the patient's identity information and sensitive content instead of deleting them, so as to ensure the integrity of the data and the effectiveness of subsequent analysis. Logical description analysis of historical medical records desensitized data. First, the desensitized medical record data is preprocessed, including removing stop words and standardizing disease terms. Then, the medical record text is parsed using natural language processing (NLP) technology to identify key information in the medical record, such as symptoms, diagnosis, treatment plan, etc., and convert it into structured data. The logical description information in the medical record data is obtained through vocabulary analysis, entity recognition and relationship extraction technology. For example, "the patient has frequent urination symptoms" is identified as a symptom description, or "diagnosed with cystitis" is identified as a disease diagnosis record. For the time information in the medical record data, it is also necessary to use time series analysis methods to time the patient's visit date and medical history records for subsequent analysis. The main tools used in this process are rule-based dictionary matching methods and deep learning models, especially the use of BERT (Bidirectional Encoder Representations from Transformers)-based models to semantically understand medical texts.The output of this step is structured logical description data, which includes various symptoms, diagnosis and treatment information in the medical record, and the information is standardized and timed to provide support for the subsequent CT image region segmentation. The image region of the CT image of the lesion is segmented according to the logical description data of the medical record. First, the potential location and type of the lesion are determined using the medical record information obtained in step S13. This information mainly includes the type of disease, the area of ​​the lesion, and the relevant prompts in the symptom description. For example, if it is marked as "bladder tumor" in the patient's medical record, then the lesion manifestation of the bladder area needs to be paid attention to in the CT image. Based on these medical record information, the region of the CT image is calibrated by the image segmentation algorithm. In this process, an image segmentation method based on edge detection, such as the Canny edge detection algorithm, is used to extract the contour of the lesion area for preliminary region division. Next, the region growing algorithm is used to further refine the lesion area to ensure the accuracy of the segmentation result. The region growing algorithm sets a seed point and expands outward from the lesion until the entire lesion area is accurately segmented. Finally, the segmentation results are optimized using a convolutional neural network (CNN) based on deep learning. The CNN model can accurately identify the shape, size, and edges of the lesion area by learning a large amount of labeled data. Through these steps, the CT segmentation image of the lesion area is finally obtained, that is, the accurate division result of the lesion area in the CT image, which provides a basis for the subsequent lesion trend analysis.

[0036] Preferably, step S2 comprises the following steps: Step S21: performing structural morphological analysis on the CT segmented image of the lesion to obtain structural morphological data of the lesion; Step S22: performing synchronous intersection recognition of lesion trends on the lesion site structure morphology data and the lesion site CT segmentation image according to the historical medical record data of the urology department to obtain synchronous intersection data of the lesion trend; Step S23: performing causal correlation analysis on the lesion trend synchronization intersection data to obtain lesion trend synchronization causal data; Step S24: perform implicit correlation deduction based on the synchronous causal data of the lesion trend to obtain causal implicit correlation data of the lesion trend.

[0037] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing structural morphological analysis on the CT segmented image of the lesion to obtain structural morphological data of the lesion; In an embodiment of the present invention, a structural morphological analysis is performed on a CT segmented image of a lesion. First, the CT segmented image of the lesion is preprocessed by an image processing algorithm to ensure that the quality of the image is suitable for subsequent analysis. This includes operations such as image denoising, contrast enhancement and edge sharpening, and uses a median filter to remove noise in the image and enhance important details in the image. Next, a morphological analysis method is applied to analyze the structure of the lesion. Morphological analysis extracts geometric features of the lesion area, such as the shape, size, and edge smoothness of the lesion area, through techniques such as expansion, corrosion, opening and closing operations. This process uses morphological operators to extract key structural information in the image. After obtaining the structural features, the shape of the lesion area is further analyzed using a geometric feature extraction method (such as rectangular fitting, circular fitting, etc.) to obtain structural morphological data of the lesion. The structural morphological data includes the geometric shape, size, and edge features of the lesion, providing structured input data for subsequent lesion trend analysis and causal deduction.

[0038] Step S22: performing synchronous intersection recognition of lesion trends on the lesion site structure morphology data and the lesion site CT segmentation image according to the historical medical record data of the urology department to obtain synchronous intersection data of the lesion trend; In an embodiment of the present invention, the structural morphological data of the lesion site and the CT segmented image of the lesion site are subjected to synchronous intersection identification of lesion trends based on the historical medical record data of the urology department. First, the disease information, symptom description, and examination records in the medical record data are extracted to identify the features related to the lesion, such as the site, type, and symptoms of the patient. Based on this information, the location and morphological features of the lesion area are identified in combination with the CT segmented image of the lesion site. Then, the multidimensional data fusion technology is used to compare and match the structural morphological data of the CT image of the lesion site with the lesion description in the medical record data to identify the intersection of the lesion trend. This process uses a data synchronous identification algorithm, such as a method based on dynamic time warping (DTW), to detect the trend of lesion change by comparing the image segmentation data with the lesion time series in the medical record. For example, if the patient's CT images at different time points show a gradual increase in the lesion area, and the medical record data describes symptoms of "worsening of the condition" or "diffusion of the lesion", the intersection between these data can be determined, thereby obtaining synchronous intersection data of lesion trends. The synchronous intersection data of lesion trends records the change trend of the lesion area, the consistency with the medical record description, and its potential evolution pattern.

[0039] Step S23: performing causal correlation analysis on the lesion trend synchronization intersection data to obtain lesion trend synchronization causal data; In an embodiment of the present invention, causal association analysis is performed on the synchronous intersection data of lesion trends. The causal association analysis aims to find out the causal relationship of lesion changes by analyzing the synchronous intersection data of lesion trends. First, the synchronous intersection data of lesion trends is prepared for causal inference, and the characteristics of lesion area changes are extracted, including morphological changes, size changes, and associations with symptom manifestations of lesions. Statistical methods, such as correlation coefficient analysis and hypothesis testing, are used to analyze the correlation between lesion area changes and patient symptoms, diagnosis, and treatment plans. In addition, the Bayesian network method is used for causal reasoning to establish a causal relationship model between lesion trends and symptom manifestations. The Bayesian network can derive the causal relationship between lesion development and medical history data by calculating conditional probabilities. For example, the Bayesian network algorithm is used to infer whether the enlargement of certain lesion sites is associated with an increased risk of bladder cancer, or whether the appearance of certain symptoms (such as hematuria) directly leads to the aggravation of lesions. The synchronous causal data of lesion trends output by this step include the change pattern of lesions, the inducing factors of symptoms, and the causal path in the evolution of lesions.

[0040] Step S24: perform implicit correlation deduction based on the synchronous causal data of the lesion trend to obtain causal implicit correlation data of the lesion trend.

[0041] In an embodiment of the present invention, implicit association deduction is performed based on the synchronous causal data of the lesion trend. The goal of implicit association deduction is to discover potential, unrevealed association patterns by analyzing causal association data. First, the synchronous causal data of the lesion trend is deeply mined by using statistical inference methods, and the implicit laws of lesion development are discovered through cluster analysis and principal component analysis (PCA) and other techniques. Cluster analysis can group cases with similar characteristics of changes in lesion areas, revealing the correlation between different types of lesion areas. Principal component analysis extracts the main change patterns in lesion data by reducing dimensionality, thereby revealing potential factors that are not revealed in the development of lesions. Then, an association rule mining algorithm (such as the Apriori algorithm) is used to mine hidden laws and associations from causal data. For example, some patients' CT images show a certain morphology of lesions, but the relationship between the morphology and symptoms is not directly described in the medical records. The potential relationship between this lesion morphology and other symptoms can be derived through association rule mining. The results of implicit association deduction provide more insights into the evolution of lesions, help speculate on the future development trend of lesions, and provide a more accurate basis for medical decision-making.

[0042] Preferably, step S22 includes the following steps: Step S221: Perform spatial domain analysis on the lesion site structure morphology data to obtain lesion location distribution data; Step S222: performing a descriptive trend comparison on the lesion location distribution data according to the historical medical records of the urology department to obtain descriptive trend comparison data of the lesion distribution; Step S223: simulating the lesion boundary tissue density similarity difference on the lesion location distribution data and the lesion site CT segmentation image based on the lesion distribution descriptive trend comparison data to obtain the lesion boundary tissue density similarity difference; Step S224: performing boundary transition density difference analysis on the lesion location distribution data according to the boundary tissue density similarity difference to obtain the lesion tissue boundary transition density difference; Step S225: Perform lesion trend synchronization intersection identification on the lesion site structure morphology data according to the lesion boundary tissue density similarity difference and the lesion tissue boundary transition density difference to obtain lesion trend synchronization intersection data.

[0043] In an embodiment of the present invention, the structural morphological data of the lesion site will be processed by spatial domain analysis. First, the structural morphological data of the lesion site, including the geometric shape, size, distribution, etc. of the lesion area, will be converted into spatial data in a three-dimensional coordinate system. By analyzing the distribution of the lesion area in three-dimensional space, a spatial clustering algorithm (such as a K-means clustering algorithm) is used to group the lesion area and determine the spatial position of each type of lesion. Next, a spatial interpolation technique, such as an inverse distance weighted (IDW) method, is used to estimate the density of the lesion area, thereby obtaining the position distribution data of the lesion area in space. The goal of this step is to accurately represent the spatial distribution of the lesion area, which is convenient for subsequent lesion trend analysis and comparison with historical medical record data. The lesion location distribution data will include the spatial location coordinates, distribution density, and the probability of existence of lesions at different spatial locations of the lesion area, providing the necessary spatial information for the subsequent synchronous intersection identification of lesion trends. Based on the historical medical record data of the urology department, the lesion location distribution data is compared and analyzed with the relevant descriptions in the medical record. First, extract the patient's medical history information from the medical record, such as past medical history, symptom records, clinical diagnosis and treatment results, with special attention to the time series data related to the lesion location. By comparing the medical record data of different patients, identify the time evolution trend of the lesion location. Map the lesion location distribution data to the lesion description part in the medical record data for quantitative analysis. Use descriptive statistical methods, such as mean, variance and trend tests (such as Kendall rank correlation test), to perform trend comparison analysis on the data of different lesion locations to identify the law and change trend of lesion distribution. The descriptive trend comparison data of lesion distribution will show the association between the spatial distribution changes of lesion locations and the time series of symptoms, diagnosis, and treatment described in the medical record, such as whether the gradual expansion of a lesion location is consistent with the worsening of symptoms or changes in treatment effects. This data will help predict the future trend of lesion location distribution and provide data support for subsequent lesion boundary analysis. Based on the descriptive trend comparison data of lesion distribution, simulate the similarity difference of lesion boundary tissue density between lesion location distribution data and CT segmentation images of lesion locations. First, the density value of each pixel area in the CT segmentation image of the lesion site will be extracted to represent the density difference between different tissue types (such as normal tissue and lesion tissue). The boundary between the lesion area and the surrounding tissue is identified by comparing the difference in tissue density. Next, a similarity measurement method, such as cosine similarity or Euclidean distance, is used to compare the density of the lesion boundary and the surrounding tissue, and the tissue density similarity difference of the lesion area is calculated. This process can determine the clarity of the lesion area boundary by comparing the density difference between adjacent pixels. By simulating the tissue density difference of the lesion boundary, the density similarity difference of the lesion boundary is obtained. This data can quantify the difference between the lesion area boundary and the normal tissue, reflecting the transition nature of the lesion area and the surrounding tissue.This data will help reveal the clarity of the lesion boundary and its histological characteristics with the surrounding tissue. According to the similarity difference of the lesion boundary tissue density, the boundary transition density difference analysis of the lesion location distribution data is performed. First, the boundary information of the lesion area is extracted, and the tissue density near the boundary is carefully analyzed to determine the transition area at the boundary. In this area, the density of normal tissue and lesion tissue will have a gradual process. Therefore, by calculating the density difference in the boundary area, the density change in the transition area can be quantified. For further analysis, the gradient algorithm is used to analyze the density change at the lesion boundary, calculate the density gradient at each pixel point, and count the density difference in different areas. This process uses image gradient operators (such as Sobel operators) to extract the transition characteristics of the lesion boundary and reflect the tissue transition density difference in the lesion area. The goal of boundary transition density difference analysis is to reveal the transition characteristics between the lesion area and the normal tissue and evaluate the boundary transition characteristics of the lesion development. The lesion tissue boundary transition density difference data finally obtained can describe the transition process between the lesion area and the surrounding tissue in detail, and provide necessary information for further lesion trend synchronous intersection identification. According to the lesion boundary tissue density similarity difference and the lesion tissue boundary transition density difference, the lesion trend synchronous intersection identification of the lesion site structure morphology data is performed. First, the density similarity difference and boundary transition density difference data of the lesion boundary are combined with the structural morphological data of the lesion site to form a multidimensional data set. This data set includes information such as the morphological characteristics of the lesion (such as size, shape, and location), the clarity of the boundary, and the density transition of the tissue. By applying data fusion technology, this information is weighted and integrated to more comprehensively describe the changing trend of the lesion area. Then, trend analysis methods such as dynamic time warping (DTW) and collaborative filtering algorithms are used to synchronously analyze the lesion data at different time points to find the intersection between lesion trends. This analysis process can reveal the evolution of the lesion area in time and space, as well as the potential direction of lesion development. The synchronous intersection data of lesion trends will eventually provide the evolution pattern of the lesion area, help identify the characteristic changes of the lesion at different stages, and thus provide a key clinical basis for the construction of the urology medical knowledge graph.

[0044] Preferably, step S223 includes the following steps: Perform multi-scale spatial coordinate transformation on the lesion location distribution data to obtain multi-scale lesion area calibration data; According to the descriptive trend comparison data of lesion distribution, multi-point neighboring density distribution analysis is performed on the multi-scale lesion area calibration data and the CT segmentation image of the lesion part to obtain multi-point neighboring density distribution data; Perform layered density fitting on the multi-point adjacent density distribution data to obtain layered lesion boundary density data; Based on the layered lesion boundary density data, position density trend deviation analysis is performed to obtain position density trend deviation data; According to the layered lesion boundary density data and the position density trend deviation data, the lesion position distribution data and the CT segmentation image of the lesion site are simulated to obtain the lesion boundary tissue density similarity difference.

[0045] In an embodiment of the present invention, a multi-scale spatial coordinate transformation is performed on the spatial coordinate information in the lesion location distribution data so as to accurately calibrate the lesion area through spatial information at different scales. The scale-invariant feature transform (SIFT) method is adopted to identify the characteristic position of the lesion area at different resolutions through multi-level spatial analysis. Specifically, each spatial coordinate point in the lesion location distribution data is converted into a local feature at different scales, and multiple scale layers are generated through a series of image transformation functions (such as Gaussian pyramid and Laplace pyramid). For each scale layer, the image difference analysis of adjacent layers is used to obtain the fine positioning of the lesion position. Then, the transformed data is fused in combination with the spatial transformation matrix of each scale layer to obtain the final multi-scale lesion area calibration data. This process can effectively improve the positioning accuracy of the lesion area at different resolutions and provide efficient and accurate basic data for subsequent density analysis. By analyzing the distribution of the lesion area at multiple scales, multi-point adjacent density distribution analysis is performed. First, the descriptive trend comparison data of the lesion distribution is combined with the multi-scale lesion area calibration data to determine the position of the center point and the boundary point of the lesion area. The proximity measurement method based on point sets (such as the k-nearest neighbor algorithm) is used to analyze the adjacency relationship between the lesion area and the surrounding tissues. The density difference between each lesion point and its adjacent area is calculated to obtain the adjacent density distribution of each point. In this process, the CT segmentation image of the lesion area is first extracted to analyze the density characteristics of the lesion boundary and its adjacent tissues. Then, the weighted density distribution function is used to perform weighted calculation on each adjacent point to obtain more accurate density distribution data. This analysis can not only accurately reveal the spatial proximity relationship of the lesion area, but also effectively reflect the density difference between the lesion area and the surrounding tissues, providing detailed spatial data support for further lesion boundary analysis. Based on the multi-point adjacent density distribution data, the density of the lesion area is hierarchically fitted. First, according to the density distribution characteristics of the lesion area, the lesion area is divided into multiple levels, usually based on the hierarchical characteristics of the lesion boundary. The density of the lesion area is fitted by the Gaussian mixture model (GMM) or other hierarchical density models to determine the density change trend of the lesion area at different levels. Specifically, each level represents the density distribution of different depths or different proximity relationships of the lesion area, and the density change of the lesion area is fitted at different levels. By fitting the density distribution of each layer, a refined layered lesion boundary density data is obtained. This process can identify the density differences at different levels within the lesion area, help accurately describe the boundary characteristics and change laws of the lesion area, and provide data support for subsequent lesion boundary identification. Based on the layered lesion boundary density data, the position density trend deviation analysis of the density change trend of the lesion area is performed. First, according to the layered density characteristics of the lesion boundary, the density change trend of different positions in the lesion area is calculated, and the density deviation between each layer is quantified.The density change trend at different positions is calculated by using a differential equation or gradient algorithm (such as weighted least squares method). By comparing the density changes at various positions in the lesion area, the degree of deviation of the density trend at different positions in the lesion area is analyzed. This process can effectively evaluate whether the density changes at the lesion boundary are consistent, identify areas with large density deviations, and thus infer the extension direction or lesion trend of the lesion. Ultimately, the obtained position information and density deviation data will provide a quantitative basis for the subsequent accurate simulation of the lesion boundary and lesion trend analysis. Using the layered lesion boundary density data and the position density trend deviation data, the lesion boundary tissue density similarity difference simulation is performed on the lesion position distribution data and the CT segmentation image of the lesion site. First, the layered lesion boundary density data obtained above is combined with the position density trend deviation data to generate a comprehensive density difference data model. Then, the density difference between the lesion area and the surrounding tissue is simulated by the tissue density similarity calculation method (such as mean square error or structural similarity index SSIM). Specifically, the tissue density difference at the lesion boundary will be represented by the difference in pixel values ​​in the CT image, and the similarity difference is calculated by comparing the density changes between the lesion area and the surrounding tissue. The simulation results will provide a quantitative basis for the boundary clarity of the lesion area, help identify the transition area between the lesion and the surrounding tissue, and the expansion trend of the lesion. The final lesion boundary tissue density similarity difference data will provide basic support for the subsequent detailed identification and trend analysis of the lesion boundary, and assist in the construction of the lesion trend part of the urology medical knowledge map.

[0046] Preferably, step S24 comprises the following steps: Step S241: performing structured classification processing on the lesion trend synchronization causal data to obtain lesion development stage division data; Step S242: deducing the stage triggering factors according to the lesion development stage division data to obtain lesion stage triggering factor deduction data; Step S243: performing layer-by-layer factor event simulation analysis on the lesion stage trigger factor deduction data to obtain layer-by-layer factor event analysis data; Step S244: perform implicit association deduction based on the layer-by-layer factor event analysis data and the lesion stage trigger factor deduction data to obtain lesion trend causal implicit association data.

[0047] In the embodiment of the present invention, first, based on the synchronization of causal data based on the lesion trend, the different development stages of the lesion are structured and classified by in-depth analysis of the causal data. In the specific operation, firstly, various causal relationships in the lesion data are identified and marked, including the starting point, development process and end point of the lesion. These causal data are grouped using a clustering analysis algorithm (such as K-means clustering method), and similar causal data are classified into the same stage. Each development stage is divided in detail according to the key time nodes, clinical manifestations and related pathological data of the lesion. Through the time series analysis of the lesion data, combined with the clinical manifestations of the lesion and the changes in the lesion area of ​​CT images, several representative development stages are divided, such as the early stage, development stage and late stage of the lesion. Finally, the lesion development stage division data obtained provides a clear stage basis for subsequent stage deduction and factor analysis, can help accurately identify the characteristics of different stages of the lesion, and provide data support for the reasoning and deduction of the knowledge graph. Based on the lesion development stage division data, the lesion stage triggering factors are deduced. By conducting in-depth analysis of the lesion characteristics and clinical data of each stage, the triggering factors related to the lesion process are extracted. For example, the early stage of the lesion is affected by certain specific external factors (such as infection, trauma, etc.), while in the late stage of the lesion, it is closely related to genetic factors or a long history of chronic diseases. By constructing a multivariate regression model, the triggering factors and their interactions at each stage of the lesion are analyzed, and a stage-by-stage deduction is performed. In the specific deduction process, the triggering factors in the historical medical records, the type of lesion, and the clinical treatment data are combined to identify the internal and external triggering factors in the development of the lesion. Using the inductive reasoning method, by comparing the clinical data of different lesion stages, the etiology and triggering events of each stage are obtained, and finally the deduction data of the triggering factors of the lesion stage are formed. This data will serve as the basis for the next step of layer-by-layer factor analysis to support the causal deduction of lesion trends. Based on the deduction data of the triggering factors of the lesion stage, a layer-by-layer factor event simulation analysis is performed. First, according to the deduced lesion triggering factors, the triggering factors of each stage are analyzed and simulated layer by layer according to the different development stages of the lesion. By simulating the events and changes caused by different triggering factors of the lesion at each stage, the event chain is gradually constructed. The event association relationship between each factor is represented by a causal graph model, and the probability of the event is calculated using the Bayesian network algorithm. The model can capture the dependencies between different factors and predict future events based on the time series relationship of the lesion triggering factors. Through layer-by-layer simulation, the key events and their transformation paths at different stages of the lesion are analyzed. In specific operations, the triggering factors of each stage are summarized first, and then the impact of different triggering factors on the progression of the lesion is simulated through the probability model of event occurrence, and finally the layer-by-layer factor event analysis data is obtained. This data reflects the hierarchical changes in the lesion process and provides a detailed event chain for implicit association deduction.Combine the layer-by-layer factor event analysis data and the lesion stage trigger factor deduction data to perform implicit association deduction. Through the causal deduction method, the implicit associations that are not directly observed in the lesion trend are identified. First, the events in the layer-by-layer factor event analysis data and the deduced trigger factor data are combined, and the potential causal associations between different stages are analyzed through statistical analysis methods (such as principal component analysis or causal relationship inference). Specifically, the time series analysis method is used to explore the implicit patterns in the development of the lesion, such as some potential risk factors gradually accumulate at a certain stage and eventually trigger the aggravation of the lesion. Through the complex network analysis model (such as the convolutional network, GCN), the causal relationship of the lesion trend is deduced to identify the implicit connection between the various factors. Through this process, the potential causal relationship that is not directly identified in the lesion development process can be found, and then the causal implicit association data of the lesion trend can be obtained. This data will provide important support for the in-depth analysis of lesion trends and the prediction of future lesion risks, and provide more comprehensive causal deduction information for the construction of the urology medical knowledge graph.

[0048] Preferably, step S3 comprises the following steps: Step S31: constructing a graph relationship for the lesion trend causal implicit correlation data to obtain a lesion causal trend relationship graph; Step S32: Perform knowledge graph representation learning on the lesion causal trend relationship graph to obtain graph association structure learning data; Step S33: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the graph association structure learning data to obtain lesion graph fusion logic adjustment data.

[0049] In an embodiment of the present invention, a graph relationship is first constructed for the causal implicit association data of the lesion trend. The goal of graph relationship construction is to form a structured graph data by parsing the causal implicit association data of the lesion, in which each node represents a lesion causal event or lesion stage, and each edge represents the association relationship between different lesion causal events or stages. In specific implementation, the concepts of nodes and edges in graph theory are used to represent the lesion stage, triggering factors, and causal relationships between lesions as a graph structure. The attributes of each node include the specific stage of the lesion, the time of occurrence, the triggering factor, clinical data, etc., and the attributes of the edge describe the strength and type of the association relationship (such as causal relationship, influence relationship, etc.). In this process, the graph convolution network (GCN) algorithm in deep learning is used to learn the potential relationship between nodes. This method can gradually construct a causal trend relationship graph of lesions based on implicit association data and local information. In the process of graph construction, the progression path of the lesion is hierarchically analyzed to determine the temporal relationship, influence and dependency relationship between different lesion stages and events, so as to form a complete lesion causal trend relationship graph. Based on the lesion causal trend relationship graph obtained in step S31, knowledge graph representation learning is performed to obtain graph association structure learning data. In specific operations, graph embedding technology is used to represent the lesion causal trend relationship graph, and each node and edge in the graph is converted into a low-dimensional vector representation. This step uses a graph embedding algorithm, such as TransE or Node2Vec, to map nodes and edges to a low-dimensional space, so that similar nodes and edges in the low-dimensional space are also represented similarly. Specifically, the graph embedding algorithm first calculates the embedding vector of each node according to the structural relationship between the nodes and edges in the graph, and then iteratively optimizes the embedding vector by optimizing the objective function (such as minimizing the distance between the embedding vector and the adjacency relationship) until the relationship between the nodes is effectively represented in the embedding space. Through this process, the association pattern of nodes and edges in the graph can be effectively captured to form graph association structure learning data, which provides a basis for further graph fusion and knowledge reasoning. In the process of knowledge graph representation learning, the optimization method used is an optimization technique based on negative sampling to improve learning efficiency and reduce computational complexity. Based on the graph association structure learning data, the graph fusion logic adjustment is performed on the lesion causal trend relationship graph to obtain the lesion graph fusion logic adjustment data. The purpose of graph fusion is to merge and optimize the lesion data from different sources to form a unified and complete lesion graph. First, the lesion causal trend relationship graph is analyzed to identify redundant and conflicting information between different data sources. By comparing similar or repeated nodes and edges in the graph, a graph aggregation algorithm is used, such as the information transmission mechanism in the graph convolutional network (GCN), to integrate information from multiple data sources, eliminate redundancy, and optimize the representation of nodes and edges.During the graph fusion process, logical adjustments need to be made according to the actual development rules of the lesion to ensure that the causal relationship and impact path between different stages are reasonable. For example, if the data of a certain lesion stage is contradictory or inconsistent during the fusion process, constraints can be used to correct and optimize it by adjusting the weights between nodes in the graph, the direction or type of the edges to eliminate these conflicts. Finally, through graph fusion, the lesion graph fusion logic adjustment data is obtained. These data reflect the comprehensive trend and causal relationship of the lesion, and provide accurate structural data support for the further application and reasoning of the urology medical knowledge graph.

[0050] Preferably, step S33 includes the following steps: Step S331: performing a topological correlation density analysis on the lesion causal trend relationship graph according to the graph correlation structure learning data to obtain topological correlation density data; Step S332: Based on the topological association density data, the relative centrality of the nodes in the lesion causal trend relationship map is evaluated to obtain the relative centrality of the nodes in the map; Step S333: performing multi-stage weight adjustment on the nodes of the lesion causal trend relationship map according to the topological association density data and the relative centrality of the map nodes to obtain multi-stage weight adjustment data for the nodes; Step S334: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the topological association density data, the graph node relative centrality and the node multi-stage weight adjustment data to obtain the lesion graph fusion logic adjustment data.

[0051] In the embodiment of the present invention, the lesion causal trend relationship map is first subjected to a topological association density analysis, the goal being to reveal the closeness and distribution characteristics between nodes and edges in the map, and to obtain topological association density data. Topological association density is an indicator for measuring the strength and closeness of the mutual association of nodes in the map, and is usually completed by calculating the degree of each node (i.e., the number of edges directly connected to the node) and the connection pattern of the edges. Specifically, the adjacency matrix in graph theory is used to represent the map, and the weighted calculation of the matrix is ​​used to quantify the strength of the association between nodes. By analyzing the mutual connections between nodes, it is determined which nodes are in the core position of the map and which nodes are in the peripheral position. This analysis is based on the adjacency relationship of the nodes and the weight of the edges, and uses standard topological density calculation methods, such as the degree centrality and edge density of the nodes, and combines the density formula of the graph to calculate the local and global density of the entire map. The topological association density data provides the connection closeness of different regions in the map, and provides a basis for subsequent node evaluation and map optimization. Based on the topological association density data, in this step, the nodes in the lesion causal trend relationship map are evaluated for relative centrality to obtain the relative centrality of the map nodes. Node centrality is an indicator that describes the importance of a node in a graph, and its evaluation is based on the connection between the node and other nodes. When evaluating, first calculate the degree centrality (i.e., the number of edges directly connected to the node) of each node in the graph, while considering the position of the node in the topological structure. The weighted centrality method is used to weight the influence of each node through the topological association density data, evaluate the direct and indirect relationship between the node and other nodes, and ensure that the centrality evaluation not only depends on the degree of the node, but also considers the network position of the node. The specific evaluation method includes evaluating the influence of the node in the entire lesion causal relationship graph based on traditional graph centrality indicators such as Betweenness and Closeness, combined with the topological density information of the graph. Relative centrality is to compare and calculate the centrality ranking of each node among all nodes, and sort them according to the importance of the nodes, and finally obtain the relative centrality data of each node. Based on the topological association density data and the relative centrality of the graph nodes, the nodes in the lesion causal trend relationship graph are multi-stage weighted. First, based on the topological association density data and node centrality obtained in steps S331 and S332, determine the importance of each node in different lesion stages and assign corresponding weights. The logic followed by the weight adjustment is that nodes in the core area with higher centrality have a stronger influence in the early stages of lesion development, while nodes located in the periphery or with lower importance gradually weaken their influence in the later stages. By calculating the weighted value of each node at each stage, the role and relationship of the nodes in the graph are adjusted to ensure that the node weights at each stage are more in line with the development trend of the lesion.Specifically, a weighted graph method is used to adjust the weight value of each node, and the weight value of the node varies with the stage of the lesion development. By combining the topological density analysis and the evaluation data of the node centrality, it is ensured that the node weight adjustment is carried out according to the relative importance of the node and the stage of the lesion process, so as to obtain the node multi-stage weight adjustment data. Based on the topological association density data, the relative centrality of the graph nodes and the multi-stage weight adjustment data of the nodes, the graph fusion logic adjustment of the lesion causal trend relationship graph is carried out, and finally the lesion graph fusion logic adjustment data is obtained. The graph fusion logic adjustment is a process of optimizing the data in the lesion causal trend relationship graph, aiming to integrate the causal relationship and influence path of each node. First, the graph structure evaluated by the topological association density data and the node centrality is combined with the multi-stage weight adjustment data of the nodes to analyze the interaction and dependency between the nodes in the graph. Then, by adjusting the nodes and their connection relationships, the causal relationship between the nodes in the graph is optimized, especially for those nodes with higher centrality, to ensure that their causal relationship is highlighted, while the relationship of the edge nodes can be appropriately weakened. Fusion logic adjustment also includes adjusting the connection strength and direction between nodes in the graph, eliminating redundant information, and enhancing the structural consistency and accuracy of the lesion relationship graph. This process can be completed through graph optimization algorithms, such as the graph filtering method in the convolutional network, which dynamically adjusts the association between nodes according to their relative importance and multi-stage weights. Ultimately, the lesion graph fusion logic adjustment data obtained provides precise structural support for subsequent knowledge reasoning and disease prediction.

[0052] Preferably, the present invention further provides a fusion system of urology medical knowledge graphs, which is used to execute the fusion method of urology medical knowledge graphs as described above. The fusion system of urology medical knowledge graphs includes: The image region segmentation module is used to obtain the historical medical records of the urology department and the CT image of the lesion site; the image region of the CT image of the lesion site is segmented according to the historical medical records of the urology department to obtain the CT segmentation image of the lesion site; The association analysis module is used to identify the synchronous intersection of lesion trends on the CT segmented images of the lesion parts according to the historical medical records of the urology department, and obtain the synchronous intersection data of lesion trends; perform implicit association deduction on the synchronous intersection data of lesion trends, and obtain the causal implicit association data of lesion trends; The graph fusion logic adjustment module is used to perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; The logic strategy design module is used to design the logic strategy based on the lesion map fusion logic adjustment data, obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

[0053] Preferably, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed, the method for fusing the urology medical knowledge graph as described in any one of the above is implemented.

[0054] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0055] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A fusion method for urology medical knowledge graph, characterized in that: The following steps are involved: Step S1: Acquire the historical medical records of the urology department and the CT image of the lesion; perform image region segmentation on the CT image of the lesion according to the historical medical records of the urology department to obtain a CT segmented image of the lesion; Step S2: performing synchronous intersection recognition of lesion trends on the CT segmented images of the lesion site according to the historical medical records of the urology department to obtain synchronous intersection data of lesion trends; performing implicit association deduction on the synchronous intersection data of lesion trends to obtain causal implicit association data of lesion trends; Step S3: Perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; Performing atlas fusion logic adjustment according to atlas association structure learning data to obtain lesion atlas fusion logic adjustment data; Step S4: Design a logic strategy based on the lesion map fusion logic adjustment data to obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

2. The fusion method of urology medical knowledge graph according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire the historical medical records of the urology department and the CT images of the lesion site; Step S12: performing data desensitization processing on the historical medical record data of the urology department to obtain desensitized data of the historical medical record data; Step S13: Performing logical description analysis on the desensitized data of historical medical records to obtain logical description data of the medical records; Step S14: performing image region segmentation on the CT image of the lesion site according to the logical description data of the medical history to obtain a CT segmented image of the lesion site.

3. The fusion method of urology medical knowledge graph according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing structural morphological analysis on the CT segmented image of the lesion to obtain structural morphological data of the lesion; Step S22: performing synchronous intersection recognition of lesion trends on the lesion site structure morphology data and the lesion site CT segmentation image according to the historical medical record data of the urology department to obtain synchronous intersection data of the lesion trend; Step S23: performing causal correlation analysis on the lesion trend synchronization intersection data to obtain lesion trend synchronization causal data; Step S24: perform implicit correlation deduction based on the synchronous causal data of the lesion trend to obtain causal implicit correlation data of the lesion trend.

4. The fusion method of urology medical knowledge graph according to claim 3 is characterized in that: Step S22 includes the following steps: Step S221: Perform spatial domain analysis on the structural morphological data of the lesion site to obtain lesion location distribution data; Step S222: performing a descriptive trend comparison on the lesion location distribution data according to the historical medical records of the urology department to obtain descriptive trend comparison data of the lesion distribution; Step S223: simulating the lesion boundary tissue density similarity difference on the lesion location distribution data and the lesion site CT segmentation image based on the lesion distribution descriptive trend comparison data to obtain the lesion boundary tissue density similarity difference; Step S224: performing boundary transition density difference analysis on the lesion location distribution data according to the boundary tissue density similarity difference to obtain the lesion tissue boundary transition density difference; Step S225: Perform lesion trend synchronization intersection identification on the lesion site structure morphology data according to the lesion boundary tissue density similarity difference and the lesion tissue boundary transition density difference to obtain lesion trend synchronization intersection data.

5. The fusion method of urology medical knowledge graph according to claim 4 is characterized in that: Step S223 includes the following steps: Perform multi-scale spatial coordinate transformation on the lesion location distribution data to obtain multi-scale lesion area calibration data; According to the descriptive trend comparison data of lesion distribution, multi-point neighboring density distribution analysis is performed on the multi-scale lesion area calibration data and the CT segmentation image of the lesion part to obtain multi-point neighboring density distribution data; Perform layered density fitting on the multi-point adjacent density distribution data to obtain layered lesion boundary density data; Based on the layered lesion boundary density data, position density trend deviation analysis is performed to obtain position density trend deviation data; According to the layered lesion boundary density data and the position density trend deviation data, the lesion position distribution data and the CT segmentation image of the lesion site are simulated to obtain the lesion boundary tissue density similarity difference.

6. The fusion method of urology medical knowledge graph according to claim 3 is characterized in that: Step S24 includes the following steps: Step S241: performing structured classification processing on the lesion trend synchronization causal data to obtain lesion development stage division data; Step S242: deducing the stage triggering factors according to the lesion development stage division data to obtain lesion stage triggering factor deduction data; Step S243: performing layer-by-layer factor event simulation analysis on the lesion stage trigger factor deduction data to obtain layer-by-layer factor event analysis data; Step S244: perform implicit association deduction based on the layer-by-layer factor event analysis data and the lesion stage trigger factor deduction data to obtain lesion trend causal implicit association data.

7. The fusion method of urology medical knowledge graph according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: constructing a graph relationship for the lesion trend causal implicit correlation data to obtain a lesion causal trend relationship graph; Step S32: Perform knowledge graph representation learning on the lesion causal trend relationship graph to obtain graph association structure learning data; Step S33: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the graph association structure learning data to obtain lesion graph fusion logic adjustment data.

8. The fusion method of urology medical knowledge graph according to claim 7 is characterized in that: Step S33 includes the following steps: Step S331: performing a topological correlation density analysis on the lesion causal trend relationship graph according to the graph correlation structure learning data to obtain topological correlation density data; Step S332: Based on the topological association density data, the relative centrality of the nodes in the lesion causal trend relationship map is evaluated to obtain the relative centrality of the nodes in the map; Step S333: performing multi-stage weight adjustment on the nodes of the lesion causal trend relationship map according to the topological association density data and the relative centrality of the map nodes to obtain multi-stage weight adjustment data for the nodes; Step S334: Performing graph fusion logic adjustment on the lesion causal trend relationship graph according to the topological association density data, the graph node relative centrality and the node multi-stage weight adjustment data to obtain the lesion graph fusion logic adjustment data.

9. A fusion system for urology medical knowledge graph, characterized in that: The fusion method for the urology medical knowledge graph according to claim 1 is used to implement the fusion system of the urology medical knowledge graph, comprising: The image region segmentation module is used to obtain the historical medical records of the urology department and the CT image of the lesion site; the image region of the CT image of the lesion site is segmented according to the historical medical records of the urology department to obtain the CT segmentation image of the lesion site; The association analysis module is used to identify the synchronous intersection of lesion trends on the CT segmented images of the lesion parts according to the historical medical records of the urology department, and obtain the synchronous intersection data of lesion trends; perform implicit association deduction on the synchronous intersection data of lesion trends, and obtain the causal implicit association data of lesion trends; The graph fusion logic adjustment module is used to perform knowledge graph representation learning on the causal implicit association data of the lesion trend to obtain graph association structure learning data; perform graph fusion logic adjustment based on the graph association structure learning data to obtain lesion graph fusion logic adjustment data; The logic strategy design module is used to design the logic strategy based on the lesion map fusion logic adjustment data, obtain the lesion map fusion logic strategy, and send the lesion map fusion logic strategy to the cloud platform to execute the fusion method of the urology medical knowledge map.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, characterized in that when the computer program is executed, the method for fusing the urology medical knowledge graph as described in any one of claims 1-8 is implemented.

Images