Disease risk assessment method and device based on disease risk mapping knowledge domain, equipment and medium

Abstract

The invention relates to the technical field of medical data processing, and discloses a disease risk assessment method based on a disease risk knowledge graph, the disease risk knowledge graph comprises a disease risk rule and a disease knowledge entity, and the disease knowledge entity comprises a focus position entity; performing organ positioning according to the physical examination data of the target object, and determining a target organ; performing organ matching and index data matching in a disease risk rule based on the target organ and the physical examination data to obtain a risk matching rule corresponding to the target organ; performing disease risk level analysis on the target organ according to the risk matching rule to obtain a disease risk level of the target object about the target organ; generating a physical examination report of the target object according to the physical examination data, the disease risk level and the target focus position; wherein the physical examination report comprises a three-dimensional model used for displaying the target focus position. The method has the beneficial effects that the pertinence and efficiency of disease risk assessment are improved, and the target object is helped to understand the health state of the target object.

Description

Technical Field

[0001] The present application relates to the field of medical data processing technology, and in particular to a disease risk assessment method, device, equipment and medium based on a disease risk knowledge graph. Background Art

[0002] With technological advancements in the medical field, the amount of medical data generated during physical examinations has exploded. This includes a variety of data, including test data, medical imaging data, and laboratory test data. The complexity and multidisciplinary nature of this data place higher demands on physical examination physicians. Physical examination physicians often possess extensive medical knowledge to facilitate the interpretation of multidisciplinary medical data. However, they may lack in-depth knowledge of each discipline, resulting in an inability to accurately associate a patient's disease risk with a specific organ when analyzing physical examination data. Furthermore, patients may have difficulty understanding some of the medical terminology used by physical examination physicians, resulting in an inability to accurately understand their own health status and disease risk, which in turn affects their level of cooperation during treatment.

[0003] In related technologies, the targetedness of disease risk assessment methods still needs to be improved. Summary of the Invention

[0004] The present application provides a disease risk assessment method, apparatus, equipment and medium based on a disease risk knowledge graph. By focusing on the target organs of the target object, the targetedness and efficiency of the disease risk assessment based on the target organs are improved. At the same time, the fixed position of the organs is utilized, and the intuitiveness of the assessment results is improved through three-dimensional model display, helping the target object to understand its own health status.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, embodiments of the present application provide a disease risk assessment method based on a disease risk knowledge graph, wherein the disease risk knowledge graph includes disease risk rules and disease knowledge entities, wherein the disease knowledge entities include lesion location entities; the method comprises: Organ positioning is performed based on the physical examination data of the target subject to determine the target organ; Performing organ matching and indicator data matching in the disease risk rules based on the target organ and the physical examination data, obtaining a risk matching rule corresponding to the target organ; performing a disease risk level analysis on the target organ according to the risk matching rule to obtain a disease risk level of the target subject with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target subject suffers from a disease to be verified, and the disease to be verified corresponds to a target lesion location in the lesion location entity; A physical examination report of the target object is generated according to the physical examination data, the disease risk level and the target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

[0006] The disease risk assessment method based on the disease risk knowledge graph proposed in the embodiment of the present application first locates the target organ that needs to be analyzed for disease risk based on the physical examination data of the target object; secondly, based on the target organ and the physical examination data, the risk matching rule corresponding to the target organ is determined, so that the disease risk level of the target organ and its target lesion location are obtained through disease risk level analysis; finally, a physical examination report is generated based on the physical examination data and the disease risk level, and the target lesion location is displayed through a three-dimensional model. Compared with the relevant technology, the present application first locates the target organ of the target object in the process of disease risk assessment, and matches the disease risk rules according to the target organ, thereby narrowing the scope of rules that need to be matched in the analysis process, effectively improving the correlation between the disease risk level and the target organ, and the accuracy of the analysis results. At the same time, the position of the organ in the target object's body is usually fixed, so that the target organ and the target lesion location can be accurately and intuitively displayed through three-dimensional modeling, thereby improving the target object's understanding of the disease risk assessment results.

[0007] Optionally, the physical examination data includes a lesion size of the target object; and generating a physical examination report of the target object according to the physical examination data, the disease risk level, and the target lesion location includes: Performing three-dimensional modeling on the target object to obtain a three-dimensional model of the object; Based on the lesion size and the target lesion position, performing three-dimensional modeling of the target lesion in the object three-dimensional model to obtain a target lesion model; Data integration is performed based on the object three-dimensional model, the target lesion model, the disease risk level and the physical examination data to obtain the physical examination report; wherein the disease risk level is displayed around the target lesion model, and the physical examination report is an interactive digital report.

[0008] Optionally, the number of target organs is at least two, and the physical examination report includes a primary model and at least two secondary models corresponding to the target organs, the primary model is a three-dimensional model of the object, the secondary model includes the target lesion model, and the secondary model is displayed by selecting any target organ.

[0009] Optionally, the disease risk knowledge graph is constructed in the following manner: Acquire professional knowledge data, perform entity recognition and relationship extraction on the professional knowledge data, and obtain the disease knowledge entities and entity relationships between the disease knowledge entities; wherein the disease knowledge entities also include organ entities, disease type entities, and symptom indicator entities; A hierarchical structured graph is constructed for the disease knowledge entities according to the entity relationships to obtain the disease risk knowledge graph; wherein the lesion location entity is subordinate to the organ entity and corresponds to the disease type entity, and the symptom indicator entity is subordinate to the disease type entity.

[0010] Optionally, the disease risk rule includes at least one abnormal indicator data in the physical examination data; and the disease risk knowledge graph is updated in the following manner: Performing index screening on abnormal indicator data of the historical object according to the risk matching rule of the historical object, and determining abnormal indicator data not used in the historical disease risk assessment as associated indicator data; wherein the historical object is the target object of the historical disease risk assessment; Extract risk rules based on the associated indicator data and the disease risk level of the historical object to obtain a risk rule to be confirmed; wherein the risk rule to be confirmed includes at least one of the associated indicator data; In response to a confirmation operation on the risk rule to be confirmed, the risk rule to be confirmed is added to the disease risk rule.

[0011] Optionally, the disease risk rule includes a disease type, and the disease type corresponds to a diseased organ; performing organ matching and indicator data matching in the disease risk rule based on the target organ and the physical examination data to obtain a risk matching rule corresponding to the target organ includes: Performing organ-corresponding screening on the disease risk rules to obtain a disease risk rule in which the diseased organ is the target organ as the organ association rule; The risk matching rule is obtained by performing data comparison based on the physical examination data of the target object in the organ association rule.

[0012] Optionally, the risk matching rule corresponds to a disease risk degree and a risk weight; and performing disease risk level analysis on the target organ according to the risk matching rule to obtain the disease risk level of the target subject with respect to the target organ includes: Performing weighted calculation on the disease risk degree corresponding to the risk matching rule according to the risk weight to obtain weighted risk data; The disease risk level of the target object is determined based on the numerical relationship between the weighted risk data and a preset risk threshold.

[0013] In a second aspect, an embodiment of the present application provides a disease risk assessment device based on a disease risk knowledge graph, wherein the disease risk knowledge graph includes disease risk rules and disease knowledge entities, wherein the disease knowledge entities include lesion location entities; the device includes: An organ positioning module is used to locate organs based on the physical examination data of the target object and determine the target organ; A rule matching module, configured to perform organ matching and indicator data matching in the disease risk rule based on the target organ and the physical examination data, and obtain a risk matching rule corresponding to the target organ; a risk assessment module, configured to perform a disease risk level analysis on the target organ according to the risk matching rule to obtain a disease risk level of the target subject with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target subject suffers from a disease to be verified, and the disease to be verified corresponds to a target lesion location in the lesion location entity; A report generation module is used to generate a physical examination report of the target object based on the physical examination data, the disease risk level and the target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

[0014] In a third aspect, an embodiment of the present application provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the method described in any one of the above embodiments by executing the computer instructions.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute any one of the methods in the above embodiments.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute any one of the methods described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1A step diagram of a disease risk assessment method based on a disease risk knowledge graph provided in an embodiment of the present application; Figure 2 This is a diagram of the steps for integrating a physical examination report in an embodiment of the present application; Figure 3a This is a schematic diagram of a physical examination report in an embodiment of the present application; Figure 3b This is a schematic diagram of a physical examination report in an embodiment of the present application; Figure 4 A diagram showing the steps for constructing a disease risk knowledge graph in an embodiment of the present application; Figure 5 A diagram showing the steps for updating the disease risk knowledge graph in an embodiment of the present application; Figure 6 A diagram showing the steps for obtaining risk matching rules in an embodiment of the present application; Figure 7 This is a step diagram for analyzing disease risk levels in an embodiment of the present application; Figure 8 A module diagram of a disease risk assessment device based on a disease risk knowledge graph provided in an embodiment of the present application; Figure 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0020] With rising health awareness, people are increasingly paying attention to their health status and disease risks, prompting a growing preference for regular physical examinations to promptly identify potential health issues. Simultaneously, with technological advances in the medical field, the amount of medical data generated during physical examinations has exploded, including test data, medical imaging data, and laboratory test data. The complexity and multidisciplinary nature of this data place higher demands on physical examination physicians, who must be able to comprehensively integrate multidisciplinary medical knowledge to provide accurate diagnoses.

[0021] In reality, doctors who perform physical exams often possess extensive medical knowledge to facilitate the interpretation of multidisciplinary medical data, but they may lack in-depth knowledge of each individual discipline. This results in doctors being unable to accurately associate a patient's disease risk with specific organs when analyzing the data, resulting in the examination results failing to reveal potential problems with these organs. Furthermore, patients may have difficulty understanding some of the medical terminology and imaging materials used by doctors, preventing them from accurately understanding their health status and impacting their cooperation during treatment.

[0022] Based on the above problems, the present application provides a disease risk assessment method, device, equipment and medium based on a disease risk knowledge graph, wherein the disease risk knowledge graph includes disease risk rules and disease knowledge entities, and the disease knowledge entities include lesion location entities; the method includes: performing organ positioning according to the physical examination data of the target object to determine the target organ; performing organ matching and indicator data matching in the disease risk rules based on the target organ and the physical examination data to obtain the risk matching rules corresponding to the target organ; performing disease risk level analysis on the target organ according to the risk matching rules to obtain the disease risk level of the target object regarding the target organ; generating a physical examination report for the target object based on the physical examination data, disease risk level and target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

[0023] The disease risk assessment method based on the disease risk knowledge graph provided in this application first locates the target organ that needs to undergo disease risk analysis based on the physical examination data of the target object; secondly, based on the target organ and the physical examination data, the risk matching rules corresponding to the target organ are determined, so as to obtain the disease risk level of the target organ and its target lesion location through disease risk level analysis; finally, a physical examination report is generated based on the physical examination data and the disease risk level, and the target lesion location is displayed through a three-dimensional model.

[0024] Compared to related technologies, this application first locates the target organ of the target subject during the disease risk assessment process and matches the disease risk rules based on the target organ, thereby narrowing the scope of rules that need to be matched during the analysis process, effectively improving the correlation between the disease risk level and the target organ, and the accuracy of the analysis results. At the same time, the position of the organ in the target subject is usually fixed, making it possible to accurately and intuitively display the target organ and target lesion location through three-dimensional modeling, improving the target subject's understanding of the disease risk assessment results.

[0025] The disease risk assessment method based on the disease risk knowledge graph provided in this specification can be applied to the physical examination data of the target subject to perform disease risk assessment on the target organ of the target subject. The target organ can be an organ of a physiological system such as the cardiovascular system, respiratory system, or digestive system, and the physical examination data can include examination items for the target organ. It is understood that this method can also be used for targeted disease risk assessment of objects other than organs after adaptive modification.

[0026] According to an embodiment of the present application, an embodiment of a disease risk assessment method based on a disease risk knowledge graph is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] In this embodiment, a disease risk assessment method based on a disease risk knowledge graph is provided, which can be used to perform disease risk assessment on the target organ of the target object based on the physical examination data of the target object. Figure 1 As shown, the disease risk knowledge graph includes disease risk rules and disease knowledge entities, and the disease knowledge entities include lesion location entities; the method includes: S100. Perform organ positioning based on the physical examination data of the target object to determine the target organ.

[0028] S200. Perform organ matching and indicator data matching in disease risk rules based on the target organ and physical examination data to obtain a risk matching rule corresponding to the target organ.

[0029] S300. Analyze the disease risk level of the target organ according to the risk matching rules to obtain the disease risk level of the target object with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target object suffers from the disease to be verified, and the disease to be verified corresponds to the target lesion location in the lesion location entity.

[0030] S400. Generate a physical examination report for the target subject based on the physical examination data, the disease risk level, and the target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

[0031] Disease risk rules may include risk judgment conditions, disease types, and disease risk levels. The risk judgment conditions may be derived from the target subject's physical examination data and include abnormal indicator data that deviates from normal data. The types of abnormal indicator data include, but are not limited to, indicator values, qualitative judgment results, or medical imaging data. The risk judgment conditions correspond to the disease types. Based on at least one data item and the logical relationship between the data items, the corresponding disease type is determined as the disease to be verified. The disease risk level of the disease to be verified is then determined based on the degree of deviation between the abnormal indicator data and the normal data.

[0032] The risk matching rule can be at least one rule that has an organ matching relationship and an indicator data matching relationship with the physical examination data, wherein the organ matching relationship indicates that the disease types included in the risk matching rule are all targeted at the target organ, and the indicator data matching relationship indicates that the indicator data included in the risk judgment conditions of the risk matching rule corresponds to the indicator data in the physical examination data, and the physical examination data can meet the risk judgment conditions.

[0033] Specifically, for the target object, the physical examination data of the target object is obtained. It should be noted that the physical examination data may include the basic indicator data, test indicator data or imaging examination results of the target object, wherein the basic indicator data may be data such as the age, gender, height or weight of the target object. The test indicator data and imaging examination results and other data may correspond to corresponding examination items. These examination items may be specifically designed according to the structure, function or common disease types of specific organs, and are used to reflect the disease risk of specific organs. By identifying the examination items accepted by the target object, the organs of the target object that may have disease risks can be determined as target organs.

[0034] Furthermore, after determining the target organ of the target subject, an organ match is performed against the disease risk rules based on the target organ to select the disease risk rule corresponding to the target organ as the organ matching rule. It is understood that disease risk rules are specific to specific disease types, and disease types are specific to specific organs. By matching the specific organs corresponding to the disease risk rules with the target organ, the scope of rule matching can be effectively narrowed, thereby improving the specificity of the risk matching rules for the target organ, and thus enhancing the accuracy and efficiency of disease risk assessment.

[0035] On the basis of obtaining the organ matching rules, based on the physical examination data of the target object, the indicator data is matched in the organ matching rules to determine whether the risk judgment conditions in the organ matching rules are met, and the organ matching rules that meet the risk judgment conditions are used as risk matching rules.

[0036] In some embodiments, the physical examination data of the evaluation object is used as the current physical examination data of the target object, and the historical physical examination data generated by the target object at multiple time points in the past are obtained. First, the historical physical examination data is screened to obtain relevant physical examination data, specifically including: performing abnormal screening of indicator data according to the current physical examination data to obtain current abnormal data; performing abnormal screening of indicator data according to the historical physical examination data to obtain historical abnormal data; calculating the correlation between the current abnormal data and the historical abnormal data, and taking the historical physical examination data corresponding to the historical abnormal data that meets the correlation requirements as the relevant physical examination data. Among them, the correlation between the current abnormal data and the historical abnormal data can include type correlation or numerical correlation of the abnormal data, etc., to determine whether the target object has a recurrence of the disease.

[0037] In other embodiments, the process of obtaining relevant physical examination data may also include: performing an indicator data trend analysis based on the historical physical examination data closest to the current time point and the current physical examination data to obtain the current health change trend of the target object, and the current health change trend corresponds to the current time point; performing an indicator data trend analysis on the historical physical examination data according to the time arrangement order of the historical physical examination data to obtain the historical health change trend of the target object, and the historical health change trends respectively correspond to the time points when the historical physical examination data were generated; calculating the similarity between the current health change trend and the historical health change trend, and taking the time point corresponding to the historical health change trend that meets the similarity condition as the target time point, and taking the historical physical examination data at the target time point as the relevant physical examination data. It can be understood that similarity in the changing trends of the indicator data indicates that the patient may suffer from the same disease. Judging by the changing trends can effectively capture the early manifestations of the same disease and quickly discover potential health problems of the target object.

[0038] Furthermore, the relevant physical examination data is weightedly fused with the current physical examination data to obtain state-weighted data. There can be multiple pieces of relevant physical examination data, each assigned different fusion weights. The size of the fusion weight is related to the time interval between the relevant physical examination data and the current physical examination data. The longer the time interval between the two, that is, the further the relevant physical examination data is from the current time point, the smaller the fusion weight; correspondingly, the shorter the time interval between the two, that is, the closer the relevant physical examination data is to the current time point, the larger the fusion weight. Based on the state-weighted data, indicator data is matched in the organ matching rule to obtain the risk matching rule corresponding to the target organ.

[0039] It is understandable that if the target object has similar physical examination data or data change trends, it means that the target object may suffer from the same disease in the same organ, that is, the current health status of the target object is a pattern that is easy to recur. The state-weighted data combines the historical physical examination data of the target object that is relatively similar to the current physical examination data, and more comprehensively and accurately represents the current health status of the target object, so that such patterns can be specifically analyzed to help doctors formulate corresponding treatment plans.

[0040] Furthermore, based on at least one risk matching rule obtained, the disease risk of the target organ is analyzed to obtain the disease risk level of the target object with respect to the target organ. It should be noted that the multiple risk matching rules for the target organ may correspond to different disease types, and the risk matching rules corresponding to the same disease type may also include different disease risk levels. All diseases corresponding to the risk matching rules are regarded as the diseases to be verified that the target object may suffer from, and a comprehensive analysis is performed based on the disease risk levels corresponding to each disease to be verified in the risk matching rules to obtain the risk level of each disease to be verified that the target object may suffer from in the target organ. It can be understood that each disease to be verified corresponds to its own target lesion location, and the target lesion location and the corresponding relationship can be pre-stored as an entity in the disease risk knowledge graph.

[0041] It should be noted that the disease risk knowledge graph also stores disease rehabilitation suggestions. Disease rehabilitation suggestions can be text content designed based on the disease type and disease risk level to assist the target object in rehabilitation treatment, including but not limited to comprehensive treatment methods and rehabilitation measures. Disease rehabilitation suggestions correspond to the disease risk level. After determining the disease risk level of the target object regarding the target organ through the disease risk rules, disease rehabilitation suggestions corresponding to the disease risk level can be obtained. For example, when the disease risk level includes low risk, medium risk and high risk, the disease rehabilitation suggestion corresponding to low risk can be resting at home, etc., the disease rehabilitation suggestion corresponding to medium risk can be taking medicine or adopting certain treatment methods, etc., and the disease rehabilitation suggestion corresponding to high risk can be seeking medical treatment as soon as possible and being hospitalized for observation, etc. It is understandable that when there are multiple diseases to be verified, the disease rehabilitation suggestions obtained can also be multiple. By fusing different disease rehabilitation suggestions, a fused rehabilitation suggestion is generated to avoid the target object from repeatedly executing the same rehabilitation suggestion and reduce the burden on the target object.

[0042] Furthermore, a physical examination report on the target subject is generated by integrating the target subject's physical examination data, the disease risk level of the target disease to be verified, its disease rehabilitation recommendations, and the location of the target lesion of the target disease to be verified. It should be noted that the position and morphology of organs in the human body are usually relatively fixed, and disease lesions for specific organs also tend to appear within a fixed area. Therefore, by combining physical examination data, target lesion location, and standard anatomical knowledge for three-dimensional modeling, the fixed position of the target organ can be used as a reference point to intuitively display the location and size of the target lesion in the three-dimensional model. On the one hand, it helps the target subject understand his or her own health status and grasp the potential health risks of the target organ, thereby improving the target subject's cooperation. On the other hand, the three-dimensional model can also help doctors better understand the spatial structure of the target lesion and its relative relationship with other organs, so as to facilitate the designation of appropriate treatment plans.

[0043] The disease risk assessment method based on the disease risk knowledge graph provided in this embodiment first locates the target organ that needs to undergo disease risk analysis based on the physical examination data of the target object; secondly, based on the target organ and the physical examination data, the risk matching rule corresponding to the target organ is determined, so as to obtain the disease risk level of the target organ and the target lesion location through disease risk level analysis; finally, a physical examination report is generated based on the physical examination data and the disease risk level, and the target lesion location is displayed through a three-dimensional model.

[0044] Compared to related technologies, this application first locates the target organ of the target subject during the disease risk assessment process and matches the disease risk rules based on the target organ, thereby narrowing the scope of rules that need to be matched during the analysis process, effectively improving the correlation between the disease risk level and the target organ, and the accuracy of the analysis results. At the same time, the position of the organ in the target subject is usually fixed, making it possible to accurately and intuitively display the target organ and target lesion location through three-dimensional modeling, improving the target subject's understanding of the disease risk assessment results.

[0045] Reference Figure 2 As shown, as an embodiment of the present application, the physical examination data includes the lesion size of the target object; and a physical examination report of the target object is generated based on the physical examination data, the disease risk level, and the target lesion location, including: S410. Perform three-dimensional modeling according to the target object to obtain a three-dimensional model of the object.

[0046] S420. Based on the lesion size and the target lesion position, perform three-dimensional modeling of the target lesion in the object three-dimensional model to obtain a target lesion model.

[0047] S430. Perform data integration based on the object three-dimensional model, target lesion model, disease risk level and physical examination data to obtain a physical examination report; wherein the disease risk level is displayed around the target lesion model, and the physical examination report is an interactive digital report.

[0048] Specifically, the body characteristics of the target object are determined according to the basic indicator data of the target object in the physical examination data, and three-dimensional modeling is performed on the target object according to the body characteristics to obtain a three-dimensional object model for representing the target object.

[0049] Furthermore, the physical examination data may also include medical imaging data of the target subject regarding the target organ. The size of the target subject's lesion on the target organ can be accurately determined through the medical imaging data, so that a three-dimensional model with the same actual size as the target lesion is established at the target lesion location as the target lesion model. On this basis, the disease risk level of the disease to be verified corresponding to the target lesion location is associated with the target lesion model, and the disease risk level is displayed around the target lesion model, so as to visually display the target lesion while warning of the health risks posed by the target lesion to the target subject. The physical examination report may also include disease rehabilitation suggestions based on the disease risk level, so as to help the target subject understand the rehabilitation process of the relevant disease while providing a health risk warning to the target subject, thereby assisting the target subject in rehabilitation treatment.

[0050] Furthermore, the object three-dimensional model, the target lesion model and the disease risk level are integrated, and the integrated three-dimensional model is integrated with the physical examination data to obtain a physical examination report containing a visualized three-dimensional model.

[0051] It is understood that the physical examination report can be a digital report, displayed in digital form on a terminal with display capabilities, including but not limited to smartphones, desktop computers, laptops, or tablets. In addition, doctors and subjects can interact with the physical examination report, for example, by rotating the three-dimensional model of the subject or the target lesion model in three dimensions to observe the target lesion from different angles and further understand the potential health risks of the subject.

[0052] Compared to related technologies, this embodiment intuitively displays the location and size of the target lesion in a 3D model. This helps the target patient understand their health status and potential health risks of the target organ, thereby improving their cooperation. Furthermore, the 3D model can help doctors better understand the spatial structure of the target lesion and its relative relationship to other organs, facilitating the design of appropriate treatment plans.

[0053] As an embodiment of the present application, the number of target organs is at least two, and the physical examination report includes a primary model and at least two secondary models corresponding to the target organs. The primary model is a three-dimensional model of the object, and the secondary model includes a target lesion model. The secondary model is displayed by selecting any target organ.

[0054] Specifically, the target subject can have multiple organs examined during a physical examination. In this case, the target subject has at least two target organs. Accordingly, it is necessary to perform disease risk level analysis and target lesion model establishment for different target organs, respectively, to obtain target lesion models corresponding to different target organs. It should be noted that there is a subordinate relationship between the object three-dimensional model and the target lesion model. The object three-dimensional model is used as a first-level model, and the target lesion model is used as a subordinate second-level model. When the first-level model is displayed, the second-level model is omitted, and only the model of the target organ corresponding to the target lesion model is displayed. When the doctor or the target subject interacts with the physical examination report, by selecting any target organ, the corresponding second-level model can be displayed in detail, thereby facilitating the doctor or the target subject to observe the position, size and disease risk level of the target lesion on the target organ, and understand the health status of the target subject.

[0055] In this embodiment, by setting a subordinate relationship for the three-dimensional model and displaying the secondary models separately, the problem of mutual occlusion between target lesion models in the case of multiple target organs is avoided, thereby ensuring the visualization effect of the physical examination report.

[0056] For example, this embodiment can be displayed on a smart phone terminal, referring to Figure 3a to Figure 3b As shown, Figure 3a A physical examination report showing a first-level model is displayed. Taking four target organs as an example, the models of the target organs are located at corresponding positions in the three-dimensional model of the object according to their positions in the human body. By selecting the target organ model corresponding to the three-dimensional model of the object or the icon on the right, the corresponding second-level model can be selected and displayed. The basic indicator data of the target object is displayed below the three-dimensional model of the object, and health warning information based on the basic indicator data is displayed above the three-dimensional model of the object. In some embodiments, when the smartphone is connected to a device that can monitor the basic indicators of the target object in real time, the basic indicator data of the target object can also be displayed in real time.

[0057] Figure 3bA physical examination report showing a secondary model is shown. Taking the heart as the target organ as an example, based on the assessment results of the disease risk level, the target lesion location of the target object on the target organ and the corresponding disease risk level are displayed in the secondary model, and the indicator data related to the specific part of the target organ are marked at the corresponding position. It is understandable that the secondary model can be rotated in three dimensions through interaction to show the specific location or specific size of the target lesion on the target organ. The indicator data related to the target organ and the organ function analysis results of the target organ are displayed below the secondary model. The organ function analysis results can be obtained through a comprehensive analysis of the physical examination data and the disease risk level, and are used to indicate whether the target organ can work normally and whether it is in a healthy state.

[0058] Reference Figure 4 As shown, as an embodiment of the present application, a disease risk knowledge graph is constructed in the following manner: S510. Acquire professional knowledge data, perform entity recognition and relationship extraction on the professional knowledge data, and obtain disease knowledge entities and entity relationships between disease knowledge entities; wherein the disease knowledge entities also include organ entities, disease type entities, and symptom indicator entities.

[0059] S520. Construct a hierarchical structured graph of disease knowledge entities based on entity relationships to obtain a disease risk knowledge graph; wherein the lesion location entity is subordinate to the organ entity and corresponds to the disease type entity, and the symptom indicator entity is subordinate to the disease type entity.

[0060] Among them, the disease risk knowledge graph can be a structured multi-level knowledge graph, in which different types of disease knowledge entities are arranged hierarchically according to entity relationships. Disease knowledge entities include organ entities, disease type entities, lesion location entities and symptom indicator entities, wherein the lesion location entity represents the different parts of the organ, which is subordinate to the organ entity and corresponds to at least one disease type entity. The disease type entity is subordinate to the lesion location entity and corresponds to at least one symptom indicator entity. The symptom indicator entity is subordinate to the disease type entity, and the same symptom indicator entity can be subordinate to different disease type entities respectively. Exemplarily, the structure of the disease risk knowledge graph can be in the form of a tree diagram or a node diagram to represent the subordinate hierarchical relationship between different types of entities.

[0061] Specifically, professional knowledge data is obtained from multiple sources, including but not limited to medical literature, clinical guidelines, medical ontologies, and historical electronic medical records. Entity recognition is performed on the acquired professional knowledge data to obtain various types of disease knowledge entities, and on this basis, relationship extraction is performed on the disease knowledge entities to obtain entity relationships between disease knowledge entities. To illustrate entity relationships, entity relationships can be mutual relationships between entities, including subordinate relationships and parallel relationships, etc. According to the entity relationships, entities at different levels can be associated to construct a disease risk knowledge graph. For example, in the case where the organ entity is the oral cavity, the lesion location entity associated with the organ entity can be parts of the oral cavity such as teeth or oral mucosa; the disease type entities associated with these lesion location entities can be caries or gingivitis, etc., which occur in the above-mentioned parts; the symptom indicator entities associated with these disease type entities can be disease manifestations such as tooth surface discoloration, red and swollen gums, or oral examination results.

[0062] Furthermore, the disease risk knowledge graph also includes disease risk rules, which can be automatically acquired based on the hierarchical structure of the disease risk knowledge graph. The structure of the disease risk knowledge graph is organs, lesion locations, disease types and symptom indicators, where lesion locations and disease types correspond one to one, and any disease type can correspond to multiple symptom indicators, and different symptom indicators can represent different probabilities of disease occurrence for any disease type. Based on the structure of the disease risk knowledge graph, the format of the disease risk rules is set to risk judgment conditions, disease types and disease risk levels, where the risk judgment conditions include symptom indicators, so that the format of the disease risk rules corresponds to the structure of the disease risk knowledge graph.

[0063] Furthermore, starting with the first-level entities in the disease risk knowledge graph, entities are extracted along the hierarchical association paths associated with any organ. Entities on the same path are then populated into the corresponding structure of the disease risk rule, resulting in multiple preliminary risk rules for that organ. It is understood that these preliminary risk rules require verification by medical experts to ensure their rationality and clinical feasibility. Once verified, the preliminary risk rules are stored as disease risk rules in the disease risk knowledge graph.

[0064] It should be noted that once disease risk rules are derived, rehabilitation recommendations can be generated for the disease types and risk levels contained in the disease risk rules based on authoritative medical guidelines and clinical research findings, resulting in corresponding rehabilitation recommendations. These recommendations must be validated by medical experts to ensure they are reasonable and clinically feasible before they can be stored in the disease risk knowledge graph.

[0065] For the same disease risk level for different disease types, the corresponding disease rehabilitation recommendations have a standardized format and a unified expression style, which complies with authoritative medical guidelines and other medical evidence, so that the target subjects can understand and implement them easily, and avoid over-treatment or delayed treatment of the target subjects. For example, when the disease risk levels include low risk, medium risk, and high risk, the disease rehabilitation recommendations corresponding to low risk are usually recommendations for adjusting the target subject's lifestyle; the disease rehabilitation recommendations corresponding to medium risk can be recommendations for regular checkups and further treatment when necessary; the disease rehabilitation recommendations corresponding to high risk can be prompt emergency measures and long-term management recommendations for the target subject.

[0066] Reference Figure 5 As shown, as an embodiment of the present application, the disease risk rule includes abnormal indicator data in at least one physical examination data; the disease risk knowledge graph is updated in the following manner: S530. Screen the abnormal indicator data of the historical object according to the risk matching rule of the historical object, and determine the abnormal indicator data that has not been used for the historical disease risk assessment as the associated indicator data; wherein the historical object is the target object of the historical disease risk assessment.

[0067] S540. Extract risk rules based on the associated indicator data and the disease risk level of the historical object to obtain a risk rule to be confirmed; wherein the risk rule to be confirmed contains at least one associated indicator data.

[0068] S550. In response to the confirmation operation on the risk rule to be confirmed, the risk rule to be confirmed is added to the disease risk rules.

[0069] Among them, relative to the target object at the current moment and its disease risk assessment process, the target object at any moment before the current moment can be a historical object, and its disease risk assessment process is regarded as a historical disease risk assessment.

[0070] Among them, abnormal indicator data of historical objects can be used for historical disease risk assessment. However, due to the fact that disease risk rules may be incomplete, have a one-sided focus, or be updated late, not all abnormal indicator data are used for disease risk assessment. Abnormal indicator data that is not used for historical disease risk assessment is regarded as associated indicator data. The associated indicator data is not included in the disease risk rules for some reason, but the associated indicator data may have an important association with a specific disease or indicate early signs of the specific disease. Only using existing disease risk rules and ignoring the importance of associated indicator data may lead to the simplification of the disease risk assessment process and excessive reliance on partial indicator data, resulting in reduced accuracy of analysis results and inability to effectively assist doctors in diagnosing the target object. Therefore, further rule mining based on unused associated indicator data, and thus constructing new disease risk rules based on the associated indicator data, can effectively improve the completeness and accuracy of disease risk rules.

[0071] Specifically, based on the risk matching rules of the target organs matched with the historical objects in the historical disease risk assessment, the abnormal indicator data used for the historical disease risk assessment is determined, so as to perform indicator screening on the abnormal indicator data of the historical objects and obtain the abnormal indicator data not used for the historical disease risk assessment as the associated indicator data.

[0072] Furthermore, based on the historical subject's disease risk level, the disease type associated with the historical subject's target organ risk can be determined. Risk rules can then be extracted for the corresponding disease type based on the associated indicator data, resulting in a pending risk rule containing at least one associated indicator data item. It will be appreciated that risk rule extraction can be performed by a large artificial intelligence model or manually by medical experts.

[0073] After obtaining the unconfirmed risk rules, they are then verified by medical experts to ensure their rationality and feasibility. After verification, the unconfirmed risk rules are stored as disease risk rules in the disease risk knowledge graph for use in assessing the disease risk level for the corresponding disease type.

[0074] It should be noted that if there are updates to medical evidence, such as authoritative medical guidelines and clinical research results, new disease rehabilitation recommendations can also be generated based on the updated medical evidence. It is understandable that the new disease rehabilitation recommendations have the same format and expression as the existing disease rehabilitation recommendations, and can provide the same level of advice for different disease risk levels. For example, the treatment depth of disease rehabilitation recommendations for low-risk, medium-risk, and high-risk levels gradually increases, making it easier for the target subjects to understand and implement them, and also avoiding over-treatment or delayed treatment of the target subjects.

[0075] In some embodiments, the knowledge entity structure of the disease risk knowledge graph may also have defects in completeness and comprehensiveness, so the knowledge entity structure needs to be updated in a timely manner. The process of updating the knowledge entity structure includes: obtaining updated knowledge; performing entity extraction and entity type identification on the updated knowledge to obtain updated entities corresponding to different entity types. The entity type may correspond to the knowledge entity structure of the disease risk knowledge graph, including organs, lesion locations, disease types, and symptom indicators; performing entity relationship extraction on the updated entity and the knowledge entities in the knowledge entity structure to obtain entity update relationships; calculating the similarity between the updated entity and the knowledge entities in the knowledge entity structure, and inserting the updated entity into the knowledge entity structure based on the similarity and entity update relationship to update the disease risk knowledge graph.

[0076] Furthermore, after updating the disease risk knowledge graph, a new hierarchical association path appears at the location of the inserted entity. Starting from the first-level entity in the disease risk knowledge graph, along the hierarchical association path associated with any organ, an updated association path containing at least one updated entity is extracted. Entity extraction is then performed on the updated association path to populate the corresponding structure of the disease risk rule, resulting in multiple updated risk rules for that organ. After confirmation by medical experts, the updated risk rules are stored as disease risk rules in the disease risk knowledge graph.

[0077] Reference Figure 6 As shown, as an embodiment of the present application, the disease risk rule includes a disease type, and the disease type corresponds to a diseased organ; based on the target organ and the physical examination data, organ matching and indicator data matching are performed in the disease risk rule to obtain a risk matching rule corresponding to the target organ, including: S210. Perform organ-corresponding screening on the disease risk rules to obtain the disease risk rules in which the diseased organ is the target organ as the organ association rule.

[0078] S220. Perform data comparison in the organ association rules based on the physical examination data of the target object to obtain risk matching rules.

[0079] Specifically, disease risk rules are used to determine the disease risk level for specific disease types based on preset risk assessment criteria. Each disease risk rule corresponds to a specific disease type, which in turn corresponds to a specific causative organ. Disease risk rules are then filtered based on the target organ, and the disease risk rule with the causative organ as the target organ is obtained as the organ association rule.

[0080] It should be noted that by matching the specific organs corresponding to the disease risk rules with the target organs, the scope of rule matching can be effectively narrowed, thereby improving the targeting of the risk matching rules to the target organs, and thus improving the accuracy and efficiency of disease risk assessment.

[0081] Furthermore, based on the physical examination data of the target object, indicator data matching is performed in the organ matching rule to determine whether the risk judgment condition in the organ matching rule is met, and the organ matching rule that meets the risk judgment condition is used as the risk matching rule.

[0082] Reference Figure 7 As shown, as an embodiment of the present application, the risk matching rule corresponds to a disease risk degree and a risk weight; the disease risk level of the target organ is analyzed according to the risk matching rule to obtain the disease risk level of the target object with respect to the target organ, including: S310. Perform weighted calculation on the disease risk degree corresponding to the risk matching rule according to the risk weight to obtain weighted risk data.

[0083] S320. Determine the disease risk level of the target object based on the numerical relationship between the weighted risk data and the preset risk threshold.

[0084] The risk matching rules include risk judgment conditions. There can be multiple risk judgment conditions, each corresponding to a different disease risk level. The disease risk level can be the probability of onset of the disease type corresponding to the risk matching rule. The higher the probability of onset, the higher the disease risk level for that disease type.

[0085] The risk weight is related to the indicator data in the risk judgment conditions, and different indicator data have different importance for the corresponding disease types, so that the risk matching rules have corresponding risk weights. To illustrate the risk weights, for the first risk matching rule containing the first indicator data, the second risk matching rule containing the second indicator data, and the third risk matching rule containing the third indicator data, all three correspond to the first disease type. Among them, the first indicator data is a strong predictive factor for the first disease type and can accurately reflect the disease risk level of the first disease type; the second indicator data has a high sensitivity to the first disease type and can reflect the early potential risk of the first disease type; the third indicator data is an auxiliary judgment indicator for the first disease type and contributes less to the distinction between healthy and diseased individuals. Based on this, the risk weight of the first risk matching rule is higher than the risk weight of the second risk matching rule, and the risk weight of the second risk matching rule is higher than the risk weight of the third risk matching rule.

[0086] Specifically, different risk matching rules correspond to their own disease risk levels and risk weights. For the same disease type, the corresponding disease risk level is weighted according to the risk weights of the risk matching rules to obtain weighted risk data for that disease type. This weighted risk data is then compared with the preset risk threshold for that disease type, and the target subject's disease risk level for that disease type is determined based on the numerical range of the weighted risk data.

[0087] It should be noted that for indicator data in the form of medical imaging data, data about target lesions can be obtained through image recognition or feature extraction to be used for disease risk assessment. For indicator data in the form of qualitative assessment results, the indicator data can be amplitude-valued to convert the qualitative assessment results into numerical form for calculation.

[0088] Accordingly, please refer to Figure 8 The present invention provides a disease risk assessment device based on a disease risk knowledge graph. The disease risk knowledge graph includes disease risk rules and disease knowledge entities. The disease knowledge entities include lesion location entities. The device includes: The organ positioning module 810 is used to perform organ positioning based on the physical examination data of the target object and determine the target organ.

[0089] The rule matching module 820 is used to perform organ matching and indicator data matching in the disease risk rules based on the target organ and the physical examination data to obtain the risk matching rule corresponding to the target organ.

[0090] The risk assessment module 830 is used to analyze the disease risk level of the target organ according to the risk matching rules to obtain the disease risk level of the target object with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target object suffers from the disease to be verified, and the disease to be verified corresponds to the target lesion location in the lesion location entity.

[0091] The report generation module 840 is used to generate a physical examination report of the target object based on the physical examination data, disease risk level and target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

[0092] In some optional implementations, the report generation module 840 includes: The object modeling unit is used to perform three-dimensional modeling according to the target object to obtain a three-dimensional model of the object.

[0093] The lesion modeling unit is used to perform three-dimensional modeling of the target lesion in the object three-dimensional model based on the lesion size and the target lesion position to obtain a target lesion model.

[0094] The report integration unit is used to integrate data based on the object three-dimensional model, target lesion model, disease risk level and physical examination data to obtain a physical examination report; wherein the disease risk level is displayed around the target lesion model, and the physical examination report is an interactive digital report.

[0095] In some optional embodiments, in the report generation module 840, the number of target organs is at least two, and the physical examination report includes a primary model and at least two secondary models corresponding to the target organs. The primary model is a three-dimensional model of the object, and the secondary model includes a target lesion model. The secondary model is displayed by selecting any target organ.

[0096] In some optional embodiments, the device further includes a knowledge graph construction module, including: The entity extraction unit is used to obtain professional knowledge data, perform entity recognition and relationship extraction on the professional knowledge data, and obtain disease knowledge entities and entity relationships between disease knowledge entities; among which, disease knowledge entities also include organ entities, disease type entities and symptom indicator entities.

[0097] The graph construction unit is used to construct a hierarchical structured graph of disease knowledge entities based on entity relationships to obtain a disease risk knowledge graph; among them, the lesion location entity is subordinate to the organ entity and corresponds to the disease type entity, and the symptom indicator entity is subordinate to the disease type entity.

[0098] In some optional implementations, the knowledge graph construction module further includes: An indicator screening unit is used to screen abnormal indicator data of historical objects according to risk matching rules of historical objects, and determine abnormal indicator data that has not been used for historical disease risk assessment as associated indicator data; wherein the historical objects are the target objects of historical disease risk assessment.

[0099] The rule extraction unit is used to extract risk rules based on the associated indicator data and the disease risk level of the historical object to obtain the risk rule to be confirmed; wherein the risk rule to be confirmed contains at least one associated indicator data.

[0100] The rule adding unit is configured to add the risk rule to be confirmed to the disease risk rules in response to a confirmation operation on the risk rule to be confirmed.

[0101] In some optional implementations, the rule matching module 820 includes: The organ screening unit is used to screen the disease risk rules for corresponding organs and obtain the disease risk rules with the diseased organs as the target organs as the organ association rules.

[0102] The data comparison unit is used to compare the data in the organ association rules based on the physical examination data of the target object to obtain the risk matching rules.

[0103] In some optional embodiments, the risk assessment module 830 includes: The weighted calculation unit is used to perform weighted calculation on the disease risk degree corresponding to the risk matching rule according to the risk weight to obtain weighted risk data.

[0104] The data comparison unit is used to determine the disease risk level of the target object based on the numerical relationship between the weighted risk data and the preset risk threshold.

[0105] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0106] The disease risk assessment device based on the disease risk knowledge graph in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0107] See also Figure 9 , Figure 9 1 is a structural diagram of a computer device provided by an embodiment of the present application. As shown in the figure, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 9 A processor 10 is taken as an example.

[0108] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0109] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0110] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0111] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0112] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0113] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0114] An embodiment of the present application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a method according to any embodiment of the present application.

[0115] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

[0116] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0117] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the disclosed technical solution based on the prompt message.

[0118] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0119] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0120] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0121] It is understandable that in the specific implementation of this application, related data such as user information, location information, navigation data, etc. are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0122] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0123] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0124] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0128] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0129] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0130] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0131] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. A disease risk assessment method based on disease risk knowledge graph, characterized in that: The disease risk knowledge graph includes disease risk rules and disease knowledge entities, and the disease knowledge entities include lesion location entities. The method includes: performing organ positioning based on the physical examination data of the target object to determine the target organ; Performing organ matching and indicator data matching in the disease risk rules based on the target organ and the physical examination data, obtaining a risk matching rule corresponding to the target organ; performing a disease risk level analysis on the target organ according to the risk matching rule to obtain a disease risk level of the target subject with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target subject suffers from a disease to be verified, and the disease to be verified corresponds to a target lesion location in the lesion location entity; A physical examination report of the target object is generated according to the physical examination data, the disease risk level and the target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

2. The method according to claim 1, characterized in that The physical examination data includes the size of the lesion of the target object; and generating a physical examination report of the target object according to the physical examination data, the disease risk level, and the target lesion location includes: Performing three-dimensional modeling on the target object to obtain a three-dimensional model of the object; Based on the lesion size and the target lesion position, performing three-dimensional modeling of the target lesion in the object three-dimensional model to obtain a target lesion model; Data integration is performed based on the object three-dimensional model, the target lesion model, the disease risk level and the physical examination data to obtain the physical examination report; wherein the disease risk level is displayed around the target lesion model, and the physical examination report is an interactive digital report.

3. The method according to claim 2, characterized in that The number of the target organs is at least two, and the physical examination report includes a primary model and at least two secondary models corresponding to the target organs. The primary model is a three-dimensional model of the object, and the secondary model includes the target lesion model. The secondary model is displayed by selecting any target organ.

4. The method according to claim 1, wherein The disease risk knowledge graph is constructed by: acquiring professional knowledge data, performing entity recognition and relationship extraction on the professional knowledge data, and obtaining the disease knowledge entities and the entity relationships between the disease knowledge entities; wherein the disease knowledge entities further include organ entities, disease type entities, and symptom indicator entities; A hierarchical structured graph is constructed for the disease knowledge entities according to the entity relationships to obtain the disease risk knowledge graph; wherein the lesion location entity is subordinate to the organ entity and corresponds to the disease type entity, and the symptom indicator entity is subordinate to the disease type entity.

5. The method according to claim 1, characterized in that The disease risk rule includes at least one abnormal indicator data in the physical examination data; Update the disease risk knowledge graph by: Performing index screening on abnormal indicator data of the historical object according to the risk matching rule of the historical object, and determining abnormal indicator data not used in the historical disease risk assessment as associated indicator data; wherein the historical object is the target object of the historical disease risk assessment; Extract risk rules based on the associated indicator data and the disease risk level of the historical object to obtain a risk rule to be confirmed; wherein the risk rule to be confirmed includes at least one of the associated indicator data; In response to a confirmation operation on the risk rule to be confirmed, the risk rule to be confirmed is added to the disease risk rule.

6. The method according to claim 1, characterized in that The disease risk rule includes a disease type, and the disease type corresponds to a diseased organ; performing organ matching and indicator data matching in the disease risk rule based on the target organ and the physical examination data to obtain a risk matching rule corresponding to the target organ includes: Performing organ-corresponding screening on the disease risk rules to obtain a disease risk rule in which the diseased organ is the target organ as the organ association rule; The risk matching rule is obtained by performing data comparison based on the physical examination data of the target object in the organ association rule.

7. The method according to claim 1, characterized in that The risk matching rules correspond to disease risk levels and risk weights; The performing disease risk level analysis on the target organ according to the risk matching rule to obtain the disease risk level of the target subject with respect to the target organ includes: Performing weighted calculation on the disease risk degree corresponding to the risk matching rule according to the risk weight to obtain weighted risk data; The disease risk level of the target object is determined based on the numerical relationship between the weighted risk data and a preset risk threshold.

8. A disease risk assessment device based on a disease risk knowledge graph, characterized in that: The disease risk knowledge graph includes disease risk rules and disease knowledge entities, and the disease knowledge entities include lesion location entities; the device includes: an organ positioning module for performing organ positioning based on the physical examination data of the target object to determine the target organ; A rule matching module, configured to perform organ matching and indicator data matching in the disease risk rule based on the target organ and the physical examination data, and obtain a risk matching rule corresponding to the target organ; a risk assessment module, configured to perform a disease risk level analysis on the target organ according to the risk matching rule to obtain a disease risk level of the target subject with respect to the target organ; wherein the disease risk level is used to describe the risk level of whether the target subject suffers from a disease to be verified, and the disease to be verified corresponds to a target lesion location in the lesion location entity; A report generation module is used to generate a physical examination report of the target object based on the physical examination data, the disease risk level and the target lesion location; wherein the physical examination report includes a three-dimensional model for displaying the target lesion location.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images