Physical examination intelligent guide system and method based on knowledge graph

Abstract

The invention provides a physical examination intelligent guide system and method based on a knowledge graph, and belongs to the technical field of medical treatment. Comprising a knowledge graph construction module, a personalized recommendation module, an examination guide decision module and a display module, and the knowledge graph construction module is used for integrating information from various sources such as medical literature, disease guidelines, clinical cases and physical examination data. According to the invention, the intelligent inspection guiding system is combined with the knowledge graph, data such as personal basic information, health conditions, family history and life styles are input, the risk assessment module is used for analyzing user data, and potential health risks are assessed for users by combining existing health risks and disease models in the knowledge graph. And on the basis of an artificial intelligence algorithm and a process rule, an optimal and shortest queuing route is planned, the customer is guided to complete all physical examination orderly in real time in the whole process, the most reasonable physical examination process is arranged for the user, physical examination is completed in the shortest time, and therefore the user satisfaction degree is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a knowledge graph-based intelligent physical examination guidance system and method. Background Art

[0002] The intelligent inspection guidance system is an automated queuing and calling management system that uses artificial intelligence algorithms and process rules to optimize the physical examination process. It arranges the most reasonable physical examination process for customers through intelligent algorithm scheduling, completes the physical examination in the shortest time, and thus improves user satisfaction.

[0003] However, the existing intelligent medical examination guidance system is unable to recommend appropriate medical examination items based on the user's personal situation, resulting in the user being unable to promptly check for their own health risks, and the priority ranking of medical examinations is not accurate enough. Therefore, this application provides a medical examination intelligent medical examination guidance system and method based on a knowledge graph to meet the needs. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a physical examination intelligent guidance system and method based on knowledge graph to solve the existing problems.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: a knowledge graph-based intelligent medical examination guidance system, comprising: a knowledge graph construction module, a personalized recommendation module, a guidance decision module and a display module. The knowledge graph construction module is used to integrate information from medical literature, disease guidelines, clinical cases, and medical examination data to construct entities and relationships in the knowledge graph. The personalized recommendation module is used to recommend suitable medical examination items based on the user's own situation. The guidance decision module is used to infer user data and medical rules in the knowledge graph to help doctors or patients make medical examination decisions, and based on artificial intelligence algorithms and process rules, plan the optimal and shortest queuing route, guide customers in real time to complete all physical examinations in an orderly manner, and configure priority rules. The display module is used to display the guidance items.

[0006] In some examples, the personalized recommendation module includes a user input analysis module, a risk assessment module and a physical examination item recommendation module. The user input module is used to input personal basic information, health status, family history, and lifestyle data. The risk assessment module is used to analyze user data and combine existing health risks and disease models in the knowledge graph to assess potential health risks for users. The physical examination item recommendation module is used to intelligently recommend personalized physical examination items based on the assessment results and user-related diseases, examination items and health recommendations in the knowledge graph. The intelligent recommendation of personalized physical examination items is performed through deep learning.

[0007] In some examples, the medical examination guidance decision module includes a physical examination priority sorting module, which is used to help doctors or patients make physical examination decisions by inferring user data and medical rules in the knowledge graph, and plan the optimal and shortest queuing route based on artificial intelligence algorithms and process rules, and guide customers to complete all physical examinations in an orderly manner in real time throughout the process. The priority rules include: priority for fasting items, priority for holding urine items, and priority for items with the shortest waiting time.

[0008] In some examples, the display module includes a large regional inspection guidance display screen, a department inspection guidance screen, a self-service inspection guidance device and a mobile display device. The large regional inspection guidance display screen is used to display physical examination items and queuing information in the inspection area. The department inspection screen is used to display the physical examination items and queuing information of the department at the door of the inspection department. The self-service inspection guidance device is used for users to register physical examination items and print physical examination forms. The mobile display device includes user mobile phones and tablets, which are used for users to view physical examination items and estimated waiting times by themselves.

[0009] In some examples, a data analysis and feedback module is also included. The data analysis and feedback module uses the user's physical examination results and the medical model in the knowledge graph. The system can intelligently interpret the physical examination report, identify abnormal indicators, and give corresponding health advice.

[0010] In some examples, the knowledge graph construction module also includes using NLP technology to extract valuable knowledge from unstructured data such as medical literature, clinical records, and cases, and integrate it into the knowledge graph.

[0011] A method for intelligent physical examination guidance based on knowledge graph, comprising the following steps: S1. The user enters basic personal information, health status, family history and lifestyle data; S2. Analyze user data through machine learning models, combine existing health risk and disease models in the knowledge graph, and assess potential health risks for users; S3: Intelligently recommend personalized physical examination items based on the evaluation results and the diseases, examination items and health advice related to the user in the knowledge graph; S4. Select the item and register the order through the self-service machine or nurse station. After the order is opened, register the information at the self-service machine or nurse station to join the queue; S5. Sort different physical examination items by physical examination priority; S6. After the current item is checked, another item is automatically assigned, and the process continues in sequence until all items are checked. S7. After all examination items are completed, submit the guidance sheet and assess potential health risks based on the physical examination results.

[0012] In some examples, the specific process of intelligently recommending physical examination items in S3 includes: S31. The evaluation results and diseases, examination items and health advice related to the user in the knowledge graph are used to build a deep learning model through a certain procedure to intelligently recommend personalized physical examination items; S32. Combine the training process of the denoising autoencoder and the contraction autoencoder with regularization (CAE+H), and train a K-layer DCAE + H stacked deep neural network through the following objective function; Among them, λ is a non-negative regularization hyperparameter that controls how strong the Jacobian parameter of the penalty is, and γ is an additional regularization hyperparameter that controls the intensity of the local perturbation of the Jacobian penalty. Indicates the extraction of contaminated sample points from the destruction process The meaning of other parameters is consistent with the expression in the original model objective function. When each layer is trained, the representation learned from the previous layer is used as input for the training of the next layer. S33. For each xi ∈ D, calculate the Jacobian of the last layer representation And its singular value decomposition SVD, the front d m The singular value vectors are stored in set B xi middle; S34. At the top of the K-layer pre-training layer, apply an output layer with the same size as the number of categories and a regression penalty term. Fine-tune the entire neural network for supervised classification, where for each example xi, the tangent direction B xi .

[0013] In some examples, the physical examination priority order is based on the rules of fasting items first, holding urine items first, and shortest waiting time items first.

[0014] The intelligent physical examination guidance system and method based on knowledge graph include:

[0015] Compared with the prior art, the present invention has at least the following beneficial effects: in the above scheme, by combining the intelligent guidance system with the knowledge graph, inputting personal basic information, health status, family history, and lifestyle data, the risk assessment module is used to analyze user data, and combined with the existing health risks and disease models in the knowledge graph, to assess potential health risks for users, and based on artificial intelligence algorithms and process rules, plan the optimal and shortest queuing route, guide customers to complete all physical examinations in an orderly manner in real time throughout the process, arrange the most reasonable physical examination process for users, and complete the physical examination in the shortest time, thereby improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings, which are incorporated herein and constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, further serve to explain the principles of the present disclosure and to enable those skilled in the relevant art to make and use the present disclosure.

[0017] Figure 1 This is a schematic diagram of the structure of the intelligent medical examination guidance system based on the knowledge graph; Figure 2 This is a flow chart of the intelligent physical examination guidance method based on knowledge graph. DETAILED DESCRIPTION

[0018] The following is a detailed description of the knowledge graph-based intelligent medical examination guidance system and method provided by the present invention in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following implementations are listed as the best and preferred embodiments, and other alternative methods can also be used by technicians in some known technical fields; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0019] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiment", "some embodiments" and the like in the specification indicate that the described embodiments may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0020] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0021] It will be understood that the meaning of “on,” “over,” and “above” in this disclosure should be interpreted in the broadest manner, so that “on” not only means “directly on” something, but also includes the meaning of being “on” something with intervening features or layers therebetween, and “on” or “over” not only means “on” or “above” something, but also includes the meaning of being “on” or “above” something with no intervening features or layers therebetween.

[0022] Additionally, spatially relative terms such as "under," "beneath," "lower," "above," "upper," and the like may be used herein for descriptive convenience to describe the relationship of one element or feature to another element or features, as shown in the accompanying drawings. Spatially relative terms are intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the accompanying drawings. The device may be oriented in other ways, and the spatially relative descriptors used herein may be similarly interpreted accordingly. Example 1

[0023] like Figure 1 As shown, an embodiment of the present invention provides an intelligent medical examination guidance system based on a knowledge graph, including: a knowledge graph construction module, a personalized recommendation module, a guidance decision module and a display module. The knowledge graph construction module is used to integrate information from multiple sources such as medical literature, disease guidelines, clinical cases, physical examination data, etc., and construct entities and relationships of the knowledge graph. The personalized recommendation module is used to recommend suitable physical examination items based on the user's own situation. The guidance decision module is used to infer user data and medical rules in the knowledge graph to help doctors or patients make physical examination decisions, and plan the optimal and shortest queuing route based on artificial intelligence algorithms and process rules, guide customers in real time throughout the process to complete all physical examinations in an orderly manner, and configure priority rules. The display module is used to display the guidance items.

[0024] What needs to be further explained in this embodiment is that the personalized recommendation module includes a user input analysis module, a risk assessment module and a physical examination item recommendation module. The user input module is used to input personal basic information, health status, family history, lifestyle and other data. The risk assessment module is used to analyze user data and combine the existing health risks and disease models in the knowledge graph to assess potential health risks for users. The physical examination item recommendation module is used to intelligently recommend personalized physical examination items based on the evaluation results and the diseases, examination items and health recommendations related to the user in the knowledge graph. The intelligent recommendation of personalized physical examination items is carried out through deep learning.

[0025] What needs to be further explained in this embodiment is that the medical examination guidance decision module includes a physical examination priority sorting module, which is used to help doctors or patients make physical examination decisions by inferring user data and medical rules in the knowledge graph, and plan the optimal and shortest queuing route based on artificial intelligence algorithms and process rules, and guide customers to complete all physical examinations in an orderly manner in real time throughout the process. The priority rules include: priority for fasting items, priority for holding urine items, priority for items with the shortest waiting time, etc.

[0026] What needs to be further explained in this embodiment is that the display module includes a large regional inspection guide display screen, a department inspection guide screen, a self-service inspection guide device and a mobile display device. The large regional inspection guide display screen is used to display physical examination items and queuing information in the inspection area. The department inspection screen is used to display the physical examination items and queuing information of the department at the door of the inspection department. The self-service inspection guide device is used for users to register physical examination items and print physical examination forms. The mobile display device includes user mobile phones and tablets, etc., which are used for users to self-check physical examination items and estimated waiting times.

[0027] It should be further explained that this embodiment also includes a data analysis and feedback module. The data analysis and feedback module uses the user's physical examination results and the medical model in the knowledge graph. The system can intelligently interpret the physical examination report, identify abnormal indicators, and give corresponding health advice.

[0028] It should be further explained in this embodiment that the knowledge graph construction module also includes using NLP technology to extract valuable knowledge from unstructured data such as medical literature, clinical records, and cases, and integrate it into the knowledge graph. Example 2

[0029] like Figure 2 As shown, a physical examination intelligent guidance method based on knowledge graph includes the following steps: S1. The user enters personal basic information, health status, family history, lifestyle and other data; S2. Analyze user data through machine learning models, combine existing health risk and disease models in the knowledge graph, and assess potential health risks for users; S3: Intelligently recommend personalized physical examination items based on the evaluation results and the diseases, examination items and health advice related to the user in the knowledge graph; S4. Select the item and register the order through the self-service machine or nurse station. After the order is opened, register the information at the self-service machine or nurse station to join the queue; S5. Sort different physical examination items by physical examination priority; S6. After the current item is checked, another item is automatically assigned, and the process continues in sequence until all items are checked. S7. After all examination items are completed, submit the guidance sheet and assess potential health risks based on the physical examination results.

[0030] It should be further explained in this embodiment that the specific process of intelligently recommending physical examination items in S3 includes: S31. The evaluation results and diseases, examination items and health advice related to the user in the knowledge graph are used to build a deep learning model through a certain procedure to intelligently recommend personalized physical examination items; S32. Combine the training process of the denoising autoencoder and the contraction autoencoder with regularization (CAE+H), and train a K-layer DCAE + H stacked deep neural network through the following objective function; Among them, λ is a non-negative regularization hyperparameter that controls how strong the Jacobian parameter of the penalty is, and γ is an additional regularization hyperparameter that controls the intensity of the local perturbation of the Jacobian penalty. Indicates the extraction of contaminated sample points from the destruction process The meaning of other parameters is consistent with the expression in the original model objective function. When each layer is trained, the representation learned from the previous layer is used as input for the training of the next layer. S33. For each xi ∈ D, calculate the Jacobian of the last layer representation And its singular value decomposition SVD, the front d m The singular value vectors are stored in set B xi middle; S34. At the top of the K-layer pre-training layer, apply an output layer with the same size as the number of categories and a regression penalty term. Fine-tune the entire neural network for supervised classification, where for each example xi, the tangent direction B xi .

[0031] It should be further explained in this embodiment that the physical examination priority ranking is based on the rules of giving priority to fasting items, holding urine items, and giving priority to items with the shortest waiting time.

[0032] The technical solution provided by the present invention combines the intelligent inspection guidance system with the knowledge graph, inputs personal basic information, health status, family history, lifestyle and other data, and the risk assessment module is used to analyze user data, combined with the existing health risks and disease models in the knowledge graph, to assess potential health risks for users, and based on artificial intelligence algorithms and process rules, plan the optimal and shortest queuing route, guide customers to complete all physical examinations in an orderly manner in real time throughout the process, arrange the most reasonable physical examination process for users, and complete the physical examination in the shortest time, thereby improving user satisfaction.

[0033] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0034] A person skilled in the art will appreciate that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc.

[0035] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A knowledge graph-based intelligent physical examination guidance system, characterized in that: include: The knowledge graph construction module, personalized recommendation module, inspection guidance decision module and display module are used to integrate information from medical literature, disease guidelines, clinical cases and physical examination data to construct entities and relationships in the knowledge graph. The personalized recommendation module is used to recommend suitable physical examination items based on the user's own situation. The inspection guidance decision module is used to infer user data and medical rules in the knowledge graph to help doctors or patients make physical examination decisions, and plan the optimal and shortest queuing route based on artificial intelligence algorithms and process rules, guide customers to complete all physical examinations in an orderly manner in real time throughout the process, and configure priority rules. The display module is used to display the inspection items, and the personalized recommendation module includes a user input analysis module, a risk assessment module and a physical examination item recommendation module. The user input module is used to input personal basic information, health status, family history, and lifestyle. The risk assessment module is used to analyze user data and combine the existing health risks and disease models in the knowledge graph to assess potential health risks for users. The physical examination item recommendation module is used to intelligently recommend personalized physical examination items based on the evaluation results and the diseases, inspection items and health suggestions related to the user in the knowledge graph. The intelligent recommendation of personalized physical examination items is carried out through deep learning.

2. According to claim 1, the intelligent medical examination guidance system based on knowledge graph is characterized in that: The medical examination guidance decision module includes a medical examination priority sorting module, which is used to help doctors or patients make medical examination decisions by inferring user data and medical rules in the knowledge graph, and plan the optimal and shortest queuing route based on artificial intelligence algorithms and process rules, and guide customers to complete all physical examinations in an orderly manner in real time throughout the process. The priority rules include: priority for fasting items, priority for holding urine items, and priority for items with the shortest waiting time.

3. The intelligent medical examination guidance system based on knowledge graph according to claim 1 is characterized in that: The display module includes a large regional inspection guidance display screen, a department inspection guidance screen, a self-service inspection guidance device and a mobile display device. The large regional inspection guidance display screen is used to display physical examination items and queuing information in the inspection area. The department inspection screen is used to display the physical examination items and queuing information of the department at the door of the inspection department. The self-service inspection guidance device is used for users to register physical examination items and print physical examination forms. The mobile display device includes user mobile phones and tablets, which are used for users to self-check physical examination items and estimated waiting times.

4. The intelligent medical examination guidance system based on knowledge graph according to claim 1 is characterized in that: It also includes a data analysis and feedback module, which uses the user's physical examination results and the medical model in the knowledge graph. The system can intelligently interpret the physical examination report, identify abnormal indicators, and give corresponding health advice.

5. The intelligent medical examination guidance system based on knowledge graph according to claim 1 is characterized in that: The knowledge graph construction module also includes using NLP technology to extract valuable knowledge from unstructured data such as medical literature, clinical records, and cases, and integrating it into the knowledge graph.

6. A method for intelligent physical examination guidance based on knowledge graph, applied to the intelligent physical examination guidance system based on knowledge graph as described in any one of claims 1 to 5, characterized in that: The following steps are involved: S1. The user enters basic personal information, health status, family history and lifestyle data; S2. Analyze user data through machine learning models, combine existing health risk and disease models in the knowledge graph, and assess potential health risks for users; S3: Intelligently recommend personalized physical examination items based on the evaluation results and the diseases, examination items and health advice related to the user in the knowledge graph; S4. Select the item and register the order through the self-service machine or nurse station. After the order is opened, register the information at the self-service machine or nurse station to join the queue; S5. Sort different physical examination items by physical examination priority; S6. After the current item is checked, another item is automatically assigned, and the process continues in sequence until all items are checked. S7. After all examination items are completed, submit the guidance sheet and assess potential health risks based on the physical examination results.

7. The method for intelligent physical examination guidance based on knowledge graph according to claim 6, characterized in that: The specific process of intelligently recommending physical examination items in S3 includes: S31. The evaluation results and diseases, examination items and health advice related to the user in the knowledge graph are used to build a deep learning model through a certain procedure to intelligently recommend personalized physical examination items; S32. Combine the training process of the denoising autoencoder and the contraction autoencoder with regularization (CAE+H), and train a K-layer DCAE + H stacked deep neural network through the following objective function; Among them, λ is a non-negative regularization hyperparameter that controls how strong the Jacobian parameter of the penalty is, and γ is an additional regularization hyperparameter that controls the intensity of the local perturbation of the Jacobian penalty. Indicates the extraction of contaminated sample points from the destruction process The meaning of other parameters is consistent with the expression in the original model objective function. When each layer is trained, the representation learned from the previous layer is used as input for the training of the next layer. S33. For each xi ∈ D, calculate the Jacobian of the last layer representation And its singular value decomposition SVD, the front d m The singular value vectors are stored in set B xi middle; S34. At the top of the K-layer pre-training layer, apply an output layer with the same size as the number of categories and a regression penalty term. Fine-tune the entire neural network for supervised classification, where for each example xi, the tangent direction B xi .

8. The method for intelligent physical examination guidance based on knowledge graph according to claim 6, characterized in that: The priority of physical examination is based on the rules of fasting items first, holding urine items first, and shortest waiting time items first.

Images