Pre-inquiry medical guidance method and system based on medical knowledge base

Abstract

The invention discloses a pre-inquiry medical guidance method and system based on a medical knowledge base, and relates to the technical field of pre-inquiry medical guidance, and the method comprises the steps: constructing a medical knowledge base in advance, and the medical knowledge base contains disease information, diagnosis and treatment guidelines, medicine knowledge and inspection standards; designing a visual pre-inquiry interface, wherein the pre-inquiry interface allows a patient to input symptom description through characters or voice; then, the pre-inquiry interface performs text analysis on patient input by using a natural language processing technology, recognizes key symptom description, further recognizes complaint symptoms of the patient by means of a medical knowledge base, generates a preliminary inquiry path and a pre-inquiry case, and visually displays the preliminary inquiry path and the pre-inquiry case to the patient for viewing; and the patient performs a subsequent registration process according to the inquiry path and the pre-inquiry case. According to the invention, the medical treatment efficiency of the patient can be improved, the tension condition of medical resources is relieved, the doctor can concentrate on subsequent diagnosis and treatment, and the utilization efficiency of the medical resources is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pre-diagnosis and medical guidance, and in particular to a pre-diagnosis and medical guidance method and system based on a medical knowledge base. Background Art

[0002] With the rapid growth of medical data and the complexity of medical information, traditional medical consultation methods have the following defects and can no longer meet the needs of modern medical services:

[0003] 1. Low time efficiency: In traditional medical consultations, doctors need to spend a lot of time communicating with patients to understand symptoms, medical history, etc. This process is often inefficient and repetitive, especially when facing a large number of patients. The doctor's time is seriously occupied, causing other patients to wait longer.

[0004] 2. Incomplete information acquisition: Patients may not be able to accurately or completely describe their symptoms and feelings, and sometimes even miss important information; this may lead to deviations in the doctor's judgment of the condition and affect the accuracy of the diagnosis.

[0005] 3. Limitation of professional knowledge: Non-professional patients often find it difficult to accurately express their conditions using medical terms, while doctors need to extract useful information from the patients’ descriptions, a process that is prone to misunderstanding or information loss.

[0006] 4. Uneven distribution of resources: Excellent doctors are limited and unevenly distributed, making it difficult for patients in some areas to obtain high-quality medical services.

[0007] 5. Fluctuation in consultation quality: The quality of a doctor’s consultation may be affected by a variety of factors, such as fatigue, emotions, and differences in experience, which may lead to unstable consultation results.

[0008] 6. Lack of personalized services: It is difficult for traditional consultations to provide personalized services and suggestions based on the specific circumstances of each patient, as doctors need to deal with a large number of patients within a limited time.

[0009] 7. Difficulty in recording and tracking: Paper records or traditional electronic record systems are not conducive to long-term storage and rapid retrieval of information, nor are they convenient for data analysis and disease trend prediction.

[0010] With the continuous development of artificial intelligence technology, pre-consultation and medical guidance technology based on medical knowledge base has emerged. It aims to assist doctors in preliminary consultation and diagnosis through intelligent means, and improve the efficiency and quality of medical services. Summary of the invention

[0011] In view of the needs and shortcomings of current technological development, the present invention provides a pre-diagnosis and medical guidance method and system based on a medical knowledge base to intelligently analyze and identify the patient's condition description, thereby achieving a preliminary judgment on the patient's condition and providing medical guidance suggestions.

[0012] In the first aspect, the present invention provides a pre-diagnosis and medical guidance method based on a medical knowledge base, and the technical solution adopted to solve the above technical problems is as follows:

[0013] A pre-diagnosis and medical guidance method based on a medical knowledge base comprises the following steps:

[0014] Pre-build a medical knowledge base that covers disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards;

[0015] Design a visual pre-consultation interface that allows patients to enter symptom descriptions via text or voice;

[0016] After the patient inputs a description of his or her symptoms via text or voice, the pre-consultation interface uses natural language processing technology to parse the patient's input, identify key symptom descriptions, and further use the medical knowledge base to identify the patient's chief symptoms, generate a preliminary consultation path and pre-consultation case, and display them intuitively to the patient. The patient then proceeds with the registration process based on the consultation path and pre-consultation case.

[0017] Optionally, the pre-consultation interface uses natural language processing technology to parse the patient input and identify key symptom descriptions. This process includes:

[0018] Segment the patient's symptom description and divide the continuous text into independent lexical units;

[0019] Part-of-speech tagging technology is used to identify the part of speech of each word to understand the patient's intention;

[0020] Analyze sentence structure, identify the subject, predicate, object and their dependencies, understand the context of the description and grasp the symptom information;

[0021] Dig deep into the underlying meaning and intent in symptom descriptions and identify key symptom descriptions.

[0022] Optionally, in the pre-consultation interface, the patient inputs a description of the symptoms by text or voice. During this process, the pre-consultation interface uses a machine learning model pre-trained with medical data to simulate the doctor's consultation thinking and conduct a pre-consultation with the patient.

[0023] After the pre-consultation, natural language processing technology is used to parse the text of the entire pre-consultation process and identify key symptom descriptions.

[0024] Optionally, the process involved in building a medical knowledge base is as follows:

[0025] Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base;

[0026] The collected data is then deduplicated, error corrected, and formatted;

[0027] Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

[0028] Further optionally, the medical knowledge base constructed supports data entry, storage, retrieval and automatic update functions.

[0029] In a second aspect, the present invention provides a pre-diagnosis and medical guidance system based on a medical knowledge base, and the technical solution adopted to solve the above technical problems is as follows:

[0030] A pre-diagnosis and medical guidance system based on a medical knowledge base, comprising:

[0031] The construction module is responsible for building a medical knowledge base covering disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards;

[0032] The pre-consultation interface is responsible for assisting patients to input symptom descriptions through text or voice;

[0033] The text parsing module is responsible for parsing the patient input using natural language processing technology to identify key symptom descriptions;

[0034] The identification and generation module is responsible for identifying the patient's main symptoms with the help of the medical knowledge base, generating a preliminary consultation path and pre-consultation cases, and visually displaying them to the patient through the pre-consultation interface. The patient then proceeds with the subsequent registration process based on the consultation path and pre-consultation cases.

[0035] Optionally, the text parsing module uses natural language processing technology to parse the patient input and identify key symptom descriptions. This process includes:

[0036] Segment the patient's symptom description and divide the continuous text into independent lexical units;

[0037] Part-of-speech tagging technology is used to identify the part of speech of each word to understand the patient's intention;

[0038] Analyze sentence structure, identify the subject, predicate, object and their dependencies, understand the context of the description and grasp the symptom information;

[0039] Dig deep into the underlying meaning and intent in symptom descriptions and identify key symptom descriptions.

[0040] Optionally, in the pre-consultation interface, the patient inputs a description of the symptoms by text or voice. During this process, the pre-consultation interface uses a machine learning model pre-trained with medical data to simulate the doctor's consultation thinking and conduct a pre-consultation with the patient.

[0041] After the pre-consultation is completed, the text parsing module uses natural language processing technology to perform text parsing on the entire pre-consultation process and identify key symptom descriptions.

[0042] Optionally, the process of building a medical knowledge base by building modules involved is as follows:

[0043] Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base;

[0044] The collected data is then deduplicated, error corrected, and formatted;

[0045] Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

[0046] Preferably, the medical knowledge base involved supports data entry, storage, retrieval and automatic update functions.

[0047] Compared with the prior art, the pre-diagnosis and medical guidance method and system of the present invention have the following beneficial effects:

[0048] The present invention can greatly improve the efficiency of patients' medical treatment, help alleviate the shortage of medical resources, enable doctors to focus more on subsequent diagnosis and treatment, and improve the efficiency of medical resource utilization; it can also improve the accuracy of medical services, and improve the quality and safety of medical services; it also helps to enhance patients' medical experience, allowing patients to experience more personalized and considerate medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Attached Figure 1 is a flow chart of a method according to Embodiment 1 of the present invention;

[0050] Attached Figure 2 This is a module connection block diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the technical solution, the technical problem solved and the technical effect of the present invention more clearly understood, the technical solution of the present invention is clearly and completely described below in conjunction with specific embodiments.

[0052] Embodiment 1:

[0053] Combined with Figure 1 This embodiment proposes a pre-diagnosis and medical guidance method based on a medical knowledge base, comprising the following steps:

[0054] S1. Pre-build a medical knowledge base, which covers disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards. The construction process is as follows:

[0055] Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base;

[0056] The collected data is then deduplicated, error corrected, and formatted;

[0057] Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

[0058] The constructed medical knowledge base supports data entry, storage, retrieval and automatic update functions.

[0059] S2. Design a visual pre-consultation interface that allows patients to input symptom descriptions through text or voice. During this process, the pre-consultation interface uses a machine learning model that has been pre-trained with medical data to simulate the doctor's consultation ideas and conduct pre-consultation with the patient.

[0060] S3. The pre-consultation interface uses natural language processing technology to parse the patient's input and identify key symptom descriptions. This process includes: segmenting the patient's symptom description and dividing the continuous text into independent vocabulary units; identifying the part of speech of each word through part-of-speech tagging technology to understand the patient's intention; analyzing the sentence structure, identifying the subject, predicate, object and their dependencies, to understand the context of the description and grasp the symptom information; deeply exploring the potential meaning and intention in the symptom description and identifying the key symptom description;

[0061] S4. The pre-consultation interface uses the medical knowledge base to identify the patient's chief symptoms, generate a preliminary consultation path (including departments and recommended doctors that meet the chief symptoms) and pre-consultation cases, and display them intuitively to the patient. The patient chooses the department and doctor based on the consultation path and pre-consultation cases and proceeds with the subsequent registration process.

[0062] Embodiment 2:

[0063] Combined with Figure 2 This embodiment proposes a pre-diagnosis and medical guidance system based on a medical knowledge base, which includes:

[0064] The construction module is responsible for building a medical knowledge base covering disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards;

[0065] The pre-consultation interface is responsible for assisting patients to input symptom descriptions through text or voice;

[0066] The text parsing module is responsible for parsing the patient input using natural language processing technology to identify key symptom descriptions;

[0067] The identification and generation module is responsible for identifying the patient's chief symptoms with the help of the medical knowledge base, generating a preliminary consultation path (including departments and recommended doctors that meet the chief symptoms) and pre-consultation cases, and presenting them to the patient through the pre-consultation interface. The patient chooses the department and doctor based on the consultation path and pre-consultation cases and proceeds with the subsequent registration process.

[0068] In this embodiment, the process of constructing the medical knowledge base by the construction module is as follows:

[0069] Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base;

[0070] The collected data is then deduplicated, error corrected, and formatted;

[0071] Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

[0072] Construction of building blocks The medical knowledge base supports data entry, storage, retrieval and automatic update functions.

[0073] In this embodiment, in the pre-consultation interface, the patient inputs a description of the symptoms by text or voice. During this process, the pre-consultation interface uses a machine learning model pre-trained with medical data to simulate the doctor's consultation thinking and conduct a pre-consultation with the patient;

[0074] After the pre-consultation, the text parsing module uses natural language processing technology to parse the entire pre-consultation process and identify key symptom descriptions. This process includes:

[0075] Segment the patient's symptom description and divide the continuous text into independent lexical units;

[0076] Part-of-speech tagging technology is used to identify the part of speech of each word to understand the patient's intention;

[0077] Analyze sentence structure, identify the subject, predicate, object and their dependencies, understand the context of the description and grasp the symptom information;

[0078] Dig deep into the underlying meaning and intent in symptom descriptions and identify key symptom descriptions.

[0079] It should be added that the business system of each department in the hospital can access the pre-consultation guidance system. Through the pre-consultation guidance system, doctors can understand the patient's pre-consultation process in more detail, saving time for subsequent consultations. At the same time, the system also gives feedback on incorrect consultation paths and updates the medical knowledge base based on the feedback information.

[0080] In summary, the use of a pre-diagnosis and medical guidance method and system based on a medical knowledge base of the present invention can improve the efficiency of patients' medical treatment, alleviate the shortage of medical resources, enable doctors to focus more on subsequent diagnosis and treatment, and improve the utilization efficiency of medical resources.

[0081] The above specific examples are used to explain the principles and implementation methods of the present invention in detail. These examples are only used to help understand the core technical content of the present invention. Based on the above specific embodiments of the present invention, any improvements and modifications made by technicians in this technical field without departing from the principles of the present invention should fall within the scope of patent protection of the present invention.

Claims

1. A pre-diagnosis and medical guidance method based on a medical knowledge base, characterized in that: The steps include: Pre-build a medical knowledge base that covers disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards; Design a visual pre-consultation interface that allows patients to enter symptom descriptions via text or voice; After the patient inputs a description of his or her symptoms via text or voice, the pre-consultation interface uses natural language processing technology to parse the patient's input, identify key symptom descriptions, and further use the medical knowledge base to identify the patient's chief symptoms, generate a preliminary consultation path and pre-consultation case, and display them intuitively to the patient. The patient then proceeds with the registration process based on the consultation path and pre-consultation case.

2. A pre-diagnosis and medical guidance method based on a medical knowledge base according to claim 1, characterized in that: The pre-consultation interface uses natural language processing technology to parse the patient's input and identify key symptom descriptions. This process includes: Segment the patient's symptom description and divide the continuous text into independent lexical units; Part-of-speech tagging technology is used to identify the part of speech of each word to understand the patient's intention; Analyze sentence structure, identify the subject, predicate, object and their dependencies, understand the context of the description and grasp the symptom information; Dig deep into the underlying meaning and intent in symptom descriptions and identify key symptom descriptions.

3. A pre-diagnosis and medical guidance method based on a medical knowledge base according to claim 2, characterized in that: In the pre-consultation interface, patients input symptom descriptions through text or voice. During this process, the pre-consultation interface uses a machine learning model pre-trained with medical data to simulate the doctor's consultation thinking and conduct pre-consultation with the patient; After the pre-consultation, natural language processing technology is used to parse the text of the entire pre-consultation process and identify key symptom descriptions.

4. A pre-diagnosis and medical guidance method based on a medical knowledge base according to claim 1, characterized in that: The process of building a medical knowledge base is as follows: Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base; The collected data is then deduplicated, error corrected, and formatted; Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

5. A pre-diagnosis and medical guidance method based on a medical knowledge base according to claim 4, characterized in that: The constructed medical knowledge base supports data entry, storage, retrieval and automatic update functions.

6. A pre-diagnosis and medical guidance system based on a medical knowledge base, characterized in that: It includes: The construction module is responsible for building a medical knowledge base covering disease information, diagnosis and treatment guidelines, drug knowledge, and inspection and testing standards; The pre-consultation interface is responsible for assisting patients to input symptom descriptions through text or voice; The text parsing module is responsible for parsing the patient input using natural language processing technology to identify key symptom descriptions; The identification and generation module is responsible for identifying the patient's main symptoms with the help of the medical knowledge base, generating a preliminary consultation path and pre-consultation cases, and visually displaying them to the patient through the pre-consultation interface. The patient then proceeds with the subsequent registration process based on the consultation path and pre-consultation cases.

7. A pre-diagnosis and medical guidance system based on a medical knowledge base according to claim 6, characterized in that: The text parsing module uses natural language processing technology to parse the patient input and identify key symptom descriptions. This process includes: Segment the patient's symptom description and divide the continuous text into independent lexical units; Part-of-speech tagging technology is used to identify the part of speech of each word to understand the patient's intention; Analyze sentence structure, identify the subject, predicate, object and their dependencies, understand the context of the description and grasp the symptom information; Dig deep into the underlying meaning and intent in symptom descriptions and identify key symptom descriptions.

8. A pre-diagnosis and medical guidance system based on a medical knowledge base according to claim 7, characterized in that: In the pre-consultation interface, patients input symptom descriptions through text or voice. During this process, the pre-consultation interface uses a machine learning model pre-trained with medical data to simulate the doctor's consultation thinking and conduct pre-consultation with the patient; After the pre-consultation is completed, the text parsing module uses natural language processing technology to perform text parsing on the entire pre-consultation process and identify key symptom descriptions.

9. The pre-diagnosis and medical guidance system based on a medical knowledge base according to claim 6, characterized in that: The process of constructing the medical knowledge base by the building module is as follows: Firstly, data are collected from the disease knowledge base, drug knowledge base, inspection and testing knowledge base, diagnosis and treatment guideline base and medical literature base; The collected data is then deduplicated, error corrected, and formatted; Finally, natural language processing and machine learning techniques are used to extract key information from the formatted text data and build a medical knowledge base.

10. The pre-diagnosis and medical guidance system based on a medical knowledge base according to claim 6, characterized in that: The medical knowledge base supports data entry, storage, retrieval and automatic update functions.

Images