CN109166605B - AI-based triage system and method for old people - Google Patents
AI-based triage system and method for old people Download PDFInfo
- Publication number
- CN109166605B CN109166605B CN201810846570.0A CN201810846570A CN109166605B CN 109166605 B CN109166605 B CN 109166605B CN 201810846570 A CN201810846570 A CN 201810846570A CN 109166605 B CN109166605 B CN 109166605B
- Authority
- CN
- China
- Prior art keywords
- user
- disease
- symptom
- severity
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an AI-based old people triage system and method, relating to the technical field of medical treatment and comprising the following steps: a database: information of each hospital is stored in advance; old man's disease confirms the module: the system is used for acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user; hospital screening module: the system is used for screening and sequencing hospitals according to hospital information and current disease names of users; department matching module: and the corresponding departments for screening the remaining hospitals are matched according to the current disease names of the users. The invention solves the problem that an old user cannot know the department registered by himself before going to a doctor, and mainly provides an AI-based old person triage system and method capable of matching corresponding hospitals and departments according to the diseases of the old.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to an AI-based old people triage system and method.
Background
Artificial intelligence is intended to produce an intelligent machine that can respond in a manner similar to human intelligence to replace human thinking and solve various problems efficiently, with low power consumption, and intelligently, and has been a popular research topic. The artificial intelligence is divided into two categories of weak artificial intelligence and strong artificial intelligence, and although the weak artificial intelligence can make a seemingly intelligent response to input information, the weak artificial intelligence does not have the capability of reasoning and autonomously solving problems and cannot realize real intellectualization. The strong artificial intelligence focuses on simulating the human brain, and the human brain activity is copied to have the capability of reasoning and autonomously solving problems, so that the intelligence is realized.
At present, since the birth of artificial intelligence, the theory and technology of artificial intelligence are becoming mature day by day, the application field is expanding continuously, especially the artificial intelligence technology applied to the service field of the old people is getting more and more concerned by the society, and more enterprises and scientific research workers participate in the research and development of the relevant theory, method and engineering of the artificial intelligence in the service field of the old people.
At present, the Chinese instrument enters an aging society, the old people often coexist with various diseases due to gradual decline of body functions, so the old people need to often go to a hospital for treatment, the current general medical examination process of the hospital is to ask a doctor at the front desk of the hospital, know a department to be registered by himself by describing the disease condition of the old people, and then register at the registration place, because the hospital often has more people, the inquiry and registration of the old people need to queue, so the waiting time of the old people is wasted; and the old people sometimes can not accurately describe and clearly see the disease conditions of the old people, so that the condition of hanging a wrong-number and seeing a wrong doctor is caused during registration, the medical efficiency is reduced, the old people often need to register again and queue for waiting again, and medical resources are wasted.
Disclosure of Invention
The invention aims to provide an AI-based triage system and method for the old, which can match corresponding hospitals and departments according to diseases of the old so as to save triage resources and improve medical efficiency.
In order to solve the technical problems, the basic scheme provided by the invention is as follows:
AI-based triage system for the elderly, comprising:
a database: information of each hospital is stored in advance;
old man's disease confirms the module: the system is used for acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
hospital screening module: the system is used for screening and sequencing hospitals according to hospital information and current disease names of users;
department matching module: and the corresponding departments for screening the remaining hospitals are matched according to the current disease names of the users.
According to the technical scheme, the current disease name of the user is obtained by inquiring the disease condition of the user and the severity of the disease condition, so that the primary judgment of the old people suffering from the disease is realized, then the hospital is screened according to the hospital information and the current disease name of the user, the screening rule can be matched according to the current disease name of the user and the special specialty of the hospital, the best N hospitals for treating the disease are screened out, and then the corresponding departments of the screened N hospitals are matched according to the current disease name of the user, so that the user can know the department which should register before seeing a doctor, the inquiry is not needed at a hospital consulting table, and the triage resource is saved; and the condition that the user hangs a wrong number due to misjudgment of the state of illness of the user is avoided, so that the registration resource is saved and the medical efficiency is improved.
Further, still include:
department confirmation module: for determining to select a department of a hospital by querying the user;
the doctor information display module: the department information display system is used for displaying all doctor information of the department according to the confirmed and selected department;
a registration module: for registering the presented doctor by asking the user.
The department confirmation module determines to select a certain department of a certain hospital by inquiring the user, for example, inquiring the user by voice which corresponding department of which hospital is selected, after the user selects a certain hospital, identifying the hospital answered by the user by voice, and selecting the corresponding department of the hospital; and displaying all doctor information of the selected corresponding departments of the hospital through a doctor information display module, wherein the doctor information can comprise: doctor name, doctor job title, doctor adept diseases, doctor working information and the like; the user can register the doctor through the registration module, so that the user can selectively register the doctor of the department corresponding to the disease.
Further, the geriatric disorder confirmation module includes:
a near meaning word database in which near meaning words of symptoms/diseases are stored in advance;
the user symptom obtaining sub-module is used for obtaining and identifying user symptoms by inquiring a user, and matching the user symptoms with a near-sense word library of symptoms/diseases to obtain symptom words;
the symptom degree obtaining sub-module is used for obtaining and identifying the severity degree of each symptom by inquiring the user and obtaining the extracted words of the severity degree;
the reasoning condition generation submodule is used for generating a reasoning statement according to the symptom words and the extracted words of the severity;
the user disease reasoning submodule: the system is used for transmitting the generated inference statement to the inference module and receiving a return value of the inference module;
and (4) whether the diagnosis is confirmed or not is judged by a submodule: the system is used for judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, judging whether the user is inquired again or not according to whether the questioning symptom words are returned or not by the reasoning module if the diagnosis is not confirmed, and inquiring the user again according to the questioning symptom words returned by the reasoning module if the user is inquired again; if not, generating an abnormal condition answer; if the diagnosis is confirmed, the confirmed disease name is used for generating a natural language answer.
The user symptom obtaining sub-module inquires about the user symptom, identifies the symptom through semantics, and matches the identified symptom with a word stock of the symptoms/diseases to obtain symptom-like words, for example, the user symptom is dizziness, and the user symptom obtaining sub-module matches the dizziness symptom with the word stock of the symptoms/diseases to obtain the symptom-like words such as dizziness and vertigo; the symptom degree obtaining sub-module inquires the severity degree of the symptom of the user and obtains the extraction words of the severity degree, for example, the system sets the severity degree of the symptom to 8 grades, which are respectively serious, more serious, common, little, slight and none; the reasoning condition generation submodule generates a reasoning statement according to the symptom words and the extracted words of the severity; the generated inference statement is transmitted to an inference module, and a return value of the inference module is received, the inference module is mainly used for inferring possible diseases of the old according to symptom words and extracted words of the severity and returning an inference result to a diagnosis-confirmed judgment submodule, the diagnosis-confirmed judgment submodule judges whether the old can be diagnosed or not according to the return value of the inference module, if the diagnosis is confirmed, a natural language answer is generated for the diagnosed disease name, for example, the old is judged to be likely to catch a cold according to the symptoms of dizziness and the slight severity of the old, and the cold is generated into a natural language answer; if the diagnosis is not confirmed, judging whether to inquire the user again, if the user needs to inquire again, then the user is asked again according to the question symptom words returned by the reasoning module, if the user is not required to be asked again, generating abnormal condition answers, for example, diseases that the elderly may suffer from cannot be judged by the symptoms of dizziness and the mild severity of the elderly, the reasoning module generates question symptom words according to the reasoning sentences, generates question-reversing sentences according to the question symptom words, asks the elderly again whether other symptoms exist, for example, the questioning symptom word generated by the reasoning module according to the symptoms and slight severity of dizziness of the old people is 'chest distress', therefore, the user symptom obtaining sub-module inquires whether the old people have chest distress again, and the old people can supplement related symptoms until a diagnosis result is obtained or the old people cannot be diagnosed by system confirmation.
Further, still include:
the user information base stores user historical disease data in advance;
the user symptom obtaining sub-module: the system is also used for acquiring historical sick data of the user from the user information base;
the inference condition generation submodule: and the system is also used for generating an inference statement according to the historical sick data of the user.
Historical sick data are stored in the user information base in advance, when a user logs in the system for consultation, the system automatically calls the historical sick data of the user to obtain related information such as past disease history, occupational diseases and seasonal diseases, diagnosis is assisted, diagnosis speed is increased, and system reasoning efficiency is improved.
Another object of the present invention is to provide an AI-based triage method for the elderly, which is based on the above system, and comprises the following steps:
a database building step: building a database for storing information of each hospital;
an old people disease confirmation step: acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
a hospital screening step: screening the hospitals according to the hospital information and the current disease names of the users;
matching departments: and matching the screened corresponding departments of the hospital according to the current disease names of the users.
Further, after the department matching step, the method also comprises the following steps:
department confirmation step: determining to select a department of a hospital by inquiring a user;
and a doctor information display step: displaying all doctor information of the department according to the confirmed and selected department;
a registration step: and registering the doctor according to the displayed doctor information.
Further, the elderly disease confirmation step specifically includes:
a near meaning word database in which near meaning words of symptoms/diseases are stored in advance;
a user symptom obtaining step: acquiring and identifying user symptoms by inquiring a user, and matching the user symptoms with a symptom/disease word library to obtain symptom words;
a symptom degree obtaining step: the severity of each symptom is obtained and identified by inquiring a user, and extracted words of the severity are obtained;
inference condition generation step: generating reasoning sentences according to the symptom words and the extracted words of the severity;
user disease reasoning step: transmitting the generated inference statement to an inference module, and receiving a return value of the inference module;
and (3) judging whether the diagnosis is confirmed: judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, and executing S1 if the diagnosis is not confirmed; if the diagnosis is confirmed, executing S2;
s1: judging whether to inquire the user again according to whether the reasoning module returns the question symptom words, if so, executing S1-1; if not, executing S1-2;
s1-1: inquiring the user again according to the question symptom words returned by the reasoning module;
s1-2: generating an abnormal condition answer;
s2: generating natural language answers for the diagnosed disease names.
Further, the inference condition generating step further comprises, before the inference condition generating step:
a user information base creating step: historical sick data of a user are stored in advance;
the user symptom obtaining step: historical sick data of the user can be acquired from the user information base;
the inference condition generating step: inference statements are also generated from the user historical sick data.
Drawings
FIG. 1 is a schematic block diagram of an embodiment of an AI-based triage system of the present invention;
FIG. 2 is a flowchart of an embodiment of the AI-based triage method of the present invention;
fig. 3 is a flowchart illustrating the geriatric disorder confirmation procedure according to the embodiment of the AI-based geriatric triage method illustrated in fig. 2.
Detailed Description
The following is further detailed by way of specific embodiments:
example one
As shown in fig. 1, the AI-based triage system of the present invention includes:
a database: information of each hospital is stored in advance;
old man's disease confirms the module: the system is used for acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
hospital screening module: the system is used for screening the hospitals according to the hospital information and the current disease names of the users;
department matching module: the corresponding department of the screened hospital is matched according to the current disease name of the user;
department confirmation module: for determining to select a department of a hospital by querying the user;
the doctor information display module: the department information display system is used for displaying all doctor information of the department according to the confirmed and selected department;
a registration module: the doctor registration device is used for registering the displayed doctor by the user.
Wherein, old man's disease confirms the module and includes:
a near word database: the method comprises the steps of storing the similar meaning words of symptoms/diseases in advance;
the user information base stores user historical disease data in advance; the historical disease data includes: occupational disease, seasonal disease, past disease name, etc.;
the user symptom obtaining sub-module is used for obtaining and identifying user symptoms by inquiring a user, and matching the user symptoms with a near-sense word library of symptoms/diseases to obtain symptom words; the system is also used for acquiring historical sick data of the user from the user information base;
the symptom degree obtaining sub-module is used for obtaining and identifying the severity degree of each symptom by inquiring the user and obtaining the extracted words of the severity degree;
the reasoning condition generation submodule is used for generating a reasoning statement according to the symptom words, the extracted words of the severity and the historical disease data of the user;
the user disease reasoning submodule: the system is used for transmitting the generated inference statement to the inference module and receiving a return value of the inference module;
and (4) whether the diagnosis is confirmed or not is judged by a submodule: the system is used for judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, judging whether the user is inquired again or not according to whether the questioning symptom words are returned or not by the reasoning module if the diagnosis is not confirmed, and inquiring the user again according to the questioning symptom words returned by the reasoning module if the user is inquired again; if not, generating an abnormal condition answer; if the diagnosis is confirmed, the confirmed disease name is used for generating a natural language answer.
The use scene of the AI-based triage system is as follows:
the old man's disease confirms the module and obtains user's present disease name through inquiring about user's disease and the severity of disease to realize the preliminary judgement to the disease that the old man suffered from, wherein, the concrete process of obtaining user's present disease name is:
the user symptom obtaining sub-module inquires about the user symptom, identifies the symptom through semantics, and matches the identified symptom with a word stock of the symptoms/diseases to obtain symptom-like words, for example, the user symptom is dizziness, and the user symptom obtaining sub-module matches the dizziness symptom with the word stock of the symptoms/diseases to obtain the symptom-like words such as dizziness and vertigo; the symptom degree obtaining sub-module asks the user about the severity degree of the symptom and obtains the extracted words of the severity degree, for example, the system sets the severity degree of the symptom to 8 grades, which are respectively "particularly severe" ═ 0, "very severe" ═ 1, "severe" ═ 2, "comparatively severe" ═ 3, "general" ═ 4, "little" ═ 5, "slight" ═ 6, "none" ═ 7;
meanwhile, the user symptom obtaining sub-module obtains historical disease data of the user from the user information base, wherein the historical disease data can include: occupational disease, seasonal disease, past disease name, etc.;
the reasoning condition generation submodule generates a reasoning statement according to the symptom words, the extracted words of the severity and the historical disease data of the user; the generated inference sentences are transmitted to an inference module, return values of the inference module are received, the inference module is mainly used for inferring possible diseases of the old according to symptom words and extracted words of the severity degree, inference results are returned to a diagnosis-confirmed judgment submodule, the diagnosis-confirmed judgment submodule judges whether the old can be diagnosed or not according to the return values of the inference module, specifically, a return value threshold value can be preset, the return value threshold value can be 3, and if the number of the return values is smaller than the return value threshold value, namely, the number of the disease names in the inference results returned by the inference modules is smaller than 3, the old is judged to be not diagnosed; if the number of the return values is equal to the return value threshold value, the diagnosis is determined;
if the diagnosis is confirmed, the diagnosis result is generated into a natural language answer, for example, if the old people are judged to possibly catch a cold through the symptoms of dizziness and slight severity of the old people, the cold is generated into a natural language answer; if the user is not diagnosed, judging whether to inquire the user again, if the user receives question symptom words from the reasoning module, inquiring the user again, and specifically, inquiring the user again according to the question symptom words returned by the reasoning module; if the question symptom word from the reasoning module is not received, the user does not need to be asked again, and an abnormal condition answer is generated, for example, the abnormal condition answer is 'sorry, which cannot be judged';
specifically, the process of querying again is: the reasoning module generates question symptom words according to the reasoning statements, generates question reversing sentences according to the question symptom words, and inquires the old again whether other symptoms exist, for example, the question symptom words generated by the reasoning module according to the dizziness symptoms and the slight severity of the old are chest stuffiness, so that the system inquires the old again whether the chest stuffiness symptoms exist; question symptom words generated by the reasoning module can be generated into question-reversing sentences, and templates of the question-reversing sentences can be ' asking for your ' symptom words '? Is the ' degree descriptor a ', ' degree descriptor B ', or ' degree descriptor C? So that the elderly can supplement relevant symptoms until a diagnosis result is obtained or the system confirms that diagnosis cannot be performed.
Then, the hospitals are screened according to the hospital information and the current disease names of the users, the hospital information can comprise the hospital names, the hospital addresses, the hospital specialty major, the comprehensive ranking of each department of the hospitals and the like, the screening rule can be matched according to the current disease names of the users and the hospital specialty major, three hospitals with the best disease treatment are screened out, and then the corresponding departments of the three screened hospitals are matched according to the current disease names of the users, so that the users can know the departments which should be registered before seeing a doctor, the departments do not need to inquire at a hospital consulting table, and the diagnosis resources are saved; and the condition that the user hangs a wrong number due to misjudgment of the state of illness of the user is avoided, so that the registration resource is saved and the medical efficiency is improved.
The department confirmation module determines to select a certain department of a certain hospital by inquiring the user, for example, inquiring the user by voice which corresponding department of which hospital is selected, after the user selects a certain hospital, identifying the hospital answered by the user by voice, and selecting the corresponding department of the hospital; and displaying all doctor information of the selected corresponding departments of the hospital through a doctor information display module, wherein the doctor information can comprise: doctor name, doctor job title, doctor adept diseases, doctor working information and the like; the user can register the doctor through the registration module, so that the user can selectively register the doctor of the department corresponding to the disease.
In order to more clearly illustrate the usage scenario of the AI-based triage system of the present invention, in this embodiment, an AI-based triage method for elderly people is further disclosed, which is based on the above system, and as shown in fig. 2, the method includes the following steps:
a database building step: building a database for storing information of each hospital;
an old people disease confirmation step: acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
a hospital screening step: screening the hospitals according to the hospital information and the current disease names of the users;
matching departments: matching the corresponding departments of the screened hospitals according to the current disease names of the users;
department confirmation step: determining to select a department of a hospital by inquiring a user;
and a doctor information display step: displaying all doctor information of the department according to the confirmed and selected department;
a registration step: and registering the doctor according to the displayed doctor information.
As shown in fig. 3, the geriatric disease confirmation step specifically includes:
building a near word library: building a database of similar meaning words of symptoms/diseases;
a user information base creating step: historical sick data of a user are stored in advance; specifically, user information and season information are obtained, historical disease data of a user are obtained and stored according to the user information and the season information, and the user information comprises: the user's name, age, gender, occupation, and past medical history; the historical disease data includes: occupational disease, seasonal disease, past disease name, etc.;
a user symptom obtaining step: acquiring and identifying user symptoms by inquiring a user, and matching the user symptoms with a symptom/disease word library to obtain symptom words; historical sick data of the user can be acquired from the user information base;
a symptom degree obtaining step: the severity of each symptom is obtained and identified by inquiring a user, and extracted words of the severity are obtained;
inference condition generation step: generating reasoning sentences according to the symptom words, the extracted words of the severity and the historical disease data of the user;
user disease reasoning step: transmitting the generated inference statement to an inference module, and receiving a return value of the inference module;
and (3) judging whether the diagnosis is confirmed: judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, and executing S1 if the diagnosis is not confirmed; if the diagnosis is confirmed, executing S2;
s1: judging whether to inquire the user again according to whether the reasoning module returns the question symptom words, if so, executing S1-1; if not, executing S1-2;
s1-1: inquiring the user again according to the question symptom words returned by the reasoning module;
s1-2: generating an abnormal condition answer;
s2: generating natural language answers for the diagnosed disease names.
Example two
The difference between the AI-based triage system in this embodiment and the first embodiment is that the system further includes:
a user information base: obtaining a diagnosis confirming result and diagnosis confirming time and storing the diagnosis confirming result and the diagnosis confirming time as historical disease data of a user;
an emotion acquisition module: for obtaining a user emotion by asking the user; specifically, the user emotion may be acquired by acquiring the tone of the user when asking the user about the symptoms and the severity of the symptoms;
the disease severity inference module: the system is used for matching the symptom words obtained by inquiring the user with historical disease data in the user information base to obtain disease names, and deducing the disease severity of the disease according to the disease names and time;
the disease severity judging module: the system comprises a reasoning condition generation module, a reasoning sentence generation module and a reasoning analysis module, wherein the reasoning condition generation module is used for comparing symptom severity extraction words obtained by inquiring a user with inferred symptom severity, and generating a reasoning sentence according to symptom words, the severity extraction words and historical diseased data if a difference value is less than or equal to a preset severity threshold value; if the difference is greater than the preset degree threshold, the emotion grade judgment module identifies the emotion of the user and judges the grade to which the emotion of the user belongs, specifically, an emotion grade comparison table is pre-arranged in the emotion grade judgment module, and the emotion grade comparison table is divided into different grades according to different emotions of the user, for example: the emotion level comparison table of the system is set to 6 levels, namely, calmness is equal to 1, happiness is equal to 2, depression is equal to 3, difficulty is equal to 4, anger is equal to 5, and violence is equal to 6; the emotion grade judging module compares corresponding emotion grades according to emotions, compares the emotion grades with a preset grade threshold, and generates reasoning sentences according to symptom words, deduced disease severity and historical disease data if the emotion grades are larger than the preset grade threshold; and if the emotion grade is less than or equal to the preset grade threshold value, the reasoning condition generating module generates a reasoning statement according to the symptom words, the extracted words of the severity and the historical diseased data.
The specific use scene is as follows:
assuming that the symptom described by the user of the old is "headache" and the symptom severity is "slight" two days before, the system obtains a diagnosis result of cold, so that the system stores the time of the cold and the cold of the old in the user information base as the historical sick data of the old, the old describes the symptom as "headache" and the symptom severity as "particularly severe" two days after, the system matches the obtained symptom word of the "headache" with the historical sick data in the user information base to obtain the cold suffered by the old two days before, deduces the severity of the cold as "relatively severe" according to the time of the cold and two days, compares the deduced severity "relatively severe" with the symptom severity "particularly severe" described by the old to obtain a difference value, and according to the division of the numerical value corresponding to the severity grade in the embodiment I, the obtained specific difference value is 3, the preset degree threshold value is assumed to be 2, if the difference value is larger than the preset degree threshold value, the symptom severity described by the old exceeds the normal development trend of the disease, and the emotion of the old is likely to be judged because the emotion of the old is too large or the mood is not good;
supposing that the emotion of the old man after two days when the symptoms are described as headache and the symptom severity is particularly serious is anger, judging the emotion grade of the old man to be 5 grade by the emotion grade judging module, supposing that the preset grade threshold is 2 and the emotion grade is greater than the preset grade threshold at the moment, indicating that the old man feels headache aggravated due to too large emotion fluctuation and does not really worsen the illness state of the old man, generating reasoning sentences according to the deduced severity of the illness state, namely generating reasoning sentences according to the normal development degree of the cold and transmitting the reasoning sentences to the reasoning module; assuming that the emotion of the old is calm when the old describes that symptoms are headache and the symptom severity is particularly severe after two days, the emotion grade judging module judges the emotion grade of the old is grade 1, and if the emotion grade is smaller than a preset grade threshold value, the old does not feel headache aggravation due to too large emotion fluctuation and really worsens the state of an illness, so that a reasoning statement is generated according to an extraction word of the severity described by the old and is transmitted to the reasoning module to reason about possible illness of the old.
The difference between the AI-based triage method in this embodiment and the first embodiment is that the method further includes the following steps:
a step of obtaining a diagnosis confirming result: the user information base obtains the diagnosis confirming result and the diagnosis confirming time and stores the diagnosis confirming result and the diagnosis confirming time as historical disease data of the user;
emotion acquisition step: obtaining a user emotion by querying the user;
and (3) disease severity deducing step: matching the symptom words obtained by inquiring the user with historical disease data in a user information base to obtain disease names, and deducing the disease severity of the disease according to the disease names and time;
judging the severity of the disease: comparing the symptom severity extraction words obtained by inquiring the user with the inferred symptom severity, and executing S3 if the difference is greater than a preset severity threshold; if the difference is less than or equal to the preset degree threshold, executing S4;
s3: recognizing the emotion of the user, judging the emotion level of the user, comparing the emotion level with a preset level threshold, and executing S3-1 if the emotion level is greater than the preset level threshold; if the emotion level is less than or equal to the preset level threshold, executing S3-2;
s3-1: generating reasoning sentences according to the symptom words, the inferred severity of the symptoms and the historical disease data;
s3-2: execution of S4;
s4: and generating reasoning sentences according to the symptom words, the extracted words of the severity and the historical diseased data.
The foregoing is merely an example of the present invention and common general knowledge of known specific structures and features of the embodiments is not described herein in any greater detail. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (4)
1. AI-based triage system for the elderly, comprising:
a database: information of each hospital is stored in advance;
old man's disease confirms the module: the system is used for acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
hospital screening module: the system is used for screening the hospitals according to the hospital information and the current disease names of the users;
department matching module: the corresponding department of the screened hospital is matched according to the current disease name of the user;
a user information base: the system is used for acquiring a diagnosis confirming result and diagnosis confirming time and storing the diagnosis confirming result and the diagnosis confirming time as historical disease data of a user;
the geriatric disorder confirmation module includes:
a near meaning word database in which near meaning words of symptoms/diseases are stored in advance;
the user symptom obtaining sub-module is used for obtaining and identifying user symptoms by inquiring a user, and matching the user symptoms with a near-sense word library of symptoms/diseases to obtain symptom words; the system is also used for acquiring historical sick data of the user from the user information base;
the symptom degree obtaining sub-module is used for obtaining and identifying the severity degree of each symptom by inquiring the user and obtaining the extracted words of the severity degree;
the reasoning condition generation submodule is used for generating a reasoning statement according to the symptom words, the extracted words of the severity and the historical disease data of the user;
the user disease reasoning submodule: the system is used for transmitting the generated inference statement to the inference module and receiving a return value of the inference module;
and (4) whether the diagnosis is confirmed or not is judged by a submodule: the system is used for judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, judging whether the user is inquired again or not according to whether the questioning symptom words are returned or not by the reasoning module if the diagnosis is not confirmed, and inquiring the user again according to the questioning symptom words returned by the reasoning module if the user is inquired again; if not, generating an abnormal condition answer; if the diagnosis is confirmed, generating a natural language answer by the name of the confirmed disease;
also comprises the following steps of (1) preparing,
an emotion acquisition module: for obtaining a user emotion by asking the user; the emotion acquisition module acquires user emotion by acquiring user tone when inquiring about user symptoms and symptom severity;
the disease severity inference module: the system is used for matching symptom words obtained by inquiring the user with historical sick data of the user in the user information base to obtain disease names, and deducing the severity of the disease according to the disease names and time;
the disease severity judging module: the reasoning condition generation submodule is used for comparing the symptom severity extraction words obtained by inquiring the user with the deduced symptom severity to obtain a difference value, and if the difference value is less than or equal to a preset degree threshold value, generating a reasoning statement according to the symptom words, the severity extraction words and the user historical disease data; if the difference value is greater than the preset degree threshold value, the emotion grade judgment module identifies the emotion of the user, judges the grade to which the emotion of the user belongs and compares the emotion grade with the preset grade threshold value, and if the emotion grade is greater than the preset grade threshold value, the inference condition generation submodule generates an inference sentence according to symptom words, the inferred disease severity and the historical disease data of the user; and if the emotion grade is less than or equal to the preset grade threshold value, the reasoning condition generation submodule generates a reasoning statement according to the symptom words, the extracted words of the severity and the historical diseased data of the user.
2. The AI-based triage system according to claim 1, further comprising:
department confirmation module: for determining to select a department of a hospital by querying the user;
the doctor information display module: the department information display system is used for displaying all doctor information of the department according to the confirmed and selected department;
a registration module: the doctor registration device is used for registering the displayed doctor by the user.
3. The AI-based triage method for the old people is characterized by comprising the following steps of:
a database building step: building a database for storing information of each hospital;
an old people disease confirmation step: acquiring the current disease name of the user by inquiring the disease condition and the severity of the disease condition of the user;
a hospital screening step: screening the hospitals according to the hospital information and the current disease names of the users;
matching departments: matching the corresponding departments of the screened hospitals according to the current disease names of the users;
a user information base creating step: obtaining a diagnosis confirming result and diagnosis confirming time and storing the diagnosis confirming result and the diagnosis confirming time as historical disease data of a user;
the old people disease confirmation step specifically comprises the following steps:
a near word database: the method comprises the steps of storing the similar meaning words of symptoms/diseases in advance;
a user symptom obtaining step: acquiring and identifying user symptoms by inquiring a user, matching the user symptoms with a symptom/disease word library to obtain symptom words, and acquiring user historical diseased data from a user information library;
a symptom degree obtaining step: the severity of each symptom is obtained and identified by inquiring a user, and extracted words of the severity are obtained;
inference condition generation step: generating reasoning sentences according to the symptom words, the extracted words of the severity and the historical disease data of the user;
user disease reasoning step: transmitting the generated inference statement to an inference module, and receiving a return value of the inference module;
and (3) judging whether the diagnosis is confirmed: judging whether the diagnosis is confirmed or not according to the return value of the reasoning module, and executing S1 if the diagnosis is not confirmed; if the diagnosis is confirmed, executing S2;
s1: judging whether to inquire the user again according to whether the reasoning module returns the question symptom words, if so, executing S1-1; if not, executing S1-2;
s1-1: inquiring the user again according to the question symptom words returned by the reasoning module;
s1-2: generating an abnormal condition answer;
s2: generating natural language answers for the diagnosed disease names;
also comprises the following steps of (1) preparing,
emotion acquisition step: acquiring a user emotion by acquiring a tone of the user when asking the user about symptoms and symptom severity;
and (3) disease severity deducing step: matching the symptom words obtained by inquiring the user with historical disease data of the user in a user information base to obtain a disease name, and deducing the disease severity of the disease according to the disease name and time;
judging the severity of the disease: comparing the symptom severity extraction words obtained by inquiring the user with the inferred symptom severity, and executing S3 if the difference is greater than a preset severity threshold; if the difference is less than or equal to the preset degree threshold, executing S4;
s3: recognizing the emotion of the user, judging the emotion level of the user, comparing the emotion level with a preset level threshold, and executing S3-1 if the emotion level is greater than the preset level threshold; if the emotion level is less than or equal to the preset level threshold, executing S3-2;
s3-1: generating reasoning sentences according to the symptom words, the inferred severity of the symptoms and the historical disease data of the user;
s3-2: execution of S4;
s4: and generating an inference sentence according to the symptom words, the extracted words of the severity and the historical sick data of the user.
4. The AI-based triage method for the elderly according to claim 3, further comprising, after the department matching step:
department confirmation step: determining to select a department of a hospital by inquiring a user;
and a doctor information display step: displaying all doctor information of the department according to the confirmed and selected department;
a registration step: and registering the doctor according to the displayed doctor information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846570.0A CN109166605B (en) | 2018-07-27 | 2018-07-27 | AI-based triage system and method for old people |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810846570.0A CN109166605B (en) | 2018-07-27 | 2018-07-27 | AI-based triage system and method for old people |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109166605A CN109166605A (en) | 2019-01-08 |
| CN109166605B true CN109166605B (en) | 2021-09-14 |
Family
ID=64898505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810846570.0A Active CN109166605B (en) | 2018-07-27 | 2018-07-27 | AI-based triage system and method for old people |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109166605B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110718300A (en) * | 2019-09-09 | 2020-01-21 | 杭州憶盛医疗科技有限公司 | Pathological diagnosis method based on data analysis |
| CN110993081B (en) * | 2019-12-03 | 2023-08-11 | 济南大学 | Doctor online recommendation method and system |
| CN111079021B (en) * | 2019-12-20 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Method, device, server and storage medium for recommending medical information content |
| CN113257411A (en) * | 2021-06-11 | 2021-08-13 | 成都安易迅科技有限公司 | Self-service medical registration interaction method and device, storage medium and self-service registration machine |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129526A (en) * | 2011-04-02 | 2011-07-20 | 中国医学科学院医学信息研究所 | Public-oriented method and system for medical treatment guide-type self-help triage registering |
| CN106557653A (en) * | 2016-11-15 | 2017-04-05 | 合肥工业大学 | A kind of portable medical intelligent medical guide system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101785669B (en) * | 2010-02-03 | 2012-05-09 | 深圳先进技术研究院 | Electrocardiograph signal detection method and device |
-
2018
- 2018-07-27 CN CN201810846570.0A patent/CN109166605B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102129526A (en) * | 2011-04-02 | 2011-07-20 | 中国医学科学院医学信息研究所 | Public-oriented method and system for medical treatment guide-type self-help triage registering |
| CN106557653A (en) * | 2016-11-15 | 2017-04-05 | 合肥工业大学 | A kind of portable medical intelligent medical guide system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109166605A (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109166605B (en) | AI-based triage system and method for old people | |
| Ryle | The structure and development of borderline personality disorder: A proposed model | |
| Lindenberger et al. | Speed and intelligence in old age. | |
| AU2003223333B2 (en) | A method and system of mass and multiple casualty triage | |
| CN114171176A (en) | Hospital triage data processing method and system based on Internet | |
| Öztürk et al. | Towards a model of context for case-based diagnostic problem solving | |
| CN113592345A (en) | Medical triage method, system, equipment and storage medium based on clustering model | |
| Fonn et al. | Health Workers for Change: developing the initiative | |
| CN107480450A (en) | A kind of intelligence point examines method and system | |
| Dodier | Clinical practice and procedures in occupational medicine: a study of the framing of individuals | |
| Mackrill | Constructing client agency in psychotherapy research | |
| CN111540441A (en) | Psychological intervention method and device based on human-computer interaction under psychological stress state | |
| KR20220095104A (en) | Big data and cloud system based AI(artificial intelligence) emergency medical care decision-making and emergency patient transfer system and method thereof | |
| CN112201350A (en) | Intelligent triage method and device and electronic equipment | |
| Mele et al. | How Artificial Intelligence enhances human learning abilities: opportunities in the fight against Covid-19 | |
| Kewley et al. | The development of the active risk management system | |
| CN113724899A (en) | Online inquiry method, device, equipment and medium based on artificial intelligence | |
| Birkun et al. | Dr. Google’s Advice on First Aid: Evaluation of the Search Engine’s Question-Answering System Responses to Queries Seeking Help in Health Emergencies | |
| Woods et al. | Perimenstrual symptoms and health-seeking behavior | |
| KR102314332B1 (en) | Medical dialog support system and method for physicians and patient using machine learning and NLP | |
| Frese III et al. | On consumer advocacy and the diagnosis of mental disorders. | |
| CN113434651B (en) | Speaking recommendation method and device and related equipment | |
| CN115982335A (en) | Active AI medical question-answering system, method, equipment and storage medium | |
| Pedro et al. | Mobile decision support for triage in emergency departments | |
| CN114822800A (en) | Internet medical triage method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |