CN114068029A - Diagnosis guiding method and system - Google Patents

Diagnosis guiding method and system Download PDF

Info

Publication number
CN114068029A
CN114068029A CN202111432679.8A CN202111432679A CN114068029A CN 114068029 A CN114068029 A CN 114068029A CN 202111432679 A CN202111432679 A CN 202111432679A CN 114068029 A CN114068029 A CN 114068029A
Authority
CN
China
Prior art keywords
patient
department
medical
symptoms
result
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.)
Pending
Application number
CN202111432679.8A
Other languages
Chinese (zh)
Inventor
刘筱
邹平
缪庆亮
施淼元
牛会花
李茂龙
杨一帆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sipic Technology Co Ltd
Original Assignee
Sipic Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Sipic Technology Co Ltd filed Critical Sipic Technology Co Ltd
Priority to CN202111432679.8A priority Critical patent/CN114068029A/en
Publication of CN114068029A publication Critical patent/CN114068029A/en
Pending legal-status Critical Current

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
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/041—Abduction
    • 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)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Animal Behavior & Ethology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The embodiment of the invention provides a diagnosis guiding method. The method comprises the following steps: gradually reasoning the symptoms input by the patient based on the medical knowledge map to determine a first result of a department of medical consultation and potential diseases; inputting the symptoms input by the patient into an end-to-end classification model based on deep learning, and outputting a second result of the department of medical guidance and the potential diseases; outputting to the patient a valid referral department and potential disease based on the first result and the second result; an interpretable reasoning path corresponding to an effective referral department and underlying disease is provided based on the medical knowledge graph. The embodiment of the invention also provides a diagnosis guiding system. The embodiment of the invention adds a knowledge reasoning function in the diagnosis guide, combines an end-to-end classification and a reasoning model, fully exerts the high recall and analytic formula high precision of the end-to-end classification, improves the accuracy of the diagnosis guide, gives an interpretable path and related information recommendation of the diagnosis guide, and improves the use experience of patients.

Description

Diagnosis guiding method and system
Technical Field
The invention relates to the field of intelligent voice, in particular to a diagnosis guiding method and system.
Background
As intelligent voice interaction has evolved, feedback is made by recognizing the user's intent from the user's input. In a hospital, a patient may not know which department to hang, and professional staff is available to help the patient to guide a doctor, however, as technology advances, online registration/medical care/prescription is gradually popularized, and at the moment, professional staff is not available to help, and some patients do not know what department to hang for their symptoms. In order to facilitate accurate registration of patients, the prior art generally uses:
deep learning end-to-end classification method: obtaining a large amount of training data by marking the department labels of the chief complaints, training a department classification model by using the training data, and classifying the chief complaints of the patients by using the classification model to obtain the department for guiding the doctor, thereby realizing intelligent doctor guiding;
the dictionary matching mode matches keywords such as diseases and symptoms from the chief complaints input by the patients, and determines the department of the medical guide by using the mapping relation between the keywords of the diseases and the symptoms and the department, so that the intelligent medical guide is realized.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the related art:
the end-to-end classification technology can obtain better generalization capability and recall rate on the premise of ensuring higher precision, but lacks interpretability, cannot give out reasons for determining departments, and needs to update models when encountering error cases. In addition, the common sense knowledge is lacked, and obvious error results are easy to occur.
The matching-based method can obtain higher precision, but has lower generalization capability and recall rate. The matching effect on the expression of the spoken language is not good. The current medical history, the past medical history and the like are not distinguished, so that the diagnosis guiding accuracy is influenced.
Disclosure of Invention
The method aims to solve the problems that the existing diagnosis guiding method in the prior art is lack of common knowledge, obvious wrong results are easy to occur, and the expression matching effect is influenced due to unclear spoken language expression of a patient in voice interaction.
In a first aspect, an embodiment of the present invention provides a method for guiding a medical examination, including:
gradually reasoning the symptoms input by the patient based on the medical knowledge map to determine a first result of a department of medical consultation and potential diseases;
inputting the patient-input symptoms into an end-to-end classification model based on deep learning, and outputting a second result of a department of medical guidance and potential diseases;
outputting to the patient a valid referral department and potential illness based on the first result and the second result;
providing interpretable inferential paths corresponding to the effective referral department and potential disease based on the medical knowledge graph.
In a second aspect, an embodiment of the present invention provides a diagnosis guidance system, including:
the reasoning program module is used for gradually reasoning the symptoms input by the patient based on the medical knowledge graph and determining a first result of a department of medical consultation and potential diseases;
a classification program module for inputting the symptoms input by the patient into an end-to-end classification model based on deep learning and outputting a second result of the department of medical education and the potential diseases;
a decision-making program module for outputting to the patient a valid referral department and potential illness based on the first result and the second result;
a referral program module for providing interpretable inferential paths corresponding to the active referral department and potential disease based on the medical knowledge-graph.
In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of the embodiments of the present invention.
In a fourth aspect, an embodiment of the present invention provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the steps of the method for guiding a patient according to any embodiment of the present invention.
The embodiment of the invention has the beneficial effects that: the knowledge reasoning function is added in the diagnosis guide, the information of the chief complaint and the non-chief complaint of the patient can be distinguished, the prior medical history and the current medical history, the part identification and the part related symptom inquiry are combined, the end-to-end classification and reasoning model is combined, the high recall and analytic formula high precision of the end-to-end classification are fully exerted, the accuracy of the diagnosis guide is improved, the interpretable path and the related information recommendation of the diagnosis guide are given, and the use experience of the patient is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for medical consultation according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a reasoning decision process of a method for guiding a patient according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a method for performing a medical procedure according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a diagnostic guidance system according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an embodiment of an electronic device for medical consultation according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a flowchart of a method for guiding a patient according to an embodiment of the present invention, which includes the following steps:
s11: gradually reasoning the symptoms input by the patient based on the medical knowledge map to determine a first result of a department of medical consultation and potential diseases;
s12: inputting the patient-input symptoms into an end-to-end classification model based on deep learning, and outputting a second result of a department of medical guidance and potential diseases;
s13: outputting to the patient a valid referral department and potential illness based on the first result and the second result;
s14: providing interpretable inferential paths corresponding to the effective referral department and potential disease based on the medical knowledge graph.
In the present embodiment, the present invention can be applied to online diagnosis guidance, and can also be applied to an online unmanned intelligent robot. For example, the following takes the case that the patient performs voice online registration through the mobile phone APP.
For step S11, the patient vocally enters symptoms of sore throat, hoarseness. The medical knowledge map is used for gradually reasoning the symptoms of the patient, for example, the symptoms of dyspnea, nasal obstruction, dry and itching throat, swallowing pain, fever with cough, expectoration and chest pain which are accompanied in the medical knowledge map are deduced.
Since the patient may not be able to accurately describe his or her actual condition, he or she may only be able to speak about something like a leg pain, a bone pain associated with the inside of the leg, and a simple leg flesh pain. Neck pain, soreness and numbness of the nerves due to stiff neck. In these details, the patient may not be accurately described, the input content is limited, and the patient is gradually guided in the process of gradual reasoning.
The medical knowledge map is used for reasoning and showing to the patient, so that the patient is guided to input more accurate symptoms, and the patient is used for gradually reasoning to gradually determine the first result of the patient's department of consultation and potential diseases.
For step S12, the symptoms input by the user in step S11 are input to the deep learning-based end-to-end classification model, the symptoms input by the patient are input to the deep learning-based end-to-end classification model, and a second result of the department and the underlying disease is output.
Before that, considering the fuzzy comparison of the description of the patient, if the patient inputs the part information and the part information is fuzzy, and the department or the disease cannot be confirmed, the possible symptoms, causes, duration and other information of the body part can be inferred according to the medical knowledge map and recommended to the patient for confirmation; for example, if the patient says "low back pain", the cause, the type of pain and the duration of the pain can be confirmed with the patient; and then, the following steps are confirmed to assist the department of medical guidance and potential diseases according to the information.
For step S13, the end-to-end classification and inference methods are fused. End-to-end classification is a classification model based on deep learning and extensive training data. The model fusion can fully exert the advantages of high recall and analytic high precision of end-to-end classification, and improve the overall performance of the system; the strategy for model fusion is as follows: the model weight is set to a, the analytical formula weight is set to (1-a), and the top n result department of the model is expressed as[<d1,pd1>,<d2,pd2>,<d3,pd3>...<dn,pdn>]，diDenotes department id, pdiThe confidence of the department i is expressed, and the top n result department of the analytical formula is expressed as [ 2 ]<k1,pk1>,<k2,pk2>,<k3,pk3>...<kn,pkn>]，kiDenotes department id, pkiRepresenting the confidence of department i. And multiplying each department result by the corresponding weight, summing the weights of the same departments, finally sorting the departments according to the weights, and taking the first k departments as final results.
In step S14, the patient inputs a symptom of vomiting with abdominal pain, and outputs the department of medical guidance, while providing a reasoning and decision process, such as the schematic diagram of the reasoning and decision process shown in fig. 2, wherein vomiting and diarrhea correspond to diarrhea, and abdominal pain alone infers fever. Diarrhea may in turn cause dehydration, and finally, acute enteritis and dysentery may be the result. And displaying the determined department of medical guidance and the inference path of the schematic diagram to the patient.
As an embodiment, before the medical knowledge-graph-based stepwise reasoning about patient-entered symptoms, the method comprises:
performing chief complaint identification and medical history identification on patient input;
acquiring basic information of the patient through preset reply or case data when the identified non-chief complaint information is received;
and providing symptom input guide examples for the identified medical history information, so that the patient can input symptoms according to the guide examples.
In the present embodiment, since the patient does not necessarily understand the symptoms, it is necessary to provide a step-by-step guidance to the patient, and it is necessary to be able to specify various items of information of the patient from the patient's chief complaint information. Performing chief information Recognition processing on the input of the patient, and judging whether the input content (text or voice, wherein the voice needs to be converted into text through Automatic Speech Recognition (ASR)) of the patient comprises the chief information; if yes, entering the next step to acquire patient information; otherwise, replying preset words, such as 'please describe your symptom in detail';
basic information of the patient, such as age, sex, pregnancy, etc., can be obtained by the patient information module in a manner of dialogue with the patient; may also be provided by the patient by way of a click; it can also be obtained by calling a patient's case database.
To further ensure the accuracy of the lead, for example, the symptoms of cough are more factors than the common cold alone. For example, through a medical history identification module, the medical history identification is carried out on the content input by the patient, and the family medical history, the past medical history, the allergy medical history or the current medical history are confirmed; for example, if there is a history of allergies, coughing may also be triggered, and thus, the accuracy of the referral may be further improved by adding a history of allergies. If the current medical history does not exist, the current medical history is fed back to the patient, and the input of the current medical history information is prompted; as the following example, "grandfather has hypertension, and is always dizzy recently" can be obtained "grandfather has hypertension < family history >, and is always dizzy < present history >" recently; the last year of thyroid operation, which is always dizziness recently, can be used as the last year of thyroid operation < past medical history >, the last year of thyroid operation always is dizziness < present medical history >, and the whole process is shown in fig. 3(a), fig. 3(b) and fig. 3 (c).
According to the embodiment, the knowledge reasoning function is added in the diagnosis guide, the chief complaint information and the non-chief complaint information of the patient can be distinguished, the prior medical history and the current medical history, the part identification and the part related symptom inquiry are combined with the end-to-end classification and reasoning model, the high recall and analytic formula high precision of the end-to-end classification are fully exerted, the diagnosis guide accuracy is improved, the interpretable path and related information recommendation of the diagnosis guide are given, and the use experience of the patient is improved.
As an embodiment, said providing an interpretable reasoning path corresponding to said effective referral department and potential disease based on said medical knowledge-graph further comprises:
and performing constraint processing of the department of medical consultation on the basic information of the patient based on the common medical knowledge, and further determining the effective department of medical consultation.
In this embodiment, the specific population may be treated based on common sense knowledge, including gender restrictions, age restrictions, allergy history restrictions, and the like. For example, men cannot see women, and so on, and some guidance results that are similar but impossible can be filtered out. Further improving the accuracy of the diagnosis guiding.
As an embodiment, before the medical knowledge-graph-based stepwise reasoning about patient-entered symptoms, the method further comprises:
when the existence of a plurality of symptoms is recognized, the irrelevant symptoms in the plurality of symptoms are determined based on the knowledge map to be respectively subjected to normalization processing, so that a plurality of effective diagnosis guide departments and potential diseases are output to the patient in the output result.
Generating an archive for the patient based at least on the patient's input and the available referral department and interpretable inferential paths for potential disease.
In this embodiment, if the patient has a plurality of symptoms, it is not reasonable to obtain only one diagnosis guide result. And then when the user inputs a plurality of symptoms and the plurality of symptoms are not related through medical knowledge map reasoning, multi-symptom normalization processing is carried out. For example, the method comprises the steps of 'no reexamination after papillary thyroid carcinoma operation', one examination for 'no reexamination after papillary thyroid carcinoma operation' during bruxism at night 'and' no correlation between the examination and the symptom 'bruxism at night', so that normalization treatment is respectively carried out, and finally, guide diagnosis is respectively carried out. "the diagnosis department of thyroid and mammary gland surgery" is not rechecked after papillary thyroid cancer operation, and the symptom "teeth grinding at night" the diagnosis department of guide department "the department of stomatology". At the end of the guide, a case of the patient is generated, so that the patient can be conveniently registered for use next time, and the use experience of the patient is improved.
Fig. 4 is a schematic structural diagram of a diagnosis guide system according to an embodiment of the present invention, which can execute the diagnosis guide method according to any of the above embodiments and is configured in a terminal.
The present embodiment provides a diagnosis guidance system 10 including: an inference program module 11, a classification program module 12, a decision program module 13 and a referral program module 14.
The reasoning program module 11 is used for performing stepwise reasoning on the symptoms input by the patient based on the medical knowledge graph and determining a first result of a department for medical consultation and a potential disease; the classification program module 12 is used for inputting the symptoms input by the patient into an end-to-end classification model based on deep learning and outputting a second result of the department of medical education and the potential diseases; the decision program module 13 is used for outputting a valid department and potential diseases to the patient based on the first result and the second result; the referral program module 14 is used to provide interpretable inferential paths corresponding to the active referral department and potential disease based on the medical knowledge-graph.
Further, the system includes a complaint identification program module for:
performing chief complaint identification and medical history identification on patient input;
acquiring basic information of the patient through preset reply or case data when the identified non-chief complaint information is received;
and providing symptom input guide examples for the identified medical history information, so that the patient can input symptoms according to the guide examples.
Further, the referral program module is further for:
and performing constraint processing of the department of medical consultation on the basic information of the patient based on the common medical knowledge, and further determining the effective department of medical consultation.
Further, the system includes a normalization program module for:
when the existence of a plurality of symptoms is recognized, the irrelevant symptoms in the plurality of symptoms are determined based on the knowledge map to be respectively subjected to normalization processing, so that a plurality of effective diagnosis guide departments and potential diseases are output to the patient in the output result.
Further, the system includes a profile generation program module for:
generating an archive for the patient based at least on the patient's input and the available referral department and interpretable inferential paths for potential disease.
The embodiment of the invention also provides a nonvolatile computer storage medium, wherein the computer storage medium stores computer executable instructions which can execute the diagnosis guide method in any method embodiment;
as one embodiment, a non-volatile computer storage medium of the present invention stores computer-executable instructions configured to:
gradually reasoning the symptoms input by the patient based on the medical knowledge map to determine a first result of a department of medical consultation and potential diseases;
inputting the patient-input symptoms into an end-to-end classification model based on deep learning, and outputting a second result of a department of medical guidance and potential diseases;
outputting to the patient a valid referral department and potential illness based on the first result and the second result;
providing interpretable inferential paths corresponding to the effective referral department and potential disease based on the medical knowledge graph.
As a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the methods in embodiments of the present invention. One or more program instructions are stored in a non-transitory computer readable storage medium that, when executed by a processor, perform a method of referral in any of the method embodiments described above.
Fig. 5 is a schematic hardware structure diagram of an electronic device of a method for guiding a medical examination according to another embodiment of the present application, and as shown in fig. 5, the electronic device includes:
one or more processors 510 and memory 520, with one processor 510 being an example in fig. 5. The apparatus of the method of medical lead may further comprise: an input device 530 and an output device 540.
The processor 510, the memory 520, the input device 530, and the output device 540 may be connected by a bus or other means, and the bus connection is exemplified in fig. 5.
The memory 520 is a non-volatile computer-readable storage medium and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the diagnosis guiding method in the embodiment of the present application. The processor 510 executes various functional applications of the server and data processing by executing the nonvolatile software programs, instructions and modules stored in the memory 520, so as to implement the diagnosis guide method of the above method embodiment.
The memory 520 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Further, the memory 520 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 520 may optionally include memory located remotely from processor 510, which may be connected to a mobile device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 530 may receive input numeric or character information. The output device 540 may include a display device such as a display screen.
The one or more modules are stored in the memory 520 and, when executed by the one or more processors 510, perform the method of referral in any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
The non-volatile computer-readable storage medium may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the device, and the like. Further, the non-volatile computer-readable storage medium may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the non-transitory computer readable storage medium optionally includes memory located remotely from the processor, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
An embodiment of the present invention further provides an electronic device, which includes: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of the embodiments of the present invention.
The electronic device of the embodiments of the present application exists in various forms, including but not limited to:
(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones, multimedia phones, functional phones, and low-end phones, among others.
(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as tablet computers.
(3) Portable entertainment devices such devices may display and play multimedia content. The devices comprise audio and video players, handheld game consoles, electronic books, intelligent toys and portable vehicle-mounted navigation devices.
(4) Other electronic devices with data processing capabilities.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (12)

1. A method of medical lead, comprising:
gradually reasoning the symptoms input by the patient based on the medical knowledge map to determine a first result of a department of medical consultation and potential diseases;
inputting the patient-input symptoms into an end-to-end classification model based on deep learning, and outputting a second result of a department of medical guidance and potential diseases;
outputting to the patient a valid referral department and potential illness based on the first result and the second result;
providing interpretable inferential paths corresponding to the effective referral department and potential disease based on the medical knowledge graph.
2. The method of claim 1, wherein prior to the step-by-step reasoning about patient-entered symptoms based on the medical knowledge-graph, the method comprises:
performing chief complaint identification and medical history identification on patient input;
acquiring basic information of the patient through preset reply or case data when the identified non-chief complaint information is received;
and providing symptom input guide examples for the identified medical history information, so that the patient can input symptoms according to the guide examples.
3. The method of claim 2, wherein said providing interpretable inference paths corresponding to the active referral department and potential disease based on the medical knowledge-graph further comprises:
and performing constraint processing of the department of medical consultation on the basic information of the patient based on the common medical knowledge, and further determining the effective department of medical consultation.
4. The method of claim 1, wherein prior to the medical knowledge-graph-based stepwise reasoning about patient-entered symptoms, the method further comprises:
when the existence of a plurality of symptoms is recognized, the irrelevant symptoms in the plurality of symptoms are determined based on the knowledge map to be respectively subjected to normalization processing, so that a plurality of effective diagnosis guide departments and potential diseases are output to the patient in the output result.
5. The method of claim 1, wherein after said providing interpretable inference paths corresponding to said valid referral department and potential disease based on said medical knowledge-graph, said method further comprises:
generating an archive for the patient based at least on the patient's input and the available referral department and interpretable inferential paths for potential disease.
6. A referral system comprising:
the reasoning program module is used for gradually reasoning the symptoms input by the patient based on the medical knowledge graph and determining a first result of a department of medical consultation and potential diseases;
a classification program module for inputting the symptoms input by the patient into an end-to-end classification model based on deep learning and outputting a second result of the department of medical education and the potential diseases;
a decision-making program module for outputting to the patient a valid referral department and potential illness based on the first result and the second result;
a referral program module for providing interpretable inferential paths corresponding to the active referral department and potential disease based on the medical knowledge-graph.
7. The system of claim 6, wherein the system further comprises a complaint identification program module for:
performing chief complaint identification and medical history identification on patient input;
acquiring basic information of the patient through preset reply or case data when the identified non-chief complaint information is received;
and providing symptom input guide examples for the identified medical history information, so that the patient can input symptoms according to the guide examples.
8. The system of claim 7, wherein the referral program module is further for:
and performing constraint processing of the department of medical consultation on the basic information of the patient based on the common medical knowledge, and further determining the effective department of medical consultation.
9. The system of claim 6, wherein the system further comprises a normalization program module to:
when the existence of a plurality of symptoms is recognized, the irrelevant symptoms in the plurality of symptoms are determined based on the knowledge map to be respectively subjected to normalization processing, so that a plurality of effective diagnosis guide departments and potential diseases are output to the patient in the output result.
10. The system of claim 6, wherein the system further comprises a profile generation program module to:
generating an archive for the patient based at least on the patient's input and the available referral department and interpretable inferential paths for potential disease.
11. An electronic device, comprising: at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any of claims 1-5.
12. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
CN202111432679.8A 2021-11-29 2021-11-29 Diagnosis guiding method and system Pending CN114068029A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111432679.8A CN114068029A (en) 2021-11-29 2021-11-29 Diagnosis guiding method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111432679.8A CN114068029A (en) 2021-11-29 2021-11-29 Diagnosis guiding method and system

Publications (1)

Publication Number Publication Date
CN114068029A true CN114068029A (en) 2022-02-18

Family

ID=80277608

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111432679.8A Pending CN114068029A (en) 2021-11-29 2021-11-29 Diagnosis guiding method and system

Country Status (1)

Country Link
CN (1) CN114068029A (en)

Similar Documents

Publication Publication Date Title
WO2021139232A1 (en) Medical knowledge graph-based triage method and apparatus, device, and storage medium
WO2021174728A1 (en) Triage data processing method and apparatus, computer device, and storage medium
CN108491486B (en) Method, device, terminal equipment and storage medium for simulating patient inquiry dialogue
CN111666477B (en) Data processing method, device, intelligent equipment and medium
KR102217457B1 (en) A chat service providing system that can provide medical consultation according to customer&#39;s needs with a chat robot
CN112015917A (en) Data processing method and device based on knowledge graph and computer equipment
CN109255013A (en) Claims Resolution decision-making technique, device, computer equipment and storage medium
CN110675944A (en) Triage method and device, computer equipment and medium
CN112256825A (en) Medical field multi-turn dialogue intelligent question-answering method and device and computer equipment
KR101943556B1 (en) Method for providing ai type care service for shopping, healthcare, company and game
CN110377719B (en) Medical question and answer method and device
CN111933291A (en) Medical information recommendation device, method, system, equipment and readable storage medium
WO2023178971A1 (en) Internet registration method, apparatus and device for seeking medical advice, and storage medium
CN112016295A (en) Symptom data processing method and device, computer equipment and storage medium
WO2023024422A1 (en) Consultation session-based auxiliary diagnosis method and apparatus, and computer device
CN110223134B (en) Product recommendation method based on voice recognition and related equipment
WO2021139231A1 (en) Triage method and apparatus based on neural network model, and computer device
CN113409907A (en) Intelligent pre-inquiry method and system based on Internet hospital
CN111008269A (en) Data processing method and device, storage medium and electronic terminal
CN117216209A (en) Ultrasonic examination report reading system based on large language model
CN111651579A (en) Information query method and device, computer equipment and storage medium
CN114664431A (en) Artificial intelligence assisted question and answer method, device, equipment and medium
CN114708976A (en) Method, device, equipment and storage medium for assisting diagnosis technology
CN117149998B (en) Intelligent diagnosis recommendation method and system based on multi-objective optimization
CN116861875A (en) Text processing method, device, equipment and storage medium based on artificial intelligence

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