CN116884629B - Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI - Google Patents
Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI Download PDFInfo
- Publication number
- CN116884629B CN116884629B CN202311141740.2A CN202311141740A CN116884629B CN 116884629 B CN116884629 B CN 116884629B CN 202311141740 A CN202311141740 A CN 202311141740A CN 116884629 B CN116884629 B CN 116884629B
- Authority
- CN
- China
- Prior art keywords
- symptom
- keywords
- characterization
- symptom keywords
- keyword
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 37
- 238000007726 management method Methods 0.000 title claims abstract description 25
- 239000003814 drug Substances 0.000 title claims abstract description 18
- 208000024891 symptom Diseases 0.000 claims description 315
- 238000012512 characterization method Methods 0.000 claims description 66
- 201000010099 disease Diseases 0.000 claims description 32
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 32
- 230000004044 response Effects 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 206010012735 Diarrhoea Diseases 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
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
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/90—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to alternative medicines, e.g. homeopathy or oriental medicines
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Alternative & Traditional Medicine (AREA)
- Pharmacology & Pharmacy (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of traditional Chinese medicine diagnosis and treatment, in particular to an AI-based digital management method and system for traditional Chinese medicine diagnosis and treatment.
Description
Technical Field
The invention relates to the technical field of traditional Chinese medicine diagnosis and treatment, in particular to an AI-based digital management method and system for traditional Chinese medicine diagnosis and treatment.
Background
With the development of computer technology and internet technology, digital medical treatment is paid attention to, and particularly, an artificial intelligence data analysis is introduced to support a platform of medical care services by utilizing information technology and communication technology to integrate and share medical data, medical resources and medical services, so that high efficiency, convenience and accuracy of medical services are realized.
For example, chinese patent publication No.: CN113257390a discloses the following matters, the invention provides an AI intelligent diagnosis and treatment system, which comprises a data acquisition system, a mobile terminal app and a physician looking-in inquiring and inquiring reproduction system, wherein the mobile terminal app comprises a client app, a physician app, a one-to-one traditional Chinese medicine diagnosis module, a traditional Chinese medicine database module, an AI artificial intelligent pathology analysis software system, a traditional Chinese medicine store management module, a transaction module and a traditional Chinese medicine statistics management analysis module, the data acquisition system is used for acquiring health condition information of a patient, uploading acquired data information to the analysis system or directly transmitting the acquired data information to the mobile terminal app, registering and storing received disease information and patient information, and recommending online on-duty traditional Chinese medicine doctors to the patient through the one-to-one diagnosis module.
However, the prior art has the following problems:
because of limited doctor receiving of the inquiry platform and large patient demand, the inquiry platform often adopts a form of collecting patient symptom descriptions in advance and then processing replies one by one, but in the actual real-time inquiry process, the doctor may need to know other symptoms related to the corresponding symptoms for making a judgment,
therefore, if the symptom description provided by the patient for the first time is comprehensive, the inquiry efficiency is directly affected;
in the prior art, the data analysis mode is not considered, so that a patient is guided to provide more comprehensive symptom description data, diagnosis of a doctor is assisted, the probability of repeated inquiry is reduced, and the inquiry efficiency is improved.
Disclosure of Invention
In order to solve the problems, the invention provides an AI-based digital management method for traditional Chinese medicine diagnosis and treatment, which comprises the following steps:
step S1, a case database is searched, diagnosis-confirming disease type information and symptom description texts in each case are obtained, characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, the characterization symptom keywords are stored in the same associated data set, the step S1 comprises the steps of extracting a plurality of cases belonging to a single disease type when the characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, obtaining the symptom keywords in the symptom description texts of each case, and determining whether the corresponding symptom keywords are the characterization symptom keywords or not based on the occurrence probability of the symptom keywords;
step S2, responding to the preset condition, extracting symptom keywords in the text information uploaded by the user terminal, analyzing whether the symptom keywords have association relation, determining a response mode to the text uploaded by the user terminal, comprising,
extracting symptom keywords with association relation under a first preset condition, comparing each symptom keyword with elements in a plurality of screened associated data sets, calculating keyword occupation ratio to screen an optimal associated data set, selecting characterization symptom keywords from the optimal associated data set, generating query information for querying corresponding symptoms based on the selected characterization symptom keywords, and feeding back the query information to a user side;
under a second preset condition, extracting each symptom keyword, comparing the symptom keywords with data in a case database one by one, calculating the occurrence probability of the residual symptom keywords when the symptom keywords appear in a single case, selecting the most relevant symptom keywords corresponding to each symptom keyword based on probability sequencing, generating query information of corresponding symptoms based on each most relevant symptom keyword, and feeding back the query information to a user side;
step S3, acquiring response information made by the user side in response to the query information;
the preset conditions are text information for describing symptoms on the user side, the first preset conditions are symptom keywords with association relations, and the second preset conditions are symptom keywords without association relations.
Further, in the step S1, it is determined whether the corresponding symptom keyword is a characterization symptom keyword based on the occurrence probability of each symptom keyword, wherein,
comparing the occurrence probability of the symptom keywords with a preset probability comparison threshold value,
if the comparison result meets the preset probability comparison result, judging that the corresponding symptom keywords are characterization symptom keywords;
the preset probability comparison result is that the occurrence probability of the symptom keywords is larger than or equal to a preset probability comparison threshold value, and the occurrence probability of the symptom keywords is the ratio of the total number of the symptom keywords to the number of cases in each case.
Further, in the step S2, it is analyzed whether the symptom keywords in the text information uploaded by the user terminal have an association relationship, wherein,
comparing the symptom keywords in the text information uploaded by the user side with the characterization symptom keywords in each associated data set,
judging that the keywords of each symptom have association relations under a preset comparison result;
judging that the keywords of each symptom have no association relationship under the non-preset comparison result;
the preset comparison result is that the associated data set contains keywords of each symptom.
Further, in the step S2, the keyword ratio R is calculated according to the formula (1),
（1）；
in the formula (1), N represents the number of symptom keywords with association relation, N represents the number of characterization symptom keywords in the screened associated data set, and the screened associated data set is an associated data set containing all symptom keywords in text information uploaded by a user side.
Further, in said step S2, an optimal set of associated data is screened, wherein,
and determining the maximum keyword occupation ratio, and determining the associated data set corresponding to the maximum keyword occupation ratio as the optimal associated data set.
Further, in said step S2, a symptom characterizing keyword is selected from said optimal association data set, wherein,
determining the residual characterization symptom keywords in the optimal association data set, and determining the residual characterization symptom keywords as selected characterization symptom keywords, wherein the residual characterization symptom keywords are residual characterization symptom keywords in the optimal association data set after the symptom keywords in the text information uploaded by the user side are removed.
Further, in the step S2, a probability of occurrence of the symptom keywords remaining when the symptom keywords occur in a single case is calculated, wherein,
the probability of occurrence of the remaining symptom keywords is the ratio of the number of cases in which the symptom keywords and the remaining symptom keywords occur simultaneously to the total number of cases.
Further, in the step S2, the most relevant symptom keywords corresponding to the symptom keywords are selected based on the probability ranking, wherein,
and ordering the occurrence probability of the residual symptom keywords, and determining the residual symptom keywords corresponding to the maximum probability as the most relevant symptom keywords.
Further, in said step S2, generating the query information comprises,
generating query information for querying the corresponding symptom based on the selected symptom-characterizing keyword, wherein,
determining a first combined sentence, wherein the first combined sentence is used as query information for querying corresponding symptoms, and the first combined sentence is a sentence formed by combining a preset sentence, a preset punctuation mark and the selected characterization symptom keywords according to a preset sequence;
and generating query information of the corresponding symptom based on each most relevant symptom keyword, wherein,
determining a second combined sentence, wherein the second combined sentence is used as query information of corresponding symptoms, and the second combined sentence is a sentence formed by combining preset sentences, preset punctuation marks and most relevant symptom keywords according to a preset sequence.
Further, a system applied to the AI-based digital management method for Chinese medical diagnosis and treatment is provided, which is characterized by comprising,
one or more processors;
a memory;
and one or more programs;
the one or more programs are configured to be executed by the one or more processors, and the memory includes a storage medium storing a computer program that is operable to perform an AI-based digital management method for chinese medical science diagnosis and treatment when executed by the processor.
Compared with the prior art, the method and the device have the advantages that the case database is searched to obtain the confirmed disease type information and the symptom description text in each case, the characterization symptom keywords corresponding to the confirmed disease type information are determined, the characterization symptom keywords are stored in the same associated data set, the symptom keywords in the text information uploaded by the user side are extracted in response to preset conditions, whether the association relationship exists among the symptom keywords is analyzed, the response mode of the text uploaded by the user side is determined, the response information of the user side responding to the query information is acquired, the patient is guided to provide more comprehensive and more characterized symptoms, the diagnosis of doctors is assisted, the probability of repeated query is reduced, and the query efficiency is further improved.
In particular, in the present invention, whether the corresponding symptom keywords are the symptom characterization keywords is determined based on the occurrence probability of each symptom keyword, in actual situations, a specific disease has its specific related symptoms, symptom keywords with high occurrence probability recorded in a plurality of cases of a single disease are related symptoms of the disease, and each symptom keyword with high occurrence probability is used as the symptom characterization keyword for characterizing the disease.
In particular, in the invention, whether the symptom keywords in the text information uploaded by the user side have an association relation is analyzed, and if the symptom keywords in the associated data set are all specific related symptoms corresponding to the disease types, the symptom keywords in the uploaded text information are all present in any associated data set, so that the symptom keywords in the text information are all specific related symptoms corresponding to the disease types corresponding to the associated data set, when data processing is convenient, the associated data set with the strongest characterization is selected, and query information is correspondingly generated subsequently, so that a patient is guided to provide more comprehensive and more characterization symptoms, diagnosis is assisted by doctors, the probability of repeated query is reduced, and the query efficiency is further improved.
Particularly, in the invention, under the first preset condition, the symptom keywords are selected from the optimal association data set, the query information for querying the corresponding symptoms is generated based on the selected characterization symptom keywords, and under the first preset condition, the association relation exists among the symptom keywords in the text information uploaded by the user side, so that the symptom keywords in the text information are compared with elements in the association data set containing all the symptom keywords in the text information uploaded by the user side, the association data set with the largest proportion of the symptom keywords in the text information, namely the association data set with the strongest association with the symptom keywords in the text information, is used as the optimal association data set, and as the characterization symptom keywords in the same association data set are a plurality of related symptoms of the same disease, other characterization symptom keywords except the symptom keywords in the text information are selected from the optimal association data set, namely the query information is generated, and other possible most existing query information except the related symptom keywords described by the patient is more guided, the diagnosis probability of the patient is more improved, the repeated symptom is more improved, and the repeated diagnosis is more effective, and the symptom is more diagnostic is represented.
Particularly, in the invention, under the second preset condition, query information of corresponding symptoms is generated based on each most relevant symptom keyword, the second preset condition characterizes that the symptom keywords in the text information uploaded by the user terminal have no association relation, and an optimal association data set corresponding to the symptom keywords in the text information cannot be determined, so that the symptom keywords in the text information are compared with data in a case database, the symptom keywords with the highest probability of occurrence of the residual symptom keywords which occur simultaneously with the symptom keywords in the text information in a single case of the case database are selected, namely, the symptom keywords with the highest association with the symptom keywords in the text information in the case database are used as the most relevant symptom keywords to generate query information, a patient is guided to provide more comprehensive and more characterizable symptoms, diagnosis is assisted by doctors, the probability of repeated query is reduced, and further the query efficiency is improved.
Drawings
Fig. 1 is a schematic diagram of steps of a digital management method of AI-based traditional Chinese medicine diagnosis and treatment according to an embodiment of the invention;
FIG. 2 is a flow chart of a symptom characterization keyword decision process in accordance with an embodiment of the present invention;
fig. 3 is a flowchart of determining association relation between keywords of each symptom in text information according to an embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
Referring to fig. 1, which is a schematic step diagram of an AI-based digital management method for traditional Chinese medicine diagnosis and treatment according to an embodiment of the present invention, the AI-based digital management method for traditional Chinese medicine diagnosis and treatment includes:
step S1, a case database is searched, diagnosis-confirming disease type information and symptom description texts in each case are obtained, characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, the characterization symptom keywords are stored in the same associated data set, the step S1 comprises the steps of extracting a plurality of cases belonging to a single disease type when the characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, obtaining the symptom keywords in the symptom description texts of each case, and determining whether the corresponding symptom keywords are the characterization symptom keywords or not based on the occurrence probability of the symptom keywords;
step S2, responding to the preset condition, extracting symptom keywords in the text information uploaded by the user terminal, analyzing whether the symptom keywords have association relation, determining a response mode to the text uploaded by the user terminal, comprising,
extracting symptom keywords with association relation under a first preset condition, comparing each symptom keyword with elements in a plurality of screened associated data sets, calculating keyword occupation ratio to screen an optimal associated data set, selecting characterization symptom keywords from the optimal associated data set, generating query information for querying corresponding symptoms based on the selected characterization symptom keywords, and feeding back the query information to a user side;
under a second preset condition, extracting each symptom keyword, comparing the symptom keywords with data in a case database one by one, calculating the occurrence probability of the residual symptom keywords when the symptom keywords appear in a single case, selecting the most relevant symptom keywords corresponding to each symptom keyword based on probability sequencing, generating query information of corresponding symptoms based on each most relevant symptom keyword, and feeding back the query information to a user side;
step S3, acquiring response information made by the user side in response to the query information;
the preset conditions are text information for describing symptoms on the user side, the first preset conditions are symptom keywords with association relations, and the second preset conditions are symptom keywords without association relations.
Specifically, in the present invention, the cases in the case database are described with disease type information and symptom descriptions.
Specifically, the specific method for acquiring the confirmed disease information and the symptom description text in each case is not limited, a crawler program capable of crawling corresponding information can be preset, and a case database which is accessed to obtain the confirmed disease information and the symptom description text is crawled in advance, which is the prior art and is not repeated.
Specifically, the specific form of uploading the text to the user terminal and the specific form of sending the query information to the user terminal are not limited, and in this embodiment, the interactive chat window with the user terminal may be provided by the query platform to realize the above functions, and of course, other forms are also possible, which will not be described herein.
Specifically, referring to fig. 2, in the step S1, it is determined whether the corresponding symptom keyword is a characterization symptom keyword based on the occurrence probability of each symptom keyword, wherein,
the occurrence probability P of the symptom keywords is compared with a preset probability comparison threshold P0,
if the comparison result meets the preset probability comparison result, judging that the corresponding symptom keywords are characterization symptom keywords;
the preset probability comparison result is that P is more than or equal to P0, and the occurrence probability of the symptom keywords is the ratio of the total number of the symptom keywords to the number of cases in each case.
Specifically, in the present embodiment, P0 is selected from within the interval [0.55,0.95 ].
Specifically, in the invention, whether the corresponding symptom keywords are the characterization symptom keywords is determined based on the occurrence probability of each symptom keyword, in actual situations, a specific disease has specific related symptoms, the symptom keywords with high occurrence probability recorded in a plurality of cases of a single disease are the related symptoms of the disease, and each symptom keyword with high occurrence probability is used as the characterization symptom keywords for characterizing the disease.
Specifically, referring to fig. 3, in the step S2, it is analyzed whether there is an association relationship between symptom keywords in the text information uploaded by the user terminal, wherein,
comparing the symptom keywords in the text information uploaded by the user side with the characterization symptom keywords in each associated data set,
judging that the keywords of each symptom have association relations under a preset comparison result;
judging that the keywords of each symptom have no association relationship under the non-preset comparison result;
the preset comparison result is that the associated data set contains keywords of each symptom.
Specifically, in the invention, whether the symptom keywords in the text information uploaded by the user side have an association relation is analyzed, and if the symptom keywords in the associated data set are all specific related symptoms corresponding to the disease types, the symptom keywords in the uploaded text information are all the specific related symptoms corresponding to the associated data set, so that the symptom keywords in the text information are indicated to be the specific related symptoms of the disease types corresponding to the associated data set, when the data processing is convenient, the associated data set with the strongest characterization is selected, and query information is correspondingly generated subsequently, so that a patient is guided to provide more comprehensive and more characterization symptoms, diagnosis of doctors is assisted, the probability of repeated query is reduced, and the query efficiency is further improved.
Specifically, in the step S2, the keyword ratio R is calculated according to the formula (1),
（1）；
in the formula (1), N represents the number of symptom keywords with association relation, N represents the number of characterization symptom keywords in the screened associated data set, and the screened associated data set is an associated data set containing all symptom keywords in text information uploaded by a user side.
Specifically, in said step S2, an optimal set of associated data is screened, wherein,
and determining the maximum keyword occupation ratio, and determining the associated data set corresponding to the maximum keyword occupation ratio as the optimal associated data set.
Specifically, in the invention, under a first preset condition, a symptom keyword is selected from an optimal association data set, query information for querying a symptom corresponding to the symptom is generated based on the selected characterization symptom keyword, and under the first preset condition, the symptom keyword in the text information uploaded by a user side is characterized to have an association relation, so that the symptom keyword in the text information is compared with elements in the association data set containing all symptom keywords in the text information uploaded by the user side, the association data set containing all symptom keywords in the text information uploaded by the user side is determined, the association data set with the largest proportion of the symptom keywords in the text information, namely the association data set with the strongest association with the symptom keyword in the text information is used as the optimal association data set, and as the characterization symptom keywords in the same association data set are a plurality of related symptoms of the same disease, other characterization symptom keywords except the symptom keywords in the text information are selected from the optimal association data set to generate query information, namely the most possible other query information except the related symptom keywords described by a patient, the most likely to exist, the query probability of the patient is reduced, the diagnosis is more comprehensively presented, and the symptom is more difficult to diagnose, and the symptom is more comprehensively represented by the query probability is improved.
Specifically, in said step S2, a symptom characterizing keyword is selected from said optimal correlation data set, wherein,
determining the residual characterization symptom keywords in the optimal association data set, and determining the residual characterization symptom keywords as selected characterization symptom keywords, wherein the residual characterization symptom keywords are residual characterization symptom keywords in the optimal association data set after the symptom keywords in the text information uploaded by the user side are removed.
Specifically, in the step S2, the probability of occurrence of the symptom keywords remaining when the symptom keywords occur in a single case is calculated, wherein,
the probability of occurrence of the remaining symptom keywords is the ratio of the number of cases in which the symptom keywords and the remaining symptom keywords occur simultaneously to the total number of cases.
Specifically, in the step S2, the most relevant symptom keywords corresponding to the symptom keywords are selected based on the probability ranking, wherein,
and ordering the occurrence probability of the residual symptom keywords, and determining the residual symptom keywords corresponding to the maximum probability as the most relevant symptom keywords.
Specifically, in the invention, under a second preset condition, query information of corresponding symptoms is generated based on each most relevant symptom keyword, the second preset condition characterizes that the symptom keywords in the text information uploaded by a user terminal have no association relation, and an optimal association data set corresponding to the symptom keywords in the text information cannot be determined, so that the symptom keywords in the text information are compared with data in a case database, the symptom keywords with the highest probability of occurrence of the residual symptom keywords which occur simultaneously with the symptom keywords in the text information in a single case of the case database are selected, namely, the symptom keywords with the highest association with the symptom keywords in the text information in the case database are used as the most relevant symptom keywords to generate query information, a patient is guided to provide more comprehensive and more characterizable symptoms, diagnosis is assisted by doctors, the probability of repeated query is reduced, and further the query efficiency is improved.
In particular, in said step S2, generating the query information comprises,
generating query information for querying the corresponding symptom based on the selected symptom-characterizing keyword, wherein,
determining a first combined sentence, wherein the first combined sentence is used as query information for querying corresponding symptoms, and the first combined sentence is a sentence formed by combining a preset sentence, a preset punctuation mark and the selected characterization symptom keywords according to a preset sequence;
for example, a keyword that characterizes symptoms is "diarrhea", a preset sentence is "whether it appears", a preset punctuation mark is "? ", a first combined sentence is formed after combination according to a preset sequence," is diarrhea occurred? ".
And generating query information of the corresponding symptom based on each most relevant symptom keyword, wherein,
determining a second combined sentence, wherein the second combined sentence is used as query information of corresponding symptoms, and the second combined sentence is a sentence formed by combining preset sentences, preset punctuation marks and most relevant symptom keywords according to a preset sequence.
Specifically, the invention does not limit the specific implementation manner of combining the preset sentence, the preset punctuation mark and the selected characterization symptom keywords or the most relevant symptom keywords into the sentence according to the preset sequence, and the method can be realized by using the splicing operation of character strings, and only the function of combining the sentence can be completed, and the description is omitted.
In particular to a system applied to the AI-based digital management method for traditional Chinese medicine diagnosis and treatment, which comprises,
one or more processors;
a memory;
and one or more programs;
the one or more programs are configured to be executed by the one or more processors, and the memory includes a storage medium storing a computer program that is operable to perform an AI-based digital management method for chinese medical science diagnosis and treatment when executed by the processor.
The AI-based digital management method for chinese medical science diagnosis and treatment of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
Claims (9)
1. The digital management method for the traditional Chinese medicine diagnosis and treatment based on the AI is characterized by comprising the following steps:
step S1, a case database is searched, diagnosis-confirming disease type information and symptom description texts in each case are obtained, characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, the characterization symptom keywords are stored in the same associated data set, the step S1 comprises the steps of extracting a plurality of cases belonging to a single disease type when the characterization symptom keywords corresponding to the diagnosis-confirming disease type information are determined, obtaining the symptom keywords in the symptom description texts of each case, and determining whether the corresponding symptom keywords are the characterization symptom keywords or not based on the occurrence probability of the symptom keywords;
step S2, responding to the preset condition, extracting symptom keywords in the text information uploaded by the user terminal, analyzing whether the symptom keywords have association relation, determining a response mode to the text uploaded by the user terminal, comprising,
extracting symptom keywords with association relation under a first preset condition, comparing each symptom keyword with elements in a plurality of screened associated data sets, calculating keyword occupation ratio to screen an optimal associated data set, selecting characterization symptom keywords from the optimal associated data set, generating query information for querying corresponding symptoms based on the selected characterization symptom keywords, and feeding back the query information to a user side;
under a second preset condition, extracting each symptom keyword, comparing the symptom keywords with data in a case database one by one, calculating the occurrence probability of the residual symptom keywords when the symptom keywords appear in a single case, selecting the most relevant symptom keywords corresponding to each symptom keyword based on probability sequencing, generating query information of corresponding symptoms based on each most relevant symptom keyword, and feeding back the query information to a user side;
step S3, acquiring response information made by the user side in response to the query information;
the method comprises the steps that a user uploads text information describing symptoms, a first preset condition is a symptom keyword with an association relation, and a second preset condition is a symptom keyword without an association relation;
in said step S2, a symptom characterizing keyword is selected from said optimal association data set, wherein,
determining the residual characterization symptom keywords in the optimal association data set, and determining the residual characterization symptom keywords as selected characterization symptom keywords, wherein the residual characterization symptom keywords are residual characterization symptom keywords in the optimal association data set after the symptom keywords in the text information uploaded by the user side are removed.
2. The AI-based digital management method for diagnosis and treatment of chinese medical science according to claim 1, wherein in step S1, it is determined whether the corresponding symptom keyword is a characterization symptom keyword based on the occurrence probability of each symptom keyword, wherein,
comparing the occurrence probability of the symptom keywords with a preset probability comparison threshold value,
if the comparison result meets the preset probability comparison result, judging that the corresponding symptom keywords are characterization symptom keywords;
the preset probability comparison result is that the occurrence probability of the symptom keywords is larger than or equal to a preset probability comparison threshold value, and the occurrence probability of the symptom keywords is the ratio of the total number of the symptom keywords to the number of cases in each case.
3. The AI-based digital management method for diagnosis and treatment of traditional Chinese medicine according to claim 1, wherein in step S2, it is analyzed whether the association relationship exists between the symptom keywords in the text information uploaded by the user terminal,
comparing the symptom keywords in the text information uploaded by the user side with the characterization symptom keywords in each associated data set,
judging that the keywords of each symptom have association relations under a preset comparison result;
judging that the keywords of each symptom have no association relationship under the non-preset comparison result;
the preset comparison result is that the associated data set contains keywords of each symptom.
4. The AI-based digital management method for diagnosis and treatment of chinese medical science according to claim 1, wherein in step S2, the keyword occupation ratio R is calculated according to formula (1),
，
in the formula (1), N represents the number of symptom keywords with association relation, N represents the number of characterization symptom keywords in the screened associated data set, and the screened associated data set is an associated data set containing all symptom keywords in text information uploaded by a user side.
5. The AI-based digital management method for diagnosis and treatment of chinese medical science according to claim 1, wherein in step S2, an optimal set of associated data is screened, wherein,
and determining the maximum keyword occupation ratio, and determining the associated data set corresponding to the maximum keyword occupation ratio as the optimal associated data set.
6. The AI-based digital management method for diagnosis and treatment of chinese medical science according to claim 1, wherein in the step S2, a probability of occurrence of the remaining symptom keywords when the symptom keywords occur in a single case is calculated, wherein the probability of occurrence of the remaining symptom keywords is a ratio of the number of cases in which the symptom keywords and the remaining symptom keywords occur simultaneously to the total number of cases.
7. The AI-based digital management method for diagnosis and treatment of chinese medical science according to claim 1, wherein in step S2, the most relevant symptom keywords corresponding to each symptom keyword are selected based on probability ranking, wherein,
and ordering the occurrence probability of the residual symptom keywords, and determining the residual symptom keywords corresponding to the maximum probability as the most relevant symptom keywords.
8. The AI-based digital management method for medical diagnosis and treatment of claim 1, wherein, in step S2, generating query information includes,
generating query information for querying the corresponding symptom based on the selected symptom-characterizing keyword, wherein,
determining a first combined sentence, wherein the first combined sentence is used as query information for querying corresponding symptoms, and the first combined sentence is a sentence formed by combining a preset sentence, a preset punctuation mark and the selected characterization symptom keywords according to a preset sequence;
and generating query information of the corresponding symptom based on each most relevant symptom keyword, wherein,
determining a second combined sentence, wherein the second combined sentence is used as query information of corresponding symptoms, and the second combined sentence is a sentence formed by combining preset sentences, preset punctuation marks and most relevant symptom keywords according to a preset sequence.
9. A system for applying the AI-based digital management method for Chinese medical diagnosis and treatment as set forth in any one of claims 1 to 8, comprising,
one or more processors;
a memory;
and one or more programs;
the one or more programs are configured to be executed by the one or more processors, the memory including a storage medium storing a computer program that is operable when executed by the processor to perform the AI-based digital management method of traditional chinese medical science diagnosis of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311141740.2A CN116884629B (en) | 2023-09-06 | 2023-09-06 | Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311141740.2A CN116884629B (en) | 2023-09-06 | 2023-09-06 | Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116884629A CN116884629A (en) | 2023-10-13 |
| CN116884629B true CN116884629B (en) | 2023-12-05 |
Family
ID=88271938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311141740.2A Active CN116884629B (en) | 2023-09-06 | 2023-09-06 | Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116884629B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016018457A (en) * | 2014-07-09 | 2016-02-01 | 株式会社東芝 | Inspection information providing system |
| CN107610774A (en) * | 2017-10-25 | 2018-01-19 | 医渡云（北京）技术有限公司 | Intelligent way of inquisition and device, storage medium, electronic equipment |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| CN111899884A (en) * | 2020-06-23 | 2020-11-06 | 北京左医科技有限公司 | Intelligent auxiliary inquiry method, device and storage medium |
| CN112652407A (en) * | 2020-06-30 | 2021-04-13 | 卫宁健康科技集团股份有限公司 | Method and device for screening diagnosis and treatment information of internet hospital and storage medium |
| KR102444460B1 (en) * | 2021-08-30 | 2022-09-19 | 주식회사 초메디신 | Method of providing chatbot service for symptom and disease matching based on ai |
| CN116313128A (en) * | 2023-03-24 | 2023-06-23 | 陈华才 | Medical science and technology big data intelligent decision method based on multistage indexes |
| CN116564478A (en) * | 2023-05-11 | 2023-08-08 | 平安科技（深圳）有限公司 | Auxiliary diagnosis method, system, equipment and storage medium for traditional Chinese medicine |
-
2023
- 2023-09-06 CN CN202311141740.2A patent/CN116884629B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016018457A (en) * | 2014-07-09 | 2016-02-01 | 株式会社東芝 | Inspection information providing system |
| CN107610774A (en) * | 2017-10-25 | 2018-01-19 | 医渡云（北京）技术有限公司 | Intelligent way of inquisition and device, storage medium, electronic equipment |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| CN111899884A (en) * | 2020-06-23 | 2020-11-06 | 北京左医科技有限公司 | Intelligent auxiliary inquiry method, device and storage medium |
| CN112652407A (en) * | 2020-06-30 | 2021-04-13 | 卫宁健康科技集团股份有限公司 | Method and device for screening diagnosis and treatment information of internet hospital and storage medium |
| KR102444460B1 (en) * | 2021-08-30 | 2022-09-19 | 주식회사 초메디신 | Method of providing chatbot service for symptom and disease matching based on ai |
| CN116313128A (en) * | 2023-03-24 | 2023-06-23 | 陈华才 | Medical science and technology big data intelligent decision method based on multistage indexes |
| CN116564478A (en) * | 2023-05-11 | 2023-08-08 | 平安科技（深圳）有限公司 | Auxiliary diagnosis method, system, equipment and storage medium for traditional Chinese medicine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116884629A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110413875B (en) | Text information pushing method and related device | |
| US7693904B2 (en) | Method and system for determining relation between search terms in the internet search system | |
| US9336485B2 (en) | Determining answers in a question/answer system when answer is not contained in corpus | |
| US20050149519A1 (en) | Document information search apparatus and method and recording medium storing document information search program therein | |
| US20070192309A1 (en) | Method and system for identifying sentence boundaries | |
| US20090287663A1 (en) | Disease name input support program, method and apparatus | |
| WO2023178971A1 (en) | Internet registration method, apparatus and device for seeking medical advice, and storage medium | |
| US20080109400A1 (en) | Method and device for configuring a variety of medical information | |
| EP3966658A1 (en) | Methods and systems for classification using expert data | |
| CN113782195A (en) | Physical examination package customization method and device | |
| CN105512300B (en) | information filtering method and system | |
| US9020962B2 (en) | Interest expansion using a taxonomy | |
| CN112669113A (en) | Product recommendation method and device, storage medium and electronic device | |
| CN106960133B (en) | Disease prediction method and device | |
| JP2009265754A (en) | Information providing system, information providing method, and information providing program | |
| CN113672758B (en) | Song list generation method, device, medium and computing equipment | |
| CN116910374B (en) | Knowledge graph-based health care service recommendation method, device and storage medium | |
| CN116884629B (en) | Digital management method and system for traditional Chinese medicine diagnosis and treatment based on AI | |
| CN113392205A (en) | User portrait construction method, device and equipment and storage medium | |
| CN117290509A (en) | Training method and device for text classification model of electronic medical record, electronic equipment and medium | |
| US20140310020A1 (en) | System and method for diagnosing a patient based on an analysis of multimedia content | |
| JP2017167829A (en) | Detection device, detection method, and detection program | |
| CN115346634A (en) | Physical examination report interpretation prediction method and system, electronic equipment and storage medium | |
| CN115588492A (en) | Diagnosis guiding method and system based on artificial intelligence | |
| CN113779373A (en) | Physical examination item determination method, physical examination item determination device, physical examination equipment and storage medium |
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 |