CN112735556A - Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia - Google Patents
Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia Download PDFInfo
- Publication number
- CN112735556A CN112735556A CN201911027991.1A CN201911027991A CN112735556A CN 112735556 A CN112735556 A CN 112735556A CN 201911027991 A CN201911027991 A CN 201911027991A CN 112735556 A CN112735556 A CN 112735556A
- Authority
- CN
- China
- Prior art keywords
- insomnia
- traditional chinese
- chinese medicine
- ancient book
- database
- 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
Links
- 208000013738 Sleep Initiation and Maintenance disease Diseases 0.000 title claims abstract description 89
- 206010022437 insomnia Diseases 0.000 title claims abstract description 88
- 239000003814 drug Substances 0.000 title claims abstract description 70
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000003745 diagnosis Methods 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000013178 mathematical model Methods 0.000 claims abstract description 18
- 230000001149 cognitive effect Effects 0.000 claims abstract description 17
- 238000011160 research Methods 0.000 claims abstract description 12
- 208000011580 syndromic disease Diseases 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 25
- 208000024891 symptom Diseases 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 16
- 238000007619 statistical method Methods 0.000 claims description 12
- 230000007717 exclusion Effects 0.000 claims description 8
- 230000004069 differentiation Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 239000008194 pharmaceutical composition Substances 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012098 association analyses Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 18
- 230000006870 function Effects 0.000 description 15
- 201000010099 disease Diseases 0.000 description 13
- 230000007812 deficiency Effects 0.000 description 12
- 238000011156 evaluation Methods 0.000 description 10
- 229940079593 drug Drugs 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 208000013403 hyperactivity Diseases 0.000 description 4
- 210000004185 liver Anatomy 0.000 description 4
- 210000000056 organ Anatomy 0.000 description 4
- 210000000952 spleen Anatomy 0.000 description 4
- 244000247747 Coptis groenlandica Species 0.000 description 3
- 235000002991 Coptis groenlandica Nutrition 0.000 description 3
- 206010062717 Increased upper airway secretion Diseases 0.000 description 3
- 208000031971 Yin Deficiency Diseases 0.000 description 3
- 210000000232 gallbladder Anatomy 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 208000026435 phlegm Diseases 0.000 description 3
- 206010000060 Abdominal distension Diseases 0.000 description 2
- 206010008479 Chest Pain Diseases 0.000 description 2
- 241000675108 Citrus tangerina Species 0.000 description 2
- 206010015137 Eructation Diseases 0.000 description 2
- 206010022998 Irritability Diseases 0.000 description 2
- 208000019790 abdominal distention Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 208000027687 belching Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000019771 cognition Effects 0.000 description 2
- 230000008506 pathogenesis Effects 0.000 description 2
- 239000006187 pill Substances 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241000213006 Angelica dahurica Species 0.000 description 1
- 241000202726 Bupleurum Species 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 108010010803 Gelatin Proteins 0.000 description 1
- 241001071795 Gentiana Species 0.000 description 1
- 235000018142 Hedysarum alpinum var americanum Nutrition 0.000 description 1
- 240000006461 Hedysarum alpinum var. americanum Species 0.000 description 1
- 206010033557 Palpitations Diseases 0.000 description 1
- 208000001431 Psychomotor Agitation Diseases 0.000 description 1
- 241000405414 Rehmannia Species 0.000 description 1
- 206010038743 Restlessness Diseases 0.000 description 1
- 241000207929 Scutellaria Species 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 208000037386 Typhoid Diseases 0.000 description 1
- 208000012886 Vertigo Diseases 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000036528 appetite Effects 0.000 description 1
- 235000019789 appetite Nutrition 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 229940126678 chinese medicines Drugs 0.000 description 1
- 229910052956 cinnabar Inorganic materials 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 229920000159 gelatin Polymers 0.000 description 1
- 239000008273 gelatin Substances 0.000 description 1
- 235000019322 gelatine Nutrition 0.000 description 1
- 235000011852 gelatine desserts Nutrition 0.000 description 1
- 238000007417 hierarchical cluster analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 201000009240 nasopharyngitis Diseases 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000010926 purge Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002936 tranquilizing effect Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 201000008297 typhoid fever Diseases 0.000 description 1
- 231100000889 vertigo Toxicity 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 230000008673 vomiting Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Medicines Containing Plant Substances (AREA)
Abstract
The invention provides a traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia, which utilizes a fuzzy mathematical model to fuzzify knowledge variables in a constructed traditional Chinese medicine ancient book diagnosis and treatment insomnia database and comprehensively utilizes research methods such as statistics, cognitive linguistics and the like. The method can greatly improve the efficiency of the structured processing of the Chinese medical ancient book text data and the accuracy and coverage rate of the algorithm identification knowledge entity, is beneficial to constructing a more scientific and reasonable Chinese medical ancient book knowledge graph, and provides high-value reference for the modernized research and application of the Chinese medical ancient book.
Description
Technical Field
The invention relates to the application of computer technology in the field of traditional Chinese medicine, in particular to a traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia.
Background
Insomnia is one of the most common clinical diseases, which refers to difficulty in falling asleep, difficulty in maintaining sleep at night and early awakening, and is insufficient or poor in sleep quality. In recent years, the incidence rate of neuropsychiatric diseases such as insomnia is rapidly increased. The relevant literature shows that 35% of the population has suffered from acute insomnia and 9% -12% have suffered from chronic insomnia, and the insomnia has become a social public health problem of great concern in many countries.
The traditional Chinese medicine has unique advantages in treating insomnia by applying holistic concept and dialectical demonstration, and the treatment is verified in clinic. Therefore, on the basis of researching ancient and modern literatures, an effective treatment scheme for treating insomnia is searched from Chinese medicines, and the method has very important practical significance.
Although ancient traditional Chinese medicine books are a source of knowledge for doctors to learn and refer to in all ages, ancient traditional Chinese medicine books inherited for thousands of years are severely limited to later people to systematically understand and learn the ancient Chinese medicine books, find rules and summarize experiences from the ancient Chinese medicine books and record the ancient Chinese medicine books in different medical record documents in a text form due to huge knowledge amount.
1) The Chinese medicine language has strong ambiguity in words, and the semantic analysis neglecting the characteristic is easy to cause the generation of wrong conclusion;
2) the syndrome is various and the diagnosis and curative effect judgment standards are not uniform;
3) the indexes of the traditional Chinese medicine treatment scheme for treating insomnia are lacked.
This has also led to the research and application of traditional Chinese medicine diagnosis data at the present stage, which is mostly developed based on structured knowledge texts. The structuring of the traditional Chinese medicine ancient book texts needs a large amount of manual labor and is difficult to deal with massive ancient book texts, so that a data processing method for diagnosing and treating insomnia by the traditional Chinese medicine ancient books is urgently needed, the problem of traditional Chinese medicine ancient book language complexity can be solved, insomnia cases can be quickly and accurately analyzed, people can be helped to understand and learn systematically, rules can be found, experiences can be mastered, and an effective treatment scheme can be provided for patients.
Disclosure of Invention
In view of the above, the present invention aims to provide a method for processing ancient book data of traditional Chinese medicine for diagnosis and treatment of insomnia, so as to solve the technical problems that the traditional Chinese medicine ancient book for diagnosis and treatment of insomnia is huge and dispersed in knowledge amount, seriously limits understanding and learning of a later system, and affects a treatment scheme.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a traditional Chinese medical ancient book data processing method for diagnosing and treating insomnia comprises the following steps:
s1: establishing a traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
s2: extracting data and carrying out standardization processing;
s3: analyzing syndrome differentiation and prescription rules based on a statistical method;
s4: establishing a fuzzy mathematical model suitable for a traditional Chinese medical ancient book diagnosis and treatment insomnia database;
s5: performing semantic analysis by combining cognitive linguistics, cognitive psychology and cognitive logic research methods;
s6: and constructing a scientific and reasonable knowledge map in the graph database according to the mathematical model.
Further, the method for establishing the traditional Chinese medicine ancient book diagnosis and treatment insomnia database in the step S1 comprises the step of formulating inclusion criteria and exclusion criteria.
The inclusion criteria include the ancient literature specifying that the relevant articles are discussed in relation to insomnia, and the medical records for treating insomnia where the prescription must have a complete pharmaceutical composition.
The exclusion criteria include the failure of the ancient books to specify insomnia symptoms or the repetition of the books.
In the research, ancient book texts included in databases and tool books such as Chinese medical classics are taken as data sources, and words describing insomnia symptoms such as insomnia and lying restlessness are taken as search terms for query, and relevant data are included by combining inclusion and exclusion standards.
Further, the data extraction and standardization process in S2 includes name normalization and unit of measure unification.
Due to the diversified languages of traditional Chinese medicine, different doctors use different names and synonyms in describing the same things (including medicine names, disease names, main symptoms and the like) in a large amount. The standardized processing of data helps to exploit the intrinsic laws in a large amount of textual data.
Further, in S3, a clustering analysis method or a correlation analysis method is used to analyze the syndrome differentiation and the prescription rule based on a statistical method.
The statistical method is adopted to analyze the distribution rules of different types of knowledge in the insomnia database, discuss the influence of time change and syndrome change on the knowledge expression rules, provide a foundation for the establishment of a fuzzy mathematical model and semantic analysis, analyze the diagnosis and treatment rules of database texts from the aspect of statistics, discuss the syndrome differentiation and prescription characteristics of doctors of different generations for diagnosing and treating insomnia, and provide technical support for the subsequent construction of a knowledge map fused with fuzzy logic.
Further, the method for establishing the fuzzy mathematical model applicable to the traditional Chinese medical ancient book diagnosis and treatment of insomnia database in S4 includes:
1) determining index parameters of a traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
2) determining the weight of each parameter index;
3) constructing a judgment matrix aiming at the parameter indexes;
4) solving the judgment matrix;
5) carrying out consistency check, judging whether the consistency ratio is less than or equal to 0.1, if so, judging that the matrix is established, carrying out 6), and if not, returning to 3);
6) optimizing the index weight;
7) establishing a fuzzy relation matrix;
8) determining a membership function, and substituting the membership function into the index weight;
9) and (5) performing normalized calculation to complete the establishment of the fuzzy mathematical model.
Furthermore, the type of the membership function is a normal type function, or a rising half Cauchy type function, or a falling half Cauchy type function, or a trapezoidal function.
Furthermore, the parameter indexes of the traditional Chinese medical ancient book diagnosis and treatment insomnia database are related to symptoms or symptoms.
Further, the semantic analysis performed in combination with the cognitive linguistics in S5 specifically includes performing semantic association and semantic fusion on the articles conforming to the fuzzy mathematical model by using a concept metaphor method.
Further, the module applying the data processing method comprises:
the traditional Chinese medical ancient book data source module is used for providing original texts;
the data input module is used for searching in the ancient book data source module in the traditional Chinese medicine;
the standard input module is used for carrying out standard inclusion and standard exclusion when searching and screening clauses;
the traditional Chinese medicine diagnosis and treatment insomnia database construction module is used for storing and primarily processing searched and screened insomnia data;
the data processing module comprises a standardization processing module, a statistical analysis module, a fuzzy mathematic module and a semantic analysis module, and is used for carrying out standardization processing, statistical analysis, fuzzy mathematic analysis and semantic analysis on the database construction module for treating insomnia;
and the knowledge map construction module is used for constructing the knowledge map in the database for diagnosing and treating insomnia in the traditional Chinese medicine.
The construction method of the traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia has the following advantages:
(1) the traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia disclosed by the invention combines the modern knowledge theory and the traditional Chinese medicine knowledge, solves the problem of traditional Chinese medicine ancient book complexity in the process of diagnosing and treating insomnia, helps later people to quickly and effectively learn and understand relevant knowledge, and provides an effective scheme for diagnosing and treating insomnia;
(2) the traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia combines a fuzzy logic analysis method in the traditional Chinese medicine ancient book text semantic analysis process, and is beneficial to realizing scientific description of traditional Chinese medicine semantics. The knowledge is integrated by a method for constructing a knowledge map, semantic integration service taking the knowledge as a central resource is established, and high-value reference can be provided for modern research of traditional Chinese medicine.
(3) The traditional Chinese medical ancient book data processing method for diagnosing and treating insomnia disclosed by the invention is used for constructing the knowledge map of the database after the fuzzification processing, and analyzing and calculating by adopting a current mature knowledge map construction method. Compared with the traditional knowledge graph construction, the fuzzy mathematical model is adopted to describe the ambiguity of the language in the traditional Chinese medical ancient books for diagnosing and treating insomnia, and the accuracy and the coverage rate of algorithm identification are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate an embodiment of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the main steps of a method for processing ancient book data of traditional Chinese medicine for diagnosis and treatment of insomnia according to the embodiment of the present invention;
fig. 2 is a system block diagram required by the ancient book data processing method for diagnosis and treatment of insomnia according to the embodiment of the present invention.
FIG. 3 is a detailed flowchart of a method for processing ancient book data of traditional Chinese medicine for diagnosing and treating insomnia according to an embodiment of the present invention;
Detailed Description
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict.
The descriptions in this document referring to "first", "second", "upper", "lower", etc. are for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," "upper," "lower," may explicitly or implicitly include at least one of the feature. In addition, the technical solutions in the embodiments may be combined with each other, but it is necessary that a person skilled in the art can realize the combination, and the technical solutions in the embodiments are within the protection scope of the present invention.
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, a method for processing ancient book data of traditional Chinese medicine for diagnosing and treating insomnia comprises the following steps:
s1: establishing a traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
s2: extracting data and carrying out standardization processing;
s3: analyzing syndrome differentiation and prescription rules based on a statistical method;
s4: establishing a fuzzy mathematical model suitable for a traditional Chinese medical ancient book diagnosis and treatment insomnia database;
s5: performing semantic analysis by combining cognitive linguistics, cognitive psychology and cognitive logic research methods;
s6: and constructing a scientific and reasonable knowledge map in the graph database according to the mathematical model.
Specifically, the embodiment uses a computer as a carrier, and as shown in fig. 2, the embodiment includes a traditional Chinese medical ancient book data source module, a data input module, a standard input module, a traditional Chinese medical diagnosis and treatment insomnia database construction module, a data processing module, and a knowledge map construction module; the data processing module comprises a standardization processing module, a statistical analysis module, a fuzzy mathematic module and a semantic analysis module;
the traditional Chinese medicine ancient book data source module provides original clauses, the data input module is used for searching in the traditional Chinese medicine ancient book data source module, the standard input module is used for standard inclusion, the primarily screened insomnia disease data clauses are placed into the traditional Chinese medicine diagnosis and treatment insomnia disease database construction module, the standard input module is used for standard exclusion, repeated clauses are eliminated in the traditional Chinese medicine diagnosis and treatment insomnia disease database construction module, the data processing module is used for carrying out standardized processing, statistical analysis, fuzzy mathematical analysis and semantic analysis on the traditional Chinese medicine diagnosis and treatment insomnia disease database construction module, and finally, the knowledge graph is constructed.
As shown in fig. 3, firstly, a traditional Chinese medicine ancient book diagnosis and treatment insomnia database is established, and the concrete steps are as follows:
1) selecting a target data source, wherein ancient book provisions recorded in databases such as Chinese medical classics and instrument books are taken as the data source in the embodiment;
2) the words such as insomnia, sleeping disorder and the like describing insomnia symptoms are used as search terms to be inquired to obtain n related articles;
3) inquiring the h-th article;
4) judging by combining with the inclusion standard, judging whether the clauses clearly indicate that the clauses are related to insomnia, if the clauses are not related to insomnia, returning to 3) inquiring the clauses h, and judging whether the clauses are related to insomnia again; if insomnia is associated, proceeding to the next step;
5) judging whether the medicines used by the related prescriptions in the article are complete, if not, returning to 3) inquiring the article h; if the recorded medicine is complete, carrying out the next step;
6) preliminarily establishing a traditional Chinese medicine diagnosis and treatment insomnia database, inputting the current clauses into the database, judging whether h is equal to n, returning to 3) to inquire the h-th clause when h is not equal to n and h is h +1, preliminarily completing the establishment of the diagnosis and treatment insomnia database when h is n, and carrying out the next step;
7) judging whether the clauses are repeated, if so, only recording the earliest clause in the year, deleting other repeated clauses, and carrying out the next step;
8) checking and arranging each article;
9) establishing an accurate traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
10) classifying and labeling data information, and perfecting a database: classifying and labeling all articles in the database, wherein the labeling information comprises: the source, the dynasty, the author, the type (theoretical discussion or clinical medical record), whether insomnia is the main symptom in the clinical medical record, etc.
In this embodiment, the value of n is an integer value, n is greater than or equal to 1, h is an integer value, h is greater than or equal to 1, h is less than or equal to n, and the initial value of h is 1, that is, when a sentence is queried and determined, the sentence starts with the first sentence.
Second, data is extracted and normalized. The data standardization process is mainly developed aiming at medical record description, and comprises the standardization of alias names such as medicine names, disease names and symptoms, the standardization of different names, and the standardization of measuring units such as disease course, age, dosage and the like. Referring to Chinese pharmacopoeia and Chinese medicinal dictionary, the name of the medicine is standardized, and the alias and synonym of the medicine are unified, such as "date", "south date" and "red date" are unified and standardized as "date"; orange peel and tangerine peel are unified into tangerine peel. If the medical record has records on the disease name, if the medical record is a standard name, the medical record is faithfully recorded; if the disease name is not standardized, the disease name is standardized and recorded, for example, the disease name is standardized as "common cold" such as "solar apoplexy", "affection by exogenous wind-cold" and "solar typhoid". If the patient is absent, the patient should be supplemented with reference to the medical description and the principal symptoms. The prescriptions of the symptom names mainly refer to books such as 'differential diagnostics of traditional Chinese medicine symptoms' and 'diagnostics of traditional Chinese medicine', and the symptoms are standardized as 'vertigo' because the symptoms are different but the pathogenesis is the same. The dosage units of course of disease, age, dosage, etc. are all unified into modern usage units such as year, month, day, gram, etc.
Thirdly, analyzing the syndrome differentiation and the prescription rule of the standardized ancient book medical records for diagnosing and treating insomnia, mainly adopting a clustering analysis method in statistics, and comprising the following specific steps of:
1) according to the correlation between syndromes and symptoms and the correlation between prescriptions and drugs, clustering variables are determined, the clustering objects selected in the embodiment have syndromes, symptoms, prescriptions and drugs, the syndromes are mainly classified into excess syndromes such as hyperactivity of heart fire, liver depression transforming into fire, phlegm-heat internal disturbance, deficiency syndromes such as yin deficiency and fire excess, deficiency of both heart and spleen and deficiency of heart and gallbladder qi, and the symptoms are mainly classified into vexation and insomnia, dreaminess and easy awakening, palpitation and uneasiness, fatigue and poor appetite, irritability, abdominal fullness and distention, chest distress and belching and the like. The prescription is as follows: cinnabar tranquilizing pill, gentian liver-fire purging decoction, coptis gallbladder-warming decoction, coptis donkey-hide gelatin decoction, mind-tranquilizing and aspiration-controlling pill and the like. Medicine preparation: coptis root, liquorice root, bupleurum root, Chinese angelica root, scutellaria root, rehmannia root, etc. Taking the related classification under each clustering factor as a clustering variable, and respectively carrying out clustering analysis on the clustering objects;
2) researching the frequency distribution of the clustering variables;
2) initializing a clustering center;
3) hierarchical clustering analysis, wherein an Euclidean distance square is used as a measurement method, and an intra-group average connection method is used as a clustering method;
4) clustering results, analyzing and summarizing the insomnia dialectics and the prescription rules.
According to the relevant rules, on the basis of the whole research of the database, different dynasties are divided, and the evolution of diagnosis and treatment rules of doctors in the past generations is researched.
Fourthly, establishing a fuzzy mathematical model suitable for the traditional Chinese medical ancient book diagnosis and treatment insomnia database. The descriptions and definitions of the disease names and symptoms in TCM are strongly ambiguous, for example, in the description of pulse conditions, the words such as micro, weak, deep, slow, soft and thin are often used, and there is no clear definition between these words. In addition, a large amount of similar fuzzy words are full of Chinese medicine languages, and the ambiguity of knowledge greatly increases the difficulty of computer information processing. The fuzzy mathematical model is adopted to assist the analysis, the qualitative analysis is quantified, and the complexity of the Chinese medicine language can be obviously reduced.
The standardized traditional Chinese medical ancient book diagnosis and treatment insomnia database is used as a data source, and the distribution rules of different knowledge are statistically analyzed. The research contents mainly comprise: syndrome-related knowledge (such as excessive syndrome of hyperactivity of heart fire, transformation of liver depression into fire, internal disturbance of phlegm-heat, and deficiency syndrome of yin deficiency with effulgent fire, deficiency of both heart and spleen, and qi deficiency of heart and gallbladder), and symptom-related knowledge (such as irritability, anger, insomnia, dreaminess, abdominal distention, chest distress, and belching). On the basis of analyzing the overall distribution rule of knowledge, the influence of factors such as dynasty, doctors, syndromes and the like on the ambiguity of the knowledge is researched, for example, weak and thready pulse conditions of insomnia patients have inconsistent distribution rules under different syndrome subgroups, and the heart-spleen deficiency syndrome is more likely to use the thready pulse condition, while the heart-gallbladder qi deficiency syndrome is more likely to use the weak pulse condition. And the knowledge fuzziness under different subgroups is researched, so that the fuzzy mathematical model can be established more accurately.
The method mainly comprises the following steps:
1) determining a parameter index; determining factors such as syndromes, symptoms, prescriptions and medicines which have great influence on the knowledge ambiguity, taking parameter indexes as a factor set of an evaluation object, dividing the factor set into several levels according to evaluation factors, setting subordinate second-level evaluation factors under the first-level evaluation factors, setting subordinate third-level evaluation factors under the second-level evaluation factors, and so on to establish a complete index evaluation systemi＝{u1，u2，u3，u4}，i＝4。
The second-level evaluation factors can be established under the syndrome of the syndrome related factors such as hyperactivity of heart fire, transformation of liver depression into fire, excessive syndrome of phlegm-heat internal disturbance and deficiency syndrome of yin deficiency and fire hyperactivity, deficiency of both heart and spleen and deficiency of heart and gallbladder qi, and similarly, the second-level evaluation factors can be established under the symptom related factors such as cough, vomiting, abdominal fullness and the like.
2) Determining the weight of each parameter index; a ═ a1，a2，a3，a4) Is a weight vector, wherein aiWeight of the ith factor, claim ai≥0，∑aiThe second level evaluation factor weight vector is listed as 1, and the same way. And comparing every two indexes according to the importance degrees of the indexes, and quantifying the indexes according to a scaling method, wherein for example, the importance of A is as high as that of B, the index is assigned to be 1, the importance of A is slightly higher than that of B, the index is assigned to be 3, the importance of A is absolutely higher than that of B, and the index is assigned to be 5.
When the importance of the indexes is compared, an expert investigation method is adopted, the opinions of the relevant experts are inquired in an anonymous mode, statistics, processing, analysis and induction are carried out on the opinions of the experts, the experience and subjective judgment of most of the experts are objectively integrated, and a large number of factors which are difficult to quantitatively analyze by adopting a technical method are reasonably estimated. The two factors are compared and judged in the same layer and belong to the same index of the previous layer.
3) Constructing a judgment matrix aiming at the parameter indexes;
wherein i, j is 1, 2 … …, n, and bii＝1，
4) Solving the judgment matrix; ma ═ λmaxa solving the maximum eigenvalue lambda of the matrix MmaxA corresponding feature vector a; common methods include a summation method, a square root method and the like;
(1) summation method:
(2) the square root method:
5) carrying out consistency check on the value of the judgment matrix, judging whether the consistency ratio is less than or equal to 0.1, if so, carrying out the next step, and if not, returning to 3); the subjective judgment of the factors has instability, so that the factor difference under the same criterion is difficult to measure accurately, and a judgment matrix obtained by comparing every two factors does not necessarily meet the consistency condition. Therefore, the number standard in the analytic hierarchy process is used for measuring the inconsistency degree of the judgment matrix: consistency ratio: CR is CI/RI, and CR is CI/RI,
when CR is less than or equal to 0.1, the matrix is judged to have consistency, otherwise, the matrix does not have consistency.
CI＝(λmax-n)/(n-1)；
6) Further optimizing the weight result:
7) establishing a fuzzy relation matrix; r ═ c1，c2，...，cn)T＝(rij)n×m。
8) Determining a membership function; substituting the index weight into the index weight;
9) normalized calculation, completing the establishment of fuzzy mathematic model, Ci＝a(i)·Ri。
Based on the distribution rule of different knowledge, the appropriate membership function is selected to evaluate the ambiguity of the knowledge. The types of membership functions used include: normal type function, increasing half Cauchy type function, decreasing half Cauchy type function, trapezoidal function, etc. Taking the tongue quality of the insomnia patient with heart-spleen deficiency as an example, if the tongue quality is mainly pale red tongue accompanied by a small amount of pale white tongue and bright red tongue according to the statistical rule, a trapezoidal function can be established to describe the membership degree. Similar methods are used to describe the ambiguity of the remaining knowledge.
Fifthly, semantic analysis and semantic fusion are carried out on the clauses in the insomnia database by combining the research methods of cognitive linguistics, cognitive psychology and cognitive logics;
taking cognitive linguistics as an example, the ancient Chinese medical books are discussed in the human body by adopting a preferred method of a concept metaphor. Cognition of causes, symptoms, prescriptions, and the like; the concept metaphor in ancient Chinese medical books is divided into three types according to different source domains: the ancient Chinese medical books are characterized in that concepts such as 'upper heat and lower cold', 'exterior cold and interior heat' exist in the ancient Chinese medical books, relative abstract phenomena of different diseases of different people under the same condition are illustrated through a physical metaphor, cognitive symbolization or visualization of five substances of 'Jinmu water fire and soil' is performed in the ancient Chinese medical books, the relations of generation, restriction, multiplication and regret are structured, and the structure is applied to the structural cognition of five zang organs and six fu organs of people, so that structural concepts such as liver wood, heart fire, spleen soil, lung metal and kidney water are generated, and the conduction relation between the five zang organs and the six fu organs is explained by using the structural relation between five elements.
The method for recognizing linguistics and the method for language study of corpus are applied to select the basic concept metaphors of six excesses in the disease and pathogenesis field of traditional Chinese medicine, such as wind, cold, summer heat, dampness, dryness, fire and the like, the struggle between healthy qi and pathogens, imbalance between yin and yang, abnormal ascending and descending and the like to research the semantics of related articles and further analyze the relationship among human bodies, syndromes, symptoms, causes, prescriptions and the like.
Sixthly, constructing a knowledge graph of the database after the fuzzification processing, and analyzing and calculating by adopting a current mature knowledge graph construction method;
the specific method for establishing the knowledge graph comprises the following steps: extracting entity words in a traditional Chinese medical ancient book diagnosis and treatment insomnia database, carrying out entity identification through a neural network based on a memory network and a statistical method, extracting entity relations by using the neural network combined with an attention mechanism, and establishing a knowledge graph by using entities as nodes and entity relations as edge sets.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia is characterized by comprising the following steps:
s1: establishing a traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
s2: extracting data and carrying out standardization processing;
s3: analyzing syndrome differentiation and prescription rules based on a statistical method;
s4: establishing a fuzzy mathematical model suitable for a traditional Chinese medical ancient book diagnosis and treatment insomnia database;
s5: performing semantic analysis by combining cognitive linguistics, cognitive psychology and cognitive logic research methods;
s6: and constructing a scientific and reasonable knowledge map in the graph database according to the mathematical model.
2. The method of claim 1, wherein the step of establishing the database of ancient books for diagnosis and treatment of insomnia in step S1 comprises establishing inclusion criteria and exclusion criteria, wherein the inclusion criteria include that the ancient books in the ancient books literature require to specify that the related texts relate to insomnia and the cases of treating insomnia, the prescription thereof has a complete pharmaceutical composition, and the exclusion criteria include that the ancient books in the descriptions do not allow to specify insomnia or that the texts repeat each other.
3. The method as claimed in claim 1, wherein the data extracted in step S2 is standardized by name normalization and unit of measure unification.
4. The method as claimed in claim 1, wherein the statistical-based method in S3 is used to analyze syndrome differentiation and prescription rules by clustering analysis or association analysis.
5. The method for processing ancient book data of traditional Chinese medicine for diagnosis and treatment of insomnia according to claim 1, wherein the method for establishing the fuzzy mathematical model applicable to the ancient book database of traditional Chinese medicine for diagnosis and treatment of insomnia in S4 comprises:
1) determining index parameters of a traditional Chinese medicine ancient book diagnosis and treatment insomnia database;
2) determining the weight of each parameter index;
3) constructing a judgment matrix aiming at the parameter indexes;
4) solving the judgment matrix;
5) carrying out consistency check, judging whether the consistency ratio is less than or equal to 0.1, if so, judging that the matrix is established, carrying out 6), and if not, returning to 3);
6) optimizing the index weight;
7) establishing a fuzzy relation matrix;
8) determining a membership function, and substituting the membership function into the index weight;
9) and (5) performing normalized calculation to complete the establishment of the fuzzy mathematical model.
6. The method as claimed in claim 5, wherein the membership function is a normal function, a raised half Cauchy function, a lowered half Cauchy function, or a trapezoidal function.
7. The method as claimed in claim 5, wherein the parameter index is related to the syndrome or the symptom.
8. The method as claimed in claim 1, wherein the semantic analysis performed in S5 in combination with cognitive linguistics comprises semantic association and semantic fusion of the articles conforming to fuzzy mathematical model by using concept metaphor.
9. The method of claim 1, wherein the data processing module comprises:
the traditional Chinese medical ancient book data source module is used for providing original texts;
the data input module is used for searching in the ancient book data source module in the traditional Chinese medicine;
the standard input module is used for carrying out standard inclusion and standard exclusion when searching and screening clauses;
the traditional Chinese medicine diagnosis and treatment insomnia database construction module is used for storing and primarily processing searched and screened insomnia data;
the data processing module comprises a standardization processing module, a statistical analysis module, a fuzzy mathematic module and a semantic analysis module, and is used for carrying out standardization processing, statistical analysis, fuzzy mathematic analysis and semantic analysis on the database construction module for treating insomnia;
and the knowledge map construction module is used for constructing the knowledge map in the database for diagnosing and treating insomnia in the traditional Chinese medicine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911027991.1A CN112735556A (en) | 2019-10-28 | 2019-10-28 | Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911027991.1A CN112735556A (en) | 2019-10-28 | 2019-10-28 | Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112735556A true CN112735556A (en) | 2021-04-30 |
Family
ID=75589009
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911027991.1A Pending CN112735556A (en) | 2019-10-28 | 2019-10-28 | Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112735556A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116340544A (en) * | 2023-04-03 | 2023-06-27 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109840282A (en) * | 2019-03-01 | 2019-06-04 | 东北大学 | A kind of knowledge mapping optimization method based on fuzzy theory |
| CN110134766A (en) * | 2019-05-09 | 2019-08-16 | 北京科技大学 | A kind of segmenting method and device towards Chinese medical book document |
| CN110245242A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | Medical knowledge map construction method, apparatus and terminal |
-
2019
- 2019-10-28 CN CN201911027991.1A patent/CN112735556A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109840282A (en) * | 2019-03-01 | 2019-06-04 | 东北大学 | A kind of knowledge mapping optimization method based on fuzzy theory |
| CN110134766A (en) * | 2019-05-09 | 2019-08-16 | 北京科技大学 | A kind of segmenting method and device towards Chinese medical book document |
| CN110245242A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | Medical knowledge map construction method, apparatus and terminal |
Non-Patent Citations (4)
| Title |
|---|
| 林佳，等: "基于模糊径向基神经网络的失眠古文献症药研究", 中国医药科学, vol. 07, no. 23, pages 50 - 53 * |
| 罗粤铭，等: "基于数据挖掘的肾系水肿茯苓运用研究", 世界科学技术-中医药现代化, vol. 21, no. 10, pages 1 - 1 * |
| 许晓娟，等: "基于模块化思维的模糊ISODATA中医证候诊断方法", 第四军医大学学报, vol. 28, no. 04, pages 289 - 291 * |
| 许晓娟，等: "模块化模糊诊断方法在中医辨证分型中的研究", 湖南中医药大学学报, vol. 27, no. 02, pages 1 - 2 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116340544A (en) * | 2023-04-03 | 2023-06-27 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
| CN116340544B (en) * | 2023-04-03 | 2024-02-23 | 浙江大学 | Visual analysis method and system for ancient Chinese medicine books based on knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meystre et al. | Natural language processing to extract medical problems from electronic clinical documents: performance evaluation | |
| Lakha et al. | Name analysis to classify populations by ethnicity in public health: validation of Onomap in Scotland | |
| CN107391906A (en) | Health diet knowledge network construction method based on neutral net and collection of illustrative plates structure | |
| CN109841282A (en) | A kind of Chinese medicine health control cloud system and its building method based on cloud computing | |
| CN107833595A (en) | Medical big data multicenter integration platform and method | |
| Wang et al. | A knowledge graph enhanced topic modeling approach for herb recommendation | |
| CN105825064A (en) | Daily traditional Chinese medicine therapy intelligent consultancy system | |
| CN113360671A (en) | Medical insurance medical document auditing method and system based on knowledge graph | |
| CN113688255A (en) | Knowledge graph construction method based on Chinese electronic medical record | |
| Sumathi et al. | Improved fuzzy weighted‐iterative association rule based ontology postprocessing in data mining for query recommendation applications | |
| Zhang et al. | Semi-supervised patient similarity clustering algorithm based on electronic medical records | |
| Zhang et al. | Metaphor research in the 21st century: A bibliographic analysis | |
| Zhang et al. | A hierarchical symptom-herb topic model for analyzing traditional Chinese medicine clinical diabetic data | |
| Hansen et al. | Assigning diagnosis codes using medication history | |
| Ding et al. | Research on question answering system for COVID-19 based on knowledge graph | |
| CN112735556A (en) | Traditional Chinese medicine ancient book data processing method for diagnosing and treating insomnia | |
| CN110827990B (en) | Typhoid fever syndrome differentiation reasoning system based on knowledge graph | |
| Lee et al. | Investigating the biomarkers of the sasang constitution via network pharmacology approach | |
| CN109360658A (en) | A kind of the disease pattern method for digging and device of word-based vector model | |
| Sakib et al. | A novel approach on machine learning based data warehousing for intelligent healthcare services | |
| Aggarwal et al. | HEDEA: a Python tool for extracting and analysing semi-structured information from medical records | |
| Chen et al. | Classification and Progression Based on CFS‐GA and C5. 0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B | |
| Liu et al. | TCMNER and PubMed: A Novel Chinese Character‐Level‐Based Model and a Dataset for TCM Named Entity Recognition | |
| Song et al. | Research of medical aided diagnosis system based on temporal knowledge graph | |
| Ansoborlo et al. | Prescreening in oncology using data sciences: the PreScIOUS study |
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 |