CN117094393A - Method and system for constructing materia medica outline grass part knowledge graph - Google Patents
Method and system for constructing materia medica outline grass part knowledge graph Download PDFInfo
- Publication number
- CN117094393A CN117094393A CN202311164063.6A CN202311164063A CN117094393A CN 117094393 A CN117094393 A CN 117094393A CN 202311164063 A CN202311164063 A CN 202311164063A CN 117094393 A CN117094393 A CN 117094393A
- Authority
- CN
- China
- Prior art keywords
- entity
- knowledge
- medicinal material
- materia medica
- grass
- 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
- 239000002398 materia medica Substances 0.000 title claims abstract description 117
- 244000025254 Cannabis sativa Species 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 43
- 239000000463 material Substances 0.000 claims abstract description 161
- 235000011389 fruit/vegetable juice Nutrition 0.000 claims description 53
- 235000014676 Phragmites communis Nutrition 0.000 claims description 20
- 238000010276 construction Methods 0.000 claims description 18
- 235000013399 edible fruits Nutrition 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 16
- 201000010099 disease Diseases 0.000 claims description 16
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 16
- 235000017166 Bambusa arundinacea Nutrition 0.000 claims description 15
- 235000017491 Bambusa tulda Nutrition 0.000 claims description 15
- 235000015334 Phyllostachys viridis Nutrition 0.000 claims description 15
- 239000011425 bamboo Substances 0.000 claims description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 10
- 206010039101 Rhinorrhoea Diseases 0.000 claims description 8
- 208000010753 nasal discharge Diseases 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 6
- 239000011888 foil Substances 0.000 claims description 5
- 230000008439 repair process Effects 0.000 claims description 5
- 210000003296 saliva Anatomy 0.000 claims description 5
- 230000001225 therapeutic effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 244000082204 Phyllostachys viridis Species 0.000 claims 1
- 238000001228 spectrum Methods 0.000 abstract description 7
- 238000003058 natural language processing Methods 0.000 abstract description 5
- 238000007418 data mining Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000007405 data analysis Methods 0.000 abstract description 3
- 239000003814 drug Substances 0.000 description 51
- 241000411851 herbal medicine Species 0.000 description 36
- 229940079593 drug Drugs 0.000 description 27
- 238000010586 diagram Methods 0.000 description 19
- 241001330002 Bambuseae Species 0.000 description 14
- 238000005065 mining Methods 0.000 description 12
- 235000008216 herbs Nutrition 0.000 description 9
- 241000209504 Poaceae Species 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 230000007721 medicinal effect Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 210000005069 ears Anatomy 0.000 description 6
- 235000019645 odor Nutrition 0.000 description 6
- 239000006049 herbal material Substances 0.000 description 5
- 231100000252 nontoxic Toxicity 0.000 description 5
- 230000003000 nontoxic effect Effects 0.000 description 5
- 235000002918 Fraxinus excelsior Nutrition 0.000 description 4
- 206010062717 Increased upper airway secretion Diseases 0.000 description 4
- 239000002956 ash Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 208000026435 phlegm Diseases 0.000 description 4
- 235000006200 Glycyrrhiza glabra Nutrition 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 241000345998 Calamus manan Species 0.000 description 2
- 235000007516 Chrysanthemum Nutrition 0.000 description 2
- 244000189548 Chrysanthemum x morifolium Species 0.000 description 2
- 241000202807 Glycyrrhiza Species 0.000 description 2
- 235000001453 Glycyrrhiza echinata Nutrition 0.000 description 2
- 235000017382 Glycyrrhiza lepidota Nutrition 0.000 description 2
- 244000178870 Lavandula angustifolia Species 0.000 description 2
- 235000010663 Lavandula angustifolia Nutrition 0.000 description 2
- 241000233855 Orchidaceae Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 235000009508 confectionery Nutrition 0.000 description 2
- 238000001647 drug administration Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000003306 harvesting Methods 0.000 description 2
- 239000001102 lavandula vera Substances 0.000 description 2
- 235000018219 lavender Nutrition 0.000 description 2
- 229940010454 licorice Drugs 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 235000012950 rattan cane Nutrition 0.000 description 2
- 231100000331 toxic Toxicity 0.000 description 2
- 230000002588 toxic effect Effects 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- 241001113925 Buddleja Species 0.000 description 1
- 241000305492 Gastrodia Species 0.000 description 1
- 244000303040 Glycyrrhiza glabra Species 0.000 description 1
- 240000008917 Glycyrrhiza uralensis Species 0.000 description 1
- 235000000554 Glycyrrhiza uralensis Nutrition 0.000 description 1
- 235000017443 Hedysarum boreale Nutrition 0.000 description 1
- 235000007858 Hedysarum occidentale Nutrition 0.000 description 1
- 241000234435 Lilium Species 0.000 description 1
- 240000003146 Lobelia chinensis Species 0.000 description 1
- 241000218378 Magnolia Species 0.000 description 1
- 241000218397 Magnolia x soulangeana Species 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000003181 Panax pseudoginseng Nutrition 0.000 description 1
- 241000382362 Persicaria tinctoria Species 0.000 description 1
- 241001522129 Pinellia Species 0.000 description 1
- 241000756042 Polygonatum Species 0.000 description 1
- 235000008737 Polygonatum biflorum Nutrition 0.000 description 1
- 244000088415 Raphanus sativus Species 0.000 description 1
- 235000006140 Raphanus sativus var sativus Nutrition 0.000 description 1
- 241000489523 Veratrum Species 0.000 description 1
- 244000273928 Zingiber officinale Species 0.000 description 1
- 235000006886 Zingiber officinale Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000021028 berry Nutrition 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000002425 crystallisation Methods 0.000 description 1
- 230000008025 crystallization Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000008397 ginger Nutrition 0.000 description 1
- 239000001947 glycyrrhiza glabra rhizome/root Substances 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 201000004792 malaria Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000006187 pill Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 210000000582 semen Anatomy 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 229940057613 veratrum Drugs 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Medicines Containing Plant Substances (AREA)
Abstract
The application relates to a method and a system for constructing a grass part knowledge graph of 'compendium of materia Medica', which comprises the following steps: extracting entity-relation-entity or entity-attribute values of at least one medicinal material characteristic description document of grass part of the compendium of materia medica; each medicinal material takes a medicinal material name entity as a central node of the knowledge graph, and establishes a medicinal material knowledge graph taking the respective medicinal material name entity as the central node according to entity-relation-entity or entity-attribute values; establishing association relations among the knowledge maps of various medicinal materials; and according to the association relation of the knowledge spectrums of the various medicinal materials, connecting the knowledge spectrums of the medicinal materials taking the medicinal material name entity as a central node of all the medicinal materials to generate a complete grass knowledge spectrum. The method adopts big data analysis technologies such as natural language processing, data mining and the like to process the grass part document of the 'materia medica schema', and constructs the grass part knowledge map of the 'materia medica schema'.
Description
Technical Field
The application relates to a method and a system for constructing a grass part knowledge graph of 'materia medica schema', belonging to the technical field of knowledge graphs.
Background
The principle of the basic theory of traditional Chinese medicine and other materials is mainly introduced in the "Ben Cao gang mu" from one roll to two rolls. The main medicine category for treating various diseases is introduced by taking one hundred thirteen diseases such as wind as the class, and the main medicines are classified into main medicines, or the main medicines are classified into a plurality of symptoms under the disease, and the main medicines are classified into the usage of medicines, and grass parts, vegetable parts, fruit trees and the like are compounded into minor medicines, and the main medicines are mainly treated. The system of the book must first be known about its 16 parts and 60 classes; otherwise, the star will sink into the sea. Each medicine marks the source of the first-load document, and if some medicine is classified, changed or combined, the correction description is used; the following is provided with comments of the columns of explaining name, collecting solution, distinguishing questions or correcting errors, repairing, smell, main treatment, application, prescription and the like. The alias name is listed under the name release, and the naming meaning is released; the correction adopts combination of different names for the same medicinal material in different herbal books; "Collection solution" introduces production area, variety, morphology, harvest, etc.; the "correct and error" identifies the suspicious error person of the traditional Chinese medicine; "repair" describes the processing method; "smell" describes the medicinal taste, and is toxic and nontoxic; "treating" includes efficacy; the application focuses on the theory of drug properties, the key points of drug administration and the academic insight of Lev; the prescription is widely recorded as an effective prescription mainly used for treating various diseases; the appendix is similar in morphology or efficacy but cannot be confirmed.
The whole book is filled with 374 kinds of medicines for folk and external use, such as pseudo-ginseng, chinese lobelia, buddleia, semen cassiae, and the like, and 11096 kinds of medicines are added. The medicine classification method includes the list of 'one ten six parts as the class and sixty kinds as the order', and the list of 'the marks as the class and the order' in each medicine, namely the list of the following names, the set solution and other items of each medicine; it is also described in terms of one herb, but different parts are the order, such as the root, tip and head of licorice. The method is characterized by comprehensively describing the knowledge of the carried medicines, establishing twenty-seven meshes for various Chinese herbal medicines, respectively introducing names and histories of the various Chinese herbal medicines, and introducing the forms, identification, collection, processing, medicine property, efficacy, main treatment, prescription application and the like of the Chinese herbal medicines from the parts of bamboo shoots, seedlings, tips, heads, ears, leaves, flowers, seeds (kernels), (fruits), juices, grasses, stems, barks, reed heads, reed roots and the like of the Chinese herbal medicines; meanwhile, the method introduces the theory of various families from Shen nong Ben Cao Jing to Yuan Ming in the period of time, and has rich and systematic contents.
The theory of traditional Chinese medicine is expanded in Ben Cao gang mu, and the application of traditional Chinese medicine should be emphasized in the book, for example, the recipe is called "different medicine spitting, chang mountain spitting with malaria phlegm, gua Ding Ture phlegm, wu Fu Jian spitting with wet phlegm, radish seed spitting with qi phlegm" in the case of veratrum. There are also the dialect and theory not discussed by the former, such as the theory that under the Magnolia strip there is "brain is the house of primordial qi", under the orange peel strip there is "spleen is the mother of primordial qi", and lung is the music instrument of qi. The compendium of materia medica corrects some errors in the materia medica books of the former, such as correcting the red arrow and the tall gastrodia tuber which mistakenly identify two things by one medicine; correcting the error orchid into orchid; correcting the lily which is mistakenly changed into a roll pill; correcting the two medicines by mistake, such as the fragrant solomonseal rhizome and the female wilt; ginger and yam which are misclassified as grasses are classified as vegetables again.
Because the 'materia medica schema' is professional oriented, the following defects exist for the popularization of the 'materia medica schema' and the application requirements of common users:
the compendium of materia medica only explicitly lists the purposes of the source, correction, name releasing, concentration, correction, odor, main treatment, application, prescription and annex of the medicinal materials; the grass of the compendium of materia does not explicitly list the parts of the bamboo shoot, seedling, tip, head, ear, leaf, flower, seed (kernel), (fruit) fruit, juice, grass, stem, bark, head, root and root, etc., which need the reader to summarize.
The description of the herbal materials in Ben Cao gang mu is relatively dispersive, and there is no induction and arrangement, such as the description of nasal discharge in rhizome, juice of blue leaves, white juice in leaves and stems, saliva of stems, juice of stems and water in stems, which can be practically classified into one category and then distinguished in detail; thus being beneficial to grasp the introduction of herbal medicine in Ben Cao gang mu. The description of some characteristics of medicinal materials such as pollen, flower water, herba Patriniae foil, internode worm, herba Patriniae and lamp flower ashes is relatively dispersed in the BenCao gang mu, and they are actually attached to some part of the corresponding medicinal materials; the reader is required to further summarize the "compendium of materia medica".
Disclosure of Invention
Aiming at the problems, the application aims to provide a construction method and a system for a grass part knowledge map of the ' materia medica schema ', which adopt big data analysis technologies such as natural language processing, data mining and the like to process a grass part document of the ' materia medica schema ', and construct the grass part knowledge map of the ' materia medica schema ', so as to make up the defects of the ' materia medica in production, sales, teaching, scientific research and popularization of the ' materia medica schema ', and can be widely applied to the analysis processing of the ' materia medica ' grass part.
In order to achieve the above purpose, the present application proposes the following technical solutions: a construction method of a grass part knowledge graph of 'materia medica schema of materia medica' comprises the following steps: acquiring a description document of at least one medicinal material characteristic of the materia medica schema grass part; extracting entity-relation-entity or entity-attribute values from the description document of at least one medicinal material characteristic of the materia medica schema grass part; wherein the entities are divided into three categories: the medicine comprises a medicine name entity, a twenty-seven mesh name entity of the medicine and a specific content entity. Taking each medicinal material name entity as a central node of the medicinal material knowledge graph, and establishing medicinal material knowledge graphs of various medicinal materials by taking the medicinal material name entity as the central node according to the entity-relation-entity or entity-attribute values; establishing association relations among the medicinal material knowledge maps; and according to the association relation of the medicinal material knowledge maps, connecting all the medicinal material knowledge maps taking the medicinal material name entity as a central node to generate a complete grass part knowledge map of 'materia medica schema'.
Further, extracting entity-relation-entity or entity-attribute values of various medicinal materials of the compendium of the materia medica comprises a mode layer and an instance layer, wherein the mode layer is constructed on the instance layer, a body library is adopted to manage the mode layer of the knowledge graph, the body library is a conceptual template of the structured knowledge base, and the mode layer comprises entity-relation-entity and entity-attribute values.
Further, the instance layer is composed of a series of facts expressed in (drug name entity 1, relationship, drug name entity 2) and (drug name entity, attribute value) triplets, and the knowledge is stored in units of facts using a database as a storage medium of instance layer data.
Further, the method for establishing the medicinal material knowledge graph by taking the medicinal material name entity as a central node comprises the following steps of: the names of the various medicinal materials are called as the central node of the knowledge graph of the medicinal materials; the first jump is from the central node to the node corresponding to each purpose of the corresponding medicinal material; the second jump is the node corresponding to each object and the attached content of the medicinal materials.
Further, the respective objects include: classical properties and individual part properties, including provenance, correction, name release, solution, correction, repair, odor, indication, application, recipe and appendix; the characteristics of each part comprise spike, tip, head, seedling, leaf, flower, seed, fruit, juice, grass, stem, bark, bamboo shoot, reed rhizome and root.
Further, the juice is the summary of the application on the nasal discharge in the rhizome, the juice of the blue leaves, the white juice in the leaves and the stems, the saliva of the stems, the juice of the vines and the water in the vines, and the juice is distinguished by adopting the name of release.
Further, the application summarizes the descriptions of flower powder, flower water, herba Patriniae foil, internode, herba Patriniae and lamp flower ashes in the compendium of the materia medica, and the accessories are respectively attached to the corresponding parts of the medicinal materials.
Further, the method for establishing the association relationship between the knowledge maps comprises the following steps: when two kinds of medicinal materials of the outline grass part of the materia medica are the same on a specific item, leaf nodes of the knowledge spectrums of the corresponding medicinal materials point to the same leaf node, the leaf nodes correlate the knowledge spectrums of the two medicinal materials of the outline grass part of the materia medica, and an incidence relation between the knowledge spectrums is established, wherein the incidence relation is a common relation and is realized through knowledge fusion.
Further, the association relationship includes: common relation between herbal parts of the herb, square relation between herbal parts of the herb, and therapeutic relation between prescriptions and diseases.
The application discloses a system for constructing a knowledge graph of a grass part of a materia medica schema, which comprises the following steps: the acquisition module is used for acquiring a description document of at least one medicinal material characteristic of the compendium of the materia medica; an extraction module for extracting entity-relation-entity or entity-attribute values from the description document of at least one medicinal material characteristic of the materia medica schema; the knowledge graph establishing module is used for establishing a medicinal material knowledge graph of various medicinal materials by taking the medicinal material name entity as a central node of the medicinal material knowledge graph according to the entity-relation-entity or entity-attribute value; the association relation establishing module is used for establishing association relations among various medicinal material knowledge maps; and the fusion module is used for connecting all the medicinal material knowledge maps taking the medicinal material name entity as a central node according to the association relation of the knowledge maps to generate a complete grass part knowledge map.
Due to the adoption of the technical scheme, the application has the following advantages:
1) Structuring the characteristics of medicinal materials: by analyzing the characteristic introduction documents of all the medicinal materials in grass part of the compendium of materia medica, the whole medicinal materials are introduced through eleven meshes. The "provenance" introduction the drug was first recorded in that document; the alias name is listed under the name release, and the naming meaning is released; the correction adopts combination of different names for the same medicinal material in different herbal books; "Collection solution" introduces production area, variety, morphology, harvest, etc.; the "correct and error" identifies the suspicious error person of the traditional Chinese medicine; "repair" describes the processing method; "smell" describes the medicinal taste, and is toxic and nontoxic; "treating" includes efficacy; the application focuses on the theory of drug properties, the key points of drug administration and the academic insight of Lev; the prescription is widely recorded as an effective prescription mainly used for treating various diseases; the appendix is similar in morphology or efficacy but cannot be confirmed. The method for constructing the knowledge map of the grass part of the materia medica schema is developed around the characteristics of various herbal medicines.
2) Structuring of the herbal parts: the application divides various herb parts into sixteen meshes, which are bamboo shoots, seedlings, tips, heads, ears, leaves, flowers, seeds (kernels), (fruit) seeds, juice, grass, stems, peels, reed heads, reed and roots respectively. Sixteen characteristics of each herb are introduced from the descriptions of names, remedies, odors, indications, applications, errors, prescriptions and accessories, wherein the accessories are summarized according to the description documents of herbal medicine in Ben Cao gang mu.
3) Knowledge fusion: the association relation among all herbal medicine knowledge maps of the 'materia medica schema' is constructed through knowledge fusion, then the association relation is displayed in the knowledge maps, and the association relation is obtained by associating the knowledge maps of related medicinal materials through leaf nodes. Multiple medicinal materials can exist in the same prescription, and the medicinal materials form a prescription relation; one prescription can treat a certain disease, so that a therapeutic relationship is formed between the prescription and the disease, and the prescription is a method for treating the disease summarized by the plum-blossom and ancestors.
4) Intelligent graph analysis mining. After the knowledge graph of herbal medicine of the compendium of materia medica is constructed, graph calculation and graph algorithm can be used for reasoning and mining on the knowledge graph, and the operations can be performed include but are not limited to: graph traversal, path computation, statistical computation, path finding, centrality analysis, population analysis, and the like.
5) Intelligent knowledge question-answering. Each herb of the 'materia medica schema' is independent, and once the knowledge graph of all the herbs of the 'materia medica schema' is constructed, the association relationship between the herbs is displayed through knowledge fusion; the knowledge points are associated by edges with semantic information, a large amount of information of associated nodes can be used in the matching association process from the question sentence to the knowledge points of the knowledge map, the semantic understanding of the question sentence can be more accurate through the information, and the association relationship, the square relationship and the treatment relationship among herbal medicine materials of the 'materia medica schema' can be queried through query sentences, which are not possessed by the herbal medicine documents of the 'materia medica schema'.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
FIG. 1 is a schematic diagram of a method for constructing a grass knowledge graph of the present application;
FIG. 2 is a schematic diagram of a global knowledge graph of each of the medicinal materials according to an embodiment of the present application;
FIG. 3 is a diagram of the classical part knowledge graph of "Ben Cao gang mu" in an embodiment of the application;
FIG. 4 is a schematic view of a "ear and skin" knowledge graph in accordance with an embodiment of the application;
FIG. 5 is a schematic diagram of a "tip, head and reed rhizome" knowledge graph in accordance with an embodiment of the application;
FIG. 6 is a schematic diagram of a "seedling, grass and seed" knowledge graph in accordance with an embodiment of the application;
FIG. 7 is a schematic diagram of a "leaf" knowledge graph in accordance with an embodiment of the application;
FIG. 8 is a schematic diagram of a "flower" knowledge graph in accordance with an embodiment of the application;
FIG. 9 is a schematic diagram of a "fruit" knowledge graph in accordance with an embodiment of the application;
FIG. 10 is a schematic diagram of a "juice" knowledge graph in accordance with an embodiment of the application;
FIG. 11 is a schematic diagram of a "stem and root" knowledge graph in accordance with an embodiment of the application;
FIG. 12 is a schematic diagram of a "bamboo shoot" knowledge graph in an embodiment of the application;
FIG. 13 is a schematic diagram of a "reed" knowledge graph, according to an embodiment of the present application;
fig. 14 is a schematic diagram of a system for constructing a grass knowledge graph of "compendium of materia medica" in an embodiment of the application.
Detailed Description
The application is depicted in detail by specific examples in order to provide a better understanding of the technical solution of the application to those skilled in the art. It should be understood, however, that the detailed description is presented only to provide a better understanding of the application, and should not be taken to limit the application. In the description of the present application, it is to be understood that the terminology used is for the purpose of description only and is not to be interpreted as indicating or implying relative importance.
In order to solve the problem that the grass part of the 'compendium of materia medica' in the prior art is not explicitly listed from the parts of bamboo shoots, seedlings, tips, heads, ears, leaves, flowers, seeds (kernels), fruit solids, juice, grass, stems, skin, reed rhizome, root and the like, the reader needs to summarize the parts. The description of the herbal materials in Ben Cao gang mu is relatively dispersive, and there is no induction and arrangement, such as the description of nasal discharge in rhizome, juice of blue leaves, white juice in leaves and stems, saliva of stems, juice of stems and water in stems, which can be practically classified into one category and then distinguished in detail; the description of some characteristics of medicinal materials in Ben Cao gang mu is relatively dispersed, and the medicinal materials are not subjected to induction finishing, such as pollen, flower water, herba Patriniae foil, internode worms, herba Patriniae and lamp flower ashes, which are respectively described, and actually are respectively attached to corresponding parts of the medicinal materials, such as flower water of chrysanthemum can be induced into flower attachment. Thus, the application is favorable for grasping the problems of introduction of herbal medicine and the like of the 'materia medica schema', and the application provides a construction method and a system of a herbal knowledge map of the 'materia medica schema', wherein the construction method comprises the following steps: acquiring an introduction document of at least one medicinal material characteristic of grass part of the compendium of materia medica; extracting entities, relations and entities or entity, attribute and attribute value and knowledge-graph characteristics from introduction documents of at least one medicinal material characteristic of grass of the compendium of materia medica; and constructing a grass part knowledge map of the 'materia medica schema' according to the extracted entity, relation and entity or entity, attribute and attribute value and the knowledge map characteristic. The application adopts big data analysis techniques such as natural language processing, data mining and the like to analyze the grass part documents of the 'materia medica schema', constructs the grass part knowledge map of the 'materia medica schema', which aims at the aspects of name releasing, solution gathering, topic distinguishing or correct and incorrect, correction, smell, main treatment, application, accessory, annex and the like, and the parts of bamboo shoots, seedlings, tips, heads, ears, leaves, flowers, seeds (kernels), (fruits), juices, grasses, stems, peels, reed heads, reed roots and the like, and also comprises the grass part knowledge map of the 'materia medica schema' related to the accessory characteristics of the medicinal material parts, so as to make up the use defect of the 'materia medica schema' in the production, sales, teaching and scientific research of Chinese herbal medicines, and can be widely applied to the analysis treatment of the Chinese herbal medicines. The following describes the inventive arrangements in detail by way of examples with reference to the accompanying drawings.
Example 1
The embodiment discloses a construction method of a grass part knowledge graph of Ben Cao gang mu, as shown in fig. 1, comprising the following steps:
s1, extracting entity-relation-entity or entity-attribute values of various medicinal materials in grass parts of the compendium of materia medica;
acquiring an introduction document of at least one medicinal material characteristic of grass part of the compendium of materia medica; the technical scheme is characterized in that the introduction document of the herbal part document, namely the medicinal material characteristics, of the 'materia medica schema' is analyzed through big data technologies such as natural language processing and data mining, so that the characteristics of the 'materia medica schema' herbal part medicinal material are analyzed, and then a knowledge graph is constructed. And extracting entity-relation-entity or entity-attribute values and knowledge graph characteristics from the introduction document of at least one medicinal material characteristic of grass part of the 'compendium of materia medica'. Wherein the entities are divided into three categories: the medicine comprises a medicine name entity, a twenty-seven mesh name entity of the medicine and a specific content entity. Such as licorice, its medicinal material name entity: licorice root. Its objective is as follows: root. Its root-treated concrete content entity: sweet, flat and nontoxic. There are therefore three types of entities: the medicine comprises a medicine name entity, a twenty-seven mesh name entity of the medicine and a specific content entity. The above description is of two triplets (licorice-root-relationship) (root-relationship-sweet, flat, nontoxic). There are three types of entities: "Glycyrrhiza uralensis (medicinal material name entity)", "root (mesh name entity)", and "sweet, flat, nontoxic (content entity)".
S2, constructing a central node of the medicinal material knowledge graph by using the name of each medicinal material, and constructing the medicinal material knowledge graph of the medicinal material by taking the medicinal material name entity of the medicinal material as the central node according to the entity-relation-entity or entity-attribute value;
extracting the entity-relation-entity or entity-attribute values and knowledge-graph characteristics of various medicinal materials in grass parts of the materia medica schema. The knowledge graph can be logically divided into a mode layer and an instance layer, the mode layer is built on the instance layer and is the core of the knowledge graph, an ontology base is adopted to manage the mode layer of the knowledge graph, the ontology base is a conceptual template of a structured knowledge base, and the knowledge base formed by the ontology base is high in hierarchical structure and low in redundancy degree. The schema layer includes entity-relationship-entity and entity-attribute values. In the embodiment, the two mode layers are adopted to specifically construct the grass part knowledge graph of the 'materia medica schema'.
The instance layer consists of a series of facts, and the knowledge will be stored in units of facts expressed in (entity 1, relationship, entity 2) and (entity, attribute value) triples, and a database is employed as the storage medium for instance layer data. The open source map database Neo4j and the relational database PostgreSQL are currently used. The knowledge patterns of all herb medicines are developed gradually, wherein the name entities of all the medicines are central nodes of the knowledge patterns of the medicines, the number of 1 st hop nodes is 27, and the 27 st hop nodes respectively correspond to twenty-seven meshes for describing the characteristics of the medicines. The unfolding of each 1-hop node is based on the content of the medicinal material characteristic introduction document and the fusion among different medicinal material characteristic introduction documents.
The method for establishing the medicinal material knowledge graph by taking each medicinal material name entity as a central node comprises the following steps of: taking the name of each medicinal material as a central node of a medicinal material knowledge graph; the first jump is from the central node to a node corresponding to twenty-seven meshes of the medicinal material; the second jump is the node corresponding to each object and the attached content of the medicinal material.
The respective objectives include: classical properties and characteristics of each part, classical properties including provenance, correction, name release, solution, correction, repair, odor, indication, application, prescription and appendix; the characteristics of each part include ear, tip, head, seedling, leaf, flower, seed (kernel), (fruit) fruit, juice, grass, stem, bark, bamboo shoot, reed rhizome and root. The twenty-seventeen meshes are the understanding of the applicant on the herbal part medicinal material document of the 'materia medica schema', so that the 'materia medica schema' knowledge map can be conveniently constructed. Wherein the provenance is the provenance of the first-load literature marked by each medicinal material in the 'compendium of materia medica'; correction, name release, solution, correction, odor, main treatment, application, auxiliary prescription and annex are introduced according to the compendium of materia medica; the bamboo shoots, seedlings, tips, heads, ears, leaves, flowers, seeds (kernels), fruits, juices, grasses, stems, barks, reed heads and roots are all parts of the herbal medicines introduced in the materia medica schema, but the juices are summarized by the embodiment after all the herbal medicines in the grasses of the materia medica schema are analyzed in a summary manner, so that a knowledge map is conveniently constructed; the twenty-seven meshes form a global mode of the grass part knowledge map of the 'materia medica schema'.
As shown in fig. 2, the central node is a name entity of each medicinal material, and one hop from the central node can reach a node corresponding to twenty-seven meshes of the characteristic description document of the medicinal material in grass of the compendium of materia medica. The two-hop node reveals twenty-seventh purpose content of a herbal medicine characteristic introduction document of the 'compendium of materia Medica', which specifically comprises:
firstly, a knowledge graph of classical characteristics of medicinal materials as shown in figure 3 is introduced, and the part constructs a first eleven-purpose knowledge graph of the characteristic introduction document of medicinal materials of grass department of Ben Cao gang mu. Classical properties mainly refer to provenance, correction, name release, collection, correction, odor, main indications, applications, prescription and annex.
Through analysis, the eleventh order of the introduction of the characteristics of the herbal materials in the grass department of the materia medica schema is the most classical characteristic of the materia medica schema, is the crystallization of the plum-hour delicacies, and is also the basic framework of the materia medica schema.
The second construction of the knowledge graph of the characteristics of each part of the medicinal materials is described in the compendium of Ben Cao by taking one object as the class and taking different parts as the purpose, such as the root division, tip division and head division of Glycyrrhrizae radix. However, in the compendium of materia medica, how many parts one herb is divided is not described in detail, but the property of the herb to be used is described for specific herbs. In this example, all herbs of grass were analyzed and mined from "Ben Cao gang mu", and the herbs were divided into sixteen parts, which were ear, tip, head, seedling, leaf, flower, seed (kernel), (fruit) fruit, juice, grass, stem, bark, bamboo shoot, reed rhizome and root. This is a general framework, and any one medicinal material cannot be used in sixteen parts, and one medicinal material is generally used in only a few parts. Of these sixteen parts, some are mutually exclusive, such as herb part of one medicinal material, and it is impossible to take the herb part. The knowledge graph construction method of sixteen drug-taking parts of the medicinal materials is respectively described below.
By mining the herbal characteristic introduction document of "Ben Cao gang mu", as shown in FIG. 4, the present embodiment finds that "ear" and "bark" introduce medicinal properties from 5 meshes, which are respectively: repairing, smell, main treatment, application and auxiliary prescription. This example reveals the 5 mesh, and of course not the ears and skin of each herb will introduce their properties from the 5 mesh. The method is a general framework of spike and skin introduction, and the knowledge map construction of the grass part medicinal material spike and skin of the 'compendium of materia medica' is developed according to the 5 meshes.
By mining the herbal characteristic description document of "Ben Cao gang mu", as shown in FIG. 5, this example found that "tip", "head" and "Lu Tou" only introduce the drug property from one purpose, it is: is mainly used for treating the diseases. This is not the case, however, for every herb, the tip, head and reed should be considered to be the drug property. The method is a general framework introduced by the tip, the head and the head of the reed rhizome, and only mainly aims at constructing the knowledge maps of the tip, the head and the head of the herb part of the grass of the 'materia medica schema'.
By mining the herbal characteristic introduction document of "Ben Cao gang mu", as shown in FIG. 6, the present embodiment finds that "Miao", "Cao" and "zi" introduce medicinal properties from 6 meshes, which are respectively: releasing name, repairing, smell, main treating, inventing and attaching prescription. The example reveals the 6 mesh, and of course not the seedlings, grasses and seeds of each herb will introduce their properties from the 6 mesh. The method is a general framework for introducing seedlings, grasses and seeds, and the knowledge map construction of the grassy portion medicinal seedlings, grasses and seeds of the 'compendium of materia medica' is developed according to the 6 meshes.
By mining the herbal characteristic introduction documents of the "Ben Cao gang mu", as shown in FIG. 7, the present embodiment finds that "leaves" introduce the drug property from 7 mesh, they are respectively: releasing name, correcting error, repairing, smell, main treating, application and prescription. This example reveals the 7 mesh, and of course not all leaves of each herb introduce their properties from the 7 mesh. The method is a general framework of leaf introduction, and the knowledge map construction of the grass part medicinal leaves of the 'compendium of materia medica' is developed according to the 7 meshes.
By mining the herbal characteristic introduction document of "Ben Cao gang mu", as shown in FIG. 8, the present embodiment finds that "bamboo shoots" introduce medicinal properties from 4 meshes, which are respectively: smell, indications, application and accessory prescription. The example reveals the 4 mesh, and of course, not every herb "bamboo shoot" introduces their properties from the 4 mesh. The method is a general framework introduced by 'bamboo shoots', and the knowledge map construction of the 'bamboo shoots' of herbal medicine in the grass part of the 'compendium of materia medica' is developed according to the 4 meshes.
By mining the herbal characteristic introduction documents of "Ben Cao gang mu", as shown in FIG. 9, the present embodiment finds that "flowers" introduce medicinal properties from 7 mesh, they are respectively: releasing name, repairing, smell, main treating, application, accessory prescription and accessory. This example reveals the 7 mesh, and certainly not flowers of every herb introduce their properties from the 7 mesh. The method is a general framework of flower introduction, and the knowledge map construction of the grass part medicinal material flowers of the 'materia medica schema of materia medica' is developed according to the 7 meshes. Wherein, the 'accessory' is not in the 'materia medica schema', and is summarized after analyzing and excavating the introduction documents of all the medicinal materials of the grass part of the 'materia medica schema', for example, the 'flower water' and the 'flower powder' are generated by flowers and are attached to the flowers; therefore, this embodiment adds this attribute, which is more favorable for summarizing the properties of flowers and constructing a knowledge graph, and is an creative contribution of this embodiment in constructing a knowledge graph of "Ben Cao gang mu".
By mining the herbal characteristic introduction documents of "Ben Cao gang mu", as shown in fig. 10, the present embodiment finds that "(fruit) is introducing the drug property from 7 meshes, they are respectively: releasing name, collecting and resolving, repairing, smell, main treating, application and prescription. This example reveals the 7 mesh, and of course not every herb will have their properties introduced from the 7 mesh. The method is a general framework introduced by (fruit) real, and the knowledge map construction of (fruit) real of herbal medicine in the section of herbal medicine of the compendium of materia medica is developed according to the 7 meshes.
By mining the herbal characteristic introduction document of "Ben Cao gang mu", as shown in FIG. 11, the present embodiment finds that "juice" introduces the medicinal properties from 4 meshes, which are respectively: repairing, smell, treating and attaching prescription. The example reveals the 4 mesh, and of course not the "juice" of each drug material introduces their properties from the 4 mesh. The method is a general framework introduced by juice, and the knowledge map construction of the grass part medicinal material juice of the materia medica schema is developed according to the 4 meshes. The medicinal material part of "juice" is not in single column in Ben Cao gang mu, but the juice of several medicinal materials is introduced from different angles by digging all medicinal materials in Ben Cao gang mu in this embodiment, so this part is summarized. For example, the "juice" of pinellia ternate is named as salivary stem, the "juice" of hydrous vine is named as water in vine, the "juice" of blue is named as blue leaf juice (also in Polygonum tinctorium), the "juice" of Chinese magnolia is named as vine juice, the "juice" of mock berry is named as juice "without being required to be released again, the" juice "of follow-up is named as white juice in leaves and stems, the" juice "of lavender is named as nasal discharge in rhizome, and the like. Therefore, the embodiment adds the part of juice to unify the introduction of different juices, so that the embodiment is more standard and unified, and the embodiment is creative contribution in constructing the knowledge map of Ben Cao gang mu.
By mining the herbal characteristic introduction documents of the "compendium of materia Medica", as shown in fig. 12, the present embodiment finds that "reed" introduces the drug property from 3 meshes, which are respectively: smell, indications and applications. The present example reveals the 3 mesh, and of course not every herb "reed" introduces their properties from the 3 mesh. The method is a general framework introduced by ' reed ", and the knowledge map construction of ' reed ' of herbal medicine of the materia medica schema is developed according to the 3 meshes.
By mining the herbal characteristic introduction document of "Ben Cao gang mu", as shown in FIG. 13, the present embodiment finds that "stems" and "roots" introduce medicinal properties from 8 meshes, which are respectively: releasing name, correcting error, repairing, smell, main treating, inventing, accessory and accessory. This example reveals the 8 mesh, and of course not every herb's "stem" and "root" introduces their properties from the 8 mesh. The method is a general framework introduced by 'stems' and 'roots', and the knowledge map construction of 'stems' and 'roots' of herbal medicines of the grass section of the 'compendium of materia medica' is developed according to the 8 meshes. Both the "stem" and "root" are not included in the framework of the compendium of materia medica, which is summarized in this example. Therefore, this example is faithful to the compendium of materia medica, and it is summarized.
In this example, juice is nasal discharge, juice of blue leaves, juice of white leaves and stems, juice of saliva, juice of rattan, and water in rattan, etc. in the rhizome of Ben Cao gang mu, and is distinguished by the name of release. For example, the nasal discharge in the rhizome of Lavender is generalized to juice, and then is called "nasal discharge in the rhizome".
Summarizing the properties of herbal materials in the grass department of the materia medica, the method also comprises the following steps: the descriptions of the powder, water, herba Patriniae foil, internode, herba Patriniae and lamp flower ashes are summarized as "attached" in Ben Cao gang mu, which are attached to the corresponding parts of the herbs respectively. For example, the "flower water" of a chrysanthemum is generalized as the "attachment" of the "flower".
S3, establishing association relations among the knowledge maps of various medicinal materials;
the above analysis mainly reveals that the medicinal properties of the herbal parts of Ben Cao gang mu and the medicinal materials of Ben Cao gang mu are related by prescription. The reason for this is that the twenty-seven mesh frame content of each medicinal material of the grass part of the materia medica schema is the same, and the distinction and the connection of the medicinal materials of the grass part of the materia medica schema can not be distinguished in the knowledge graph. The differences and the relations of the different herbal medicine knowledge maps of the grass parts of the compendium of the materia medica are reflected on the specific contents of each clause, and the differences and the relations of the different herbal medicine knowledge maps are reflected on the leaf nodes of the knowledge maps. When the knowledge maps of all the medicinal materials of the grass part are fused, when the properties of the medicinal materials are the same on a specific item, the leaf nodes of the medicinal materials are fused, that is to say, the medicinal materials share certain same leaf nodes. The association between herbal medicines of the 'materia medica schema' is realized by adopting the knowledge fusion mode. The more leaf nodes the two herbs share in the grass of the Ben Cao gang mu, the greater the commonality between them. On the contrary, the fewer leaf nodes shared by two herbs in the grass of the Ben Cao gang mu, the larger the difference between them. This is the commonality between the herbs.
The association relation comprises: common relationships among herbal parts of Ben Cao gang mu, fang Zi relationship among herbal parts of Ben Cao gang mu and therapeutic relationships between prescriptions and diseases. The prescription in the compendium of materia medica combines a plurality of medicinal materials together to treat a certain disease, and a prescription relation is formed by a plurality of medicinal materials on the same prescription; the prescription treats a certain disease, and thus, a treatment relationship is formed between the prescription and the disease.
According to the method for constructing the knowledge map of the herbal parts of the herbal compendium, the knowledge map is constructed according to twenty-seven meshes of the herbal parts of the herbal compendium, and the association relationship between the herbal materials is constructed through leaf nodes and auxiliary formulas. In order to facilitate the construction of the knowledge graph of the herbal medicine of the 'materia medica schema', the embodiment generalizes and summarizes the herbal medicine of the 'materia medica schema', and provides a new part 'juice' and a new attribute 'accessory', so that all the herbal medicine of the 'materia medica schema' can be unified under one frame; therefore, the knowledge graph spectrum can fully reveal the properties of herbal medicines and the basic characteristics of the medicinal materials in the grass part of the herbal medicine. Therefore, the application does not simply convert the introduction document of the herbal medicine of the herbal schema into the knowledge graph, but fully reveals the purpose of each herb property of the herbal medicine of the herbal schema and the basic characteristics of the medicinal materials through the knowledge graph. The application also integrates the knowledge maps of all herbal parts of the herbal compendium, and the common relation between the two herbal parts of the herbal compendium can be easily seen through the knowledge maps. The prescription of the 'materia medica outline' associates various medicinal materials, which is an empirical summary of plum delicacies and ancestor practitioners; the prescriptions reveal two relationships, namely the prescription relationship between the prescription Chinese medicinal materials and the therapeutic relationship between the prescriptions and diseases.
And S4, connecting the medicinal material knowledge maps taking the medicinal material name entity as a central node according to the association relation of the medicinal material knowledge maps of the grassroots, and generating a complete grassroots knowledge map.
The application can efficiently construct the grass part knowledge graph of the 'materia medica schema' through the natural language processing technology, and store the constructed knowledge graph into the corresponding database so as to facilitate the subsequent data processing and various application development work. The high efficiency of the application is characterized in that once the description document of herbal medicine of the 'compendium of materia medica' is constructed into a knowledge graph and the knowledge graph is stored in a database, the knowledge graph is changed into a Chinese herbal medicine intelligent knowledge graph platform through the association of supporting technical files related to the 'compendium of materia medica' and the context environments of production, sales, teaching, scientific research and the like, and all knowledge points related to the prescription of the Chinese herbal medicine are related by edges, so that the research and development of deep medicine production related applications such as intelligent graph calculation, intelligent knowledge question answering and the like can be carried out.
Example two
Based on the same inventive concept, this embodiment discloses a system for constructing a grass part knowledge map of "compendium of materia medica", as shown in fig. 14, comprising:
the extraction module is used for extracting entity-relation-entity or entity-attribute values from a description document of at least one medicinal material characteristic of grass part of the compendium of materia medica;
the knowledge graph establishing module is used for establishing a central node of the knowledge graph of the medicinal material by using various medicinal material name entities, and establishing the knowledge graph of the medicinal material by using various medicinal material name entities as the central node according to entity-relation-entity or entity-attribute values;
the association relation establishing module is used for establishing association relations among various herbal medicine knowledge maps of the herbal schema;
the fusion module is used for connecting the knowledge maps of the medicinal materials with the medicinal material name entity as a central node according to the association relation of the knowledge maps of the various medicinal materials of the grass part of the 'materia medica schema', so as to generate a complete knowledge map of the grass part, namely, the knowledge maps of all the medicinal materials of the grass part of the 'materia medica schema' are fused together.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the application without departing from the spirit and scope of the application, which is intended to be covered by the claims. The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily appreciate variations or alternatives within the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (10)
1. The method for constructing the outline grass part knowledge graph of the materia medica is characterized by comprising the following steps of:
acquiring a description document of at least one medicinal material characteristic of the materia medica schema grass part;
extracting entity-relation-entity or entity-attribute values from the description document of at least one medicinal material characteristic of the materia medica schema grass part;
taking each medicinal material name entity as a central node of the medicinal material knowledge graph, and establishing medicinal material knowledge graphs of various medicinal materials taking the medicinal material name entity as the central node according to the entity-relation-entity or entity-attribute values;
establishing association relations among the medicinal material knowledge maps;
and connecting all the medicinal material knowledge maps taking the medicinal material name entity as a central node according to the association relation of the medicinal material knowledge maps to generate a complete grass part knowledge map.
2. The method for constructing a knowledge graph of the grass of the materia medica of claim 1, wherein extracting entity-relation-entity or entity-attribute values of various medicinal materials of the grass of the materia medica comprises a pattern layer and an instance layer, the pattern layer is constructed above the instance layer, a ontology library is adopted to manage the pattern layer of the knowledge graph, the ontology library is a conceptual template of a structured knowledge library, and the pattern layer comprises entity-relation-entity and entity-attribute values.
3. The method for constructing a knowledge map of the grass of the materia medica according to claim 2, characterized in that the instance layer consists of a series of facts, and knowledge is stored in units of facts expressed in (entity 1, relationship, entity 2) and (entity, attribute value) triplets, and a database is used as a storage medium of instance layer data.
4. The method for constructing a knowledge map of the grass of the compendium of materia medica according to claim 1, wherein the method for constructing the knowledge map of the medicinal material with the entity of the name of the medicinal material as a central node comprises the following steps: taking various medicinal material name entities as central nodes of a medicinal material knowledge graph; the first jump is from the central node to the node corresponding to each purpose of the corresponding medicinal material; the second jump is the node corresponding to each object and the attached content of the medicinal materials.
5. The method for constructing a knowledge map of the grass of the compendium of materia of claim 4, wherein said objects comprise: classical properties and individual part properties, including provenance, correction, name release, solution, correction, repair, odor, indication, application, recipe and appendix; the characteristics of each part comprise spike, tip, head, seedling, leaf, flower, seed, fruit, juice, grass, stem, bark, bamboo shoot, reed rhizome and root.
6. The method for constructing a knowledge map of the grass of the compendium of materia medica of claim 5, wherein the juice is nasal discharge in rhizome, juice of blue leaves, white juice in leaves and stems, saliva in stems, juice of vines and water in vines, and is distinguished by a name of release.
7. The construction method of the herbal outline grass part knowledge map according to claim 5, wherein the subsidiary is a description of pollen, flower water, herba Patriniae foil, internode worms, herba Patriniae and lamp flowers in the herbal outline, and the subsidiary is respectively attached to the corresponding parts of the medicinal materials.
8. The method for constructing the knowledge map of the grass of the compendium of materia medica according to claim 1, wherein said method for establishing the association relationship between the knowledge maps of each of said medicinal materials comprises: when two medicinal materials of the outline grass part of the materia medica are the same on a specific item, leaf nodes of the corresponding medicinal material knowledge maps point to the same leaf node, the leaf nodes correlate the knowledge maps of the two medicinal materials of the outline grass part of the materia medica, and an incidence relation between the medicinal material knowledge maps is established, wherein the incidence relation is a commonality relation and is realized through knowledge fusion.
9. The method for constructing a knowledge map of the grass of the compendium of materia of claim 8, wherein said association relationship comprises: common relation between herbal parts of the herb, square relation between herbal parts of the herb, and therapeutic relation between prescriptions and diseases.
10. A system for constructing a knowledge map of a grass part of the compendium of materia medica, comprising:
the acquisition module is used for acquiring a description document of at least one medicinal material characteristic of the compendium of the materia medica;
an extraction module for extracting entity-relation-entity or entity-attribute values from the description document of at least one medicinal material characteristic of the materia medica schema;
the knowledge graph establishing module is used for establishing the knowledge graph of each medicinal material by taking the medicinal material name entity as a central node of the medicinal material knowledge graph according to the entity-relation-entity or entity-attribute values;
the association relation establishing module is used for establishing association relations among the medicinal material knowledge maps;
and the fusion module is used for connecting all the medicinal material knowledge maps taking the medicinal material name entity as a central node according to the association relation of the medicinal material knowledge maps to generate a complete grass part knowledge map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311164063.6A CN117094393A (en) | 2023-09-11 | 2023-09-11 | Method and system for constructing materia medica outline grass part knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311164063.6A CN117094393A (en) | 2023-09-11 | 2023-09-11 | Method and system for constructing materia medica outline grass part knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117094393A true CN117094393A (en) | 2023-11-21 |
Family
ID=88777297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311164063.6A Pending CN117094393A (en) | 2023-09-11 | 2023-09-11 | Method and system for constructing materia medica outline grass part knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094393A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408338A (en) * | 2023-12-14 | 2024-01-16 | 神州医疗科技股份有限公司 | Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia |
-
2023
- 2023-09-11 CN CN202311164063.6A patent/CN117094393A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117408338A (en) * | 2023-12-14 | 2024-01-16 | 神州医疗科技股份有限公司 | Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia |
| CN117408338B (en) * | 2023-12-14 | 2024-03-12 | 神州医疗科技股份有限公司 | Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | The origin and domestication of Aquilaria, an important agarwood-producing genus | |
| CN117094393A (en) | Method and system for constructing materia medica outline grass part knowledge graph | |
| Bibi et al. | The endemic medicinal plants of Northern Balochistan, Pakistan and their uses in traditional medicine | |
| Outlaw Jr et al. | The jujube (Ziziphus jujuba Mill.), a multipurpose plant | |
| Ahmad et al. | The medicinal plants of Salt Range | |
| Hoekou et al. | Ethnobotanical study of latex plants in the maritime Region of Togo | |
| Karki et al. | Priority species of medicinal plants in South Asia: report of an Expert Consultation on Medicinal Plants Species Prioritization for South Asia held on 22-23 Sept., 1997, New Delhi, India | |
| Jamera et al. | Ritual plants used by the Manobo tribe of Surigao del Sur, Philippines | |
| Nasir et al. | Medicinal plants: a promising resource for poverty alleviation in the milieu of Swat | |
| Timsina et al. | Six-year demographic study of the terrestrial orchid, Crepidium acuminatum: implications for conservation | |
| Sahoo et al. | Traditional medicinal plants of odisha | |
| Rao et al. | Rationale for conservation of medicinal plants | |
| Goldschmidt | Pre-standardised pharmacology: Han through Song | |
| Kannan et al. | Comparative macro-microscopic studies of three wild Solanum species (S. melongena L., S. incanum L. and S. virginianum L.) | |
| Pineda et al. | Inventory of Ethnopharmacologically-significant plants used by the manobos in Surigao del Sur, Philippines | |
| Xiu et al. | Achievements of the Compendium Bencao Tujing (Illustrated Classic of Materia Medica): A preliminary study | |
| Thomas | Problems and prospects of medicinal plant cultivation in Thiruvananthapuram district | |
| Waheed et al. | Survey of medicinal plants and patterns of knowledge in district Swabi/Khyber Pakhtunkhwa, Pakistan | |
| Tilovova | Hyponymic and graduonymic relations of forestry terms in German and Uzbek languages | |
| Mulyani et al. | Local wisdom of Cikondang village community in the utilization of medicinal plants | |
| Palero et al. | Medicinal Plants as Treatment for Common Symptoms of COVID-19 in Maibu Village, Butuan City, Philippines | |
| Balick et al. | Good botanical practices | |
| Nadjafi et al. | The status of exudate species in Iran and existing challenges in their sustainable utilization. | |
| Le Hoang Pham et al. | Solanaceae diversity in Vietnam: a preliminary taxonomic inventory for conservation and utilization. | |
| Lal et al. | High adaptability of Blepharis sindica T. Anders seeds towards moisture scarcity: A possible reason for the vulnerability of this medicinal plant from the Indian Thar desert |
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 |