CN112086206A - Prescription searching method and device for deduction by using editable knowledge graph - Google Patents
Prescription searching method and device for deduction by using editable knowledge graph Download PDFInfo
- Publication number
- CN112086206A CN112086206A CN202010940270.6A CN202010940270A CN112086206A CN 112086206 A CN112086206 A CN 112086206A CN 202010940270 A CN202010940270 A CN 202010940270A CN 112086206 A CN112086206 A CN 112086206A
- Authority
- CN
- China
- Prior art keywords
- syndrome
- prescription
- chinese medicine
- knowledge graph
- current
- 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
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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- 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
-
- 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)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a prescription searching method and a device for deduction by using an editable knowledge graph, which comprises the following steps: according to the obtained current symptoms, inquiring syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function; screening the syndrome with cosine similarity closest to the current symptom in the syndrome element space; and searching a corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom. The application utilizes knowledge graph technology to replace doctors to diagnose, and solves the problem that the existing prescription is required to be prescribed by highly depending on the personal experience of traditional Chinese medicine, so that the problem of non-symptomatic medicine is easily caused.
Description
Technical Field
The application belongs to the technical field of natural language processing and knowledge maps, and particularly relates to a prescription searching method and device for deduction by using an editable knowledge map.
Background
Natural language processing is a technique that can recognize and extract entities and entity relationships in natural language (human language or human writing of information in a literal language). Understanding the language is not as simple as one might imagine, as background knowledge in many other areas is confounded in natural language. If a sentence or an article is to be processed, analysis of the emotion/background/context of the author, etc. must be relied upon. Due to the extensive and detailed knowledge involved, some research or academic institutions accumulate knowledge through knowledge graphs.
The knowledge-graph technology development comes from graph theory. The concept of a graph originates from the problem of the cuneiform, to solve which one abstracts the graph into a triplet form, i.e. (point-edge-point). Some problems in real life are solved by the processing of mathematical matrices. With the continuous development of perceptrons and the continuous accumulation of internet information, researchers begin to try to use a knowledge graph constructed by a large amount of structured knowledge as a basis for inferring data of a neural network, so that the performance of some knowledge inference networks is further improved.
Traditional Chinese medicine fuses extensive knowledge as crystals fusing thousands of years of medical civilization. The diagnostician not only needs to understand the nature, flavor and meridian tropism of each herb, but also needs to judge the symptoms, such as pulse condition and tongue, etc., of the body. The nature, taste, meridian tropism and symptoms mentioned here are only two typical examples to illustrate that the back of TCM covers a wide accumulation of knowledge and is not exhaustive of all the knowledge involved in TCM.
However, at present, the diagnosis and prescription of diseases mainly depend on the personal experience of traditional Chinese medicine, but the problems of misdiagnosis and the like are easily caused under the condition of insufficient personal experience, so that the prescription cannot effectively treat the diseases.
Disclosure of Invention
The application provides a prescription searching method and a device for deduction by using an editable knowledge graph, which at least solve the problem that the existing prescription is required to be made highly depending on the personal experience of the traditional Chinese medicine, so that the problem of non-symptomatic medicine is easily caused.
According to one aspect of the present application, there is provided a prescription search method for deduction using an editable knowledge-graph, comprising:
according to the obtained current symptoms, inquiring syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function;
screening the syndrome with cosine similarity closest to the current symptom in the syndrome element space;
and searching a corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom.
In one embodiment, the recipe lookup method further comprises:
and constructing a Chinese medicine diagnosis and treatment knowledge map by using a pytorch deep learning framework, and performing pooling operation by using an activation function.
In one embodiment, the construction of the traditional Chinese medicine diagnosis and treatment knowledge graph comprises the following steps:
establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data;
and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
In one embodiment, according to the obtained current symptom, inquiring the syndrome element corresponding to the current symptom from the pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function, includes:
inquiring single-hot vector codes corresponding to the current symptoms;
and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
According to another aspect of the present application, there is also provided a prescription search apparatus for deduction using an editable knowledge-graph, including:
the syndrome element query unit is used for querying syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through a query function according to the obtained current symptoms;
the syndrome determining unit is used for screening the syndrome of which the cosine similarity in the syndrome element space is closest to the current symptom;
and the prescription determining unit is used for searching the corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom.
In one embodiment, the prescription lookup apparatus further comprises:
and the traditional Chinese medicine diagnosis and treatment knowledge map construction unit is used for constructing the traditional Chinese medicine diagnosis and treatment knowledge map through the pitorch deep learning framework and performing pooling operation by adopting an activation function.
In one embodiment, the construction of the traditional Chinese medicine diagnosis and treatment knowledge graph comprises the following steps:
establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data;
and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
In one embodiment, according to the obtained current symptom, inquiring the syndrome element corresponding to the current symptom from the pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function, includes:
inquiring single-hot vector codes corresponding to the current symptoms;
and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a recipe search method for deduction using an editable knowledge graph according to the present application.
Fig. 2 is a flow chart of constructing a traditional Chinese medicine diagnosis and treatment knowledge graph in the embodiment of the present application.
Fig. 3 is a flowchart of querying a syndrome element corresponding to a current symptom in the embodiment of the present application.
FIG. 4 is a triple knowledge diagram for Codonopsis pilosula.
FIG. 5 is a schematic diagram of symptom/syndrome elements.
Fig. 6 is a block diagram of a prescription search apparatus for deduction using an editable knowledge map according to the present application.
Fig. 7 is a specific implementation of an electronic device in an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Based on the existing problems in the background art that the traditional Chinese medicine is relied on to manually diagnose diseases and prepare prescriptions, the knowledge map technology is used for replacing the manual prescription preparation mode. According to one aspect of the present application, there is provided a prescription search method for deduction using an editable knowledge-graph, as shown in fig. 1, including:
s101: and inquiring the syndrome elements corresponding to the current symptoms from a pre-constructed Chinese medical diagnosis and treatment knowledge graph through an inquiry function according to the acquired current symptoms.
In one embodiment, as shown in fig. 2, the construction of the traditional Chinese medicine diagnosis and treatment knowledge graph includes:
s201: establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data.
In an embodiment, according to the obtained current symptom, a syndrome element corresponding to the current symptom is queried from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through a query function, as shown in fig. 3, including:
s301: and inquiring the one-hot vector code corresponding to the current symptom.
S302: and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
S202: and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
In one embodiment, as shown in fig. 4, fig. 4 is a triple knowledge diagram of dangshen, which is abstracted by G (V, E), where V is the complete set of all entities, and V ═ dangshen, primordial qi exhaustion, middle-jiao, pacify stomach, nourish, tonify stomach … … }; e is the set of all edges, i.e. the set of relationships between entities, E ═ treatment, associated with famous physicians, with efficacy. The whole knowledge graph G is described mathematically, typically using word vectors, degree matrices, adjacency matrices.
However, knowledge maps derived from tcmkb are widespread, but do not provide an effective basis for patient diagnosis. The reason is that first, knowledge is flawed; second, the knowledge graph is too broad. Therefore, the knowledge base can only be used as a clear map for inquiring the relation between the knowledge, but can not provide the basis for diagnosis.
And the software Gephi is used for assisting the construction of the knowledge graph. "Gephi is a free cross-platform JVM-based complex network analysis software for open source, which is mainly used for interactive visualization and detection open source tool of various networks and complex systems, dynamic and hierarchical graphs". In traditional Chinese medicine diagnosis, the syndrome of a patient is generally diagnosed first, and then the prescription medicinal materials are presumed. Therefore, the construction of the knowledge graph should include the relationship E ═ element relationship between symptoms and syndromes, element relationship between syndromes and syndromes, and relationship between syndromes and herbs. Entity V should include symptom corpus V1, syndrome element corpus V2, and herb corpus V3, V ═ V1, V2, V3 }. The description of the relationship between the entities is described by using an adjacency matrix.
FIG. 5 is a schematic view of symptom/syndrome elements, showing the relationship between the symptom and syndrome elements. Dark and red tongue, purple dark tongue and ecchymosis and petechia on tongue are all the decisive symptoms of blood stasis. The arrows therefore point from the symptoms to the syndrome elements. There is also a relationship between Chinese herbs, which is the symptom can reflect the corresponding syndrome element, and the shorter the distance, the more decisive the symptom is for the syndrome element. It can be seen from the figure that dark red tongue and petechia on the tongue more indicative of blood stasis than purple tongue. So if the four entities containing blood stasis are represented by V1, the relationship of the edges is represented by the adjacency matrix a (embodying the relationship between the entities in the figure).
This figure is described with V1 and A4x4, the description of V1 being a one-hot encoding method in computer technology, which ensures that the representations between the vectors are perfectly orthogonal. This ensures that the linear transformations are not affected by each other. Such an adjacency matrix has three (Am, As) in total to represent different deductions (symptom/syndrome element, syndrome element/syndrome, syndrome/prescription drug).
In one embodiment, the recipe lookup method further comprises:
and constructing a Chinese medicine diagnosis and treatment knowledge map by using a pytorch deep learning framework, and performing pooling operation by using an activation function.
S102: and screening the syndrome with cosine similarity closest to the current symptom in the syndrome element space.
S103: and searching a corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom.
In one embodiment, based on the experience given by the clinician (relationship between symptom-syndrome element-syndrome-drug), a graph G ═ V, E can be constructed, i.e., the entity is encoded with unique heat vectors and the correspondence of the adjacency matrix.
First, the first step of deduction relationship will be described, wherein symptoms correspond to the deduction of syndrome elements. The query function using F to represent the one-hot coding is an example of whether the symptom corresponds to which one-hot vector or the upper side, if the patient has symptoms of dark red tongue and dark purple tongue, one vector is used to describe that the patient is Vp ═ 1100, and then the vector with the symptom information of the patient is used to perform nonlinear mapping. If the whole process is represented by F, the corresponding relation of the function is as follows:
the first step is derived: f (V)p)＝Relu8(VpAf) A is the adjacency matrix mentioned above
In the first step, a is equal to 8.
The second step of deduction needs to use cosine similarity to find the closest syndrome in the syndrome element space from the vector obtained by the first step of deduction. At present, there are eight main syndromes of coronary heart disease: the syndrome of congealing cold in the heart-vessel, the syndrome of yin deficiency of heart and kidney, the syndrome of blood stasis obstruction of heart and blood, the syndrome of phlegm-turbid obstruction, the syndrome of yang deficiency of heart and kidney, the syndrome of qi deficiency and blood stasis, the syndrome of deficiency of both qi and yin, and the syndrome of qi stagnation and blood stasis.
A syndrome matrix Bs corresponding to the syndrome elements is formed through the above table. Although a large number of cases are covered here, this is not an exhaustive list of all cases, which are not shown here due to spatial relationships.
At the same time, a degree matrix Ds is formed for normalization, which is the same, and not all cases are listed due to space limitations.
And a second step of deduction:
the formula of Relu is the same as that of the first step, except that a is 0, namely the classic Relu activation function
Third step deduction
And the third step of deduction deduces a result according to the result deduced in the second step and the input of the first step. The adjacency matrix used here is basically the same as the adjacency matrix used before, but the contents are slightly different.
An adjacency matrix Bm and a degree matrix Dm.
And a third step of deduction:
concat represents vector stitching
The method for deducing to obtain the prescription based on the knowledge graph comprises the following steps:
symptom-derived syndrome elements:
the first step is derived: (V)p)＝Relu8(VpAf)
The syndrome elements derive the syndromes:
and a second step of deduction:
the syndrome indicates that the prescription drugs are:
and a third step of deduction:
these three steps are very similar to the graph convolution, but the operation of each step is different. VpAD-1 inside this can be considered a graph-convolution like operation, while the activation function Relu completes the pooling operation. In the whole deduction process, all functions are continuous functions, and a gradient exists in a definition domain (except for the gradient of relu, the gradient of 0 point needs to be additionally defined to be 0. the whole operation is a learnable process, and as the diagnosis and prescription process is carried out according to the traditional Chinese medicine diagnosis and treatment guideline for coronary heart disease stable angina, the clinical experience is further learnt in the clinical practice.
Gradient descending operation can be realized by utilizing a deep learning framework of the pyroch, so that the real relation between symptoms, syndrome elements, syndromes and prescription drugs can be continuously accumulated in application. And can be continuously adjusted through visualization of gephi software.
Based on the same inventive concept, the embodiment of the present application further provides a prescription searching apparatus using editable knowledge graph to perform deduction, which can be used to implement the method described in the above embodiments, as described in the following embodiments. The principle of solving the problems of the prescription searching device which utilizes the editable knowledge graph to deduce is similar to the prescription searching method which utilizes the editable knowledge graph to deduce, so the implementation of the prescription searching device which utilizes the editable knowledge graph to deduce can refer to the implementation of the prescription searching method which utilizes the editable knowledge graph to deduce, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
As shown in fig. 6, the present application provides a prescription search apparatus for deduction using an editable knowledge-graph, comprising:
the syndrome element query unit 601 is configured to query a syndrome element corresponding to a current symptom from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through a query function according to the obtained current symptom;
a syndrome determining unit 602 configured to screen a syndrome with a cosine similarity closest to a current symptom in a syndrome element space;
the prescription determining unit 603 is configured to search a corresponding prescription from the medical treatment knowledge graph according to the syndrome closest to the current symptom.
In one embodiment, the prescription lookup apparatus further comprises:
and the traditional Chinese medicine diagnosis and treatment knowledge map construction unit is used for constructing the traditional Chinese medicine diagnosis and treatment knowledge map through the pitorch deep learning framework and performing pooling operation by adopting an activation function.
In one embodiment, the construction of the traditional Chinese medicine diagnosis and treatment knowledge graph comprises the following steps:
establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data;
and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
In one embodiment, according to the obtained current symptom, inquiring the syndrome element corresponding to the current symptom from the pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function, includes:
inquiring single-hot vector codes corresponding to the current symptoms;
and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
An embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all steps in the method in the foregoing embodiment, and referring to fig. 7, the electronic device specifically includes the following contents:
a processor (processor)701, a memory 702, a communication Interface 703, a bus 704, and a nonvolatile memory 705;
the processor 701, the memory 702 and the communication interface 703 complete mutual communication through the bus 704;
the processor 701 is configured to call the computer programs in the memory 702 and the nonvolatile memory 705, and when the processor executes the computer programs, the processor implements all the steps in the method in the foregoing embodiments, for example, when the processor executes the computer programs, the processor implements the following steps:
according to the obtained current symptoms, inquiring syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function;
screening the syndrome with cosine similarity closest to the current symptom in the syndrome element space;
and searching a corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom.
Embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and the computer program when executed by a processor implements all the steps of the method in the above embodiments, for example, the processor implements the following steps when executing the computer program:
according to the obtained current symptoms, inquiring syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function;
screening the syndrome with cosine similarity closest to the current symptom in the syndrome element space;
and searching a corresponding prescription from the medical treatment knowledge map according to the syndrome closest to the current symptom.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment. Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or end product executes, it may execute sequentially or in parallel (e.g., parallel processors or multi-threaded environments, or even distributed data processing environments) according to the method shown in the embodiment or the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description 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 so forth) having computer-usable program code embodied therein. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification.
In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.
Claims (10)
1. A prescription lookup method for deduction using an editable knowledge map, comprising:
according to the obtained current symptoms, inquiring syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through an inquiry function;
screening the syndrome of which the cosine similarity in the syndrome element space is closest to the current symptom;
and searching a corresponding prescription from the Chinese medical diagnosis and treatment knowledge graph according to the syndrome closest to the current symptom.
2. The prescription lookup method according to claim 1, further comprising:
and constructing the Chinese medicine diagnosis and treatment knowledge graph by using a pytorch deep learning framework, and performing pooling operation by using an activation function.
3. The prescription lookup method according to claim 1, wherein the construction of the traditional Chinese medicine diagnosis and treatment knowledge graph comprises:
establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data;
and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
4. The prescription search method according to claim 3, wherein the step of querying the syndrome elements corresponding to the current symptoms from the pre-constructed TCM diagnosis and treatment knowledge graph through a query function according to the obtained current symptoms comprises:
inquiring single-hot vector codes corresponding to the current symptoms;
and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
5. A prescription lookup apparatus for deduction using an editable knowledge map, comprising:
the syndrome element query unit is used for querying syndrome elements corresponding to the current symptoms from a pre-constructed traditional Chinese medicine diagnosis and treatment knowledge graph through a query function according to the obtained current symptoms;
a syndrome determining unit for screening the syndrome of which the cosine similarity in the syndrome element space is closest to the current symptom;
and the prescription determining unit is used for searching a corresponding prescription from the traditional Chinese medicine diagnosis and treatment knowledge graph according to the syndrome closest to the current symptom.
6. The prescription lookup device of claim 5 further comprising:
and the traditional Chinese medicine diagnosis and treatment knowledge map construction unit is used for constructing the traditional Chinese medicine diagnosis and treatment knowledge map through a pyrrch deep learning framework and performing pooling operation by adopting an activation function.
7. The prescription lookup apparatus as claimed in claim 5, wherein the construction of the TCM medical knowledge graph comprises:
establishing a relation between entities by adopting an adjacent matrix according to the obtained entities and carrying out one-hot vector coding on the entities, wherein the entities comprise: symptom data, syndrome element data, syndrome data and prescription data;
and establishing a traditional Chinese medicine diagnosis and treatment knowledge map according to the relationship between symptoms and syndrome elements, the relationship between syndrome elements and syndromes and the relationship between syndromes and prescriptions.
8. The prescription search device of claim 7, wherein the querying the syndrome elements corresponding to the current symptom from the pre-constructed TCM diagnosis and treatment knowledge graph through a query function according to the obtained current symptom comprises:
inquiring single-hot vector codes corresponding to the current symptoms;
and carrying out nonlinear mapping from the Chinese medicine diagnosis and treatment knowledge graph by using the unique heat vector coding to obtain syndrome elements corresponding to the current symptoms.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the recipe lookup method for deduction using an editable knowledge map as claimed in any one of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of recipe lookup using editable knowledge maps for deduction as claimed in any one of claims 1 to 4.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940270.6A CN112086206A (en) | 2020-09-09 | 2020-09-09 | Prescription searching method and device for deduction by using editable knowledge graph |
| CN202011382471.5A CN112382412A (en) | 2020-09-09 | 2020-12-01 | Prescription searching method and device for deduction by using editable knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010940270.6A CN112086206A (en) | 2020-09-09 | 2020-09-09 | Prescription searching method and device for deduction by using editable knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112086206A true CN112086206A (en) | 2020-12-15 |
Family
ID=73731679
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010940270.6A Pending CN112086206A (en) | 2020-09-09 | 2020-09-09 | Prescription searching method and device for deduction by using editable knowledge graph |
| CN202011382471.5A Pending CN112382412A (en) | 2020-09-09 | 2020-12-01 | Prescription searching method and device for deduction by using editable knowledge graph |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011382471.5A Pending CN112382412A (en) | 2020-09-09 | 2020-12-01 | Prescription searching method and device for deduction by using editable knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN112086206A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820375A (en) * | 2021-02-04 | 2021-05-18 | 闽江学院 | Traditional Chinese medicine recommendation method based on multi-graph convolution neural network |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169078A (en) * | 2017-05-10 | 2017-09-15 | 京东方科技集团股份有限公司 | Knowledge of TCM collection of illustrative plates and its method for building up and computer system |
| CN110085325B (en) * | 2019-04-30 | 2021-06-01 | 王小岗 | Method and device for constructing knowledge graph about traditional Chinese medicine experience data |
| CN110335675B (en) * | 2019-06-20 | 2021-10-01 | 北京科技大学 | Syndrome differentiation method based on traditional Chinese medicine knowledge graph library |
| CN110459321B (en) * | 2019-08-20 | 2020-10-23 | 山东众阳健康科技集团有限公司 | Traditional Chinese medicine auxiliary diagnosis system based on syndrome element |
| CN110827990B (en) * | 2019-10-31 | 2022-08-19 | 北京科技大学 | Typhoid fever syndrome differentiation reasoning system based on knowledge graph |
| CN110838368B (en) * | 2019-11-19 | 2022-11-15 | 广州西思数字科技有限公司 | Active inquiry robot based on traditional Chinese medicine clinical knowledge map |
-
2020
- 2020-09-09 CN CN202010940270.6A patent/CN112086206A/en active Pending
- 2020-12-01 CN CN202011382471.5A patent/CN112382412A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820375A (en) * | 2021-02-04 | 2021-05-18 | 闽江学院 | Traditional Chinese medicine recommendation method based on multi-graph convolution neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112382412A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Holzinger et al. | Knowledge discovery and interactive data mining in bioinformatics-state-of-the-art, future challenges and research directions | |
| Vogt et al. | The new holism: P4 systems medicine and the medicalization of health and life itself | |
| Belle et al. | Big data analytics in healthcare | |
| Shi et al. | TMFUF: a triple matrix factorization-based unified framework for predicting comprehensive drug-drug interactions of new drugs | |
| Niederer et al. | Verification of cardiac tissue electrophysiology simulators using an N-version benchmark | |
| Buchman | The community of the self | |
| Bourqui et al. | Metabolic network visualization eliminating node redundance and preserving metabolic pathways | |
| Kwak et al. | DeepHealth: Deep Learning for Health Informatics reviews, challenges, and opportunities on medical imaging, electronic health records, genomics, sensing, and online communication health | |
| Yu et al. | Stnn-ddi: a substructure-aware tensor neural network to predict drug–drug interactions | |
| Zeng et al. | Teichmüller shape descriptor and its application to Alzheimer’s disease study | |
| Cui et al. | Artificial intelligence in spinal imaging: current status and future directions | |
| Wu et al. | The item network and domain network of burnout in Chinese nurses | |
| Maries et al. | Grace: A visual comparison framework for integrated spatial and non-spatial geriatric data | |
| Nerella et al. | Transformers in healthcare: A survey | |
| Vonach et al. | A method for rapid production of subject specific finite element meshes for electrical impedance tomography of the human head | |
| Cheng et al. | The application of braden scale and rough set theory for pressure injury risk in elderly male population | |
| Chen et al. | Using data mining strategies in clinical decision making: a literature review | |
| CN112086206A (en) | Prescription searching method and device for deduction by using editable knowledge graph | |
| Liao et al. | Convolutional herbal prescription building method from multi-scale facial features | |
| Shafqat et al. | SmartHealth: IoT-enabled context-aware 5G ambient cloud platform | |
| Elmahdy et al. | A snapshot of artificial intelligence research 2019–2021: is it replacing or assisting physicians? | |
| Liu et al. | Kgdal: knowledge graph guided double attention lstm for rolling mortality prediction for aki-d patients | |
| Górska et al. | Non-Debye Relaxations: The Ups and Downs of the Stretched Exponential vs. Mittag–Leffler’s Matchings | |
| Rojas-Arce et al. | The advent of the digital twin: A prospective in healthcare in the next decade | |
| Goyal et al. | Medicine recommendation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201215 |