CN116467418A - Medical question-answer knowledge generation method and device, electronic equipment and storage medium - Google Patents
Medical question-answer knowledge generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116467418A CN116467418A CN202310446180.5A CN202310446180A CN116467418A CN 116467418 A CN116467418 A CN 116467418A CN 202310446180 A CN202310446180 A CN 202310446180A CN 116467418 A CN116467418 A CN 116467418A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- medical
- feature
- word
- question
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000004927 fusion Effects 0.000 claims abstract description 22
- 230000011218 segmentation Effects 0.000 claims description 53
- 239000013598 vector Substances 0.000 claims description 50
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 21
- 238000012216 screening Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 239000004973 liquid crystal related substance Substances 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000007726 management method Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010018498 Goitre Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 201000003872 goiter Diseases 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to digital medical technology, and discloses a medical question-answer knowledge generation method, which comprises the following steps: acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet; constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics; acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem; and carrying out feature fusion on the knowledge features and the word feature sequences of the medical questions to generate medical question-answering knowledge. The invention further provides a medical question-answer knowledge generation device, electronic equipment and a storage medium. The invention can improve the knowledge generation efficiency and accuracy of the medical question and answer.
Description
Technical Field
The present invention relates to the field of digital medical technology, and in particular, to a method and apparatus for generating medical question-answer knowledge, an electronic device, and a computer readable storage medium.
Background
Patient education in the Internet medical setting is generally general knowledge explanation and medicine guidance of diseases in the forms of articles, interactive questions and answers and the like. The existing knowledge question and answer method based on medical facts mainly depends on the examination of expert doctors, the generation of the knowledge question and answer method is easily influenced by manual writing efficiency, meanwhile, the richness and fluency of sentence generation are limited, meanwhile, the related knowledge search is carried out by manually writing the medical question and answer knowledge more by using an Internet search engine, valuable information is required to be screened out from more disordered information, and therefore the efficiency is low and the generated result is inaccurate. In summary, the prior art has the problem of low medical question and answer knowledge generation efficiency and accuracy.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a computer readable storage medium for generating medical question-answer knowledge, which mainly aim to solve the problem that the medical question-answer knowledge generation efficiency and accuracy are low.
In order to achieve the above object, the present invention provides a method for generating knowledge of medical question and answer, comprising:
acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet;
constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem;
and carrying out feature fusion on the knowledge features and the word feature sequences of the medical questions to generate medical question-answering knowledge.
Optionally, the extracting information from the article to be processed to obtain a knowledge triplet includes:
preprocessing the article to be processed to obtain a word segmentation data set;
extracting entity relations from the word segmentation data set to obtain an entity set;
and carrying out relation screening on the entity set to obtain a knowledge triplet.
Optionally, the preprocessing the article to be processed to obtain a word segmentation dataset includes:
performing word segmentation processing on the article to be processed to obtain input word segmentation and corresponding part of speech;
acquiring a preset deactivated part-of-speech tag, and screening the input word according to the part-of-speech tag and the part-of-speech corresponding to the input word to obtain a word segmentation data set.
Optionally, the extracting the entity relation from the word segmentation dataset to obtain an entity set includes:
vector representation is carried out on the word segmentation data set, and word segmentation vectors are obtained;
extracting features of the word segmentation vectors to obtain word segmentation feature vectors;
and carrying out relationship classification on the word segmentation feature vectors, and obtaining an entity set according to a relationship classification result.
Optionally, the constructing a knowledge graph according to the knowledge triplet includes:
obtaining a knowledge entity library, and preselecting candidate entity objects from the knowledge entity library;
performing similarity calculation on the candidate entity object and the knowledge triples, and obtaining an entity object according to a similarity calculation result;
and carrying out knowledge fusion on the entity objects to obtain a knowledge graph.
Optionally, the feature encoding the medical question to obtain a word feature sequence of the medical question includes:
word vector embedding is carried out on the medical problems to obtain embedded vectors;
splicing a preset position information vector with the embedded vector to obtain an input feature vector;
and carrying out layer normalization on the input feature vector to obtain the word feature sequence of the medical problem.
Optionally, the feature fusion of the knowledge feature and the word feature sequence of the medical question to generate a medical question-answer knowledge includes:
obtaining entity categories of the medical problems, and primarily screening the knowledge features according to the entity categories to obtain initial knowledge features;
and carrying out probability calculation on the feature sequence of the initial knowledge feature and the word feature sequence of the medical question, and generating medical question-answering knowledge according to a probability calculation result.
In order to solve the above problems, the present invention also provides a medical question-answer knowledge generation device, the device comprising:
the information extraction module is used for obtaining articles to be processed, extracting information from the articles to be processed and obtaining knowledge triples;
the node characteristic extraction module is used for constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
the feature coding module is used for acquiring medical problems, and carrying out feature coding on the medical problems to obtain word feature sequences of the medical problems;
and the feature fusion module is used for carrying out feature fusion on the knowledge features and the word feature sequences of the medical problems to generate medical question-answering knowledge.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the question and answer knowledge generation method described above.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one computer program that is executed by a processor in an electronic device to implement the above-mentioned medical question-and-answer knowledge generation method.
According to the embodiment of the invention, the knowledge graph of the article to be processed is constructed to automatically generate the medical question-answer knowledge, so that the full utilization of the question-answer knowledge can be realized; according to the knowledge triples, a knowledge graph is constructed, medical knowledge and a knowledge system can be displayed in a graphical mode, integration of multiple aspects of medical knowledge can be realized, and accuracy of knowledge generation of medical questions and answers is improved; the node characteristic extraction is carried out on the knowledge graph, so that the dimension of data can be reduced, and the working efficiency of medical question-answering knowledge is improved; the knowledge features and the word feature sequences of the medical problems are subjected to feature fusion, so that the medical knowledge can be comprehensively utilized, and the accuracy of generating the medical question-answering knowledge is improved. Therefore, the medical question-answering knowledge generation method, the device, the electronic equipment and the computer readable storage medium can solve the problem that the medical question-answering knowledge generation efficiency and the accuracy are low.
Drawings
FIG. 1 is a flowchart of a method for generating knowledge of medical questions and answers according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of information extraction of the article to be processed to obtain a knowledge triplet according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of feature encoding the medical question to obtain a word feature sequence of the medical question according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a knowledge generation device for medical questions and answers according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing the method for generating knowledge of medical question and answer according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a medical question-answer knowledge generation method. The execution subject of the medical question-answer knowledge generation method includes, but is not limited to, at least one of a server, a terminal, and the like, which can be configured to execute the method provided by the embodiment of the application. In other words, the medical question-answer knowledge generation method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a schematic flow chart of a method for generating knowledge of medical question and answer according to an embodiment of the invention is shown. In this embodiment, the method for generating the medical question-answer knowledge includes:
s1, acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet;
in the embodiment of the invention, the articles to be processed comprise published medical academic research, professional medical knowledge papers and the like; the purpose of information extraction is to refine key medical knowledge and topics in the articles to be processed, and a Stanford Open IE (Open information extraction) technology can be adopted to extract a knowledge tuple from medical academic articles.
Referring to fig. 2, in the embodiment of the present invention, the information extraction of the article to be processed to obtain a knowledge triplet includes:
s21, preprocessing the article to be processed to obtain a word segmentation data set;
s22, extracting entity relations from the word segmentation data set to obtain an entity set;
s23, carrying out relation screening on the entity set to obtain a knowledge triplet.
In the embodiment of the invention, the pretreatment of the article to be treated comprises the treatment of word segmentation, word segmentation part-of-speech analysis, syntactic analysis and the like, and the obtained word segmentation data set comprises the treated word segmentation, the corresponding part-of-speech and the like.
In the embodiment of the invention, the entity relationship refers to the relationship between nouns and verbs in the word segmentation dataset, such as a main-predicate relationship, a guest-moving relationship, a prepositioned object and the like; the entity relation extraction is to integrally extract the relation among the word segmentation in the word segmentation data set to obtain complete basic noun phrases, namely the entity set, wherein the entity relation extraction can be based on a supervised learning algorithm of machine learning, original corpus training is carried out by using medical articles through a machine learning method, and then the entity relation extraction is carried out by using a trained model.
In the embodiment of the invention, the relation screening is carried out according to a preset screening rule, wherein the screening rule is used for reserving the entity set containing three entity words to obtain a knowledge triplet; the knowledge triples comprise three parts, namely subjects, predicates and objects, for example, the knowledge triples can be simply expressed by a knowledge triples, namely, a knowledge structure of an entity-relation-entity, when the university of Zhejiang is located in Hangzhou.
In the embodiment of the present invention, the preprocessing the article to be processed to obtain a word segmentation dataset includes:
performing word segmentation processing on the article to be processed to obtain input word segmentation and corresponding part of speech;
acquiring a preset deactivated part-of-speech tag, and screening the input word according to the part-of-speech tag and the part-of-speech corresponding to the input word to obtain a word segmentation data set.
In the embodiment of the invention, the article to be processed can be subjected to word segmentation by using a word segmentation device, wherein the word segmentation device comprises but is not limited to a crust word segmentation device; the part of speech of the input segmentation includes nouns, verbs, adjectives, adverbs, auxiliary words and the like; further, the deactivated-part-of-speech tag may be an adjective, an adverb, an auxiliary word, or the like.
In the embodiment of the present invention, the extracting the entity relationship from the word segmentation dataset to obtain the entity set includes:
vector representation is carried out on the word segmentation data set, and word segmentation vectors are obtained;
extracting features of the word segmentation vectors to obtain word segmentation feature vectors;
and carrying out relationship classification on the word segmentation feature vectors, and obtaining an entity set according to a relationship classification result.
In the embodiment of the invention, word2vec (Word vector model) can be adopted for vector representation, and the Word vector model is utilized to carry out mapping calculation on the Word segmentation data set so as to obtain Word segmentation vectors; the feature extraction can input the word segmentation vector into a preset neural network, the feature of the word segmentation vector is extracted by utilizing the neural network model, and the neural network can become a feature extractor after multiple times of training, so that the feature extraction of a new word segmentation vector is facilitated; the relationship classification can be completed by classifying the relationship types through a nonlinear layer of the neural network according to predefined relationship types, wherein the relationship types can comprise physical position relationships, partial overall relationships, character social relationships and the like.
S2, constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
in an embodiment of the present invention, the constructing a knowledge graph according to the knowledge triplet includes:
obtaining a knowledge entity library, and preselecting candidate entity objects from the knowledge entity library;
performing similarity calculation on the candidate entity object and the knowledge triples, and obtaining an entity object according to a similarity calculation result;
and carrying out knowledge fusion on the entity objects to obtain a knowledge graph.
In the embodiment of the invention, the knowledge entity library is an existing medical knowledge entity library, wherein the medical knowledge has entity objects with corresponding relations; and the similarity calculation can be carried out by utilizing a cosine value calculation method and is screened according to the size of the similarity calculation result, wherein the maximum similarity calculation result is the correct entity object.
Further, in the embodiment of the present invention, knowledge fusion is to associate a plurality of entity objects according to the entity relationships between the entity objects, so as to form an integral relationship network, that is, the knowledge graph.
In the embodiment of the invention, the knowledge graph is a relational network formed by organization representation of knowledge of the articles to be processed, and the relational network consists of nodes and edges connected with different nodes, wherein each node comprises an entity in the articles to be processed, the edges connected with different nodes are the relations among the entities, node characteristic extraction can use a pre-trained node classifier to classify the node and adjacent nodes thereof, the classified nodes are subjected to aggregation calculation to obtain aggregated adjacent node characteristics, and values obtained by weighting and summing the adjacent node characteristics are input into the node classifier to generate knowledge characteristics.
S3, acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem;
in the embodiment of the present invention, the medical question may be a medical question that the user consults when using a medical knowledge question answering web page, software, an applet, etc., for example, "what matters about hypertension needs to be noted in terms of diet? "
Referring to fig. 3, in an embodiment of the present invention, the feature encoding the medical question to obtain a word feature sequence of the medical question includes:
s31, word vector embedding is carried out on the medical problems to obtain embedded vectors;
s32, splicing the preset position information vector with the embedded vector to obtain an input feature vector;
s33, carrying out layer normalization on the input feature vector to obtain the word feature sequence of the medical problem.
In the embodiment of the invention, word vector embedding can be calculated by using ELMO (Embedding from Language Models, word embedding model); the position information vector comes from the coding layer in the word embedding model, and because the semantic information carried by the words or the characters at different positions in the medical question text is different, the coding layer of the ELMO model respectively adds one different position information vector to the words or the characters at different positions to distinguish, and the position information vector is added at the tail end of the embedding vector; layer normalization is the variance and mean calculation performed by the output layer in the word embedding model.
In the embodiment of the present invention, the word vector embedding is performed on the medical problem to obtain an embedded vector, which includes:
carrying out format specification processing on the article to be processed to obtain a standard sentence;
performing character encoding on the standard sentence to obtain an initial word vector;
and carrying out linear mapping on the initial word vector to obtain an embedded vector.
In the embodiment of the invention, format specification processing is to represent sentences in the medical problem according to input dimensions of B, W and C, wherein B is expressed as the number of sentences in the medical problem, W is expressed as the number of words in the sentences, and C is expressed as the number of characters contained in each word; character encoding can utilize the character encoding layer of the word embedding model to realize text conversion according to a UNICODE encoding method.
And S4, carrying out feature fusion on the knowledge features and the word feature sequences of the medical problems to generate medical question-answering knowledge.
In the embodiment of the present invention, the feature fusion is performed on the knowledge feature and the word feature sequence of the medical question to generate the medical question-answering knowledge, which includes:
obtaining entity categories of the medical problems, and primarily screening the knowledge features according to the entity categories to obtain initial knowledge features;
and carrying out probability calculation on the feature sequence of the initial knowledge feature and the word feature sequence of the medical question, and generating medical question-answering knowledge according to a probability calculation result.
In the embodiment of the invention, the entity categories are obtained according to the node attributes in the knowledge graph, and comprise four entity categories: diseases, symptoms, organs and routine examination, e.g., "what is thyromegaly? "the problem belongs to the disease class of problems; and correspondingly screening the knowledge graph according to the entity category to obtain the knowledge characteristic under a certain category, namely the initial knowledge characteristic.
In the embodiment of the invention, probability calculation can utilize a softmax classification function to carry out probability ranking on the feature sequence of the initial knowledge feature and the word feature sequence of the medical question, the initial feature with the largest probability calculation result is selected as a target knowledge feature, and medical knowledge contained in the corresponding node of the target knowledge feature in the knowledge graph is an answer to the medical question, so that medical question-answering knowledge can be generated.
According to the knowledge graph-fused medical question-answer knowledge generation method, the knowledge graph of the article to be processed is constructed to automatically generate the medical question-answer knowledge, so that the full utilization of the question-answer knowledge can be realized; according to the knowledge triples, a knowledge graph is constructed, medical knowledge and a knowledge system can be displayed in a graphical mode, integration of multiple aspects of medical knowledge can be realized, and accuracy of knowledge generation of medical questions and answers is improved; the node characteristic extraction is carried out on the knowledge graph, so that the dimension of data can be reduced, and the working efficiency of medical question-answering knowledge is improved; the knowledge features and the word feature sequences of the medical problems are subjected to feature fusion, so that the medical knowledge can be comprehensively utilized, and the accuracy of generating the medical question-answering knowledge is improved. Therefore, the medical question-answer knowledge generation method provided by the invention can solve the problem of low medical question-answer knowledge generation efficiency and accuracy.
Fig. 4 is a functional block diagram of a medical question-answer knowledge generation device according to an embodiment of the present invention.
The medical question-answer knowledge generation apparatus 100 of the present invention may be mounted in an electronic device. Depending on the implemented functions, the medical question-answer knowledge generating device 100 may include an information extraction module 101, a node feature extraction module 102, a feature encoding module 103, and a feature fusion module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the information extraction module 101 is configured to obtain an article to be processed, and extract information from the article to be processed to obtain a knowledge triplet;
the node feature extraction module 102 is configured to construct a knowledge graph according to the knowledge triplet, and perform node feature extraction on the knowledge graph to obtain knowledge features;
the feature coding module 103 is configured to obtain a medical problem, perform feature coding on the medical problem, and obtain a word feature sequence of the medical problem;
the feature fusion module 104 is configured to perform feature fusion on the knowledge feature and the word feature sequence of the medical question, so as to generate a medical question-answer knowledge.
In detail, each module in the medical question-answer knowledge generating device 100 in the embodiment of the present invention adopts the same technical means as the medical question-answer knowledge generating method in the drawings when in use, and can generate the same technical effects, which are not described herein.
Fig. 5 is a schematic structural diagram of an electronic device for implementing a method for generating knowledge of a medical question and answer according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and may further comprise a computer program, such as a question and answer knowledge generation program, stored in the memory 11 and executable on the processor 10.
The processor 10 may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing Unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and so on. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (e.g., executes a medical question-and-answer knowledge generation program, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device and process data.
The memory 11 includes at least one type of readable storage medium including flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory 11 may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device. The memory 11 may be used not only for storing application software installed in an electronic device and various types of data, such as codes of a medical question-answer knowledge generation program, but also for temporarily storing data that has been output or is to be output.
The communication bus 12 may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Fig. 5 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 5 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device may further include various sensors, bluetooth modules, wi-Fi modules, etc., which are not described herein.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The medical question and answer knowledge generation program stored in the memory 11 in the electronic device 1 is a combination of a plurality of instructions, which when executed in the processor 10, may implement:
acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet;
constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem;
and carrying out feature fusion on the knowledge features and the word feature sequences of the medical questions to generate medical question-answering knowledge.
In particular, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of the drawings, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:
acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet;
constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem;
and carrying out feature fusion on the knowledge features and the word feature sequences of the medical questions to generate medical question-answering knowledge.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A method of generating a medical question-answer knowledge, the method comprising:
acquiring an article to be processed, and extracting information from the article to be processed to obtain a knowledge triplet;
constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
acquiring a medical problem, and performing feature coding on the medical problem to obtain a word feature sequence of the medical problem;
and carrying out feature fusion on the knowledge features and the word feature sequences of the medical questions to generate medical question-answering knowledge.
2. The method for generating knowledge of a medical question and answer according to claim 1, wherein said extracting information from said article to be processed to obtain a knowledge triplet comprises:
preprocessing the article to be processed to obtain a word segmentation data set;
extracting entity relations from the word segmentation data set to obtain an entity set;
and carrying out relation screening on the entity set to obtain a knowledge triplet.
3. The method for generating the knowledge of a medical question and answer according to claim 2, wherein the preprocessing the article to be processed to obtain a word segmentation dataset includes:
performing word segmentation processing on the article to be processed to obtain input word segmentation and corresponding part of speech;
acquiring a preset deactivated part-of-speech tag, and screening the input word according to the part-of-speech tag and the part-of-speech corresponding to the input word to obtain a word segmentation data set.
4. The method for generating knowledge of medical question and answer according to claim 2, wherein said extracting entity relation from said word segmentation dataset to obtain an entity set comprises:
vector representation is carried out on the word segmentation data set, and word segmentation vectors are obtained;
extracting features of the word segmentation vectors to obtain word segmentation feature vectors;
and carrying out relationship classification on the word segmentation feature vectors, and obtaining an entity set according to a relationship classification result.
5. The method for generating knowledge of a medical question and answer according to claim 1, wherein said constructing a knowledge graph from said knowledge triples comprises:
obtaining a knowledge entity library, and preselecting candidate entity objects from the knowledge entity library;
performing similarity calculation on the candidate entity object and the knowledge triples, and obtaining an entity object according to a similarity calculation result;
and carrying out knowledge fusion on the entity objects to obtain a knowledge graph.
6. The method for generating knowledge of medical question and answer according to claim 1, wherein said feature encoding said medical question to obtain a word feature sequence of said medical question comprises:
word vector embedding is carried out on the medical problems to obtain embedded vectors;
splicing a preset position information vector with the embedded vector to obtain an input feature vector;
and carrying out layer normalization on the input feature vector to obtain the word feature sequence of the medical problem.
7. The method for generating knowledge of a medical question and answer according to any one of claims 1 to 6, wherein the feature fusion of the knowledge feature with the word feature sequence of the medical question to generate knowledge of a medical question comprises:
obtaining entity categories of the medical problems, and primarily screening the knowledge features according to the entity categories to obtain initial knowledge features;
and carrying out probability calculation on the feature sequence of the initial knowledge feature and the word feature sequence of the medical question, and generating medical question-answering knowledge according to a probability calculation result.
8. A medical question-answer knowledge generation device, the device comprising:
the information extraction module is used for obtaining articles to be processed, extracting information from the articles to be processed and obtaining knowledge triples;
the node characteristic extraction module is used for constructing a knowledge graph according to the knowledge triplet, and extracting node characteristics of the knowledge graph to obtain knowledge characteristics;
the feature coding module is used for acquiring medical problems, and carrying out feature coding on the medical problems to obtain word feature sequences of the medical problems;
and the feature fusion module is used for carrying out feature fusion on the knowledge features and the word feature sequences of the medical problems to generate medical question-answering knowledge.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the question-and-answer knowledge generation method of any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the medical question-answer knowledge generation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446180.5A CN116467418A (en) | 2023-04-14 | 2023-04-14 | Medical question-answer knowledge generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310446180.5A CN116467418A (en) | 2023-04-14 | 2023-04-14 | Medical question-answer knowledge generation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116467418A true CN116467418A (en) | 2023-07-21 |
Family
ID=87176872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310446180.5A Pending CN116467418A (en) | 2023-04-14 | 2023-04-14 | Medical question-answer knowledge generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467418A (en) |
-
2023
- 2023-04-14 CN CN202310446180.5A patent/CN116467418A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112131393A (en) | Construction method of medical knowledge map question-answering system based on BERT and similarity algorithm | |
| CN112487202B (en) | Chinese medical named entity recognition method and device fusing knowledge map and BERT | |
| Ling et al. | Integrating extra knowledge into word embedding models for biomedical NLP tasks | |
| CN110612522B (en) | Establishment of solid model | |
| US20160098456A1 (en) | Implicit Durations Calculation and Similarity Comparison in Question Answering Systems | |
| CN113378970B (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN111695354A (en) | Text question-answering method and device based on named entity and readable storage medium | |
| CN114662477B (en) | Method, device and storage medium for generating deactivated word list based on Chinese medicine dialogue | |
| CN111475645B (en) | Knowledge point labeling method, knowledge point labeling device and computer readable storage medium | |
| Liu et al. | A genetic algorithm enabled ensemble for unsupervised medical term extraction from clinical letters | |
| CN116578704A (en) | Text emotion classification method, device, equipment and computer readable medium | |
| CN114840685A (en) | Emergency plan knowledge graph construction method | |
| WO2022227171A1 (en) | Method and apparatus for extracting key information, electronic device, and medium | |
| CN113918704A (en) | Question-answering method and device based on machine learning, electronic equipment and medium | |
| CN113111159A (en) | Question and answer record generation method and device, electronic equipment and storage medium | |
| Jin et al. | Textual content prediction via fuzzy attention neural network model without predefined knowledge | |
| CN116821373A (en) | Map-based prompt recommendation method, device, equipment and medium | |
| CN116860935A (en) | Content management method, device, equipment and medium based on prompt word question-answer interaction | |
| Sarrouti et al. | A new and efficient method based on syntactic dependency relations features for ad hoc clinical question classification | |
| CN116702776A (en) | Multi-task semantic division method, device, equipment and medium based on cross-Chinese and western medicine | |
| CN116522944A (en) | Picture generation method, device, equipment and medium based on multi-head attention | |
| CN116450916A (en) | Information query method and device based on fixed-segment classification, electronic equipment and medium | |
| CN112529743B (en) | Contract element extraction method, device, electronic equipment and medium | |
| US20220165430A1 (en) | Leveraging deep contextual representation, medical concept representation and term-occurrence statistics in precision medicine to rank clinical studies relevant to a patient | |
| CN114676307A (en) | Ranking model training method, device, equipment and medium based on user retrieval |
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 |