Liu Ning

Bio: Liu Ning is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Graph (abstract data type) & Question answering. The author has an hindex of 2, co-authored 9 publications receiving 10 citations. Previous affiliations of Liu Ning include Beijing Institute of Petrochemical Technology.

Intelligent question-answering method and device based on knowledge graph

Abstract: The embodiment of the invention provides an intelligent question-answering method and device based on a knowledge graph. The intelligent question-answering method comprises the steps: receiving a userquestion transmitted by a client, and respectively carrying out the entity recognition and intention recognition; and generating a knowledge graph query statement according to the entity identification result and the intention identification result, searching in a knowledge graph database to obtain an answer corresponding to the user question, and returning the answer to the client, wherein the knowledge graph database comprises entity names, entity attribute information and entity relationship information. The intelligent question-answering method and device based on a knowledge graph generates knowledge graph query statement after entity identification and intention identification are carried out based on a user question, and carries out searching in the knowledge graph database containing the entity name, the entity attribute information and the entity relation information to obtain the answer corresponding to the user question and return the answer to the client, thus achieving intelligent automatic answering of the user question, and improving the answering efficiency and accuracy.

The Intelligent Diagnostic System for Common Diseases using the Optimized Medical Knowledge Graph

Abstract: With the development of artificial intelligence technology, Clinical Decision Support System (CDSS) has been widely used. This paper presents a CDSS system, which called the Intelligent Auxiliary Diagnostic System for Common Disease (CD-IADS). CD-IADS assists the primary doctors in the diagnosis of common diseases with the patient's symptoms, signs, tests and personal background, which improves the primary doctors' working efficiency and reduces their misdiagnosis rate. In CD-IADS, medical experts construct the Medical Knowledge Graph according to medical literature and clinical experience firstly. Then, information entropy and particle swarm optimization (PSO) algorithms are used to optimize the special weights based on medical records. The system combines the advantages of the medical expert system and the artificial intelligence algorithm to support the diagnosis of common diseases. The paper takes the common diseases of the respiratory department as an example, and the TOP-1 and TOP-3 diagnostic accuracy rates are up to 64.6% and 86.0% respectively.

Medical knowledge graph construction method and device based on electronic medical record

Abstract: The embodiment of the invention provides a medical knowledge graph construction method and device based on electronic medical records. The method comprises the steps of extracting symptom entities from the electronic medical records with body parts as anchor points; constructing a binary entity pair of symptoms and symptom details for the symptom entity; determining a corresponding relationship type for the binary entity pair; and constructing a medical knowledge graph by taking two entities in the binary entity pair as nodes and taking the relationship type of the binary entity pair as an edge. According to the embodiment of the invention, the symptom entity is extracted by taking the body part as the anchor point in the electronic medical record, so that a relatively comprehensive symptom entity extraction result can be obtained, the completeness of the symptom entity in the medical knowledge graph is improved, and the reference value of the medical knowledge graph is further improved. In addition, a binary entity pair of symptoms and symptom details and a corresponding relationship type are constructed, so that the medical corresponding relationship between the symptoms and thesymptom details can be analyzed according to the medical knowledge graph.

Disease inference system based on medical knowledge graph

Abstract: The embodiment of the invention provides a disease inference system based on a medical knowledge graph, wherein the system includes an acquisition module for obtaining diagnosis evidence information of patients, and a disease inference module for querying the medical knowledge graph according to the diagnosis evidence information of the patients, obtaining the clinical manifestation correspondingto the diagnosis evidence information, querying the medical knowledge graph according to the clinical manifestation and obtaining disease information corresponding to the clinical manifestation; the medical knowledge graph is a mapping map established in advance according to a disease knowledge base and the professional knowledge of doctors and used for representing the interrelationship among thediagnosis evidence entity, the clinical manifestation entity and the suspected disease entity.

Character image recognition method and device based on OCR

Abstract: The embodiment of the invention provides a character image recognition method and a device based on OCR. The method comprises the steps of performing OCR and word segmentation processing on a to-be-recognized text image to obtain a to-be-corrected text; splicing adjacent scattered string characters in the text to be corrected into a combined character; obtaining a candidate statement list according to the combined characters and a confusion set corresponding to the scattered string characters; selecting a candidate statement with the maximum probability as an error correction result text according to a natural language probability statistical model; according to the method of the invention, OCR recognition and word segmentation processing are carried out on a to-be-recognized text image toobtain a to-be-corrected text containing hash characters; the method comprises the following steps: obtaining a candidate statement list, splicing continuous scattered string characters into a combined character, or replacing the combined character with replacement characters of a confusion set corresponding to the scattered string characters to obtain the candidate statement list, and finally determining an error correction result text according to a natural language probability statistical model, so that a character image can be identified more simply and accurately.

Question and answer method and device based on dictionary tree, recognition equipment and readable storage medium

Abstract: The invention is applicable to the technical field of natural language processing, and provides a question-answering method and device based on a dictionary tree, recognition equipment and a readablestorage medium. Inputting the inquiry information into a preset dictionary tree to obtain a first entity of the inquiry information; inputting the first entity into a preset knowledge graph to obtaina second entity corresponding to the first entity; and generating answer information according to the second entity, and returning the answer information to the user. Visibly, the problem that in theprior art, due to the fact that many name calling modes of alias names of entities exist, a question-answering system in the prior art cannot well recognize user input can be solved, and the effect that a user can be accurately replied in the question-answering process is achieved.

An Emergency Rescue System Architecture Based on Metaverse

Abstract: The imperfect staffing in pre-hospital first aid and the unreasonable dispatching of ambulances pose a threat to the life and health of the public. In order to solve the above problems, this paper proposes an emergency rescue system based on metaverse, which adds the function of personal doctor on the basis of the shared vehicle scheduling system based on blockchain. Metaverse is the fusion and interaction between the virtual and the real world, with blockchain, smart contracts, and other main technologies. Through the combination of metaverse and intelligent doctor assistant, the function and use process of personal doctor are designed. This paper also proposes an insurance-like payment mechanism, which is based on the premise of controlling the packing order of transactions in the blockchain by controlling the level of Gas Price and solving the problem of who pays and how to pay the transaction fee of the system. It not only ensures the normal operation of emergency rescue activities but also protects the interests of each node in the blockchain.

An Emergency Rescue System Architecture Based on Metaverse

Abstract: The imperfect staffing in pre-hospital first aid and the unreasonable dispatching of ambulances pose a threat to the life and health of the public. In order to solve the above problems, this paper proposes an emergency rescue system based on metaverse, which adds the function of personal doctor on the basis of the shared vehicle scheduling system based on blockchain. Metaverse is the fusion and interaction between the virtual and the real world, with blockchain, smart contracts, and other main technologies. Through the combination of metaverse and intelligent doctor assistant, the function and use process of personal doctor are designed. This paper also proposes an insurance-like payment mechanism, which is based on the premise of controlling the packing order of transactions in the blockchain by controlling the level of Gas Price and solving the problem of who pays and how to pay the transaction fee of the system. It not only ensures the normal operation of emergency rescue activities but also protects the interests of each node in the blockchain.

Pig disease diagnosis method and system

Abstract: The invention provides a pig disease diagnosis method and system The method comprises the steps: extracting case information of pigs and sign data information, corresponding to cases, of the pigs through a knowledge graph platform; analyzing the extracted case information and the extracted sign data information through a big data platform, and calculating the correlation degree between the corresponding case and the sign data; monitoring the sign data of the pigs in real time, and triggering the knowledge graph platform according to the abnormality of the sign data of the pigs so as to diagnose the diseases of the pigs; and on the basis of the correlation degree between the case and the sign data, determining the probability that the pigs suffer from the diseases through the big data platform According to the invention, the knowledge graph platform and the big data platform are introduced to establish the correlation degree between the diseases of the pigs and the sign data, so thatthe sign data of the pigs are monitored in real time to discover the diseases of the pigs in time, and the diagnosis accuracy of the diseases of the pigs is improved

Query feedback method and device, computer equipment and storage medium

Abstract: The invention relates to a query feedback method and device, computer equipment and a storage medium. The method comprises the steps of performing semantic feature recognition on a query statement toobtain a recognition result of the query statement, wherein the recognition result comprises an original semantic entity and semantic information; obtaining at least two candidate semantic entities based on an identification result of the query statement; screening out a target semantic entity from the at least two candidate semantic entities; sending a feedback result corresponding to the targetsemantic entity to the terminal. According to the scheme, the candidate semantic entities are jointly queried by combining the original semantic entities and the semantic information on the basis of an artificial intelligence technology, so that the sources of the subsequently determined target semantic entities are wider, the diversity of the target semantic entities is improved, the diversity offeedback results is further improved, and the purpose of improving the feedback effect is achieved.