Back to results
US 12,603,169 B2Granted
Intelligent triage method and device, storage medium and electronic device
AssigneeBoe Technology Group Co., Ltd.
InventorZhenzhong Zhang
Life of this patent
Estimating the term…
Abstract
The present disclosure provides an intelligent triage method and device, a storage medium and an electronic device. The method includes: obtaining disease information of a target outpatient, and obtaining a vector of the target outpatient according to the disease information; vectorizing each doctor in a doctor knowledge graph to obtain a plurality of doctor vectors; and calculating matching degrees between the vector of the target outpatient and the plurality of doctor vectors using a matching degree calculation model, and recommending a doctor for the target outpatient according to magnitudes of the matching degrees.
Claims12
An intelligent triage method, comprising:
- obtaining, by a server, disease information of a target outpatient, and obtaining a vector of the target outpatient according to the disease information;
- vectorizing, by a server, each doctor in a doctor knowledge graph to obtain a plurality of doctor vectors, wherein the doctor knowledge graph is constructed by:
- selecting Uniform Resource Locators (URLs) as seeds, and putting the URLs into a queue to be crawled;
- for seed URLs in the queue to be crawled, accessing website by simulating manual browsing to obtain crawled web Hyper Text Markup Language (HTML) data comprising doctor information;
- parsing the doctor information in the crawled web HTML data to obtain a new link, and performing next layer crawling using the new link as a seed URL, to obtain corpus information of a plurality of doctors;
- performing, by the server, semantic analysis on the corpus information through natural language processing, and extracting relationships among the plurality of doctors;
- with the plurality of doctors as entities, constructing, by the server, the doctor knowledge graph according to the relationships among the plurality of doctors, wherein edges in the doctor knowledge graph represent the relationships between doctors;
- and
- calculating, by the server, matching degrees between the vector of the target outpatient and the plurality of doctor vectors using a matching degree calculation model, and recommending a doctor for the target outpatient according to magnitudes of the matching degrees, and sending a recommended doctor to a terminal device of the target outpatient;
- wherein vectorizing, by the server, each doctor in the doctor knowledge graph to obtain the plurality of doctor vectors comprises:
- vectorizing, by the server, each doctor in the doctor knowledge graph through a graph neural network to obtain the plurality of doctor vectors;
- wherein vectorizing, by the server, each doctor in the doctor knowledge graph through the graph neural network to obtain the plurality of doctor vectors comprises:
- initializing, by the server, node vectors corresponding to individual doctors in the doctor knowledge graph;
- and
- iteratively updating, by the server, each of the node vectors by using a pre-trained graph neural network to obtain the plurality of doctor vectors;
- wherein iteratively updating, by the server, each of the node vectors by using the pre-trained graph neural network to obtain the plurality of doctor vectors comprises:
- updating, by the server, each of the node vectors according to the following equation to obtain the plurality of doctor vectors:
- h
- t
- +
- 1
- (
- e
- i
- )
- =
- ∑
- e
- k
- ∈
- Np
- (
- e
- i
- )
- σ
-
- (
- W
- p
- ×
- e
- i
- +
- W
- ph
- ×
- h
- t
- (
- e
- k
- )
- )
- +
- ∑
- e
- j
- ∈
- Nc
-
- (
- e
- i
- )
- σ
-
- (
- W
- c
- ×
- e
- i
- +
- W
- ch
- ×
- h
- t
- (
- e
- j
- )
- )
- wherein Wp, Wph, Wc, Wch are parameters of the graph neural network, σ is an activation function in the graph neural network, t is number of network iterations, ei is a node corresponding to an i-th doctor in the doctor knowledge graph, Np(ei) is a parent node set for the node ei, ek is a k-th parent node of the node ei, Nc(ei) is a child node set for the node ei, ej is a j-th child node of the node ei, and hτ(ei) represents a vector of the node ei after t network iterations.
82 more elements
A server, comprising:
- a processor, and
- a memory storing instructions executable by the processor;
- wherein the processor is configured to:
- obtain disease information of a target outpatient, and obtaining a vector of the target outpatient according to the disease information;
- vectorize each doctor in a doctor knowledge graph to obtain a plurality of doctor vectors, wherein the doctor knowledge graph is constructed by:
- selecting Uniform Resource Locators (URLs) as seeds, and putting the URLs into a queue to be crawled;
- for the seed URLs in the queue to be crawled, accessing website by simulating manual browsing to obtain crawled web Hyper Text Markup Language (HTML) data comprising doctor information;
- parsing the doctor information in the crawled web HTML data to obtain a new link, and performing next layer crawling using the new link as a seed URL, to obtain corpus information of a plurality of doctors;
- performing semantic analysis on the corpus information through natural language processing, and extracting relationships among the plurality of doctors;
- with the plurality of doctors as entities, constructing the doctor knowledge graph according to the relationships among the plurality of doctors, wherein edges in the doctor knowledge graph represent the relationships between doctors;
- and
- calculate matching degrees between the vector of the target outpatient and the plurality of doctor vectors using a matching degree calculation model, and recommend a doctor for the target outpatient according to magnitudes of the matching degrees, and send a recommended doctor to a terminal device of the target outpatient;
- wherein the processor is configured to:
- vectorize each doctor in the doctor knowledge graph through a graph neural network to obtain the plurality of doctor vectors;
- wherein the processor is configured to:
- initialize node vectors corresponding to individual doctors in the doctor knowledge graph;
- and
- iteratively update each of the node vectors by using a pre-trained graph neural network to obtain the plurality of doctor vectors;
- wherein iteratively updating each of the node vectors by using the pre-trained graph neural network to obtain the plurality of doctor vectors comprises:
- updating each of the node vectors according to the following equation to obtain the plurality of doctor vectors:
- h
- t
- +
- 1
- (
- e
- i
- )
- =
- ∑
- e
- k
- ∈
- Np
- (
- e
- i
- )
- σ
-
- (
- W
- p
- ×
- e
- i
- +
- W
- ph
- ×
- h
- t
- (
- e
- k
- )
- )
- +
- ∑
- e
- j
- ∈
- Nc
-
- (
- e
- i
- )
- σ
-
- (
- W
- c
- ×
- e
- i
- +
- W
- ch
- ×
- h
- t
- (
- e
- j
- )
- )
- wherein Wp, Wph, Wc, and Wch are parameters of the graph neural network, σ is an activation function in the graph neural network, t is number of network iterations, ei is a node corresponding to an i-th doctor in the doctor knowledge graph, Np(ei) is a parent node set for the node ei, ek, is a k-th parent node of the node ei, Nc(ei) is a child node set for the node ei, ej is a j-th child node of the node ei, and hτ(ei) represents a vector of the node ei after t network iterations.
85 more elements
Dependencies are inferred from the claim text.