CN111816301B - Medical inquiry assisting method, device, electronic equipment and medium - Google Patents
Medical inquiry assisting method, device, electronic equipment and medium Download PDFInfo
- Publication number
- CN111816301B CN111816301B CN202010645468.1A CN202010645468A CN111816301B CN 111816301 B CN111816301 B CN 111816301B CN 202010645468 A CN202010645468 A CN 202010645468A CN 111816301 B CN111816301 B CN 111816301B
- Authority
- CN
- China
- Prior art keywords
- disease
- entity
- image
- vector
- text
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 201000010099 disease Diseases 0.000 claims abstract description 273
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 273
- 208000037920 primary disease Diseases 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 7
- 239000013598 vector Substances 0.000 claims description 109
- 238000007689 inspection Methods 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 19
- 208000024891 symptom Diseases 0.000 claims description 14
- 238000012790 confirmation Methods 0.000 claims description 10
- 238000003745 diagnosis Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000004590 computer program Methods 0.000 description 15
- 238000004458 analytical method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000001960 triggered effect Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000002604 ultrasonography Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010365 information processing Effects 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
Abstract
The invention relates to artificial intelligence and provides a medical inquiry assisting method, a device, electronic equipment and a medium. The method can determine a user to be diagnosed, acquire illness state text information and illness state image information of the user to be diagnosed, identify entities in the illness state text information to obtain target text entities, determine first disease entities related to the target text entities from a pre-built text knowledge graph, determine second disease entities related to the illness state image information from a pre-built image knowledge graph, fuse the first disease entities and the second disease entities to obtain a target set, determine probability of each disease entity in the target set, determine the disease entity with the highest probability as a main disease of the user to be diagnosed, and determine candidate diseases of the user to be diagnosed from the target set according to the probability. The invention can improve the accuracy of inquiry assistance. Furthermore, the present invention relates to blockchain technology, wherein the primary disease and the candidate disease may be stored in a blockchain.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a medical inquiry assisting method, a medical inquiry assisting device, electronic equipment and a medical inquiry assisting medium.
Background
Because the existing disease diagnosis method mainly completes diagnosis according to personal experience of doctors, and simultaneously experienced advanced doctors are less, the current method cannot meet the huge number of requirements for treatment. With the rapid development of artificial intelligence and the development of hospital informatization, an intelligent auxiliary consultation mode is generated, however, the mode only analyzes text information, and analysis of image information (such as electrocardiogram) in a medical scene is omitted, so that the accuracy of consultation assistance is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a medical consultation assistance method, apparatus, electronic device, and medium that can not only improve the accuracy of the consultation assistance, but also improve the efficiency of the consultation of the medical staff.
A medical consultation assistance method, the medical consultation assistance method comprising:
When a medical inquiry auxiliary request is received, determining a user to be diagnosed according to the medical inquiry auxiliary request;
acquiring illness state text information and illness state image information of the user to be diagnosed;
identifying an entity in the illness state text information to obtain a target text entity;
determining a first disease entity associated with the target text entity from a pre-constructed text knowledge-graph and a second disease entity associated with the condition image information from a pre-constructed image knowledge-graph;
fusing the first disease entity and the second disease entity to obtain a target set;
Determining a probability of each disease entity in the target set;
and determining the disease entity with the highest probability as the main disease of the user to be diagnosed, and determining the candidate disease of the user to be diagnosed from the target set according to the probability.
According to a preferred embodiment of the present invention, the determining the user to be diagnosed according to the medical consultation assistance request includes:
Acquiring any idle thread from a thread connection pool;
analyzing the method body of the medical inquiry auxiliary request by using the arbitrary idle thread to obtain data information carried by the medical inquiry auxiliary request;
acquiring a preset tag, and acquiring information corresponding to the preset tag from the data information as an identity identification code;
And determining the user to be diagnosed by using the identification code.
According to a preferred embodiment of the present invention, the acquiring the textual information and the image information of the condition of the user to be diagnosed includes one or more of the following combinations:
Downloading a file corresponding to the identification code from a first preset website to serve as the illness state text information, and downloading a file corresponding to the identification code from a second preset website to serve as the illness state image information; and/or
And identifying the medical record book of the user to be diagnosed by utilizing an optical character identification algorithm to obtain the illness state text information, and controlling a medical instrument to acquire illness state image information of the user to be diagnosed.
According to a preferred embodiment of the present invention, the identifying the entity in the illness state text information, and obtaining the target text entity include:
performing word segmentation processing on the illness state text information to obtain a plurality of word segments;
Converting each word into a word vector, and combining the word vectors according to the sequence of each word in the illness state text information to obtain a vector sequence corresponding to the illness state text information;
extracting the characteristics of the vector sequence by utilizing a two-way long-short term memory network to obtain a first characteristic vector corresponding to each word segment in a forward long-short term memory network and a second characteristic vector corresponding to each word segment in a reverse long-short term memory network;
Splicing the first feature vector and the second feature vector to obtain a target vector corresponding to each word segmentation;
Multiplying each target vector by a preset weight matrix, and adding a preset bias value to obtain a score vector of each word segment, wherein each element in the score vector represents the score of the label corresponding to each word segment;
for each score vector, determining a label corresponding to the element with the highest score as a target label of each word to obtain a plurality of target labels in the illness state text information;
Acquiring target labels corresponding to symptom entities in a preset symptom library from the plurality of target labels as first text entities, and acquiring target labels corresponding to sign entities in a preset sign library from the plurality of target labels as second text entities;
and combining the first text entity and the second text entity to obtain the target text entity.
According to a preferred embodiment of the present invention, before determining the second disease entity associated with the disease image information from a pre-constructed image knowledge-graph, the medical consultation assistance method further includes:
Acquiring a plurality of inspection images by utilizing a web crawler technology, and acquiring a plurality of inspection diseases corresponding to the inspection images;
performing alignment processing on the plurality of inspection images to obtain a plurality of alignment images;
Converting each alignment image into an image vector and each inspection disease into a text vector based on pixels in each alignment image;
calculating the similarity between the image vector and the text vector as the association degree between the examination image and the examination disease;
the image knowledge graph is generated based on the image vector, the examination disease, and the degree of association.
According to a preferred embodiment of the present invention, said determining the probability of each disease entity in said target set comprises:
Acquiring associated text entities associated with each disease entity from the text knowledge graph, and acquiring a first association degree of each disease entity and the associated text entity;
acquiring an associated image corresponding to each disease entity from the image knowledge graph, and acquiring a second association degree of each disease entity and the associated image;
Multiplying the first association degree by the second association degree to obtain a target value of each disease, wherein the target value represents the probability that the associated text entity and the associated image exist in each disease at the same time;
Calculating the sum of target values of all disease entities in the target set to obtain a total value;
dividing the target value for each disease by the total value to obtain a probability for each disease entity.
According to a preferred embodiment of the present invention, after determining the disease with the highest probability as the primary disease of the user to be diagnosed and determining the candidate disease from the target set according to the probability, the medical inquiry assisting method further includes:
Acquiring user information of the user to be diagnosed, and generating information to be confirmed according to the user information, the main diseases and the candidate diseases;
the information to be confirmed is sent to terminal equipment of the appointed contact person;
when the confirmation information sent by the terminal equipment is received within the preset time, extracting the confirmed disease from the confirmation information;
generating a diagnostic report according to the user information and the diagnosed disease;
encrypting the diagnosis report by adopting a symmetric encryption algorithm to obtain a ciphertext;
And storing the mapping relation between the user information and the ciphertext, and sending the ciphertext to the client of the user to be diagnosed.
A medical consultation assistance device, the medical consultation assistance device comprising:
a determining unit, configured to determine a user to be diagnosed according to a medical inquiry assistance request when the medical inquiry assistance request is received;
The acquisition unit is used for acquiring the illness state text information and illness state image information of the user to be diagnosed;
the identification unit is used for identifying the entity in the illness state text information to obtain a target text entity;
The determining unit is further used for determining a first disease entity associated with the target text entity from a pre-constructed text knowledge graph and determining a second disease entity associated with the disease image information from a pre-constructed image knowledge graph;
the fusion unit is used for fusing the first disease entity and the second disease entity to obtain a target set;
the determining unit is further configured to determine a probability of each disease entity in the target set;
The determining unit is further configured to determine a disease entity with the highest probability as a primary disease of the user to be diagnosed, and determine a candidate disease of the user to be diagnosed from the target set according to the probability.
An electronic device, the electronic device comprising:
a memory storing at least one instruction; and
And a processor executing instructions stored in the memory to implement the medical consultation assistance method.
A computer-readable storage medium having stored therein at least one instruction for execution by a processor in an electronic device to implement the medical interrogation assistance method.
According to the technical scheme, when the disease text information and the disease image information of the user to be diagnosed are analyzed, the analysis of the disease image information is added, so that the analysis of the disease image information is not limited to the analysis of the text information, the accuracy of inquiry assistance can be improved, and further, the target set comprising the first disease entity and the second disease entity can be comprehensively obtained through the text knowledge graph and the image knowledge graph, and the comprehensiveness is improved. In addition, by analyzing the probability of each disease entity in the target set and determining the disease entity with the highest probability as the main disease, and selecting the candidate disease from the target set, the medical staff can confirm the confirmed disease again, so that the invention can provide inquiry assistance for the medical staff, and further can improve the inquiry efficiency of the medical staff.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the medical consultation assistance method of the present invention.
Fig. 2 is a functional block diagram of a preferred embodiment of the medical consultation assistance device of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a medical diagnosis assisting method according to a preferred embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Referring to FIG. 1, a flow chart of a preferred embodiment of the medical consultation assistance method of the present invention is shown. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.
The medical inquiry assisting method is applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware of the electronic devices comprises, but is not limited to, microprocessors, application SPECIFIC INTEGRATED Circuits (ASICs), programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), digital processors (DIGITAL SIGNAL processors, DSPs), embedded devices and the like.
The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a Personal computer, a tablet computer, a smart phone, a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a game console, an interactive internet protocol television (Internet Protocol Television, IPTV), a smart wearable device, etc.
The electronic device may also include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network server, a server group composed of a plurality of network servers, or a Cloud based Cloud Computing (Cloud Computing) composed of a large number of hosts or network servers.
The network in which the electronic device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), and the like.
In at least one embodiment of the invention, the medical consultation assistance method is applied in the field of artificial intelligence.
And S10, when a medical inquiry auxiliary request is received, determining a user to be diagnosed according to the medical inquiry auxiliary request.
In at least one embodiment of the present invention, the request for assistance in a medical care may be triggered by a medical staff member or may be triggered at a predetermined time, which is not limited by the present invention.
Further, the information carried by the auxiliary request for medical inquiry includes, but is not limited to: identification codes, preset labels, etc.
In at least one embodiment of the present invention, the determining, by the electronic device, the user to be diagnosed according to the medical inquiry assistance request includes:
Acquiring any idle thread from a thread connection pool;
analyzing the method body of the medical inquiry auxiliary request by using the arbitrary idle thread to obtain data information carried by the medical inquiry auxiliary request;
acquiring a preset tag, and acquiring information corresponding to the preset tag from the data information as an identity identification code;
And determining the user to be diagnosed by using the identification code.
Because the identity code has uniqueness, the user to be diagnosed can be accurately determined through the identity code, in addition, the medical inquiry auxiliary request is analyzed by directly acquiring an idle thread from the thread connection pool, and the creation time of the thread is saved, so that the analysis speed of the medical inquiry auxiliary request is improved, and the determination efficiency of the user to be diagnosed is improved.
S11, acquiring the illness state text information and illness state image information of the user to be diagnosed.
In at least one embodiment of the present invention, the condition text information includes symptom information communicated by the user to be diagnosed with a medical staff member, and sign information of the user to be diagnosed. Further, the condition image information includes, but is not limited to: and the electrocardiogram, color Doppler ultrasound image and the like of the user to be diagnosed.
In at least one embodiment of the present invention, the electronic device obtaining the textual information of the condition and the image information of the condition of the user to be diagnosed includes one or a combination of more of the following ways:
(1) Downloading a file corresponding to the identification code from a first preset website to serve as the illness state text information, and downloading a file corresponding to the identification code from a second preset website to serve as the illness state image information;
(2) And identifying the medical record book of the user to be diagnosed by utilizing an optical character identification algorithm to obtain the illness state text information, and controlling a medical instrument to acquire illness state image information of the user to be diagnosed.
By the implementation mode, the illness state text information and illness state image information of the user to be diagnosed can be accurately obtained.
S12, identifying the entity in the illness state text information to obtain a target text entity.
In at least one embodiment of the invention, the target text entities include symptom entities and sign entities.
In at least one embodiment of the present invention, the electronic device identifying an entity in the condition text information, and obtaining a target text entity includes:
performing word segmentation processing on the illness state text information to obtain a plurality of word segments;
Converting each word into a word vector, and combining the word vectors according to the sequence of each word in the illness state text information to obtain a vector sequence corresponding to the illness state text information;
extracting the characteristics of the vector sequence by utilizing a two-way long-short term memory network to obtain a first characteristic vector corresponding to each word segment in a forward long-short term memory network and a second characteristic vector corresponding to each word segment in a reverse long-short term memory network;
Splicing the first feature vector and the second feature vector to obtain a target vector corresponding to each word segmentation;
Multiplying each target vector by a preset weight matrix, and adding a preset bias value to obtain a score vector of each word segment, wherein each element in the score vector represents the score of the label corresponding to each word segment;
for each score vector, determining a label corresponding to the element with the highest score as a target label of each word to obtain a plurality of target labels in the illness state text information;
Acquiring target labels corresponding to symptom entities in a preset symptom library from the plurality of target labels as first text entities, and acquiring target labels corresponding to sign entities in a preset sign library from the plurality of target labels as second text entities;
and combining the first text entity and the second text entity to obtain the target text entity.
The target label can be B-PER, E-PER, B-ORG, I-ORG, E-ORG, B-EVE, I-EVE, E-EVE, O and the like.
The label with the highest score is determined to be the target label, so that a plurality of target labels in the illness state text information can be accurately determined, and further the target text entity can be accurately determined through the preset symptom library and the relation between the entity in the preset sign library and the plurality of target labels.
S13, determining a first disease entity associated with the target text entity from a pre-constructed text knowledge graph, and determining a second disease entity associated with the disease image information from a pre-constructed image knowledge graph.
In at least one embodiment of the present invention, the text knowledge graph includes a degree of association between a text entity and a disease entity.
Further, the image knowledge graph comprises a correlation degree between the inspection image and the inspection disease.
In at least one embodiment of the present invention, the medical inquiry assisting method further includes, before determining a second disease entity associated with the disease image information from a pre-constructed image knowledge-graph:
Acquiring a plurality of inspection images by utilizing a web crawler technology, and acquiring a plurality of inspection diseases corresponding to the inspection images;
performing alignment processing on the plurality of inspection images to obtain a plurality of alignment images;
Converting each alignment image into an image vector and each inspection disease into a text vector based on pixels in each alignment image;
calculating the similarity between the image vector and the text vector as the association degree between the examination image and the examination disease;
the image knowledge graph is generated based on the image vector, the examination disease, and the degree of association.
By carrying out alignment processing on the inspection image, inaccuracy of the generated image vector caused by inclination and other problems of the inspection image can be avoided, and further the accuracy of image vector conversion is improved.
In at least one embodiment of the present invention, the determining a second disease entity associated with the disease image information from a pre-constructed image knowledge-graph comprises:
converting the disease image information into disease image vectors;
obtaining disease vectors corresponding to each disease in all diseases from the image knowledge graph;
Calculating the similarity between the disease image vector and each disease vector;
and selecting a disease vector with similarity larger than a preset threshold value as a target disease vector, and determining a disease corresponding to the target disease vector as the second disease entity.
S14, fusing the first disease entity and the second disease entity to obtain a target set.
In at least one embodiment of the invention, the elements in the target set comprise the first disease entity and the second disease entity.
S15, determining the probability of each disease entity in the target set.
In at least one embodiment of the invention, the electronic device determining the probability of each disease entity in the target set comprises:
Acquiring associated text entities associated with each disease entity from the text knowledge graph, and acquiring a first association degree of each disease entity and the associated text entity;
acquiring an associated image corresponding to each disease entity from the image knowledge graph, and acquiring a second association degree of each disease entity and the associated image;
Multiplying the first association degree by the second association degree to obtain a target value of each disease, wherein the target value represents the probability that the associated text entity and the associated image exist in each disease at the same time;
Calculating the sum of target values of all disease entities in the target set to obtain a total value;
dividing the target value for each disease by the total value to obtain a probability for each disease entity.
S16, determining the disease entity with the highest probability as the main disease of the user to be diagnosed, and determining the candidate disease of the user to be diagnosed from the target set according to the probability.
It is emphasized that the primary disease and the candidate disease may also be stored in a blockchain node in order to further ensure privacy and security of the primary disease and the candidate disease.
In at least one embodiment of the present invention, the determining, by the electronic device, the candidate disease of the user to be diagnosed from the target set according to the probability includes:
Sequencing all disease entities in the target set according to the sequence from the big probability to the small probability to obtain a target queue;
Extracting first N disease entities from the target queue to serve as target disease entities, wherein the value of N is a configuration value;
Deleting the main disease from the target disease entity to obtain the candidate disease.
By the above embodiment, the candidate diseases can be rapidly determined.
In at least one embodiment of the present invention, after determining the disease with the highest probability as the primary disease of the user to be diagnosed and determining the candidate disease from the target set according to the probability, the medical inquiry assisting method further includes:
Acquiring user information of the user to be diagnosed, and generating information to be confirmed according to the user information, the main diseases and the candidate diseases;
the information to be confirmed is sent to terminal equipment of the appointed contact person;
when the confirmation information sent by the terminal equipment is received within the preset time, extracting the confirmed disease from the confirmation information;
generating a diagnostic report according to the user information and the diagnosed disease;
encrypting the diagnosis report by adopting a symmetric encryption algorithm to obtain a ciphertext;
And storing the mapping relation between the user information and the ciphertext, and sending the ciphertext to the client of the user to be diagnosed.
By analyzing the confirmation information, the accuracy of the diagnosis report can be ensured, and the accuracy of the inquiry assistance can be improved.
According to the technical scheme, when the disease text information and the disease image information of the user to be diagnosed are analyzed, the analysis of the disease image information is added, so that the analysis of the disease image information is not limited to the analysis of the text information, the accuracy of inquiry assistance can be improved, and further, the target set comprising the first disease entity and the second disease entity can be comprehensively obtained through the text knowledge graph and the image knowledge graph, and the comprehensiveness is improved. In addition, by analyzing the probability of each disease entity in the target set and determining the disease entity with the highest probability as the main disease, and selecting the candidate disease from the target set, the medical staff can confirm the confirmed disease again, so that the invention can provide inquiry assistance for the medical staff, and further can improve the inquiry efficiency of the medical staff.
Fig. 2 is a functional block diagram of a preferred embodiment of the medical aid of the present invention. The medical inquiry assisting apparatus 11 includes a determination unit 110, an acquisition unit 111, an identification unit 112, a fusion unit 113, a processing unit 114, a conversion unit 115, a calculation unit 116, a generation unit 117, a transmission unit 118, an extraction unit 119, and an encryption unit 120. The module/unit referred to in the present invention refers to a series of computer program segments capable of being executed by the processor 13 and of performing a fixed function, which are stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.
When receiving the medical inquiry assistance request, the determination unit 110 determines the user to be diagnosed according to the medical inquiry assistance request.
In at least one embodiment of the present invention, the request for assistance in a medical care may be triggered by a medical staff member or may be triggered at a predetermined time, which is not limited by the present invention.
Further, the information carried by the auxiliary request for medical inquiry includes, but is not limited to: identification codes, preset labels, etc.
In at least one embodiment of the present invention, the determining unit 110 determines the user to be diagnosed according to the medical consultation assistance request includes:
Acquiring any idle thread from a thread connection pool;
analyzing the method body of the medical inquiry auxiliary request by using the arbitrary idle thread to obtain data information carried by the medical inquiry auxiliary request;
acquiring a preset tag, and acquiring information corresponding to the preset tag from the data information as an identity identification code;
And determining the user to be diagnosed by using the identification code.
Because the identity code has uniqueness, the user to be diagnosed can be accurately determined through the identity code, in addition, the medical inquiry auxiliary request is analyzed by directly acquiring an idle thread from the thread connection pool, and the creation time of the thread is saved, so that the analysis speed of the medical inquiry auxiliary request is improved, and the determination efficiency of the user to be diagnosed is improved.
The acquiring unit 111 acquires the condition text information and condition image information of the user to be diagnosed.
In at least one embodiment of the present invention, the condition text information includes symptom information communicated by the user to be diagnosed with a medical staff member, and sign information of the user to be diagnosed. Further, the condition image information includes, but is not limited to: and the electrocardiogram, color Doppler ultrasound image and the like of the user to be diagnosed.
In at least one embodiment of the present invention, the acquiring unit 111 acquires the condition text information and condition image information of the user to be diagnosed, including one or more of the following combinations:
(1) Downloading a file corresponding to the identification code from a first preset website to serve as the illness state text information, and downloading a file corresponding to the identification code from a second preset website to serve as the illness state image information;
(2) And identifying the medical record book of the user to be diagnosed by utilizing an optical character identification algorithm to obtain the illness state text information, and controlling a medical instrument to acquire illness state image information of the user to be diagnosed.
By the implementation mode, the illness state text information and illness state image information of the user to be diagnosed can be accurately obtained.
The recognition unit 112 recognizes the entity in the illness state text information, and obtains a target text entity.
In at least one embodiment of the invention, the target text entities include symptom entities and sign entities.
In at least one embodiment of the present invention, the identifying unit 112 identifies an entity in the illness state text information, and obtaining the target text entity includes:
performing word segmentation processing on the illness state text information to obtain a plurality of word segments;
Converting each word into a word vector, and combining the word vectors according to the sequence of each word in the illness state text information to obtain a vector sequence corresponding to the illness state text information;
extracting the characteristics of the vector sequence by utilizing a two-way long-short term memory network to obtain a first characteristic vector corresponding to each word segment in a forward long-short term memory network and a second characteristic vector corresponding to each word segment in a reverse long-short term memory network;
Splicing the first feature vector and the second feature vector to obtain a target vector corresponding to each word segmentation;
Multiplying each target vector by a preset weight matrix, and adding a preset bias value to obtain a score vector of each word segment, wherein each element in the score vector represents the score of the label corresponding to each word segment;
for each score vector, determining a label corresponding to the element with the highest score as a target label of each word to obtain a plurality of target labels in the illness state text information;
Acquiring target labels corresponding to symptom entities in a preset symptom library from the plurality of target labels as first text entities, and acquiring target labels corresponding to sign entities in a preset sign library from the plurality of target labels as second text entities;
and combining the first text entity and the second text entity to obtain the target text entity.
The target label can be B-PER, E-PER, B-ORG, I-ORG, E-ORG, B-EVE, I-EVE, E-EVE, O and the like.
The label with the highest score is determined to be the target label, so that a plurality of target labels in the illness state text information can be accurately determined, and further the target text entity can be accurately determined through the preset symptom library and the relation between the entity in the preset sign library and the plurality of target labels.
The determining unit 110 determines a first disease entity associated with the target text entity from a pre-constructed text knowledge-graph and a second disease entity associated with the disease image information from a pre-constructed image knowledge-graph.
In at least one embodiment of the present invention, the text knowledge graph includes a degree of association between a text entity and a disease entity.
Further, the image knowledge graph comprises a correlation degree between the inspection image and the inspection disease.
In at least one embodiment of the present invention, the acquisition unit 111 acquires a plurality of inspection images using web crawler technology and acquires a plurality of inspection diseases corresponding to the plurality of inspection images before determining a second disease entity associated with the disease image information from a pre-constructed image knowledge graph;
The processing unit 114 performs alignment processing on the plurality of inspection images to obtain a plurality of alignment images;
The conversion unit 115 converts each alignment image into an image vector based on the pixels in each alignment image, and converts each inspection disease into a text vector;
The calculation unit 116 calculates the similarity of the image vector and the text vector as the association degree of the examination image and the examination disease;
The generation unit 117 generates the image knowledge map based on the image vector, the inspection disease, and the degree of association.
By carrying out alignment processing on the inspection image, inaccuracy of the generated image vector caused by inclination and other problems of the inspection image can be avoided, and further the accuracy of image vector conversion is improved.
In at least one embodiment of the present invention, the determining unit 110 determines the second disease entity associated with the disease image information from a pre-constructed image knowledge-graph includes:
converting the disease image information into disease image vectors;
obtaining disease vectors corresponding to each disease in all diseases from the image knowledge graph;
Calculating the similarity between the disease image vector and each disease vector;
and selecting a disease vector with similarity larger than a preset threshold value as a target disease vector, and determining a disease corresponding to the target disease vector as the second disease entity.
The fusion unit 113 fuses the first disease entity and the second disease entity to obtain a target set.
In at least one embodiment of the invention, the elements in the target set comprise the first disease entity and the second disease entity.
The determination unit 110 determines a probability for each disease entity in the target set.
In at least one embodiment of the present invention, the determining unit 110 determines a probability of each disease entity in the target set comprises:
Acquiring associated text entities associated with each disease entity from the text knowledge graph, and acquiring a first association degree of each disease entity and the associated text entity;
acquiring an associated image corresponding to each disease entity from the image knowledge graph, and acquiring a second association degree of each disease entity and the associated image;
Multiplying the first association degree by the second association degree to obtain a target value of each disease, wherein the target value represents the probability that the associated text entity and the associated image exist in each disease at the same time;
Calculating the sum of target values of all disease entities in the target set to obtain a total value;
dividing the target value for each disease by the total value to obtain a probability for each disease entity.
The determining unit 110 determines a disease entity with the highest probability as a primary disease of the user to be diagnosed, and determines a candidate disease of the user to be diagnosed from the target set according to the probability.
It is emphasized that the primary disease and the candidate disease may also be stored in a blockchain node in order to further ensure privacy and security of the primary disease and the candidate disease.
In at least one embodiment of the present invention, the determining unit 110 determines the candidate disease of the user to be diagnosed from the target set according to the probability includes:
Sequencing all disease entities in the target set according to the sequence from the big probability to the small probability to obtain a target queue;
Extracting first N disease entities from the target queue to serve as target disease entities, wherein the value of N is a configuration value;
Deleting the main disease from the target disease entity to obtain the candidate disease.
By the above embodiment, the candidate diseases can be rapidly determined.
In at least one embodiment of the present invention, after determining a disease with the highest probability as a primary disease of the user to be diagnosed and determining a candidate disease from the target set according to the probability, the obtaining unit 111 obtains user information of the user to be diagnosed and generates information to be confirmed according to the user information, the primary disease and the candidate disease;
the sending unit 118 sends the information to be confirmed to the terminal equipment of the appointed contact person;
When receiving the confirmation information sent by the terminal device within a preset time, the extraction unit 119 extracts a confirmed disease from the confirmation information;
The generating unit 117 generates a diagnosis report based on the user information and the diagnosed disease;
The encryption unit 120 performs encryption processing on the diagnosis report by adopting a symmetric encryption algorithm to obtain a ciphertext;
the sending unit 118 stores the mapping relationship between the user information and the ciphertext, and sends the ciphertext to the client of the user to be diagnosed.
By analyzing the confirmation information, the accuracy of the diagnosis report can be ensured, and the accuracy of the inquiry assistance can be improved.
According to the technical scheme, when the disease text information and the disease image information of the user to be diagnosed are analyzed, the analysis of the disease image information is added, so that the analysis of the disease image information is not limited to the analysis of the text information, the accuracy of inquiry assistance can be improved, and further, the target set comprising the first disease entity and the second disease entity can be comprehensively obtained through the text knowledge graph and the image knowledge graph, and the comprehensiveness is improved. In addition, by analyzing the probability of each disease entity in the target set and determining the disease entity with the highest probability as the main disease, and selecting the candidate disease from the target set, the medical staff can confirm the confirmed disease again, so that the invention can provide inquiry assistance for the medical staff, and further can improve the inquiry efficiency of the medical staff.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing the medical consultation assistance method.
In one embodiment of the invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and a computer program, such as a medical consultation assistance program, stored in the memory 12 and executable on the processor 13.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and may include more or less components than illustrated, or may combine certain components, or different components, e.g. the electronic device 1 may further include input-output devices, network access devices, buses, etc.
The Processor 13 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is an operation core and a control center of the electronic device 1, connects various parts of the entire electronic device 1 using various interfaces and lines, and executes an operating system of the electronic device 1 and various installed applications, program codes, etc.
The processor 13 executes the operating system of the electronic device 1 and various types of applications installed. The processor 13 executes the application program to implement the steps of the various embodiments of the medical consultation assistance method described above, such as the steps shown in figure 1.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules/units may be a series of instruction segments of a computer program capable of performing a specific function for describing the execution of the computer program in the electronic device 1. For example, the computer program may be divided into a determining unit 110, an acquiring unit 111, an identifying unit 112, a fusing unit 113, a processing unit 114, a converting unit 115, a calculating unit 116, a generating unit 117, a transmitting unit 118, an extracting unit 119, and an encrypting unit 120.
The memory 12 may be used to store the computer program and/or module, and the processor 13 may implement various functions of the electronic device 1 by running or executing the computer program and/or module stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, the memory 12 may include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a physical memory, such as a memory bank, a TF card (Trans-FLASH CARD), or the like.
The integrated modules/units of 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. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above.
Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. 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 blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In connection with fig. 1, the memory 12 in the electronic device 1 stores a plurality of instructions to implement a medical consultation assistance method, the processor 13 being executable to implement:
When a medical inquiry auxiliary request is received, determining a user to be diagnosed according to the medical inquiry auxiliary request;
acquiring illness state text information and illness state image information of the user to be diagnosed;
identifying an entity in the illness state text information to obtain a target text entity;
determining a first disease entity associated with the target text entity from a pre-constructed text knowledge-graph and a second disease entity associated with the condition image information from a pre-constructed image knowledge-graph;
fusing the first disease entity and the second disease entity to obtain a target set;
Determining a probability of each disease entity in the target set;
and determining the disease entity with the highest probability as the main disease of the user to be diagnosed, and determining the candidate disease of the user to be diagnosed from the target set according to the probability.
Specifically, the specific implementation method of the above instructions by the processor 13 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed systems, devices, and methods 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.
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.
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 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 (9)
1. A medical consultation assistance method, characterized in that the medical consultation assistance method comprises:
When a medical inquiry auxiliary request is received, determining a user to be diagnosed according to the medical inquiry auxiliary request;
acquiring illness state text information and illness state image information of the user to be diagnosed;
identifying an entity in the illness state text information to obtain a target text entity;
Determining a first disease entity associated with the target text entity from a pre-constructed text knowledge-graph and a second disease entity associated with the condition image information from a pre-constructed image knowledge-graph, comprising: converting the disease image information into disease image vectors; obtaining disease vectors corresponding to each disease in all diseases from the image knowledge graph; calculating the similarity between the disease image vector and each disease vector; selecting a disease vector with similarity larger than a preset threshold as a target disease vector, and determining a disease corresponding to the target disease vector as the second disease entity;
fusing the first disease entity and the second disease entity to obtain a target set;
Determining a probability of each disease entity in the target set;
Determining a disease entity with the highest probability as a main disease of the user to be diagnosed, and determining candidate diseases of the user to be diagnosed from the target set according to the probability;
wherein prior to determining a second disease entity associated with the disease image information from a pre-constructed image knowledge graph, the medical interrogation assistance method further comprises: acquiring a plurality of inspection images by utilizing a web crawler technology, and acquiring a plurality of inspection diseases corresponding to the inspection images; performing alignment processing on the plurality of inspection images to obtain a plurality of alignment images; converting each alignment image into an image vector and each inspection disease into a text vector based on pixels in each alignment image; calculating the similarity between the image vector and the text vector as the association degree between the examination image and the examination disease; the image knowledge graph is generated based on the image vector, the examination disease, and the degree of association.
2. The method of assisting in medical interrogation as claimed in claim 1, wherein said determining a user to be diagnosed from said request for assisting in medical interrogation comprises:
Acquiring any idle thread from a thread connection pool;
analyzing the method body of the medical inquiry auxiliary request by using the arbitrary idle thread to obtain data information carried by the medical inquiry auxiliary request;
acquiring a preset tag, and acquiring information corresponding to the preset tag from the data information as an identity identification code;
And determining the user to be diagnosed by using the identification code.
3. The medical consultation assistance method of claim 2, wherein the obtaining of the textual information and the image information of the condition of the user to be diagnosed includes one or more of the following:
Downloading a file corresponding to the identification code from a first preset website to serve as the illness state text information, and downloading a file corresponding to the identification code from a second preset website to serve as the illness state image information; and/or
And identifying the medical record book of the user to be diagnosed by utilizing an optical character identification algorithm to obtain the illness state text information, and controlling a medical instrument to acquire illness state image information of the user to be diagnosed.
4. The medical consultation assistance method of claim 1 wherein said identifying an entity in said condition text information to obtain a target text entity includes:
performing word segmentation processing on the illness state text information to obtain a plurality of word segments;
Converting each word into a word vector, and combining the word vectors according to the sequence of each word in the illness state text information to obtain a vector sequence corresponding to the illness state text information;
extracting the characteristics of the vector sequence by utilizing a two-way long-short term memory network to obtain a first characteristic vector corresponding to each word segment in a forward long-short term memory network and a second characteristic vector corresponding to each word segment in a reverse long-short term memory network;
Splicing the first feature vector and the second feature vector to obtain a target vector corresponding to each word segmentation;
Multiplying each target vector by a preset weight matrix, and adding a preset bias value to obtain a score vector of each word segment, wherein each element in the score vector represents the score of the label corresponding to each word segment;
for each score vector, determining a label corresponding to the element with the highest score as a target label of each word to obtain a plurality of target labels in the illness state text information;
Acquiring target labels corresponding to symptom entities in a preset symptom library from the plurality of target labels as first text entities, and acquiring target labels corresponding to sign entities in a preset sign library from the plurality of target labels as second text entities;
and combining the first text entity and the second text entity to obtain the target text entity.
5. The method of assisting in medical interrogation of claim 1, wherein said determining the probability of each disease entity in the target set comprises:
Acquiring associated text entities associated with each disease entity from the text knowledge graph, and acquiring a first association degree of each disease entity and the associated text entity;
acquiring an associated image corresponding to each disease entity from the image knowledge graph, and acquiring a second association degree of each disease entity and the associated image;
Multiplying the first association degree by the second association degree to obtain a target value of each disease, wherein the target value represents the probability that the associated text entity and the associated image exist in each disease at the same time;
Calculating the sum of target values of all disease entities in the target set to obtain a total value;
dividing the target value for each disease by the total value to obtain a probability for each disease entity.
6. The medical consultation assistance method of claim 1, wherein after determining a disease with a highest probability as a primary disease of the user to be diagnosed and determining a candidate disease from the target set according to the probability, the medical consultation assistance method further includes:
Acquiring user information of the user to be diagnosed, and generating information to be confirmed according to the user information, the main diseases and the candidate diseases;
the information to be confirmed is sent to terminal equipment of the appointed contact person;
when the confirmation information sent by the terminal equipment is received within the preset time, extracting the confirmed disease from the confirmation information;
generating a diagnostic report according to the user information and the diagnosed disease;
encrypting the diagnosis report by adopting a symmetric encryption algorithm to obtain a ciphertext;
And storing the mapping relation between the user information and the ciphertext, and sending the ciphertext to the client of the user to be diagnosed.
7. A medical consultation assistance device, characterized in that the medical consultation assistance device comprises:
a determining unit, configured to determine a user to be diagnosed according to a medical inquiry assistance request when the medical inquiry assistance request is received;
The acquisition unit is used for acquiring the illness state text information and illness state image information of the user to be diagnosed;
the identification unit is used for identifying the entity in the illness state text information to obtain a target text entity;
the determining unit is further configured to determine a first disease entity associated with the target text entity from a pre-constructed text knowledge graph, and determine a second disease entity associated with the disease image information from a pre-constructed image knowledge graph, including: converting the disease image information into disease image vectors; obtaining disease vectors corresponding to each disease in all diseases from the image knowledge graph; calculating the similarity between the disease image vector and each disease vector; selecting a disease vector with similarity larger than a preset threshold as a target disease vector, and determining a disease corresponding to the target disease vector as the second disease entity;
the fusion unit is used for fusing the first disease entity and the second disease entity to obtain a target set;
the determining unit is further configured to determine a probability of each disease entity in the target set;
The determining unit is further configured to determine a disease entity with the highest probability as a primary disease of the user to be diagnosed, and determine a candidate disease of the user to be diagnosed from the target set according to the probability;
Wherein the medical inquiry assisting apparatus further comprises, before determining a second disease entity associated with the disease image information from a pre-constructed image knowledge graph: the acquisition unit is further used for acquiring a plurality of inspection images by utilizing a web crawler technology and acquiring a plurality of inspection diseases corresponding to the inspection images; the processing unit is used for carrying out alignment processing on the plurality of inspection images to obtain a plurality of alignment images; a conversion unit configured to convert each of the aligned images into an image vector and each of the inspection diseases into a text vector based on pixels in each of the aligned images; a calculation unit configured to calculate a similarity between the image vector and the text vector as a degree of association between the inspection image and the inspection disease; and the generation unit is used for generating the image knowledge graph based on the image vector, the checked diseases and the association degree.
8. An electronic device, the electronic device comprising:
a memory storing at least one instruction; and
A processor executing instructions stored in the memory to implement the medical interrogation assistance method of any one of claims 1 to 6.
9. A computer-readable storage medium, characterized by: the computer-readable storage medium having stored therein at least one instruction for execution by a processor in an electronic device to implement the medical interrogation assistance method of any one of claims 1-6.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010645468.1A CN111816301B (en) | 2020-07-07 | Medical inquiry assisting method, device, electronic equipment and medium | |
| PCT/CN2020/111914 WO2021114736A1 (en) | 2020-07-07 | 2020-08-27 | Medical consultation assistance method and apparatus, electronic device, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010645468.1A CN111816301B (en) | 2020-07-07 | Medical inquiry assisting method, device, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111816301A CN111816301A (en) | 2020-10-23 |
| CN111816301B true CN111816301B (en) | 2024-07-02 |
Family
ID=
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685102A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Breast lesion image classification method, device, computer equipment and storage medium |
| CN110504028A (en) * | 2019-08-22 | 2019-11-26 | 上海软中信息系统咨询有限公司 | A kind of disease way of inquisition, device, system, computer equipment and storage medium |
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109685102A (en) * | 2018-11-13 | 2019-04-26 | 平安科技（深圳）有限公司 | Breast lesion image classification method, device, computer equipment and storage medium |
| CN110504028A (en) * | 2019-08-22 | 2019-11-26 | 上海软中信息系统咨询有限公司 | A kind of disease way of inquisition, device, system, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021114736A1 (en) | Medical consultation assistance method and apparatus, electronic device, and medium | |
| CN112417096B (en) | Question-answer pair matching method, device, electronic equipment and storage medium | |
| CN111985241B (en) | Medical information query method, device, electronic equipment and medium | |
| WO2021120688A1 (en) | Medical misdiagnosis detection method and apparatus, electronic device and storage medium | |
| CN111949708B (en) | Multi-task prediction method, device, equipment and medium based on time sequence feature extraction | |
| CN112232203B (en) | Pedestrian recognition method and device, electronic equipment and storage medium | |
| CN111986763B (en) | Disease data analysis method, device, electronic equipment and storage medium | |
| CN114462412B (en) | Entity identification method, entity identification device, electronic equipment and storage medium | |
| WO2023109631A1 (en) | Data processing method and apparatus, device, storage medium, and program product | |
| CN113470775B (en) | Information acquisition method, device, equipment and storage medium | |
| CN112199494B (en) | Medical information searching method, device, electronic equipment and storage medium | |
| CN113724830B (en) | Medication risk detection method based on artificial intelligence and related equipment | |
| CN112052409B (en) | Address resolution method, device, equipment and medium | |
| CN112435745B (en) | Method and device for recommending treatment strategy, electronic equipment and storage medium | |
| CN111816301B (en) | Medical inquiry assisting method, device, electronic equipment and medium | |
| CN114360732B (en) | Medical data analysis method, device, electronic equipment and storage medium | |
| CN111933241B (en) | Medical data analysis method, device, electronic equipment and storage medium | |
| CN116612849A (en) | Medical treatment scheme recommendation method, device, equipment and storage medium | |
| CN113627186B (en) | Entity relation detection method based on artificial intelligence and related equipment | |
| CN113420143B (en) | Method, device, equipment and storage medium for generating document abstract | |
| CN113326365B (en) | Reply sentence generation method, device, equipment and storage medium | |
| CN113408265B (en) | Semantic analysis method, device and equipment based on human-computer interaction and storage medium | |
| CN115169360A (en) | User intention identification method based on artificial intelligence and related equipment | |
| CN112199493B (en) | Medication accuracy determining method and device, electronic equipment and storage medium | |
| CN113688119B (en) | Medical database construction method based on artificial intelligence and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |