CN112037905A

CN112037905A - Medical question answering method, equipment and storage medium

Info

Publication number: CN112037905A
Application number: CN202010685557.9A
Authority: CN
Inventors: 朱卫国; 李源杰; 郭安辉
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-07-16
Filing date: 2020-07-16
Publication date: 2020-12-04
Anticipated expiration: 2040-07-16
Also published as: CN112037905B

Abstract

The embodiment of the invention provides a medical question answering method, equipment and a storage medium, wherein the method comprises the following steps: receiving a target key field input by a user through a search input box in a home page operation interface; semantic analysis is carried out on the target key field to obtain the target entity attribute corresponding to the target key field; determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base; responding to the click operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the target question, the target answer and the tracing data are references. After the user searches the answer, the accuracy of the answer can be determined by taking the tracing data as a basis, the method can be applied to search in the medical field, and the experience of searching the answer in the medical field is improved.

Description

Medical question answering method, equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a medical question answering method, medical question answering equipment and a storage medium.

Background

With the maturity of artificial intelligence technology, natural language processing technology has also been rapidly developed. Natural speech processing techniques are an important direction in the field of artificial intelligence. It can realize effective communication between human and computer by natural language. The question-answering system is a system which takes natural language understanding technology as a core, completes analysis and processing of user questions and generates correct answers.

When the current question-answering system faces the user question, the pushed answers are various. For each answer, the user does not determine whether the answer is accurate or not. In some professional fields, such as medical fields, this will cause great trouble to users, so that users cannot accurately distinguish answers, and the question-answering experience of users is affected.

Disclosure of Invention

The embodiment of the invention provides a medical question-answering method, equipment and a storage medium, which solve the technical problems that in the prior art, whether each answer user is accurate or not is not judged according to the answer, so that in some professional fields, such as the medical field, the answer cannot be accurately distinguished by the user, and the question-answering experience of the user is influenced.

In a first aspect, an embodiment of the present invention provides a medical question answering method, including:

receiving a target key field input by a user through a search input box in a home page operation interface;

performing semantic analysis on the target key field to acquire a target entity attribute corresponding to the target key field;

determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base;

responding to the click operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the system comprises a target question, a target answer and tracing data, wherein the tracing data are references.

Further, the method as described above, the pre-constructed knowledge base is a knowledge graph;

the step of determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base comprises the following steps:

acquiring a candidate triple set from the pre-constructed knowledge graph according to the target entity attribute, wherein the candidate triple set comprises at least one candidate triple;

matching the target entity attribute and the candidate triple by adopting a matching model to obtain a candidate triple meeting the matching requirement as a target triple;

and acquiring the target question-answer pairs corresponding to the target triples from the pre-constructed knowledge graph.

Further, before determining at least one target question-answer pair satisfying the matching requirement according to the target entity attribute and the pre-constructed knowledge base, the method further includes:

acquiring document types and format information which are configured by medical professionals through a configuration interface and meet accurate requirements in a preset medical field;

acquiring the constructed corpus of the knowledge graph according to the document types and the format information meeting the accuracy requirements;

receiving a schema set in the medical field input by a medical professional through a configuration interface;

extracting the constructing three-tuple data in the schema set range from the constructing corpus;

acquiring a constructed question-answer pair corresponding to the constructed triple data;

and constructing a knowledge graph according to the constructed ternary group data and the corresponding constructed question-answer pairs.

Further, before constructing the knowledge graph according to the constructed triple data and the corresponding constructed question-answer pairs, the method further includes:

sending the constructed ternary group data and the corresponding constructed question-answer pairs to a user terminal corresponding to a medical professional so that the user terminal displays the constructed ternary group data and the corresponding constructed question-answer pairs for the medical professional to check;

receiving an audit result sent by the user terminal;

if the verification result is determined to be not passed, acquiring the corrected construction ternary group data and the corresponding construction question-answer pair;

correspondingly, the constructing a knowledge graph according to the constructed triple data and the corresponding constructed question-answer pairs comprises the following steps:

and constructing a knowledge graph according to the modified constructed triple data and the corresponding constructed question-answer pairs.

Further, the method as described above, further comprising:

responding to the triggering operation of a user through a question option in the home page operation interface, and displaying a question-answer pair recording interface;

responding to the submitting operation of the recorded question-answer pairs input by the user on the question-answer pair recording interface, and judging whether the user is a medical professional or not;

and if the user is determined to be a medical professional, extracting the record triple corresponding to the record question-answer pair, and updating the record question-answer pair and the corresponding record triple into a knowledge base.

Further, the method as described above, further comprising:

responding to the triggering operation of the user management options in the home page operation interface by the user, and displaying a user management interface;

responding to the triggering operation of the user through the question options in the user management interface, and displaying the option of the to-be-submitted audit question and the option of the submitted audit question;

responding to the triggering operation of the user on the option of the to-be-submitted audit problem, displaying an interface of the to-be-submitted audit problem, inputting the to-be-submitted audit problem through the interface of the to-be-submitted audit and the submitting operation after a certain medical professional is selected, sending the to-be-submitted audit problem to the interface of the to-be-submitted audit problem corresponding to the medical professional, and handing over the to-be-submitted audit problem to the interface of the to-be-submitted audit problem corresponding to the user;

if the post-audit answer and the tracing data corresponding to the audit question to be submitted, which are sent by the user terminal corresponding to the medical professional, are received within a preset time period, updating the corresponding audit question-answer pair into the knowledge base;

and if the post-audit answer and the tracing data corresponding to the audit question to be submitted, which are sent by the user terminal corresponding to the medical professional, are not received within a preset time period, distributing the audit question to be submitted to other medical professionals according to a preset distribution rule, and updating the corresponding audit question and answer pair into the knowledge base after the post-audit answer and the tracing data corresponding to the audit question to be submitted are sent by the user terminal corresponding to the other medical professionals.

Further, the method as described above, further comprising:

responding to the triggering operation of the user through the friend invitation option in the user management interface, and displaying a friend invitation operation interface, wherein the friend invitation operation interface comprises an invitation code;

responding to the triggering operation of the user on the sharing option in the friend invitation operation interface, and jumping to a sharing interface of a preset application program to enable the friend to register through an invitation code in the sharing interface.

Further, the method as described above, further comprising:

responding to the triggering operation of a user through a medical professional authentication option in the user management interface, and displaying a medical professional authentication interface;

performing medical professional authentication on a user in response to a department category, a professional level and an authentication certificate which are input by the user on a medical professional authentication interface;

and if the user passes the authentication, adding the user into a selection catalogue of the medical professional to be submitted by an auditing interface.

In a second aspect, an embodiment of the present invention provides a medical question answering apparatus, including:

a memory, a processor, and a computer program;

wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of the first aspects.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of the first aspect.

The embodiment of the invention provides a medical question answering method, equipment and a storage medium, which receives a target key field input by a user through a search input box in a homepage operation interface; semantic analysis is carried out on the target key field to obtain the target entity attribute corresponding to the target key field; determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base; responding to the click operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the target question, the target answer and the tracing data are references. Because each question-answer pair has the tracing data corresponding to the answer in the pre-constructed knowledge base, and the form of the tracing data is the form of the reference document, the accuracy and the traceability of the answer of each question can be ensured, so that the accuracy of the answer can be determined by taking the tracing data as the basis after the user searches the answer, the method can be applied to the search in the medical field, and the experience of searching the answer in the medical field is improved.

It should be understood that what is described in the summary above is not intended to limit key or critical features of embodiments of the invention, nor is it intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.

Fig. 1 is a flowchart of a medical question answering method according to an embodiment of the present invention;

fig. 2 is a schematic view of a home page operation interface in the medical question answering method according to the embodiment of the present invention;

fig. 3 is a schematic view of a display interface of a target question-answer pair in the medical question-answer method according to the embodiment of the present invention;

fig. 4 is a flowchart of a medical question answering method according to a second embodiment of the present invention;

fig. 5 is a flowchart of a medical question answering method according to a third embodiment of the present invention;

fig. 6 is a schematic diagram of a question-answer pair recording interface in the medical question-answer method according to the embodiment of the present invention;

fig. 7 is a flowchart of a medical question answering method according to a fourth embodiment of the present invention;

fig. 8 is a flowchart of a medical question answering method according to a fifth embodiment of the present invention;

fig. 9 is a flowchart of a medical question answering method according to a sixth embodiment of the present invention;

fig. 10 is a schematic diagram of a medical professional authentication interface in the medical question-answering method according to the embodiment of the present invention;

fig. 11 is a schematic structural diagram of a medical question answering apparatus according to a seventh embodiment of the present invention;

fig. 12 is a schematic structural diagram of a medical question answering apparatus according to an eighth embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and the embodiments of the present invention are illustrative only and are not intended to limit the scope of the present invention.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, and in the above-described drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

First, an application scenario of the embodiment of the present invention is explained. Specifically, the medical question answering method provided by the embodiment of the invention can provide services for users by adopting clients or webpages. Such as applications on a smartphone, computer, or other electronic device. In an application scenario, when a user has a search requirement for answers corresponding to medical questions and answers, the medical question and answer method provided by the embodiment of the invention can be adopted. Specifically, the target key field can be input through a search input box in a home page operation interface in a client or a webpage so as to search and query the medical answer. Or in another application scenario, when the user has a special question asking demand for medical knowledge, the medical question answering method provided by the embodiment of the invention can be adopted. Specifically, the question to be submitted may be input through a to-be-submitted review interface under a user management interface in the client or the web page, and a certain medical professional may be selected, and the medical professional may answer the question to be submitted. It is understood that if the medical professional does not reply to the to-be-submitted question within the preset time period, other medical professionals may reply to the to-be-submitted question. Or in another application scenario, when the user is a medical professional, the medical question-answering method provided by the embodiment of the present invention may be adopted after medical questions are encountered in clinical or academic research and accurate answers are found by searching documents. Specifically, the recorded questions and answers can be submitted through a question-answer recording interface in the client or the webpage, and the tracing data of the answers is recorded. So as to be shared with other users when the other users perform answer search of the question.

It can be understood that the application scenario of the medical question answering method provided in this embodiment is also other application scenarios, which is not limited in this embodiment.

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

Example one

Fig. 1 is a flowchart of a medical question-answering method according to an embodiment of the present invention, and as shown in fig. 1, an execution main body of the medical question-answering method according to the embodiment is a medical question-answering device, which may be integrated in an electronic device, and the electronic device may be a smart phone, a computer, or other device with independent computing and processing capabilities. The medical question answering method provided by the embodiment includes the following steps.

Step 101, receiving a target key field input by a user through a search input box in a home page operation interface.

The user is the user of the medical question-answering method, and the user can be a medical professional, such as a doctor or a medical researcher. Or may be a person without medical professional knowledge, such as a patient, a health person, etc., and the user is not limited in this embodiment.

Specifically, in this embodiment, after the user opens the client or the web page corresponding to the medical question and answer method provided in this embodiment, the user enters the homepage operation interface. As shown in fig. 2, a search input box is included at the upper end of the home page operation interface, and a user can input a target key field in the search input box by clicking the search input box and receive the target key field input by the user by clicking a key for confirming a search.

Wherein, the target key field is a key field in the target question. The target question is a question for which the user needs to search for an answer. It will be appreciated that the target key field may also be the target issue.

As shown in fig. 2, besides the search input box, the homepage operation interface may further include question-answer pairs pushed to the user by at least one dimension. Such as at least one dimension may include: hot spot recommendation dimensions, attention dimensions, topic dimensions, and the like. Controls for these dimensions may be disposed below the search input box. And the user clicks the control of a certain dimension, and at least one question and answer pair pushed to the user by the dimension is displayed in the operation interface.

It can be understood that, in order to display as many question and answer pairs as possible in the homepage operation interface, the answers may be briefly displayed, and after receiving the click operation of the user on a certain question and answer pair, the user enters the interface of the question and answer pair, and the question, the detailed answer, and the trace data are displayed in the interface. The retrospective data may be a reference to the answer. Such as a paper entitled xx published at a time in a journal published by a publisher in the reference. It is understood that the answer reference may be one or more.

It should be noted that, the lowest part of the home page operation interface may further include a focus option, a question option, a favorite option, and a user management option, where the user management option is a "my" option in fig. 2. And after the user clicks each option to enter the corresponding operation interface, the corresponding function is realized by operating in the operation interface.

It can be understood that before the user clicks the attention control to view the pushed at least one question-answer pair, the user can enter the attention configuration operation interface by triggering the attention option below the home page operation interface to configure the department concerned.

And 102, performing semantic analysis on the target key field to acquire the target entity attribute corresponding to the target key field.

Specifically, in this embodiment, semantic parsing is performed on the target key field, including performing entity extraction and intention identification on the target key field, and after the entity extraction and the intention identification, the target entity attribute corresponding to the target key field is obtained.

And 103, determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base.

In this embodiment, the pre-constructed knowledge base may include a large number of question-answer pairs, each question-answer pair includes not only a question and an answer, but also includes the retroactive data of the answer, and the retroactive data is a reference document, that is, the answer of each question is obtained from the reference document, so as to ensure the accuracy and traceability of the answer.

Specifically, in this embodiment, as an optional implementation, the questions in each question-answer pair are subjected to semantic parsing to obtain the entity attribute of each question. And then matching the target entity attribute with the entity attribute of each question to obtain the matching degree of the target entity attribute and the entity attribute of each question. And judging whether the matching degree meets the matching requirement, and if so, taking the question-answer pair corresponding to at least one question-answer meeting the matching requirement as a target question-answer pair.

After the target question-answer pairs are determined, if the target question-answer pairs are multiple, the target question-answer pairs can be arranged in sequence on the search result display interface according to the matching degree for simple display.

Step 104, responding to the triggering operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the target question, the target answer and the tracing data are references.

Specifically, in this embodiment, the user clicks a certain target question-answer pair on the search result display interface, and in response to the user's trigger operation on the target question-answer pair, jumps to the display interface of the target question-answer pair, and displays the target question-answer pair on the display interface of the target question-answer pair.

As shown in fig. 3, the target question may be displayed first, then the target answer may be displayed, and finally the retrospective data of the target answer may be displayed. This retrospective data is a reference. For example, after searching for the target key field of "how to evaluate liver function", the target question searched out is "how to evaluate liver function". The target answer is shown in fig. 3. It can be understood that, if the content of the target answer is more, the user may implement the full display of the target answer through a sliding operation. And displaying the tracing data below the target answer, wherein the tracing data is a reference.

In the medical question-answering method provided by the embodiment, the target key fields input by a user through the search input box in the homepage operation interface are received; semantic analysis is carried out on the target key field to obtain the target entity attribute corresponding to the target key field; determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base; responding to the click operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the target question, the target answer and the tracing data are references. Because each question-answer pair has the tracing data corresponding to the answer in the pre-constructed knowledge base, and the form of the tracing data is the form of the reference document, the accuracy and the traceability of the answer of each question can be ensured, so that the accuracy of the answer can be determined by taking the tracing data as the basis after the user searches the answer, the method can be applied to the search in the medical field, and the experience of searching the answer in the medical field is improved.

Example two

Fig. 4 is a flowchart of a medical question-answering method provided in a second embodiment of the present invention, and as shown in fig. 4, the medical question-answering method provided in this embodiment is further refined in step 103 on the basis of the medical question-answering method provided in the first embodiment of the present invention, and further includes a step of constructing a knowledge base, where the knowledge base is a knowledge graph, and the medical question-answering method provided in this embodiment includes the following steps.

Step 201, obtaining document types and format information meeting the accurate requirements in the medical field configured by the medical professional through the configuration interface.

Optionally, in this embodiment, a client for constructing the knowledge graph is provided on a user terminal of the medical professional, and after the medical professional logs in the client, the medical professional performs related authentication on whether the medical professional is the medical professional, and after the authentication is passed, the configuration interface may be opened to perform configuration of the document type and format information that meet the accuracy requirement in the medical field. The types of documents that meet the accuracy requirements, as configured, can be clinical guidelines, superior medical journals, superior medical papers, and the like. The configured document format meeting the accuracy requirement can be a picture format, a PDF format and the like.

Step 202, acquiring a constructed corpus of the knowledge graph according to the document type and the format information meeting the accuracy requirement.

Specifically, in this embodiment, documents in the medical field may be acquired by accessing a third-party platform, and then each document is analyzed to extract a document that meets the accuracy requirement of configuration in terms of document type and format, so as to obtain a corpus of the constructed knowledge graph, where the corpus may be represented as a constructed corpus.

The medical field may be the field of geriatric care, infectious diseases, hematopathy, or other departments.

Step 203, receiving a set of schemas in the medical field input by the medical professional through the configuration interface.

In this embodiment, the configuration interface includes a configuration control for a schema set in the medical field in addition to a configuration control for a document type and a document format.

When the knowledge graph is constructed, the SPO triple data is extracted from the construction corpus, where the SPO triple data refers to a triple composed of an entity S, a relationship P (or an attribute P), and an entity O (or an attribute value O), where S is a subject of P and O is an object of P. When extracting the SPO triple data, it is necessary to determine a relationship/attribute P, a subject (S) type and an object (O) type of the P in the SPO triple data to be extracted from the construction corpus. And the relationship/attribute P, and the subject (S) type and object (O) type of P form the schema set.

Since the medical professional knows the medical field very professionally, the medical professional configures the schema set in the medical field through the configuration interface, so that the schema set can be configured accurately.

It will be appreciated that each medical professional is different in the medical field in which it is skilled, so the medical field in which it is skilled can be determined for the medical professional's certification information and displayed in the configuration interface to enable each medical professional to configure the corresponding set of schemas for the medical field in which it is skilled.

And step 204, extracting the constructing three-tuple data in the schema set range from the constructing linguistic data.

In this embodiment, an extraction algorithm may be used to extract the triple data in the constructed corpus, and when the triple data is extracted, the schema set is used as a constraint condition, so that the extracted triple data is within the scope of the schema set, and the extracted triple data is determined as the triple data of the constructed knowledge graph, which may be represented as the constructed triple data.

Step 205, obtaining a constructed question-answer pair corresponding to the constructed triple data.

In this embodiment, after the construction triple data is extracted from the corpus, the corresponding question, answer, and trace data may be extracted from the corresponding corpus, and the corresponding question, answer, and trace data are expressed as a construction question-answer pair.

And step 206, constructing a knowledge graph according to the constructed ternary group data and the corresponding constructed question-answer pairs.

Specifically, in this embodiment, all the constructed triple-component data may be obtained, the association relationship between the constructed triple-component data is extracted, and a graph structure is constructed according to the association relationship, so as to construct the knowledge graph. And storing the mapping relation between each constructed triple data and the corresponding question-answer pair in the knowledge graph.

In the medical question-answering method provided by the embodiment, in the process of constructing the knowledge graph, since the medical professional configures the document type and the format information which meet the accuracy requirement in the preset medical field through the configuration interface before the constructed corpus of the knowledge graph is acquired, the accuracy and the authority of the constructed corpus are ensured. And when the constructed triple data are extracted from the constructed corpus, the schema set in the medical field is also configured by medical professionals, so that the accuracy of the extracted constructed triple data is ensured. And further, the constructed knowledge graph can accurately reflect the objective relation between the real objects in the medical field and the accuracy of question-answer pairs.

Optionally, in this embodiment, before step 206, the following steps are further included:

and step 2051, sending the constructed ternary group data and the corresponding constructed question-answer pairs to a user terminal corresponding to the medical professional, so that the user terminal displays the constructed ternary group data and the corresponding constructed question-answer pairs for the medical professional to check.

Step 2052, receiving the audit result sent by the user terminal.

And step 2053, if the verification result is determined to be not passed, acquiring the corrected three-element constructed data and the corresponding constructed question-answer pair.

In this embodiment, the constructed triple-component data and the corresponding constructed question-answer pairs are sent to a user terminal corresponding to a medical professional, after the user terminal displays the constructed triple-component data and the corresponding constructed question-answer pairs, the medical professional performs auditing on each constructed triple-component data and the corresponding constructed question-answer pairs, and if the constructed triple-component data and the corresponding constructed question-answer pairs meet the accuracy requirement, the auditing is passed. And if the constructed triple data and the corresponding constructed question-answer pair do not meet the accuracy requirement, the examination is not passed. And after the audit is not passed, correcting the constructed triple data and/or the corresponding constructed question-answer pair.

It can be understood that, if the audit is passed, the audit result that is passed is sent to the medical question and answer device, and if the audit is not passed, the result that is not passed, the modified three-component constructed data and the corresponding constructed question and answer pair are sent to the medical question and answer device together, so that the medical question and answer device can obtain the modified three-component constructed data and the corresponding constructed question and answer pair.

Accordingly, step 206 specifically includes: and constructing a knowledge graph according to the modified constructed triple data and the corresponding constructed question-answer pairs.

In the medical question-answering method provided by the embodiment, in the process of constructing the knowledge graph, the constructed ternary group data and the corresponding constructed question-answer pair are acquired and then sent to the user terminal of the medical professional, and the medical professional performs auditing, so that the constructed ternary group data of the knowledge graph and the corresponding constructed question-answer pair are accurate, and the accuracy of the knowledge graph is further improved.

And step 207, receiving a target key field input by a user through the search input box in the home page operation interface.

And 208, performing semantic analysis on the target key field to acquire the target entity attribute corresponding to the target key field.

In this embodiment, the implementation manners of steps 207 to 208 are the same as the implementation manners of steps 101 to 102 in the first embodiment of the present invention, and are not described in detail here.

And step 209, determining at least one target question-answer pair meeting the matching requirement according to the target entity attribute and a pre-constructed knowledge base.

Optionally, in this embodiment, step 209 includes the following steps:

step 2091, a candidate triple set is obtained from the pre-constructed knowledge graph according to the target entity attribute, and the candidate triple set includes at least one candidate triple.

Specifically, in this embodiment, the target entity attribute is analyzed, the triple data whose correlation with the target entity attribute satisfies the preset correlation is acquired from the pre-constructed knowledge graph and is used as the candidate triple data, and the candidate triple set is formed by the candidate triple data.

The relevance of the target entity attribute and each triple data can be represented by the number of the associated nodes. And if the number of the associated nodes of the target entity attribute and the triple data is greater than or equal to the number of the preset nodes, determining that the triple data does not meet the preset correlation.

Or, other data is used to represent the correlation between the target entity attribute and each triplet of data, which is not limited in this embodiment.

And 2092, performing matching calculation on the target entity attribute and the candidate triple by adopting a matching model to obtain a candidate triple meeting the matching requirement as a target triple.

Specifically, the target entity attribute and each candidate triple are input into a matching model, the matching model performs matching calculation on the target entity attribute and each candidate triple, the matching degree of the target entity attribute and each candidate triple is calculated, candidate triple data with the matching degree greater than a preset matching degree is determined as a candidate triple meeting the matching requirement, and the candidate triple meeting the matching requirement is determined as a target triple.

The matching model may be a deep learning model, such as a convolutional neural network model, a cyclic neural network model, or the like.

Step 2093, a target question-answer pair corresponding to the target triple is obtained from the pre-constructed knowledge graph.

In this embodiment, each constructed triple and the corresponding constructed question-answer pair are stored in association in the knowledge map, so that the target question-answer pair corresponding to the target triple is obtained from the knowledge map, and the target question-answer pair includes a target question, a target answer and tracing data.

It should be noted that, before step 2091, the target entity attribute may also be checked through the knowledge graph, and if the target entity attribute is not the entity attribute of the medical field corresponding to the knowledge graph, it is determined that the problem of the user search corresponding to the target entity attribute is an invalid problem, and the invalid problem can be quickly responded.

Step 210, responding to the click operation of the user on the target question-answer pair, and displaying the target question-answer pair, wherein the target question-answer pair comprises: the target question, the target answer and the tracing data are references.

In this embodiment, the implementation manner of step 210 is similar to that of step 104 in the first embodiment of the present invention, and is not described in detail here.

In the medical question-answering method provided by the embodiment, when at least one target question-answering pair meeting the matching requirement is determined according to the target entity attribute and a pre-constructed knowledge base, a candidate triple set is obtained from a pre-constructed knowledge graph according to the target entity attribute, wherein the candidate triple set comprises at least one candidate triple; matching calculation is carried out on the target entity attribute and the candidate triple by adopting a matching model, so that the candidate triple meeting the matching requirement is obtained and serves as the target triple; and acquiring target question-answer pairs corresponding to the target triples from a pre-constructed knowledge graph. The method comprises the steps of firstly acquiring a candidate triple set matched with the target entity attribute from a knowledge graph, and then performing matching calculation on the target entity attribute and the candidate triple in the candidate triple set, so that the calculation amount of the matching calculation performed by a matching algorithm can be effectively reduced while the acquired target triple is an accurate triple, and the efficiency of determining a target question-answer pair meeting the matching requirement is improved.

EXAMPLE III

Fig. 5 is a flowchart of a medical question-answering method provided in the third embodiment of the present invention, and as shown in fig. 5, the medical question-answering method provided in this embodiment is based on the medical question-answering method provided in the first embodiment or the second embodiment of the present invention, and further includes other steps, and then the medical question-answering method provided in this embodiment further includes the following steps.

Step 301, responding to the triggering operation of the user through the question option in the home page operation interface, and displaying a question-answer pair recording interface.

Specifically, in this embodiment, as shown in fig. 2, a question option is included at the lowest part of the home page operation interface, and the user clicks the question option, so that the operation interface jumps from the home page operation interface to the question-answer pair recording interface.

Step 302, in response to the submitting operation of the recorded question-answer pair input by the user on the question-answer pair recording interface, judging whether the user is a medical professional.

In this embodiment, as shown in fig. 6, the question-answer pair recording interface includes an input box for questions, an input box for answers to the questions, and an input box for references, and the user can input the questions in the input boxes for questions. And inputting answers corresponding to the recorded questions and answers in an input box of the answers to the questions. The reference is entered in an input box of the reference. The input questions, question answers and references constitute a recorded question-answer pair.

Step 303, if the user is determined to be a medical professional, extracting the recording triple corresponding to the recorded question-answer pair, and updating the recorded question-answer pair and the corresponding recording triple into a knowledge base.

In this embodiment, after the user clicks the submit button, whether the user passes the authentication of the medical professional can be determined from the medical question-answering device through the logged-in user name, and if it is determined that the user passes the authentication of the medical professional, it is indicated that the recorded question-answer pair is a question-answer pair approved by the medical professional, so that the accuracy of the recorded question-answer pair is ensured. And extracting triple data from the question-answer pair, wherein the triple data is a recording triple, and updating the recorded question-answer pair and the corresponding recording triple into a knowledge base. The question-answer pairs in the knowledge base can be enriched continuously, and the accuracy of the question-answer pairs in the knowledge base is ensured.

It will be appreciated that since each question-answer pair in the knowledge base is subject to review by a medical professional, information about the medical professional reviewing the target question-answer pair may also be displayed when the target question-answer pair is displayed. Such as the name of the medical professional reviewing the target question-answer pair, the department to which the medical professional belongs, etc., are displayed below the reference.

Example four

Fig. 7 is a flowchart of a medical question-answering method according to a fourth embodiment of the present invention, and as shown in fig. 7, the medical question-answering method according to the fourth embodiment of the present invention further includes other steps on the basis of the medical question-answering method according to any one of the first to third embodiments of the present invention, and then the medical question-answering method according to the third embodiment of the present invention further includes the following steps.

Step 401, responding to the triggering operation of the user management option in the home page operation interface by the user, displaying the user management interface.

Specifically, as shown in fig. 2, a user management option is included at the lowest part of the home page operation interface, and the user management option is the "my" option in fig. 2. The user jumps from the home os to the user management interface by clicking on this "my" option. As shown in FIG. 7, a question option, i.e., the option of "My questions," is included in the user management interface.

Step 402, responding to the triggering operation of the user through the question option in the user management interface, and displaying the interface of the question to be submitted and the interface of the question submitted.

In this embodiment, the user jumps the operation interface from the user management interface to the question management interface by clicking the question option. The question management interface comprises a to-be-submitted review question option and a submitted review question option.

And 403, responding to the triggering operation of the option of the to-be-submitted audit problem by the user, displaying an interface of the to-be-submitted audit problem, inputting the to-be-submitted audit problem through the interface of the to-be-submitted audit problem and the submitting operation after a certain medical professional is selected, sending the to-be-submitted audit problem to the interface of the to-be-submitted audit problem corresponding to the medical professional, and handing over the to-be-submitted audit problem to the interface of the to-be-submitted audit problem corresponding to the user.

In this embodiment, the user clicks the option of the to-be-submitted review question, and the interface jumps from the question management interface to the to-be-submitted review question interface. The method comprises the steps that an input box for the to-be-submitted audit problem is arranged in an audit interface to be submitted, the to-be-submitted audit problem can be input through the input box for the to-be-submitted audit problem, and identification information of all medical professionals for registration, such as the name and the picture of each medical professional, is displayed in the audit interface to be submitted. After the user can select a certain medical professional, the user clicks a submission button to submit the to-be-submitted audit problem. And sending the to-be-submitted auditing problem to a to-be-audited interface corresponding to the medical professional.

It can be understood that, after the user submits the to-be-submitted question by clicking the submit button, the to-be-submitted question is handed over to the interface of the submitted question corresponding to the user, and after clicking the option of the submitted question, the user enters the interface of the submitted question to see the handed over to-be-submitted question.

Step 404, if the post-audit answer and the tracing data corresponding to the to-be-submitted audit question sent by the user terminal corresponding to the medical professional are received within a preset time period, updating the corresponding audit question-answer pair to a knowledge base.

As shown in fig. 7, after the to-be-submitted audit problem is sent to the to-be-audited interface corresponding to the medical professional, the medical professional can enter the to-be-audited interface by clicking the option of "my audit" in the user management interface, at this time, the to-be-submitted audit problem in the to-be-submitted audit problem interface of the user is the to-be-audited problem in the to-be-audited interface of the medical professional. If the medical professional timely checks the problem to be checked, answers the problem to be checked, inputs the answer and the tracing data into the interface to be checked, and feeds the answer and the tracing data back to the user, the medical question-answering equipment receives the checked answer and the tracing data corresponding to the problem to be checked, which are sent by the user terminal corresponding to the medical professional, within a preset time period. The user can check the checked answers and the traced data in the interface of the submitted checking questions.

In this embodiment, in order to enrich the question-answer pairs in the knowledge base continuously, the submitted questions in the submitted question-and-answer interface, the examined answers, and the tracing data form examined question-and-answer pairs, and the examined question-and-answer pairs are updated into the knowledge base.

Step 405, if the post-audit answer and the trace-back data corresponding to the audit question to be submitted, which are sent by the user terminal corresponding to the medical professional, are not received within a preset time period, distributing the audit question to be submitted to other medical professionals according to a preset distribution rule, so that after the post-audit answer and the trace-back data corresponding to the audit question to be submitted are sent by the user terminal corresponding to the other medical professionals, the corresponding audit question-answer pair is updated to a knowledge base.

In this embodiment, if the post-audit answer and the trace-back data corresponding to the to-be-submitted audit problem sent by the user terminal corresponding to the medical professional are not received within the preset time period, it is indicated that the medical professional selected by the user cannot answer the to-be-submitted audit problem in time, and the to-be-submitted audit problem is distributed to other medical professionals according to the preset distribution rule, where the preset distribution rule may be a matching degree between a department to which the other medical professionals belong and the to-be-submitted audit problem, a quantity of the reply problems, and a highest-ranked medical professional in the comprehensive scoring performed by factors such as a product limit of the reply and the like, and is used as a medical professional who distributes the to-be-submitted audit problem. And sending the to-be-submitted audit question to the to-be-audited interfaces corresponding to the user terminals of the other allocated medical professionals, and answering the to-be-submitted audit question by the other allocated medical professionals.

Similarly, after receiving the post-audit answer and the tracing data corresponding to the audit problem to be submitted, which are sent by the user terminal corresponding to the other medical professionals, the user can check the post-audit answer and the tracing data in the audit problem submitted interface. And forming a question-answer pair of the submitted question in the interface of the submitted question and the audited answer and the retroactive data, updating the question-answer pair into the knowledge base, and continuously enriching the question-answer pair in the knowledge base on the premise of ensuring the accuracy of the question-answer pair of the audition.

EXAMPLE five

Fig. 8 is a flowchart of a medical question-answering method according to a fifth embodiment of the present invention, and as shown in fig. 8, the medical question-answering method according to the fifth embodiment of the present invention further includes other steps on the basis of the medical question-answering method according to any one of the first to fourth embodiments of the present invention, and then the medical question-answering method according to the present embodiment further includes the following steps.

Step 501, responding to a triggering operation of a user through an invitation friend option in a user management interface, displaying an invitation friend operation interface, wherein the invitation friend operation interface comprises an invitation code.

In this embodiment, as shown in fig. 7, the user management interface further includes an invite friend option, and the user enters the invite friend operation interface by clicking the invite friend option, as shown in fig. 9, where the invite friend operation interface includes an invite code and a sharing option. Wherein the invitation code can be arranged in the middle area of the corresponding two-dimensional code.

Step 502, in response to a triggering operation of the user on the sharing option in the friend invitation operation interface, jumping to a sharing interface of a preset application program, so that the friend registers through an invitation code in the sharing interface.

In this embodiment, after the user clicks the sharing option, the operation interface jumps to the sharing interface of the preset application program from the operation interface of the invitation friend, and the preset application program may be some instant messaging software, for example. And sending the invitation code to the instant messaging software of the friend, and finishing the registration process through the invitation code when the friend registers the application program corresponding to the medical question-answering method.

It should be noted that, if it is monitored that a friend registers an application corresponding to the medical question-answering method, information of the invited friend can be viewed in an interface corresponding to the "my invitation" option in the user management interface of the user.

In the medical question-answering method provided by the embodiment, the friend invitation operation interface is displayed by responding to the triggering operation of the friend invitation option in the user management interface by a user, and the friend invitation operation interface comprises an invitation code; responding to the triggering operation of the user on the sharing option in the friend invitation operation interface, jumping to the sharing interface of the preset application program, so that friends register through invitation codes in the sharing interface, each registered user of the application program using the medical question-answering method can be guaranteed to be a traceable user, and the safety of the application program of the medical question-answering method is guaranteed.

EXAMPLE six

Fig. 9 is a flowchart of a medical question-answering method provided in a sixth embodiment of the present invention, and as shown in fig. 9, the medical question-answering method provided in this embodiment further includes other steps on the basis of the medical question-answering method provided in any one of the first to fifth embodiments of the present invention, and then the medical question-answering method provided in this embodiment further includes the following steps.

Step 601, responding to the triggering operation of the medical professional authentication option in the user management interface by the user, and displaying the medical professional authentication interface.

In this embodiment, as shown in fig. 7, the user management interface further includes a medical professional authentication option, that is, a "physician authentication" option in fig. 7, and if the user is a medical professional, the user clicks the medical professional authentication option, and the interface jumps from the user management interface to the medical professional authentication interface.

Step 602, performing medical professional authentication on the user in response to the department category, professional level and authentication certificate input by the user on the medical professional authentication interface.

As shown in fig. 10, the medical professional authentication interface may include authentication status information, and may further include a department setting option, a professional level option, and an upload authentication certificate option. The user can select the department category to be input by clicking the department setting option. The user can configure the professional level as primary, intermediate or advanced by clicking on the professional level option. The user can upload the medical practice qualification certificate by clicking the upload authentication certificate option.

In this embodiment, after the user inputs the department category, the professional level, and the uploaded medical qualification certificate, the user is authenticated as a medical professional.

Step 603, if the user passes the authentication, adding the user to a selection catalog of the medical professional to be submitted with the auditing interface.

In the medical question-answering method provided by this embodiment, a medical professional authentication interface is displayed by responding to a trigger operation of a user for authenticating a medical professional via a user management interface; responding to the department category, the professional level and the authentication certificate which are input by the user on the medical professional authentication interface, and performing medical professional authentication on the user; if the user passes the authentication, the user is added into a selection directory of the medical professional in the check interface to be submitted, the user can be authenticated whether the user is the medical professional, the problem can be recorded and responded only by the medical professional, authentication information is obtained during the check of the problem, and the accuracy of the answer corresponding to each problem is improved.

As shown in fig. 7, a "real-name authentication" option, an "invited answer" option, a "leaderboard" option, and the like may also be included in the user management interface.

EXAMPLE seven

Fig. 11 is a schematic structural diagram of a medical question answering apparatus according to a seventh embodiment of the present invention, and as shown in fig. 11, a medical question answering apparatus 70 according to a seventh embodiment of the present invention includes: a memory 71, a processor 72 and a computer program.

The computer program is stored in the memory 71 and configured to be executed by the processor 72 to implement the medical question-answering method provided in the first to sixth embodiments of the present invention. The related description may be understood by referring to the related description and effects corresponding to fig. 1 to fig. 10, and redundant description is not repeated here.

In the present embodiment, the memory 71 and the processor 72 are connected by a bus.

Example eight

Fig. 12 is a schematic structural diagram of a medical question-answering device according to an eighth embodiment of the present invention, where the medical question-answering device may be a smart phone, a computer, a digital broadcast terminal, a tablet device, a personal digital assistant, or the like.

The medical question-answering device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 88, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the apparatus 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Power components 806 provide power to the various components of device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 800.

The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 88 is configured to output and/or input audio signals. For example, the audio component 88 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio assembly 88 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed status of the device 800, the relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in the position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration/deceleration of the device 800, and a change in the temperature of the device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, communications component 816 further includes a Near Field Communications (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor of the vehicle-end device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

A non-transitory computer-readable storage medium, where instructions in the storage medium, when executed by a processor of a vehicle-end device, enable the vehicle-end device to execute the vehicle-end data processing method.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only.

It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A medical question-answering method is characterized by comprising the following steps:

2. The method of claim 1, wherein the pre-built knowledge base is a knowledge graph;

3. The method according to claim 2, wherein before determining at least one target question-answer pair satisfying matching requirements according to the target entity attributes and a pre-constructed knowledge base, further comprising:

4. The method of claim 3, wherein before constructing the knowledge graph according to the constructed triple data and the corresponding constructed question-answer pairs, further comprising:

receiving an audit result sent by the user terminal;

5. The method of claim 1, further comprising:

6. The method of claim 1, further comprising:

7. The method of claim 6, further comprising:

8. The method of claim 6, further comprising:

9. A medical question-answering apparatus, characterized by comprising:

a memory, a processor, and a computer program;

wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-8.

10. A computer-readable storage medium, on which a computer program is stored, which computer program is executable by a processor to implement the method according to any one of claims 1-8.