CN112037905A - Medical question and answer method, equipment and storage medium - Google Patents
Medical question and answer method, equipment and storage medium Download PDFInfo
- Publication number
- CN112037905A CN112037905A CN202010685557.9A CN202010685557A CN112037905A CN 112037905 A CN112037905 A CN 112037905A CN 202010685557 A CN202010685557 A CN 202010685557A CN 112037905 A CN112037905 A CN 112037905A
- Authority
- CN
- China
- Prior art keywords
- question
- user
- answer
- target
- interface
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
技术领域technical field
本发明实施例涉及人工智能技术领域,尤其涉及一种医用问答方法、设备及存储介质。The embodiments of the present invention relate to the technical field of artificial intelligence, and in particular, to a medical question answering method, device and storage medium.
背景技术Background technique
随着人工智能技术的成熟,自然语言处理技术也得到了快速发展。自然语音处理技术是人工智能领域中的一个重要方向。它能够实现人与计算机之间用自然语言进行有效通信。问答系统是一个以自然语言理解技术为核心,完成对用户问题的分析处理,并生成正确答案的系统。With the maturity of artificial intelligence technology, natural language processing technology has also developed rapidly. Natural speech processing technology is an important direction in the field of artificial intelligence. It enables effective communication between humans and computers using natural language. The question answering system is a system that takes natural language understanding technology as the core, completes the analysis and processing of user questions, and generates correct answers.
目前的问答系统在面对用户问题时,推送出的答案多种多样。而对于每个答案用户并没有依据判断该答案的准确与否。那么在某些专业领域,如医疗领域中,这将给用户带来很大的困扰,导致用户无法对答案进行准确性地辨别,影响用户的问答体验。When faced with user questions, the current question answering system pushes out various answers. For each answer, the user has no basis to judge the accuracy of the answer. Then, in some professional fields, such as the medical field, this will bring great trouble to the user, so that the user cannot accurately identify the answer, which affects the user's Q&A experience.
发明内容SUMMARY OF THE INVENTION
本发明实施例提供一种医用问答方法、设备及存储介质,解决了现有技术中对于每个答案用户并没有依据判断该答案的准确与否,那么在某些专业领域,如医疗领域中,这将给用户带来很大的困扰,导致用户无法对答案进行准确性地辨别,影响用户的问答体验的技术问题。The embodiments of the present invention provide a medical question and answer method, equipment and storage medium, which solve the problem that in the prior art, the user does not judge whether the answer is accurate or not based on each answer, so in some professional fields, such as the medical field, This will bring great trouble to the user, cause the user to be unable to accurately identify the answer, and affect the user's question-and-answer experience.
第一方面,本发明实施例提供一种医用问答方法,包括:In a first aspect, an embodiment of the present invention provides a medical question and answer method, including:
接收用户通过首页操作界面中搜索输入框输入的目标关键字段;Receive the target key field entered by the user through the search input box in the homepage operation interface;
对所述目标关键字段进行语义解析,以获取所述目标关键字段对应的目标实体属性;Semantic analysis is performed on the target key field to obtain the target entity attribute corresponding to the target key field;
根据所述目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对;Determine at least one target question-answer pair that meets the matching requirement according to the target entity attribute and the pre-built knowledge base;
响应于用户对所述目标问答对的点击操作,显示所述目标问答对,所述目标问答对中包括:目标问题,目标答案及追溯数据,所述追溯数据为参考文献。In response to the user's click operation on the target question-and-answer pair, the target question-and-answer pair is displayed, and the target question-and-answer pair includes: the target question, the target answer, and retrospective data, and the retrospective data is a reference.
进一步地,如上所述的方法,所述预先构建的知识库为知识图谱;Further, in the above-mentioned method, the pre-built knowledge base is a knowledge graph;
所述根据所述目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对,包括:The determining at least one target question-answer pair that meets the matching requirement according to the target entity attribute and the pre-built knowledge base includes:
根据所述目标实体属性从所述预先构建的知识图谱中获取候选三元组集合,所述候选三元组集合中包括至少一个候选三元组;Obtain a candidate triplet set from the pre-built knowledge graph according to the target entity attribute, where the candidate triplet set includes at least one candidate triplet;
将所述目标实体属性与所述候选三元组采用匹配模型进行匹配计算,以获得满足匹配要求的候选三元组作为目标三元组;The target entity attribute and the candidate triplet are matched and calculated by using a matching model, so as to obtain the candidate triplet that meets the matching requirements as the target triplet;
从所述预先构建的知识图谱中获取所述目标三元组对应的目标问答对。The target question-answer pair corresponding to the target triplet is obtained from the pre-built knowledge graph.
进一步地,如上所述的方法,所述根据所述目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对之前,还包括:Further, in the above method, before determining at least one target question-answer pair that meets the matching requirement according to the target entity attribute and the pre-built knowledge base, the method further includes:
获取医学专业人员通过配置界面配置的在预设医学领域中满足准确要求的文献类型及格式信息;Obtain the document type and format information configured by medical professionals through the configuration interface to meet the precise requirements in the preset medical field;
根据所述满足准确要求的文献类型及格式信息获取所述知识图谱的构建语料;Obtain the construction corpus of the knowledge graph according to the document type and format information that meet the exact requirements;
接收医学专业人员通过配置界面输入的所述医学领域中的schema集合;receiving a schema set in the medical field input by a medical professional through a configuration interface;
从所述构建语料中抽取在schema集合范围内的构建三元组数据;extracting the construction triplet data within the scope of the schema set from the construction corpus;
获取与所述构建三元组数据对应的构建问答对;obtaining the construction question and answer pair corresponding to the construction triplet data;
根据所述构建三元组数据及对应的构建问答对构建知识图谱。A knowledge graph is constructed according to the constructed triplet data and the corresponding constructed question-answer pairs.
进一步地,如上所述的方法,所述根据所述构建三元组数据及对应的构建问答对构建知识图谱之前,还包括:Further, in the above-mentioned method, before constructing the knowledge graph according to the constructing triplet data and the corresponding constructing question-and-answer pairs, the method further includes:
将所述构建三元组数据及对应的构建问答对发送至医学专业人员对应的用户终端,以使用户终端显示所述构建三元组数据及对应的构建问答对,以由所述医学专业人员进行审核;Sending the construction triplet data and the corresponding construction question-and-answer pair to the user terminal corresponding to the medical professional, so that the user terminal displays the construction triplet data and the corresponding construction question and answer pair, so that the medical professional can display the construction triplet data and the corresponding construction question and answer pair. conduct an audit;
接收所述用户终端发送的审核结果;receiving the audit result sent by the user terminal;
若确定所述审核结果为未通过,则获取修正后的构建三元组数据及对应的构建问答对;If it is determined that the audit result is not passed, the revised construction triplet data and the corresponding construction question-and-answer pair are obtained;
相应地,所述根据所述构建三元组数据及对应的构建问答对构建知识图谱,包括:Correspondingly, the construction of the knowledge graph according to the construction triplet data and the corresponding construction question and answer pairs includes:
根据所述修正后的构建三元组数据及对应的构建问答对构建知识图谱。A knowledge graph is constructed according to the revised construction triplet data and corresponding construction question-answer pairs.
进一步地,如上所述的方法,还包括:Further, the above-mentioned method also includes:
响应于用户通过首页操作界面中提问选项的触发操作,显示问答对记录界面;In response to the user's triggering operation through the question option in the homepage operation interface, the question and answer pair record interface is displayed;
响应于用户在所述问答对记录界面输入的记录问答对的提交操作,判断所述用户是否为医学专业人员;determining whether the user is a medical professional in response to the submission operation of the recorded question-and-answer pair input by the user in the question-and-answer pair record interface;
若确定所述用户为医学专业人员,则提取所述记录问答对对应的记录三元组,并将所述记录问答对及对应的记录三元组更新到知识库中。If it is determined that the user is a medical professional, the record triplet corresponding to the record question-and-answer pair is extracted, and the record question-answer pair and the corresponding record triplet are updated into the knowledge base.
进一步地,如上所述的方法,还包括:Further, the above-mentioned method also includes:
响应于用户通过首页操作界面中用户管理选项的触发操作,显示用户管理界面;In response to the user's triggering operation through the user management option in the homepage operation interface, the user management interface is displayed;
响应于用户通过所述用户管理界面中问题选项的触发操作,显示待提交审核问题选项及已提交审核问题选项;In response to the user's triggering operation through the question option in the user management interface, the option to be submitted for review and the option of the submitted review question are displayed;
响应于用户对所述待提交审核问题选项的触发操作,显示待提交审核问题界面,通过待提交审核界面输入待提交审核问题及选择某一医学专业人员后的提交操作,将所述待提交审核问题发送至该医学专业人员对应的待审核界面中,并将所述待提交审核问题移交到所述用户对应的已提交审核问题界面中;In response to the user's triggering operation on the option of the question to be submitted for review, the interface of the question to be submitted for review is displayed, and the question to be submitted for review is input through the interface for review to be submitted and a submission operation after selecting a medical professional is performed, and the question to be submitted for review is selected. sending the question to the pending review interface corresponding to the medical professional, and handing over the pending review question to the user's corresponding submitted review question interface;
若预设时间段内接收到该医学专业人员对应的用户终端发送的所述待提交审核问题对应的审核后答案及追溯数据,则将对应的审核问答对更新到所述知识库中;If the post-audit answer and retrospective 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-and-answer pair into the knowledge base;
若预设时间段内未接收到该医学专业人员对应的用户终端发送的所述待提交审核问题对应的审核后答案及追溯数据,则对所述待提交审核问题按照预设分配规则分配给其他医学专业人员,以在其他医学专业人员对应的用户终端发送所述待提交审核问题对应的审核后答案及追溯数据后,将对应的审核问答对更新到所述知识库中。If the post-review answer and retrospective data corresponding to the to-be-submitted review question sent by the user terminal corresponding to the medical professional are not received within a preset time period, the to-be-submitted review question is allocated to other The medical professional updates the corresponding audit question-and-answer pair into the knowledge base after the user terminals corresponding to other medical professionals send the post-audit answers and traceability data corresponding to the audit questions to be submitted.
进一步地,如上所述的方法,还包括:Further, the above-mentioned method also includes:
响应于用户通过所述用户管理界面中邀请好友选项的触发操作,显示邀请好友操作界面,在所述邀请好友操作界面中包括邀请码;In response to the triggering operation of the user through the option of inviting friends in the user management interface, displaying an operation interface for inviting friends, including an invitation code in the operation interface for inviting friends;
响应于用户在邀请好友操作界面中对分享选项的触发操作,跳转到预设应用程序的分享界面,以使好友通过所述分享界面中的邀请码进行注册。In response to the user's triggering operation of the sharing option in the inviting friend operation interface, jump to the sharing interface of the preset application program, so that the friend can register through the invitation code in the sharing interface.
进一步地,如上所述的方法,还包括:Further, the above-mentioned method also includes:
响应于用户通过所述用户管理界面中医学专业人员认证选项的触发操作,显示医学专业人员认证界面;In response to the user's triggering operation through the medical professional certification option in the user management interface, displaying a medical professional certification interface;
响应于用户在医学专业人员认证界面输入的科室类别、专业级别及认证证书,对所述用户进行医学专业人员认证;Performing medical professional certification on the user in response to the department category, specialty level, and certification certificate entered by the user in the medical professional certification interface;
若所述用户通过认证,则将所述用户添加到待提交审核界面对所述医学专业人员的选择目录中。If the user passes the authentication, the user is added to the selection list of the medical professional in the to-be-submitted review interface.
第二方面,本发明实施例提供一种医用问答设备,包括:In a second aspect, an embodiment of the present invention provides a medical question and answer device, including:
存储器,处理器以及计算机程序;memory, processors and computer programs;
其中,所述计算机程序存储在所述存储器中,并被配置为由所述处理器执行以实现如第一方面中任一项所述的方法。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 the first aspects.
第三方面,本发明实施例提供一种计算机可读存储介质,其特征在于,其上存储有计算机程序,所述计算机程序被处理器执行以实现如第一方面中任一项所述的方法。In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, characterized in that 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 aspects. .
本发明实施例提供一种医用问答方法、设备及存储介质,通过接收用户通过首页操作界面中搜索输入框输入的目标关键字段;对目标关键字段进行语义解析,以获取目标关键字段对应的目标实体属性;根据目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对;响应于用户对目标问答对的点击操作,显示目标问答对,目标问答对中包括:目标问题,目标答案及追溯数据,追溯数据为参考文献。由于在预先构建的知识库中,每个问答对均具有答案对应的追溯数据,并且该追溯数据的形式是参考文献的形式,能够保证每个问题的答案的准确性和可追溯性,所以用户在搜索到答案后,能够以追溯数据为依据确定该答案的准确性,可以应用在医学领域的搜索中,提高了对医学领域搜索答案的体验。Embodiments of the present invention provide a medical question answering method, device, and storage medium. By receiving a target key field input by a user through a search input box in a homepage operation interface, semantic analysis is performed on the target key field to obtain the corresponding target key field. At least one target question-answer pair that meets the matching requirements is determined according to the target entity attribute and the pre-built knowledge base; in response to the user's click operation on the target question-and-answer pair, the target question-answer pair is displayed, and the target question-answer pair includes: target question , the target answer and the traceability data, the traceability data is the reference. In the pre-built knowledge base, each question-and-answer pair has traceability data corresponding to the answer, and the traceback data is in the form of references, which can ensure the accuracy and traceability of the answers to each question, so users After the answer is searched, the accuracy of the answer can be determined based on the retrospective data, which can be applied to the search in the medical field, and improves the experience of searching for an answer in the medical field.
应当理解,上述发明内容部分中所描述的内容并非旨在限定本发明的实施例的关键或重要特征,亦非用于限制本发明的范围。本发明的其它特征将通过以下的描述变得容易理解。It should be understood that the content described in the above summary section is not intended to limit the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become apparent from the following description.
附图说明Description of drawings
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.
图1为本发明实施例一提供的医用问答方法的流程图;1 is a flowchart of a medical question and answer method provided in
图2为本发明实施例提供的医用问答方法中首页操作界面的示意图;2 is a schematic diagram of a homepage operation interface in a medical question and answer method provided by an embodiment of the present invention;
图3为本发明实施例提供的医用问答方法中目标问答对的显示界面的示意图;3 is a schematic diagram of a display interface of a target question and answer pair in a medical question and answer method provided by an embodiment of the present invention;
图4为本发明实施例二提供的医用问答方法的流程图;4 is a flowchart of a medical question and answer method provided in Embodiment 2 of the present invention;
图5为本发明实施例三提供的医用问答方法的流程图;5 is a flowchart of a medical question and answer method provided in Embodiment 3 of the present invention;
图6为本发明实施例提供的医用问答方法中问答对记录界面的示意图;6 is a schematic diagram of a question-and-answer pair recording interface in a medical question-and-answer method provided by an embodiment of the present invention;
图7为本发明实施例四提供的医用问答方法的流程图;7 is a flowchart of a medical question and answer method provided in Embodiment 4 of the present invention;
图8为本发明实施例五提供的医用问答方法的流程图;8 is a flowchart of a medical question and answer method provided in Embodiment 5 of the present invention;
图9为本发明实施例六提供的医用问答方法的流程图;9 is a flowchart of a medical question and answer method provided in Embodiment 6 of the present invention;
图10为本发明实施例提供的医用问答方法中医学专业人员认证界面的示意图;10 is a schematic diagram of a medical professional certification interface in a medical question and answer method provided by an embodiment of the present invention;
图11为本发明实施例七提供的医用问答设备的结构示意图;11 is a schematic structural diagram of a medical question answering device provided in Embodiment 7 of the present invention;
图12为本发明实施例八提供的医用问答设备的结构示意图。FIG. 12 is a schematic structural diagram of a medical question answering device provided in Embodiment 8 of the present invention.
具体实施方式Detailed ways
下面将参照附图更详细地描述本发明的实施例。虽然附图中显示了本发明的某些实施例,然而应当理解的是,本发明可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例,相反提供这些实施例是为了更加透彻和完整地理解本发明。应当理解的是,本发明的附图及实施例仅用于示例性作用,并非用于限制本发明的保护范围。Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the invention are shown in the drawings, it should be understood that the 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 the purpose of A more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only used for exemplary purposes, and are not used to limit the protection scope of the present invention.
本发明实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本发明实施例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the embodiments of the present invention and the above-mentioned drawings are used to distinguish similar objects, while It is not necessary to describe a particular order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the invention described herein can, for example, be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having", and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.
首先对本发明实施例的应用场景进行说明。具体地,本发明实施例提供的医用问答方法可采用客户端或网页为用户提供服务。如可以为在智能手机、计算机或其他电子设备上的应用程序。在一种应用场景中,用户有对医学问答对应答案的搜索需求时,可采用本发明实施例提供的医用问答方法。具体地,可通过客户端或网页中的首页操作界面中的搜索输入框输入目标关键字段进行医学答案的搜索查询。或者在另一种应用场景中,当用户有对医学知识的专项提问需求时,可采用本发明实施例提供的医学问答方法。具体地,可通过客户端或网页中的用户管理界面下的待提交审核界面输入待提交审核问题,并可选择某一医学专业人员,由该医学专业人员进行待提交审核问题的回答。可以理解的是,若该医学专业人员预设时间段内未进行待提交审核问题的答复,也可由其他医学专业人员进行该待提交审核问题的答复。或者在又一种应用场景中,在用户为医学专业人员时,在临床或学术研究中遇到医学上的问题,并通过查找文献寻找到准确的答案后,可采用本发明实施例提供的医学问答方法。具体地,可通过客户端或网页中的问答对记录界面,提交记录的问题及答案,并记录答案的追溯数据。以在其他用户进行该问题的答案搜索时,分享给其他用户。First, the application scenarios of the embodiments of the present invention are described. Specifically, the medical question answering method provided by the embodiment of the present invention may use a client terminal or a web page to provide services for the user. For example, it can be an application on a smartphone, computer or other electronic device. In an application scenario, when a user has a search requirement for an answer corresponding to a medical question and answer, the medical question and answer method provided by the embodiment of the present invention may be used. Specifically, a search query for medical answers can be performed by entering a target key field through a search input box in the homepage operation interface of the client or the webpage. Or in another application scenario, when the user has a special questioning demand for medical knowledge, the medical question answering method provided by the embodiment of the present invention may be adopted. Specifically, the to-be-submitted review questions can be input through the to-be-submitted review interface under the user management interface in the client or webpage, and a medical professional can be selected, and the medical professional can answer the to-be-submitted review questions. It can be understood that, if the medical professional does not reply to the question to be submitted for review within a preset time period, other medical professionals can also answer the question to be submitted for review. Or in another application scenario, when the user is a medical professional and encounters a medical problem in clinical or academic research, and finds an accurate answer by searching literature, the medical treatment provided by the embodiment of the present invention can be used. Question and answer method. Specifically, the recorded questions and answers can be submitted through the Q&A record interface in the client or the web page, and the retrospective data of the answers can be recorded. to share with other users when they search for the answer to this question.
可以理解的是,本实施例提供的医用问答方法的应用场景还以为其他应用场景,本实施例中对此不作限定。It can be understood that the application scenarios of the medical question answering method provided in this embodiment can also be other application scenarios, which are not limited in this embodiment.
以下将参照附图来具体描述本发明的实施例。Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
实施例一Example 1
图1为本发明实施例一提供的医用问答方法的流程图,如图1所示,本实施例提供的医用问答方法的执行主体为医用问答设备,该医用问答设备可以集成在电子设备中,电子设备可以为智能手机,计算机等具有独立计算和处理能力的设备。则本实施例提供的医用问答方法包括以下几个步骤。FIG. 1 is a flowchart of a medical question and answer method provided in
步骤101,接收用户通过首页操作界面中搜索输入框输入的目标关键字段。Step 101: Receive the target key field input by the user through the search input box in the homepage operation interface.
其中,用户为该医用问答方法的使用用户,该用户可以为医用专业人员,如可以为医师,医学研究人员。或者还可以为没有医学专业知识的人员,如患者,健康人员等,本实施例中对该用户不作限定。The user is a user of the medical question answering method, and the user may be a medical professional, such as a doctor or a medical researcher. Or it can also be a person without medical professional knowledge, such as a patient, a healthy person, etc., and the user is not limited in this embodiment.
具体地,本实施例中,在用户打开本实施例提供的医用问答方法对应的客户端或网页后,进入首页操作界面。如图2所示,在首页操作界面的上端包括搜索输入框,用户通过点击搜索输入框,可在搜索输入框输入目标关键字段,并通过点击确认搜索的按键后,医用问答设备接收到用户输入的目标关键字段。Specifically, in this embodiment, after the user opens the client or web page corresponding to the medical question answering method provided in this embodiment, the user enters the home page operation interface. As shown in Figure 2, a search input box is included on the upper end of the homepage operation interface. By clicking the search input box, the user can input the target key field in the search input box, and after clicking the button to confirm the search, the medical question answering device receives the user Enter the target key field.
其中,目标关键字段为目标问题中的关键字段。目标问题为用户需要搜索答案的问题。可以理解的是,目标关键字段也可以就是目标问题。Among them, the target key field is the key field in the target question. The target question is the question for which the user needs to search for an answer. Understandably, the target key field can also be the target question.
如图2所示,在首页操作界面中除了包括搜索输入框外,还可以包括至少一个维度向用户推送的问答对。如至少一个维度可以包括:热点推荐维度,关注维度,专题维度等。这些维度的控件可设置在搜索输入框的下方。用户通过点击某一个维度的控件,在操作界面中显示该维度下向该用户推送的至少一个问答对。As shown in FIG. 2 , in addition to the search input box, the homepage operation interface may also include a question-and-answer pair that is pushed to the user in at least one dimension. For example, at least one dimension may include: a hotspot recommendation dimension, a concern dimension, a topic dimension, and the like. Controls for these dimensions can be placed below the search input box. By clicking a control of a certain dimension, the user displays at least one question-and-answer pair pushed to the user under the dimension in the operation interface.
可以理解的是,在首页操作界面中显示每个问答对时,为了能尽量多的显示问答对,可对答案进行简要显示,在接收到用户对某一问答对的点击操作后,进入该问答对的界面,在该界面中显示问题,详细的答案及追溯数据。该追溯数据可以为该答案的参考文献。如参考文献为某出版社出版的某期刊在某个时间刊登的名称为xx的论文。可以理解的是,答案的参考文献可以为一个或多个。It is understandable that when each question and answer pair is displayed on the home page operation interface, in order to display as many question and answer pairs as possible, the answer can be briefly displayed, and after receiving the user's click operation on a question and answer pair, enter the question and answer pair. The right interface, in which questions, detailed answers and traceback data are displayed. This retrospective data can be a reference for this answer. For example, the reference is a paper named xx published by a journal published by a certain publishing house at a certain time. It is understood that the reference for the answer can be one or more.
需要说明的是,在首页操作界面的最下方还可以包括关注选项,提问选项,收藏选项及用户管理选项,用户管理选项即为图2中的“我的”选项。用户通过点击每个选项进入对应的操作界面后,通过在操作界面中进行操作实现对应的功能。It should be noted that the bottom part of the homepage operation interface may also include a follow option, a question option, a favorite option, and a user management option, and the user management option is the “My” option in FIG. 2 . After the user enters the corresponding operation interface by clicking each option, the corresponding function is realized by operating in the operation interface.
可以理解的是,用户在点击关注控件查看推送的至少一个问答对前,可通过触发首页操作界面下方的关注选项,进入到关注配置操作界面,进行所关注科室的配置。It is understandable that, before clicking the follow control to view at least one question-and-answer pair pushed, the user can enter the follow configuration operation interface by triggering the follow option at the bottom of the homepage operation interface, and configure the concerned department.
步骤102,对目标关键字段进行语义解析,以获取目标关键字段对应的目标实体属性。Step 102: Perform semantic analysis on the target key field to obtain the target entity attribute corresponding to the target key field.
具体地,本实施例中,对目标关键字段进行语义解析,包括对目标关键字段进行实体抽取及意图识别,在实体抽取和意图识别后,获取该目标关键字段对应的目标实体属性。Specifically, in this embodiment, semantic analysis is performed on the target key field, including entity extraction and intention recognition for the target key field, and after entity extraction and intention recognition, the target entity attribute corresponding to the target key field is obtained.
步骤103,根据目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对。Step 103: Determine at least one target question-answer pair that meets the matching requirement according to the target entity attribute and the pre-built knowledge base.
本实施例中,预先构建的知识库中可以包括大量的问答对,并且在每个问答对中不仅包括问题和答案,而且还包括答案的追溯数据,追溯数据为参考文献,即每个问题的答案的获得,都是从参考文献中得到的,以保证该答案的准确性和可追溯性。In this embodiment, the pre-built knowledge base may include a large number of question-and-answer pairs, and each question-and-answer pair includes not only questions and answers, but also retrospective data of the answers. The retrospective data are references, that is, the The answers are obtained from references to ensure the accuracy and traceability of the answers.
具体地,本实施例中,作为一种可选实施方式,对每个问答对中的问题进行语义解析,以获得每个问题的实体属性。然后将目标实体属性与每个问题的实体属性进行匹配,以获得目标实体属性与每个问题的实体属性的匹配度。判断匹配度是否达到匹配要求,若达到匹配要求,则将满足匹配要求的至少一个问答对应的问答对作为目标问答对。Specifically, in this embodiment, as an optional implementation manner, semantic analysis is performed on the questions in each question-answer pair to obtain the entity attributes of each question. The target entity attribute is then matched with the entity attribute of each question to obtain the matching degree of the target entity attribute with the entity attribute of each question. It is judged whether the matching degree meets the matching requirement, and if the matching requirement is met, the question-and-answer pair corresponding to at least one question and answer that meets the matching requirement is used as the target question-answer pair.
在确定出目标问答对后,若目标问答对为多个,可以按照匹配度的高低在搜索结果显示界面上先后排布进行简单显示。After the target question-and-answer pair is determined, if there are multiple target question-answer pairs, they can be arranged in sequence on the search result display interface according to the matching degree for simple display.
步骤104,响应于用户对目标问答对的触发操作,显示目标问答对,目标问答对中包括:目标问题,目标答案及追溯数据,追溯数据为参考文献。Step 104: In response to the user's triggering operation on the target question and answer pair, the target question and answer pair is displayed, and the target question and answer pair includes: the target question, the target answer and the retrospective data, and the retrospective data is a reference document.
具体地,本实施例中,用户在搜索结果显示界面上点击某一个目标问答对,响应于用户对该目标问答对的触发操作,跳转到该目标问答对的显示界面,在该目标问答对的显示界面上显示目标问答对。Specifically, in this embodiment, the user clicks on a certain target question and answer pair on the search result display interface, and in response to the user's triggering operation on the target question and answer pair, jumps to the display interface of the target question and answer pair, and in the target question and answer pair The target question-answer pair is displayed on the display interface of .
如图3所示,可首先显示目标问题,然后显示目标答案,最后显示目标答案的追溯数据。该追溯数据为参考文献。如在搜索“肝功能怎样评价”的目标关键字段后,搜索出的目标问题为“肝功能如何评价”。目标答案为图3所示。可以理解的是,若目标答案的内容较多,用户可通过滑动的操作实现目标答案的全部显示。在目标答案的下方显示追溯数据,该追溯数据为参考文献。As shown in Figure 3, the target question may be displayed first, then the target answer, and finally the retrospective data for the target answer. This retrospective data is a reference. For example, after searching for the target key field of "how to evaluate liver function", the searched target question is "how to evaluate liver function". The target answer is shown in Figure 3. It can be understood that, if the content of the target answer is large, the user can display all the target answers through the sliding operation. The retrospective data is displayed below the target answer, and the retrospective data is the reference.
本实施例提供的医用问答方法,通过接收用户通过首页操作界面中搜索输入框输入的目标关键字段;对目标关键字段进行语义解析,以获取目标关键字段对应的目标实体属性;根据目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对;响应于用户对目标问答对的点击操作,显示目标问答对,目标问答对中包括:目标问题,目标答案及追溯数据,追溯数据为参考文献。由于在预先构建的知识库中,每个问答对均具有答案对应的追溯数据,并且该追溯数据的形式是参考文献的形式,能够保证每个问题的答案的准确性和可追溯性,所以用户在搜索到答案后,能够以追溯数据为依据确定该答案的准确性,可以应用在医学领域的搜索中,提高了对医学领域搜索答案的体验。The medical question answering method provided by this embodiment receives the target key field input by the user through the search input box in the homepage operation interface; performs semantic analysis on the target key field to obtain the target entity attribute corresponding to the target key field; The entity attributes and the pre-built knowledge base determine at least one target question-answer pair that meets the matching requirements; in response to the user's click operation on the target question-answer pair, the target question-answer pair is displayed, and the target question-answer pair includes: target question, target answer and retrospective data, Traced data are references. In the pre-built knowledge base, each question-and-answer pair has traceability data corresponding to the answer, and the traceback data is in the form of references, which can ensure the accuracy and traceability of the answers to each question, so users After the answer is searched, the accuracy of the answer can be determined based on the retrospective data, which can be applied to the search in the medical field, and improves the experience of searching for an answer in the medical field.
实施例二Embodiment 2
图4为本发明实施例二提供的医用问答方法的流程图,如图4所示,本实施例提供的医用问答方法,是在本发明实施例一提供的医用问答方法的基础上,对步骤103的进一步细化,并且还包括了构建知识库的步骤,其中,知识库为知识图谱,则本实施例提供的医用问答方法包括以下步骤。Fig. 4 is a flowchart of the medical question and answer method provided in the second embodiment of the present invention. As shown in Fig. 4 , the medical question and answer method provided by the present embodiment is based on the medical question and answer method provided by the first embodiment of the present invention. 103 is further refined, and also includes the step of building a knowledge base, where the knowledge base is a knowledge graph, and the medical question answering method provided by this embodiment includes the following steps.
步骤201,获取医学专业人员通过配置界面配置的医学领域中满足准确要求的文献类型及格式信息。Step 201: Obtain document type and format information in the medical field configured by medical professionals through a configuration interface that meets accurate requirements.
可选地,本实施例中,在医学专业人员的用户终端上设置有构建知识图谱的客户端,则医学专业人员登录到该客户端后,进行是否为医学专业人员的相关认证,在认证能通过后,可打开配置界面,进行医学领域中满足准确要求的文献类型及格式信息的配置。如配置的满足准确要求的文献类型可以为临床指南,优秀医学期刊,优秀医学论文等。配置的满足准确要求的文献格式如可以为图片格式,PDF格式等。Optionally, in this embodiment, a client for building a knowledge graph is set on the user terminal of a medical professional, and after the medical professional logs in to the client, the relevant certification of whether it is a medical professional is performed. After passing, the configuration interface can be opened to configure the document types and format information that meet the exact requirements in the medical field. For example, the configured document types that meet the exact requirements can be clinical guidelines, excellent medical journals, excellent medical papers, etc. The configured document format that meets the exact requirements can be image format, PDF format, etc.
步骤202,根据满足准确要求的文献类型及格式信息获取知识图谱的构建语料。Step 202: Acquire the construction corpus of the knowledge graph according to the document type and format information that meet the exact requirements.
具体地,本实施例中,可通过访问第三方平台,获取在医学领域中的文献,然后对各个文献进行解析,提取出在文献类型和格式上都满足配置的准确要求的文献,以获得构建知识图谱的语料,该语料可以表示为构建语料。Specifically, in this embodiment, documents in the medical field can be obtained by accessing a third-party platform, and then each document can be parsed to extract documents that meet the exact requirements of the configuration in terms of document type and format, so as to obtain the construction The corpus of the knowledge graph, which can be represented as a construction corpus.
其中,医学领域可以为老年护理领域,传染病学领域,血液病领域,或其他科室的领域等。Among them, the medical field can be the field of geriatric care, the field of infectious diseases, the field of hematology, or the field of other departments.
步骤203,接收医学专业人员通过配置界面输入的医学领域中的schema集合。Step 203: Receive a schema set in the medical field input by a medical professional through a configuration interface.
本实施例中,在配置界面中除了包括对文献类型及格式的配置控件,还包括对医学领域中的schema集合的配置控件。In this embodiment, in addition to the configuration controls for document types and formats, the configuration interface also includes configuration controls for schema collections in the medical field.
在对知识图谱进行构建时,要从构建语料中抽取SPO三元组数据,SPO三元组数据,是指实体S、关系P(或者属性P),实体O(或者属性值O)构成的三元组,其中S是P的主体,O是P的客体。在对SPO三元组数据进行抽取时,需要确定从构建语料中所要抽取的SPO三元组数据中,关系/属性P,以及该P的主体(S)类型以及客体(O)类型。而关系/属性P,以及该P的主体(S)类型以及客体(O)类型就构成了schema集合。When constructing the knowledge graph, the SPO triplet data should be extracted from the construction corpus. The SPO triplet data refers to the three elements consisting of entity S, relation P (or attribute P), and entity O (or attribute value O). A tuple, where S is the subject of P and O is the object of P. When extracting the SPO triplet data, it is necessary to determine the relationship/attribute P, the subject (S) type and the object (O) type of the SPO triplet data to be extracted from the construction corpus. The relationship/attribute P, as well as the subject (S) type and object (O) type of the P constitute the schema set.
由于医学专业人员对医学领域有非常专业的了解,所以由医学专业人员通过配置界面对医学领域中的schema集合进行配置,能够对schema集合进行准确地配置。Since medical professionals have a very professional understanding of the medical field, the schema collection in the medical field is configured by the medical professional through the configuration interface, and the schema collection can be configured accurately.
可以理解的是,每个医学专业人员所擅长的医学领域不同,所以可针对医学专业人员的认证信息确定该医学专业人员所擅长的医学领域,并在配置界面中显示该医学领域,以使每个医学专业人员针对所擅长的医学领域进行对应schema集合的配置。It can be understood that each medical professional specializes in different medical fields, so the medical field that the medical professional is good at can be determined according to the certification information of the medical professional, and the medical field is displayed in the configuration interface, so that each medical professional can Each medical professional configures the corresponding schema set according to the medical field they are good at.
步骤204,从构建语料中抽取在schema集合范围内的构建三元组数据。Step 204, extracting the construction triplet data within the scope of the schema set from the construction corpus.
本实施例中,可采用抽取算法对构建语料中的三元组数据进行抽取,并在对三元组数据进行抽取时,以schema集合为约束条件,使得抽取得到的三元组数据在schema集合范围内,将抽取得到的三元组数据确定为构建知识图谱的三元组数据,可表示为构建三元组数据。In this embodiment, an extraction algorithm can be used to extract the triplet data in the construction corpus, and when extracting the triplet data, the schema set is used as a constraint, so that the extracted triplet data is in the schema set Within the scope, the extracted triplet data is determined as the triplet data for constructing the knowledge graph, which can be expressed as constructing triplet data.
步骤205,获取与构建三元组数据对应的构建问答对。Step 205: Acquire the constructed question and answer pair corresponding to the constructed triple data.
本实施例中,在从语料中抽取得到构建三元组数据后,还可以从对应的语料中抽取到对应的问题,答案及追溯数据,将对应的问题,答案及追溯数据表示为构建问答对。In this embodiment, after the construction triplet data is extracted from the corpus, the corresponding questions, answers and retrospective data can also be extracted from the corresponding corpus, and the corresponding questions, answers and retrospective data can be expressed as constructing a question-and-answer pair .
步骤206,根据构建三元组数据及对应的构建问答对构建知识图谱。Step 206 , constructing a knowledge graph according to the constructing triplet data and the corresponding constructing question-answer pairs.
具体地,本实施例中,可获取所有的构建三元组数据,提取各个构建三元组数据间的关联关系,并根据各关联关系构建图结构,以构建出知识图谱。并在该知识图谱中存储每个构建三元组数据与对应的问答对间的映射关系。Specifically, in this embodiment, all construction triplet data can be obtained, the association relationship between each construction triplet data can be extracted, and a graph structure can be constructed according to each association relationship, so as to construct a knowledge graph. And the mapping relationship between each constructed triple data and the corresponding question-answer pair is stored in the knowledge graph.
本实施例提供的医用问答方法,在构建知识图谱的过程中,由于在获取知识图谱的构建语料前,由医学专业人员通过配置界面配置的在预设医学领域中满足准确要求的文献类型及格式信息,所以保证了构建语料的准确性和权威性。并且在从构建语料中抽取构建三元组数据时,该医学领域中的schema集合也是有医学专业人员配置的,所以保证了抽取出的构建三元组数据的准确性。进而能够使构建出的知识图谱能够准确反映出该医学领域中的实物间的客观关系和问答对的准确性。In the medical question answering method provided by this embodiment, in the process of constructing the knowledge graph, before acquiring the construction corpus of the knowledge graph, the document types and formats that meet the exact requirements in the preset medical field are configured by medical professionals through the configuration interface. information, so the accuracy and authority of the constructed corpus are guaranteed. In addition, when the construction triple data is extracted from the construction corpus, the schema set in the medical field is also configured by medical professionals, so the accuracy of the extracted construction triple data is ensured. Furthermore, the constructed knowledge graph can accurately reflect the objective relationship between objects in the medical field and the accuracy of question-and-answer pairs.
可选地,本实施例中,在步骤206之前,还包括以下步骤:Optionally, in this embodiment, before step 206, the following steps are further included:
步骤2051,将构建三元组数据及对应的构建问答对发送至医学专业人员对应的用户终端,以使用户终端显示构建三元组数据及对应的构建问答对,以由医学专业人员进行审核。Step 2051: Send the construction triplet data and the corresponding construction question and answer pair to the user terminal corresponding to the medical professional, so that the user terminal displays the construction triplet data and the corresponding construction question and answer pair for review by the medical professional.
步骤2052,接收用户终端发送的审核结果。Step 2052: Receive the audit result sent by the user terminal.
步骤2053,若确定审核结果为未通过,则获取修正后的构建三元组数据及对应的构建问答对。Step 2053: If it is determined that the audit result is not passed, the revised construction triplet data and the corresponding construction question-and-answer pair are acquired.
本实施例中,将构建三元组数据及对应的构建问答对发送至医学专业人员对应的用户终端,在用户终端显示构建三元组数据及对应的构建问答对后,医学专业人员对各构建三元组数据及对应的构建问答对进行审核,若构建三元组数据及对应的构建问答对满足准确要求,则审核通过。若构建三元组数据及对应的构建问答对不满足准确要求,则审核未通过。在审核未通过后,对该构建三元组数据和/或对应的构建问答对进行修正。In this embodiment, the construction triplet data and the corresponding construction question and answer pairs are sent to the user terminal corresponding to the medical professional, and after the construction triplet data and the corresponding construction question and answer pair are displayed on the user terminal, the medical professional The triplet data and the corresponding construction question-and-answer pair are reviewed. If the construction triplet data and the corresponding construction question-and-answer pair meet the accurate requirements, the review is passed. If the construction triplet data and the corresponding construction question-and-answer pair do not meet the exact requirements, the audit will fail. After the review fails, the construction triplet data and/or the corresponding construction question-and-answer pair are corrected.
可以理解的是,若审核通过,则将审核通过的审核结果发送给医用问答设备,若审核未通过,则将审核未通过的结果及修正后的构建三元组数据及对应的构建问答对一同发送给医用问答设备,以使医用问答设备获取到修正后的构建三元组数据及对应的构建问答对。It is understandable that if the audit is passed, the audit result that has passed the audit will be sent to the medical question-and-answer device. If the audit is not passed, the result of the audit that has not passed the audit will be combined with the revised construction triplet data and the corresponding construction question-and-answer pair. Send it to the medical question answering device, so that the medical question answering device can obtain the revised construction triplet data and the corresponding construction question answering pair.
相应地,则步骤206具体为:根据修正后的构建三元组数据及对应的构建问答对构建知识图谱。Correspondingly, step 206 is specifically: constructing a knowledge graph according to the revised construction triplet data and the corresponding construction question and answer pairs.
本实施例提供的医用问答方法,在构建知识图谱的过程中,获取到构建三元组数据及对应的构建问答对后,发送给医学专业人员的用户终端,由医学专业人员进行审核,以使构建知识图谱的构建三元组数据和对应的构建问答对的准确性,进一步提高了知识图谱的准确性。In the medical question answering method provided in this embodiment, in the process of constructing the knowledge graph, after acquiring the constructing triplet data and the corresponding constructing question and answer pair, it is sent to the user terminal of the medical professional, and the medical professional will review it, so that the The accuracy of constructing triplet data for constructing knowledge graph and corresponding constructing question-answer pairs further improves the accuracy of knowledge graph.
步骤207,接收用户通过首页操作界面中搜索输入框输入的目标关键字段。Step 207: Receive the target key field input by the user through the search input box in the homepage operation interface.
步骤208,对目标关键字段进行语义解析,以获取目标关键字段对应的目标实体属性。Step 208: Perform semantic analysis on the target key field to obtain the target entity attribute corresponding to the target key field.
本实施例中,步骤207-步骤208的实现方式与本发明实施例一中的步骤101-步骤102的实现方式相同,在此不再一一赘述。In this embodiment, the implementation manners of steps 207 to 208 are the same as the implementation manners of steps 101 to 102 in
步骤209,根据目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对。Step 209: Determine at least one target question-answer pair that meets the matching requirement according to the target entity attribute and the pre-built knowledge base.
可选地,本实施例中,步骤209包括以下步骤:Optionally, in this embodiment,
步骤2091,根据目标实体属性从预先构建的知识图谱中获取候选三元组集合,候选三元组集合中包括至少一个候选三元组。Step 2091: Obtain a candidate triplet set from a pre-built knowledge graph according to the attribute of the target entity, where the candidate triplet set includes at least one candidate triplet.
具体地,本实施例中,对目标实体属性进行解析,并从预先构建的知识图谱中获取与目标实体属性相关度满足预设相关度的三元组数据作为候选三元组数据,由候选三元组数据构成候选三元组集合。Specifically, in this embodiment, the attribute of the target entity is parsed, and triplet data whose correlation degree with the attribute of the target entity meets the preset degree of correlation is obtained from a pre-built knowledge graph as candidate triplet data, and the candidate triplet The tuple data constitutes a set of candidate triples.
其中,目标实体属性与各三元组数据的相关度可以采用关联节点数表示。若目标实体属性与某三元组数据的关联节点数小于预设节点数,则确定该三元组数据满足预设相关度,若目标实体属性与某三元组数据的关联节点数大于或等于预设节点数,则确定该三元组数据不满足预设相关度。The correlation between the attribute of the target entity and each triplet data can be represented by the number of associated nodes. If the number of associated nodes between the attribute of the target entity and a certain triplet data is less than the preset number of nodes, it is determined that the triplet data satisfies the preset degree of relevancy, if the number of associated nodes between the attribute of the target entity and a certain triplet data is greater than or equal to If the number of nodes is preset, it is determined that the triplet data does not meet the preset correlation degree.
或者采用其他数据表示目标实体属性与各三元组数据的相关度,本实施例中不作限定。Alternatively, other data may be used to represent the correlation between the attribute of the target entity and the data of each triple, which is not limited in this embodiment.
步骤2092,将目标实体属性与候选三元组采用匹配模型进行匹配计算,以获得满足匹配要求的候选三元组作为目标三元组。Step 2092 , perform matching calculation between the target entity attribute and the candidate triplet using a matching model, so as to obtain a candidate triplet that meets the matching requirements as the target triplet.
具体地,将目标实体属性和各候选三元组输入到匹配模型中,匹配模型将目标实体属性与各候选三元组进行匹配计算,计算出目标实体属性与各候选三元组的匹配度,将匹配度大于预设匹配度的候选三元组数据确定为满足匹配要求的候选三元组,将满足匹配要求的候选三元组确定为目标三元组。Specifically, the target entity attribute and each candidate triplet are input into the matching model, and the matching model performs matching calculation on the target entity attribute and each candidate triplet, and calculates the matching degree between the target entity attribute and each candidate triplet, The candidate triplet data with the matching degree greater than the preset matching degree is determined as the candidate triplet that meets the matching requirement, and the candidate triplet that meets the matching requirement is determined as the target triplet.
其中,匹配模型可以为深度学习模型,如可以为卷积神经网络模型,循环神经网络模型等。The matching model may be a deep learning model, such as a convolutional neural network model, a recurrent neural network model, or the like.
步骤2093,从预先构建的知识图谱中获取目标三元组对应的目标问答对。Step 2093: Obtain the target question-answer pair corresponding to the target triplet from the pre-built knowledge graph.
本实施例中,由于知识图谱中关联存储有每个构建三元组与对应的构建问答对,所以从知识图谱中获取目标三元组对应的目标问答对,在该目标问答对中包括目标问题、目标答案及追溯数据。In this embodiment, since each construction triplet and the corresponding construction question-and-answer pair are stored in the knowledge graph, the target question-answer pair corresponding to the target triplet is obtained from the knowledge graph, and the target question-answer pair includes the target question , target answers and retrospective data.
需要说明的是,在步骤2091之前,还可以通过知识图谱对目标实体属性进行校验,若目标实体属性并非该知识图谱对应的医学领域的实体属性,则确定该目标实体属性对应的用户搜索的问题是一个无效问题,能够快速对无效问题进行响应。It should be noted that, before step 2091, the attribute of the target entity can also be verified through the knowledge graph. If the attribute of the target entity is not the entity attribute of the medical field corresponding to the knowledge graph, the user searched for the attribute corresponding to the attribute of the target entity is determined. The question is an invalid question, and a quick response to the invalid question is possible.
步骤210,响应于用户对目标问答对的点击操作,显示目标问答对,目标问答对中包括:目标问题,目标答案及追溯数据,追溯数据为参考文献。Step 210: In response to the user's click operation on the target question and answer pair, the target question and answer pair is displayed, and the target question and answer pair includes: the target question, the target answer and the retrospective data, and the retrospective data is a reference.
本实施例中,步骤210的实现方式与本发明实施例一中的步骤104的实现方式类似,在此不再一一赘述。In this embodiment, the implementation manner of step 210 is similar to the implementation manner of step 104 in
本实施例提供的医用问答方法,在根据目标实体属性及预先构建的知识库确定满足匹配要求的至少一个目标问答对时,根据目标实体属性从预先构建的知识图谱中获取候选三元组集合,候选三元组集合中包括至少一个候选三元组;将目标实体属性与候选三元组采用匹配模型进行匹配计算,以获得满足匹配要求的候选三元组作为目标三元组;从预先构建的知识图谱中获取目标三元组对应的目标问答对。首先从知识图谱中获取到与目标实体属性匹配的候选三元组集合,然后将目标实体属性与候选三元组集合中的候选三元组进行匹配计算,能够在保证获取到的目标三元组是准确三元组的同时,有效降低了匹配算法进行匹配计算的计算量,提高了确定满足匹配要求的目标问答对的效率。In the medical question answering method provided in this embodiment, when at least one target question answering pair that meets the matching requirements is determined according to the attributes of the target entity and the pre-built knowledge base, the candidate triplet set is obtained from the pre-built knowledge graph according to the attributes of the target entity, The candidate triplet set includes at least one candidate triplet; the target entity attribute and the candidate triplet are matched and calculated by using a matching model, so as to obtain the candidate triplet that meets the matching requirements as the target triplet; The target question-answer pair corresponding to the target triplet is obtained from the knowledge graph. First, the set of candidate triples matching the attributes of the target entity is obtained from the knowledge graph, and then the attribute of the target entity is matched with the candidate triples in the set of candidate triples, which can guarantee the obtained target triples. While it is an accurate triple, it effectively reduces the calculation amount of the matching algorithm for the matching calculation, and improves the efficiency of determining the target question-answer pair that meets the matching requirements.
实施例三Embodiment 3
图5为本发明实施例三提供的医用问答方法的流程图,如图5所示,本实施例提供的医用问答方法,是在本发明实施例一或实施例二提供的医用问答方法的基础上,还包括了其他步骤,则本实施例提供的医用问答方法还包括以下步骤。FIG. 5 is a flowchart of the medical question and answer method provided in the third embodiment of the present invention. As shown in FIG. 5 , the medical question and answer method provided in this embodiment is the basis of the medical question and answer method provided in the first or second embodiment of the present invention. If other steps are included above, the medical question answering method provided in this embodiment further includes the following steps.
步骤301,响应于用户通过首页操作界面中提问选项的触发操作,显示问答对记录界面。Step 301 , in response to the user's triggering operation through the question option in the homepage operation interface, a question-and-answer pair record interface is displayed.
具体地,本实施例中,如图2所示,在首页操作界面的最下方包括提问选项,则用户通过点击该提问选项,操作界面从首页操作界面跳转到问答对记录界面中。Specifically, in this embodiment, as shown in FIG. 2 , a question option is included at the bottom of the homepage operation interface, and the user clicks the question option, and the operation interface jumps from the homepage operation interface to the question-and-answer pair record interface.
步骤302,响应于用户在问答对记录界面输入的记录问答对的提交操作,判断用户是否为医学专业人员。Step 302, in response to the user's input operation of submitting a recorded question-and-answer pair on the question-and-answer pair record interface, determine whether the user is a medical professional.
本实施例中,如图6所示,在问答对记录界面中,包括问题的输入框,问题答案的输入框及参考文献的输入框,用户可在问题的输入框中输入问题。在问题答案的输入框中输入记录的问答对应的答案。在参考文献的输入框中输入参考文献。输入的问题,问题答案及参考文献构成了记录问答对。In this embodiment, as shown in FIG. 6 , the Q&A pair record interface includes a question input box, a question answer input box, and a reference input box, and the user can input a question in the question input box. Enter the answer corresponding to the recorded question and answer in the question answer input box. Enter the reference in the reference input box. Entered questions, question answers, and references constitute a recorded question-answer pair.
步骤303,若确定用户为医学专业人员,则提取记录问答对对应的记录三元组,并将记录问答对及对应的记录三元组更新到知识库中。Step 303, if it is determined that the user is a medical professional, extract the record triplet corresponding to the record question-and-answer pair, and update the record question-answer pair and the corresponding record triplet to the knowledge base.
本实施例中,在用户点击提交按键后,通过登录的用户名可从医用问答设备中判断该用户是否通过了医学专业人员的认证,若确定该用户通过了医学专业人员的认证,则说明该记录的问答对是通过医学专业人员审核后的问答对,保证该记录问答对的准确性。从该问答对中提取中三元组数据,该三元组数据为记录三元组,并将记录问答对及对应的记录三元组更新到知识库中。能够使知识库中的问答对不断进行丰富,并保证知识库中问答对的准确性。In this embodiment, after the user clicks the submit button, it can be determined from the medical question-and-answer device whether the user has passed the certification of a medical professional through the logged-in user name. If it is determined that the user has passed the certification of a medical professional, it means that the The recorded question-and-answer pair is the question-and-answer pair that has been reviewed by medical professionals to ensure the accuracy of the recorded question-and-answer pair. The middle triplet data is extracted from the question-answer pair, and the triplet data is a record triplet, and the record question-answer pair and the corresponding record triplet are updated into the knowledge base. It can continuously enrich the question and answer pairs in the knowledge base, and ensure the accuracy of the question and answer pairs in the knowledge base.
可以理解的是,由于知识库中的每个问答对都经过医学专业人员的审核,所以还可以在显示目标问答对时,显示审核该目标问答对的医学专业人员的信息。如在参考文献的下方显示审核该目标问答对的医学专业人员的姓名,所属科室等信息。Understandably, since each question-and-answer pair in the knowledge base is reviewed by a medical professional, information of the medical professional who reviewed the target question-and-answer pair can also be displayed when the target question-answer pair is displayed. For example, the names of the medical professionals who reviewed the target question-and-answer pair, the departments they belong to, and other information are displayed below the references.
实施例四Embodiment 4
图7为本发明实施例四提供的医用问答方法的流程图,如图7所示,本实施例提供的医用问答方法,是在本发明实施例一至实施例三任意一个实施例提供的医用问答方法的基础上,还包括了其他步骤,则本实施例提供的医用问答方法还包括以下步骤。FIG. 7 is a flowchart of a medical question and answer method provided in Embodiment 4 of the present invention. As shown in FIG. 7 , the medical question and answer method provided in this embodiment is a medical question and answer method provided in any one of
步骤401,响应于用户通过首页操作界面中用户管理选项的触发操作,显示用户管理界面。Step 401, in response to a user's triggering operation through the user management option in the homepage operation interface, display a user management interface.
具体地,如图2所示,在首页操作界面的最下方包括用户管理选项,用户管理选项即为图2中的“我的”选项。则用户通过点击该“我的”选项,操作界面从首页操作界面跳转到用户管理界面中。如图7所示,在用户管理界面中包括问题选项,即“我的问题”的选项。Specifically, as shown in FIG. 2 , a user management option is included at the bottom of the homepage operation interface, and the user management option is the “My” option in FIG. 2 . Then the user clicks the "My" option, and the operation interface jumps from the homepage operation interface to the user management interface. As shown in FIG. 7 , a question option, that is, an option of "My Question", is included in the user management interface.
步骤402,响应于用户通过用户管理界面中问题选项的触发操作,显示待提交审核问题界面及已提交审核问题界面。Step 402 , in response to the user's triggering operation through the question option in the user management interface, the interface of the question to be submitted for review and the interface of the question that has been submitted for review are displayed.
本实施例中,用户通过点击问题选项,将操作界面从用户管理界面跳转到问题管理界面。在问题管理界面中包括待提交审核问题选项和已提交审核问题选项。In this embodiment, the user jumps the operation interface from the user management interface to the problem management interface by clicking the question option. Included in the issue management interface are the Pending Review Issues option and the Submitted Review Issues option.
步骤403,响应于用户对待提交审核问题选项的触发操作,显示待提交审核问题界面,通过待提交审核界面输入待提交审核问题及选择某一医学专业人员后的提交操作,将待提交审核问题发送至该医学专业人员对应的待审核界面中,并将待提交审核问题移交到用户对应的已提交审核问题界面中。Step 403: In response to the user's triggering operation of the option to be submitted for review questions, an interface to be submitted for review is displayed, and the to-be-submitted review questions are input through the to-be-submitted review interface and the submission operation after selecting a medical professional, and the to-be-submitted review questions are sent. to the pending review interface corresponding to the medical professional, and hand over the pending review questions to the user's corresponding submitted review questions interface.
本实施例中,用户通过点击待提交审核问题选项,界面从问题管理界面跳转到待提交审核问题界面。在待提交审核界面中具有待提交审核问题的输入框,通过该待提交审核问题的输入框可输入待提交审核问题,并且在待提交审核问题界面中还显示有进行注册的所有医学专业人员的标识信息,如每个医学专业人员的姓名,照片等。用户可选择某一个医学专业人员后,点击提交按键,进行该待提交审核问题的提交。以将该待提交审核问题发送至医学专业人员对应的待审核界面中。In this embodiment, the user clicks the option of the question to be submitted for review, and the interface jumps from the question management interface to the interface of the question to be submitted for review. In the to-be-submitted review interface, there is an input box for questions to be submitted for review, through which questions to be submitted for review can be input, and the interface for questions to be submitted for review also displays the information of all registered medical professionals Identifying information such as each medical professional's name, photo, etc. After the user can select a medical professional, click the submit button to submit the question to be submitted for review. to send the pending review question to the pending review interface corresponding to the medical professional.
可以理解的是,在用户通过点击提交按键对该待审核问题进行提交后,该待提交审核问题移交到用户对应的已提交审核问题界面中,用户通过点击已提交审核问题选项后,进入到该已提交审核问题界面中,可查看到移交的该待提交审核问题。It is understandable that after the user submits the question to be reviewed by clicking the submit button, the question to be submitted for review will be transferred to the user's corresponding submitted review question interface, and the user will enter the In the Submitted Review Questions interface, you can view the transferred review questions to be submitted.
步骤404,若预设时间段内接收到该医学专业人员对应的用户终端发送的待提交审核问题对应的审核后答案及追溯数据,则将对应的审核问答对更新到知识库中。Step 404: If the post-audit answer and traceback data corresponding to the audit question to be submitted and sent by the user terminal corresponding to the medical professional are received within a preset time period, the corresponding audit question-and-answer pair is updated into the knowledge base.
如图7所示,将该待提交审核问题发送至医学专业人员对应的待审核界面中后,该医学专业人员通过点击用户管理界面中的“我的审核”的选项,可进入待审核界面,此时在用户待提交审核问题界面中待提交审核问题,在医学专业人员处为待审核界面中的待审核问题。若医学专业人员及时查看到有待审核问题后,对该待审核问题进行回答,并将答案及追溯数据输入到待审核界面中后,反馈给用户,则医学问答设备在预设时间段内接收到该医学专业人员对应的用户终端发送的待提交审核问题对应的审核后答案及追溯数据。用户能够在已提交审核问题界面中查看到审核后的答案及追溯数据。As shown in Figure 7, after the question to be submitted for review is sent to the pending review interface corresponding to the medical professional, the medical professional can enter the pending review interface by clicking the "My Review" option in the user management interface. At this time, the questions to be submitted for review in the user's to-be-submitted review-question interface are the questions to be submitted for review in the to-be-reviewed interface for medical professionals. If medical professionals view the question to be reviewed in time, answer the question to be reviewed, input the answer and traceability data into the interface to be reviewed, and then feed it back to the user, the medical question answering device will receive it within a preset time period. The post-review answers and traceability data corresponding to the review questions to be submitted are sent by the user terminal corresponding to the medical professional. Users can view the reviewed answers and retrospective data in the Submitted Review Questions interface.
本实施例中,为了对知识库中的问答对不断进行丰富,将已提交审核问题界面中的已提交问题,审核后的答案及追溯数据形成审核问答对,更新到知识库中。In this embodiment, in order to continuously enrich the question and answer pairs in the knowledge base, the submitted questions in the submitted audit questions interface, the audited answers and the retrospective data are formed into audit question and answer pairs, which are updated in the knowledge base.
步骤405,若预设时间段内未接收到该医学专业人员对应的用户终端发送的待提交审核问题对应的审核后答案及追溯数据,则对待提交审核问题按照预设分配规则分配给其他医学专业人员,以在其他医学专业人员对应的用户终端发送待提交审核问题对应的审核后答案及追溯数据后,将对应的审核问答对更新到知识库中。Step 405: If the post-audit answer and retrospective data corresponding to the audit question to be submitted and sent by the user terminal corresponding to the medical professional are not received within the preset time period, the audit question to be submitted is allocated to other medical professions according to the preset allocation rules. After the user terminals corresponding to other medical professionals send the post-audit answers and traceability data corresponding to the audit questions to be submitted, the corresponding audit question-and-answer pairs are updated into the knowledge base.
本实施例中,若预设时间段内未接收到该医学专业人员对应的用户终端发送的待提交审核问题对应的审核后答案及追溯数据,则说明用户选择的医学专业人员无法及时对该待提交审核问题进行回答,则按照预设分配规则分配给其他医学专业人员,该预设的分配规则可以为其他医学专业人员的所属科室与待提交审核问题的匹配度,回复问题的数量,回复的积极度等因素进行综合评分中排在最前面的医学专业人员作为分配该待提交审核问题的医学专业人员。将该待提交审核问题发送给分配的其他医学专业人员的用户终端对应的待审核界面中,由该分配的其他医学专业人员对该待提交审核问题进行回答。In this embodiment, if the user terminal corresponding to the medical professional has not received the post-audit answer and the retrospective data corresponding to the question to be submitted for review sent by the user terminal corresponding to the medical professional, it means that the medical professional selected by the user cannot timely respond to the question. Submit the review questions to answer, and then assign them to other medical professionals according to the preset allocation rules. The preset allocation rules can be the match between the departments of other medical professionals and the questions to be submitted for review, the number of questions answered, and the number of questions answered. The highest-ranking medical professional in a composite score based on factors such as positivity is the medical professional who assigns the question to be submitted for review. The to-be-submitted review question is sent to the to-be-reviewed interface corresponding to the user terminal of the assigned other medical professional, and the assigned other medical professional answers the to-be-submitted review question.
同理,接收到该其他医学专业人员对应的用户终端发送的待提交审核问题对应的审核后答案及追溯数据后,用户能够在已提交审核问题界面中查看到审核后的答案及追溯数据。将已提交审核问题界面中的已提交问题,审核后的答案及追溯数据形成审核问答对,更新到知识库中,能够保证该审核问答对的准确性的前提下,能够使知识库中的问答对不断进行丰富。Similarly, after receiving the post-review answers and traceability data corresponding to the review questions to be submitted sent by the user terminal corresponding to the other medical professional, the user can view the post-review answers and traceability data in the submitted review questions interface. The submitted questions in the submitted audit questions interface, the audited answers and retrospective data are formed into audit question and answer pairs, and updated to the knowledge base. Under the premise that the accuracy of the audit question and answer pairs can be ensured, the questions and answers in the knowledge base can be updated. To continue to enrich.
实施例五Embodiment 5
图8为本发明实施例五提供的医用问答方法的流程图,如图8所示,本实施例提供的医用问答方法,是在本发明实施例一至实施例四任意一个实施例提供的医用问答方法的基础上,还包括了其他步骤,则本实施例提供的医用问答方法还包括以下步骤。FIG. 8 is a flowchart of a medical question and answer method provided in Embodiment 5 of the present invention. As shown in FIG. 8 , the medical question and answer method provided in this embodiment is a medical question and answer method provided in any one of
步骤501,响应于用户通过用户管理界面中邀请好友选项的触发操作,显示邀请好友操作界面,在邀请好友操作界面中包括邀请码。Step 501 , in response to a triggering operation by the user through the option of inviting friends in the user management interface, displaying an operation interface for inviting friends, including an invitation code in the operation interface for inviting friends.
本实施例中,如图7所示,在用户管理界面中还包括邀请好友选项,用户通过点击邀请好友选项,进入邀请好友操作界面,如图9所示,在邀请好友操作界面中包括邀请码及分享选项。其中邀请码可设置在对应的二维码的中间区域。In this embodiment, as shown in FIG. 7 , the user management interface also includes an option to invite friends. The user clicks the option to invite friends to enter the operation interface for inviting friends. As shown in FIG. 9 , the operation interface for inviting friends includes an invitation code. and sharing options. The invitation code can be set in the middle area of the corresponding QR code.
步骤502,响应于用户在邀请好友操作界面中对分享选项的触发操作,跳转到预设应用程序的分享界面,以使好友通过分享界面中的邀请码进行注册。Step 502 , in response to the user triggering the sharing option in the inviting friend operation interface, jump to the sharing interface of the preset application, so that the friend can register through the invitation code in the sharing interface.
本实施例中,用户点击分享选项后,操作界面从邀请好友操作界面跳转到预设应用程序的分享界面,如预设应用程序可以为某即时通信软件。将该邀请码发送到好友的即时通信软件中,好友在注册该医用问答方法对应的应用程序时,通过该邀请码完成注册过程。In this embodiment, after the user clicks the share option, the operation interface jumps from the friend invitation operation interface to the sharing interface of the preset application program, for example, the preset application program may be an instant messaging software. The invitation code is sent to the instant messaging software of the friend, and the friend completes the registration process through the invitation code when registering the application program corresponding to the medical question answering method.
需要说明的是,如监测到好友注册了医用问答方法对应的应用程序,则在该用户的用户管理界面中“我的邀请”选项对应的界面中可查看到邀请好友的信息。It should be noted that, if it is detected that a friend has registered an application program corresponding to the medical question answering method, the information about the friend's invitation can be viewed in the interface corresponding to the "My Invitation" option in the user management interface of the user.
本实施例提供的医用问答方法,通过响应于用户通过用户管理界面中邀请好友选项的触发操作,显示邀请好友操作界面,在邀请好友操作界面中包括邀请码;响应于用户在邀请好友操作界面中对分享选项的触发操作,跳转到预设应用程序的分享界面,以使好友通过分享界面中的邀请码进行注册,能够保证每个使用该医用问答方法的应用程序的注册用户都是可以追溯的用户,保证了该医用问答方法的应用程序的安全性。In the medical question answering method provided by this embodiment, in response to the user's triggering operation through the option of inviting friends in the user management interface, the operation interface of inviting friends is displayed, and the invitation code is included in the operation interface of inviting friends; For the trigger operation of the sharing option, jump to the sharing interface of the preset application, so that friends can register through the invitation code in the sharing interface, which can ensure that each registered user of the application using the medical question and answer method can be traced back users, the security of the application of this medical question answering method is guaranteed.
实施例六Embodiment 6
图9为本发明实施例六提供的医用问答方法的流程图,如图9所示,本实施例提供的医用问答方法,是在本发明实施例一至实施例五任意一个实施例提供的医用问答方法的基础上,还包括了其他步骤,则本实施例提供的医用问答方法还包括以下步骤。FIG. 9 is a flowchart of a medical question and answer method provided in Embodiment 6 of the present invention. As shown in FIG. 9 , the medical question and answer method provided in this embodiment is a medical question and answer method provided in any one of
步骤601,响应于用户通过用户管理界面中医学专业人员认证选项的触发操作,显示医学专业人员认证界面。Step 601 , in response to a user's triggering operation through the medical professional certification option in the user management interface, display a medical professional certification interface.
本实施例中,如图7所示,在用户管理界面中还包括医学专业人员认证选项,即图7中的“医师认证”选项,若用户为医学专人人员,则该用户通过点击医学专业人员认证选项,界面从用户管理界面跳转到医学专业人员认证界面。In this embodiment, as shown in FIG. 7 , the user management interface also includes a medical professional certification option, that is, the “Physician Certification” option in FIG. 7 . If the user is a medical professional, the user clicks on the medical professional Certification options, the interface jumps from the user management interface to the medical professional certification interface.
步骤602,响应于用户在医学专业人员认证界面输入的科室类别、专业级别及认证证书,对用户进行医学专业人员认证。Step 602, in response to the department category, professional level and certification certificate input by the user on the medical professional certification interface, perform medical professional certification on the user.
其中,如图10所示,在医学专业人员认证界面中可以包括认证状态信息,还可以包括科室设置选项,专业级别选项及上传认证证书选项。用户通过点击科室设置选项,可选择需要输入的科室类别。用户通过点击专业级别选项,可配置专业级别为初级,中级或高级。用户通过点击上传认证证书选项,可上传医师执业资格证书。Among them, as shown in FIG. 10 , the medical professional certification interface may include certification status information, and may also include department setting options, professional level options, and upload certification certificate options. The user can select the department category to be entered by clicking the department setting option. Users can configure the professional level as Beginner, Intermediate or Advanced by clicking the Professional Level option. The user can upload the doctor's qualification certificate by clicking on the upload certification certificate option.
本实施例中,在用户输入科室类别,专业级别及上传医师执业资格证书后,对该用户进行是否为医学专业人员的认证。In this embodiment, after the user inputs the department category, the professional level, and uploads the doctor's practice qualification certificate, whether the user is a medical professional is authenticated.
步骤603,若用户通过认证,则将用户添加到待提交审核界面对医学专业人员的选择目录中。Step 603, if the user passes the authentication, the user is added to the selection list of medical professionals on the to-be-submitted review interface.
本实施例提供的医用问答方法中,通过响应于用户通过用户管理界面中医学专业人员认证选项的触发操作,显示医学专业人员认证界面;响应于用户在医学专业人员认证界面输入的科室类别、专业级别及认证证书,对用户进行医学专业人员认证;若用户通过认证,则将用户添加到待提交审核界面对医学专业人员的选择目录中,能够对用户进行是否为医学专业人员的认证,能够在只能医学专业人员进行问题的记录及答复,问题的审核时,获取认证信息,提高每个问题对应答案的准确性。In the medical question answering method provided by this embodiment, the medical professional certification interface is displayed in response to the user's triggering operation through the medical professional certification option in the user management interface; Level and certification certificate, the user is certified as a medical professional; if the user passes the certification, the user will be added to the selection list of medical professionals in the review interface to be submitted, and the user can be certified as a medical professional. Only medical professionals can record and answer questions. When reviewing questions, they can obtain certification information to improve the accuracy of the answers to each question.
如图7所示,在用户管理界面中还可以包括“实名认证”选项,“受邀回答”选项,“积分排行榜”选项等。As shown in FIG. 7 , the user management interface may also include an option of "real-name authentication", an option of "answer by invitation", an option of "point ranking", and the like.
实施例七Embodiment 7
图11为本发明实施例七提供的医用问答设备的结构示意图,如图11所示,本发明实施例提供一种医用问答设备70,包括:存储器71,处理器72以及计算机程序。FIG. 11 is a schematic structural diagram of a medical question answering device according to Embodiment 7 of the present invention. As shown in FIG. 11 , an embodiment of the present invention provides a medical
其中,计算机程序存储在存储器71中,并被配置为由处理器72执行以实现本发明实施例一至实施例六提供的医用问答方法。相关说明可以对应参见图1至图10所对应的相关描述和效果进行理解,此处不做过多赘述。The computer program is stored in the
其中,本实施例中,存储器71和处理器72通过总线连接。Wherein, in this embodiment, the
实施例八Embodiment 8
图12为本发明实施例八提供的医用问答设备的结构示意图,该医用问答设备可以是智能手机,计算机,数字广播终端,平板设备,个人数字助理等。FIG. 12 is a schematic structural diagram of a medical question answering device according to Embodiment 8 of the present invention. The medical question answering device may be a smart phone, a computer, a digital broadcasting terminal, a tablet device, a personal digital assistant, or the like.
医用问答设备800可以包括以下一个或多个组件:处理组件802,存储器804,电源组件806,多媒体组件808,音频组件88,输入/输出(I/O)接口812,传感器组件814,以及通信组件816。Medical
处理组件802通常控制装置800的整体操作,诸如与显示,电话呼叫,数据通信,相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令,以完成上述的方法的全部或部分步骤。此外,处理组件802可以包括一个或多个模块,便于处理组件802和其他组件之间的交互。例如,处理组件802可以包括多媒体模块,以方便多媒体组件808和处理组件802之间的交互。The
存储器804被配置为存储各种类型的数据以支持在装置800的操作。这些数据的示例包括用于在装置800上操作的任何应用程序或方法的指令,联系人数据,电话簿数据,消息,图片,视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现,如静态随机存取存储器(SRAM),电可擦除可编程只读存储器(EEPROM),可擦除可编程只读存储器(EPROM),可编程只读存储器(PROM),只读存储器(ROM),磁存储器,快闪存储器,磁盘或光盘。
电源组件806为装置800的各种组件提供电力。电源组件806可以包括电源管理系统,一个或多个电源,及其他与为装置800生成、管理和分配电力相关联的组件。
多媒体组件808包括在装置800和用户之间的提供一个输出接口的屏幕。在一些实施例中,屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板,屏幕可以被实现为触摸屏,以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。触摸传感器可以不仅感测触摸或滑动动作的边界,而且还检测与触摸或滑动操作相关的持续时间和压力。在一些实施例中,多媒体组件808包括一个前置摄像头和/或后置摄像头。当装置800处于操作模式,如拍摄模式或视频模式时,前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件88被配置为输出和/或输入音频信号。例如,音频组件88包括一个麦克风(MIC),当装置800处于操作模式,如呼叫模式、记录模式和语音识别模式时,麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中,音频组件88还包括一个扬声器,用于输出音频信号。Audio component 88 is configured to output and/or input audio signals. For example, audio component 88 includes a microphone (MIC) that is configured to receive external audio signals when
I/O接口812为处理组件802和外围接口模块之间提供接口,上述外围接口模块可以是键盘,点击轮,按钮等。这些按钮可包括但不限于:主页按钮、音量按钮、启动按钮和锁定按钮。The I/
传感器组件814包括一个或多个传感器,用于为装置800提供各个方面的状态评估。例如,传感器组件814可以检测到装置800的打开/关闭状态,组件的相对定位,例如组件为装置800的显示器和小键盘,传感器组件814还可以检测装置800或装置800一个组件的位置改变,用户与装置800接触的存在或不存在,装置800方位或加速/减速和装置800的温度变化。传感器组件814可以包括接近传感器,被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器,如CMOS或CCD图像传感器,用于在成像应用中使用。在一些实施例中,该传感器组件814还可以包括加速度传感器,陀螺仪传感器,磁传感器,压力传感器或温度传感器。
通信组件816被配置为便于装置800和其他设备之间有线或无线方式的通信。装置800可以接入基于通信标准的无线网络,如WiFi,2G或3G,或它们的组合。在一个示例性实施例中,通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中,通信组件816还包括近场通信(NFC)模块,以促进短程通信。例如,在NFC模块可基于射频识别(RFID)技术,红外数据协会(IrDA)技术,超宽带(UWB)技术,蓝牙(BT)技术和其他技术来实现。
在示例性实施例中,装置800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现,用于执行上述方法。In an exemplary embodiment,
在示例性实施例中,还提供了一种包括指令的非临时性计算机可读存储介质,例如包括指令的存储器804,上述指令可由车端设备800的处理器执行以完成上述方法。例如,非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions, such as a
一种非临时性计算机可读存储介质,当该存储介质中的指令由车端设备的处理器执行时,使得车端设备能够执行上述车端数据的处理方法。A non-transitory computer-readable storage medium, when an instruction in the storage medium is executed by a processor of a vehicle-end device, enables the vehicle-end device to execute the above-mentioned method for processing vehicle-end data.
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本申请的其它实施方案。本发明旨在涵盖本发明的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本发明未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的。Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention which follow the general principles of the present invention and include common knowledge or conventional techniques in the technical field not disclosed by the present invention . The description and examples are to be regarded as exemplary only.
应当理解的是,本申请并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求书来限制。It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying 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 (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010685557.9A CN112037905B (en) | 2020-07-16 | 2020-07-16 | Medical question-answering method, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010685557.9A CN112037905B (en) | 2020-07-16 | 2020-07-16 | Medical question-answering method, device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112037905A true CN112037905A (en) | 2020-12-04 |
CN112037905B CN112037905B (en) | 2024-09-13 |
Family
ID=73579382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010685557.9A Active CN112037905B (en) | 2020-07-16 | 2020-07-16 | Medical question-answering method, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112037905B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112632232A (en) * | 2021-03-09 | 2021-04-09 | 北京世纪好未来教育科技有限公司 | Text matching method, device, equipment and medium |
CN113515643A (en) * | 2021-05-19 | 2021-10-19 | 思必驰科技股份有限公司 | User identity verification method and device |
CN114168725A (en) * | 2021-12-08 | 2022-03-11 | 北京字节跳动网络技术有限公司 | Object question and answer processing method and device, electronic equipment, medium and product |
CN114385830A (en) * | 2022-01-14 | 2022-04-22 | 中国建设银行股份有限公司 | Operation and maintenance knowledge online question and answer method and device, electronic equipment and storage medium |
CN114911916A (en) * | 2022-06-06 | 2022-08-16 | 中国工商银行股份有限公司 | Method, apparatus, device and medium for updating natural language processing system |
CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101662450B1 (en) * | 2015-05-29 | 2016-10-05 | 포항공과대학교 산학협력단 | Multi-source hybrid question answering method and system thereof |
CN107015983A (en) * | 2016-01-27 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for being used in intelligent answer provide knowledge information |
CN107908803A (en) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | The response method and device, storage medium, terminal of question and answer interaction |
WO2019101210A1 (en) * | 2017-11-27 | 2019-05-31 | 中兴通讯股份有限公司 | Intelligent question and answer method and device |
CN110147436A (en) * | 2019-03-18 | 2019-08-20 | 清华大学 | A kind of mixing automatic question-answering method based on padagogical knowledge map and text |
CN110390003A (en) * | 2019-06-19 | 2019-10-29 | 北京百度网讯科技有限公司 | Question and answer processing method and system, computer equipment and readable medium based on medical treatment |
CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
CN111161873A (en) * | 2019-12-06 | 2020-05-15 | 广州市医康传媒信息技术有限公司 | Medical question-answering voice information processing system, method, device and storage medium |
CN111191048A (en) * | 2020-01-02 | 2020-05-22 | 南京邮电大学 | Construction method of emergency question answering system based on knowledge graph |
-
2020
- 2020-07-16 CN CN202010685557.9A patent/CN112037905B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101662450B1 (en) * | 2015-05-29 | 2016-10-05 | 포항공과대학교 산학협력단 | Multi-source hybrid question answering method and system thereof |
CN107015983A (en) * | 2016-01-27 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus for being used in intelligent answer provide knowledge information |
WO2019101210A1 (en) * | 2017-11-27 | 2019-05-31 | 中兴通讯股份有限公司 | Intelligent question and answer method and device |
CN107908803A (en) * | 2017-12-26 | 2018-04-13 | 上海智臻智能网络科技股份有限公司 | The response method and device, storage medium, terminal of question and answer interaction |
CN110147436A (en) * | 2019-03-18 | 2019-08-20 | 清华大学 | A kind of mixing automatic question-answering method based on padagogical knowledge map and text |
CN110390003A (en) * | 2019-06-19 | 2019-10-29 | 北京百度网讯科技有限公司 | Question and answer processing method and system, computer equipment and readable medium based on medical treatment |
CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
CN111161873A (en) * | 2019-12-06 | 2020-05-15 | 广州市医康传媒信息技术有限公司 | Medical question-answering voice information processing system, method, device and storage medium |
CN111191048A (en) * | 2020-01-02 | 2020-05-22 | 南京邮电大学 | Construction method of emergency question answering system based on knowledge graph |
Non-Patent Citations (1)
Title |
---|
祖永亮: "基于多特征融合的中文自动问答系统研究与设计", 中国优秀硕士学位论文全文数据库信息科技辑, no. 4, pages 1138 - 1401 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112632232A (en) * | 2021-03-09 | 2021-04-09 | 北京世纪好未来教育科技有限公司 | Text matching method, device, equipment and medium |
CN113515643A (en) * | 2021-05-19 | 2021-10-19 | 思必驰科技股份有限公司 | User identity verification method and device |
CN114168725A (en) * | 2021-12-08 | 2022-03-11 | 北京字节跳动网络技术有限公司 | Object question and answer processing method and device, electronic equipment, medium and product |
CN114168725B (en) * | 2021-12-08 | 2024-08-27 | 北京字节跳动网络技术有限公司 | Object question and answer processing method and device, electronic equipment, medium and product |
CN114385830A (en) * | 2022-01-14 | 2022-04-22 | 中国建设银行股份有限公司 | Operation and maintenance knowledge online question and answer method and device, electronic equipment and storage medium |
CN114911916A (en) * | 2022-06-06 | 2022-08-16 | 中国工商银行股份有限公司 | Method, apparatus, device and medium for updating natural language processing system |
CN115238101A (en) * | 2022-09-23 | 2022-10-25 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
CN115238101B (en) * | 2022-09-23 | 2023-01-03 | 中国电子科技集团公司第十研究所 | Multi-engine intelligent question-answering system oriented to multi-type knowledge base |
Also Published As
Publication number | Publication date |
---|---|
CN112037905B (en) | 2024-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112037905B (en) | Medical question-answering method, device and storage medium | |
US10078489B2 (en) | Voice interface to a social networking service | |
US9275272B2 (en) | Tag suggestions for images on online social networks | |
CN114072832A (en) | Memory-based conversational reasoning and question-answering for assistant systems | |
RU2615632C2 (en) | Method and device for recognizing communication messages | |
US10740368B2 (en) | Query-composition platforms on online social networks | |
US11074509B1 (en) | Predictive learner score | |
WO2022160596A1 (en) | Inquiry information processing method and apparatus, and medium | |
US20230350952A1 (en) | Unified graph representation of skills and acumen | |
US11928607B2 (en) | Predictive learner recommendation platform | |
Park et al. | Bayesian network-based high-level context recognition for mobile context sharing in cyber-physical system | |
CN104035995A (en) | Method and device for generating group tags | |
CN109670077A (en) | Video recommendation method, device and computer readable storage medium | |
KR20140004601A (en) | System and method for matching users having matter of common interest and change of talent using tag applicable to mobile messenger | |
US20170371869A1 (en) | Crowd-matching translators | |
CN105264523A (en) | Simplified collaborative searching through pattern recognition | |
CN114138817A (en) | Data query method, device, medium and product based on relational database | |
CN106095868A (en) | Obtain the method and device of mood information | |
WO2022116527A1 (en) | Data processing method and device | |
JP5891909B2 (en) | Server apparatus, program, and communication system | |
CN111274444B (en) | Method and device for generating video cover determination model, and method and device for determining video cover | |
CN113656557A (en) | Message reply method, device, storage medium and electronic equipment | |
CN116016421A (en) | Method, computing device readable storage medium, and computing device for facilitating media-based content sharing performed in a computing device | |
CN112016001A (en) | Friend recommendation method, device and computer readable medium | |
CN107291259B (en) | Information display method and device for information display |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20250523 Address after: 100730 Beijing city Dongcheng District Wangfujing Park No. 1 Patentee after: PEKING UNION MEDICAL COLLEGE Hospital Country or region after: China Address before: 100730 Beijing City, Dongcheng District, Peking Union Medical College Hospital, Room 908 of the Tomorrow Building Patentee before: Zhu Weiguo Country or region before: China Patentee before: Li Yuanjie Patentee before: Guo Anhui |
|
TR01 | Transfer of patent right |