技术领域technical field
本发明实施例涉及通信技术领域，尤其涉及一种药品推荐方法及设备。Embodiments of the present invention relate to the field of communication technologies, and in particular, to a method and device for recommending medicines.
背景技术Background technique
随着医学的发展，患者可以从当地药店或网上药房购买到更多的药品，为患者提供了方便，于是为了节省时间以及医疗费用，有越来越多的人在患轻微病症时，会选择到附近的药店自行买药治疗。With the development of medicine, patients can purchase more medicines from local pharmacies or online pharmacies, which provides convenience for patients. Therefore, in order to save time and medical expenses, more and more people will choose Go to a nearby pharmacy to buy medicine for treatment by yourself.
现有技术中，会在药店中配置多名药师，通过药师进行药品导购。In the prior art, a plurality of pharmacists will be arranged in the pharmacy, and the pharmacists will guide the purchase of medicines.
然而，药师的执药能力参差不齐，有时推荐的药品并不合适，用户体验不佳。However, the ability of pharmacists to administer medicines is uneven, and sometimes the medicines recommended are not suitable, and the user experience is not good.
发明内容Contents of the invention
本发明实施例提供一种药品推荐方法及设备，以提高药品推荐的准确性Embodiments of the present invention provide a drug recommendation method and equipment to improve the accuracy of drug recommendation
第一方面，本发明实施例提供一种药品推荐方法，包括：In the first aspect, the embodiment of the present invention provides a drug recommendation method, including:
接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；Receive the personal information input by the user; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, drug allergy history;
根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表；其中，所述药品知识库是根据药品书籍和/或网络问诊数据构建的；According to the personal information, search in the drug knowledge base, and obtain the first drug list according to the search results; wherein, the drug knowledge base is constructed based on drug books and/or network consultation data;
根据预设的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；其中，所述药品推理库是根据药品推荐规则和所述药品知识库，通过推理引擎构建的；所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。According to the preset drug reasoning library, the drugs in the first drug list are screened to obtain the second drug list, so as to push the second drug list to the user; wherein, the drug reasoning library is based on the drug recommendation The rules and the drug knowledge base are constructed through a reasoning engine; the drug recommendation rules are established according to the contraindications of the drug, contraindicated groups and drug interaction attributes.
在一种可能的设计中，所述根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表，包括：In a possible design, the search is performed in the drug knowledge base according to the personal information, and according to the search result, the first list of drugs is obtained, including:
根据所述个人信息确定用户的症状；determine the user's symptoms based on said personal information;
通过词频-逆文本频率指数TF-IDF算法，在药品知识库中查找与所述用户的症状匹配的药品，获得第一药品列表。Through the word frequency-inverse text frequency index TF-IDF algorithm, the medicines matching the user's symptoms are searched in the medicine knowledge base, and the first medicine list is obtained.
在一种可能的设计中，所述根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表之前，还包括：In a possible design, before performing a search in the drug knowledge base according to the personal information, and obtaining the first list of drugs according to the search result, the method further includes:
对所述药品书籍进行信息抽取，通过结构化处理，确定抽取到的各药品与其治疗症状的关联关系，以构建第一知识库；Carrying out information extraction on the medicine books, and determining the relationship between the extracted medicines and their treatment symptoms through structured processing, so as to build a first knowledge base;
获取网络问诊数据，并通过挖掘算法，确定所述网络问诊数据中各药品与其治疗症状的关联关系，以构建第二知识库；Obtaining online medical consultation data, and determining the relationship between each drug in the online medical consultation data and its treatment symptoms through a mining algorithm, so as to construct a second knowledge base;
将所述第一知识库与所述第二知识库进行融合，获得所述药品知识库。The first knowledge base is fused with the second knowledge base to obtain the drug knowledge base.
在一种可能的设计中，所述接收用户输入的个人信息，包括：In a possible design, the receiving personal information input by the user includes:
接收用户输入的语音信息，并将所述语音信息作为该用户的个人信息。The voice information input by the user is received, and the voice information is used as the user's personal information.
在一种可能的设计中，所述接收用户输入的语音信息，并将所述语音信息作为该用户的个人信息之后，还包括：In a possible design, after receiving the voice information input by the user and using the voice information as the user's personal information, it further includes:
通过语音识别算法对该语音信息进行识别，获得文字信息；Recognize the voice information through a voice recognition algorithm to obtain text information;
将所述文字信息输入自然语言理解NLU模型，通过所述NLU模型对所述文字信息进行关键信息抽取，获得信息抽取结果；The text information is input into a natural language understanding NLU model, and the key information is extracted from the text information through the NLU model to obtain an information extraction result;
所述根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表，包括：According to the personal information, search in the drug knowledge base, and obtain the first list of drugs according to the search results, including:
根据所述信息抽取结果，在药品知识库中进行检索以及相关性计算，获得第一药品列表。According to the information extraction result, search and correlation calculation are performed in the drug knowledge base to obtain the first drug list.
在一种可能的设计中，所述接收用户输入的个人信息，包括：In a possible design, the receiving personal information input by the user includes:
接收用户输入的触控信息，并将所述触控信息作为该用户的个人信息。The touch information input by the user is received, and the touch information is used as the user's personal information.
第二方面，本发明实施例提供一种药品推荐设备，包括：In the second aspect, an embodiment of the present invention provides a drug recommendation device, including:
接收模块，用于接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；The receiving module is used to receive the personal information input by the user; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, drug allergy history;
检索模块，用于根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表；其中，所述药品知识库是根据药品书籍和/或网络问诊数据构建的；The retrieval module is used to search in the drug knowledge base according to the personal information, and obtain the first drug list according to the search results; wherein, the drug knowledge base is constructed according to drug books and/or network consultation data ;
筛选模块，用于根据预设的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；其中，所述药品推理库是根据药品推荐规则和所述药品知识库，通过推理引擎构建的；所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。A screening module, configured to screen the drugs in the first drug list according to a preset drug reasoning library to obtain a second drug list, so as to push the second drug list to the user; wherein, the drug reasoning The database is constructed through a reasoning engine according to the drug recommendation rules and the drug knowledge base; the drug recommendation rules are established according to the contraindications of the drug, contraindicated groups and drug interaction attributes.
在一种可能的设计中，所述检索模块具体用于：In a possible design, the retrieval module is specifically used for:
根据所述个人信息确定用户的症状；determine the user's symptoms based on said personal information;
通过词频-逆文本频率指数TF-IDF算法，在药品知识库中查找与所述用户的症状匹配的药品，获得第一药品列表。Through the word frequency-inverse text frequency index TF-IDF algorithm, the medicines matching the user's symptoms are searched in the medicine knowledge base, and the first medicine list is obtained.
在一种可能的设计中，所述设备还包括：In a possible design, the device also includes:
第一构建模块，用于对所述药品书籍进行信息抽取，通过结构化处理，确定抽取到的各药品与其治疗症状的关联关系，以构建第一知识库；The first building block is used to extract information from the drug books, and determine the relationship between the extracted drugs and their treatment symptoms through structured processing, so as to build a first knowledge base;
获取网络问诊数据，并通过挖掘算法，确定所述网络问诊数据中各药品与其治疗症状的关联关系，以构建第二知识库；Obtaining online medical consultation data, and determining the relationship between each drug in the online medical consultation data and its treatment symptoms through a mining algorithm, so as to construct a second knowledge base;
将所述第一知识库与所述第二知识库进行融合，获得所述药品知识库。The first knowledge base is fused with the second knowledge base to obtain the drug knowledge base.
在一种可能的设计中，所述接收模块具体用于：In a possible design, the receiving module is specifically used for:
接收用户输入的语音信息，并将所述语音信息作为该用户的个人信息。The voice information input by the user is received, and the voice information is used as the user's personal information.
在一种可能的设计中，所述设备，还包括：In a possible design, the device further includes:
语音识别模块，用于通过语音识别算法对该语音信息进行识别，获得文字信息；The speech recognition module is used to recognize the speech information through a speech recognition algorithm to obtain text information;
将所述文字信息输入自然语言理解NLU模型，通过所述NLU模型对所述文字信息进行关键信息抽取，获得信息抽取结果；The text information is input into a natural language understanding NLU model, and the key information is extracted from the text information through the NLU model to obtain an information extraction result;
所述检索模块具体用于：The retrieval module is specifically used for:
根据所述信息抽取结果，在药品知识库中进行检索以及相关性计算，获得第一药品列表。According to the information extraction result, search and correlation calculation are performed in the drug knowledge base to obtain the first drug list.
第三方面，本发明实施例提供一种药品推荐设备，包括：至少一个处理器和存储器；In a third aspect, an embodiment of the present invention provides a drug recommendation device, including: at least one processor and a memory;
所述存储器存储计算机执行指令；the memory stores computer-executable instructions;
所述至少一个处理器执行所述存储器存储的计算机执行指令，使得所述至少一个处理器执行如上第一方面以及第一方面各种可能的设计所述的方法。The at least one processor executes the computer-executed instructions stored in the memory, so that the at least one processor executes the method described in the above first aspect and various possible designs of the first aspect.
第四方面，本发明实施例提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如上第一方面以及第一方面各种可能的设计所述的方法。In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the above first aspect and the first Aspects of various possible designs of the described method.
本实施例提供的药品推荐方法及设备，该方法通过接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；根据所述个人信息，在根据药品书籍和/或网络问诊数据构建的药品知识库中进行检索，并根据检索结果，获得第一药品列表；通过根据药品推荐规则和所述药品知识库构建的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户，本实施例提供的方法能够在保证用户的用药安全的前提下，准确的向用户推荐适合的药品，进而提升用户的用药体验。The drug recommendation method and equipment provided in this embodiment, the method receives the personal information input by the user; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, drug allergy history; according to the Personal information is searched in the drug knowledge base constructed based on drug books and/or online consultation data, and according to the search results, the first list of drugs is obtained; through the drug reasoning base constructed based on drug recommendation rules and the drug knowledge base , screen the drugs in the first drug list to obtain a second drug list, so as to push the second drug list to the user. The method provided in this embodiment can accurately Recommend suitable medicines to users, thereby improving the user's medication experience.
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 technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the 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. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.
图1为本发明一实施例提供的一应用场景的结构示意图；FIG. 1 is a schematic structural diagram of an application scenario provided by an embodiment of the present invention;
图2为本发明又一实施例提供的药品推荐方法的流程示意图；Fig. 2 is a schematic flowchart of a drug recommendation method provided by another embodiment of the present invention;
图3为本发明又一实施例提供的药品推荐方法的流程示意图；Fig. 3 is a schematic flowchart of a drug recommendation method provided by another embodiment of the present invention;
图4为本发明又一实施例提供的药品推荐设备的结构示意图；Fig. 4 is a schematic structural diagram of a drug recommendation device provided by another embodiment of the present invention;
图5为本发明又一实施例提供的药品推荐设备的结构示意图；Fig. 5 is a schematic structural diagram of a drug recommendation device provided by another embodiment of the present invention;
图6为本发明又一实施例提供的药品推荐设备的硬件结构示意图。Fig. 6 is a schematic diagram of a hardware structure of a drug recommendation device according to another embodiment of the present invention.
具体实施方式Detailed ways
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
下面以具体地实施例对本发明的技术方案进行详细说明。下面这几个具体的实施例可以相互结合，对于相同或相似的概念或过程可能在某些实施例不再赘述。The technical solution of the present invention will be described in detail below with specific embodiments. The following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.
图1为本发明一实施例提供的一应用场景的结构示意图。如图1所示，终端101为能够接收用户输入的个人信息的终端，例如，智能手机、平板、计算机等，本实施例对终端101的实现方式不做限定。终端101可以包括用于接收用户输入的个人信息的接收模块，用于将该个人信息输入药品知识库进行检索并输出药品推荐列表的检索模块。FIG. 1 is a schematic structural diagram of an application scenario provided by an embodiment of the present invention. As shown in FIG. 1 , the terminal 101 is a terminal capable of receiving personal information input by a user, such as a smart phone, a tablet, a computer, etc., and the implementation of the terminal 101 is not limited in this embodiment. The terminal 101 may include a receiving module for receiving personal information input by the user, and a retrieval module for inputting the personal information into the drug knowledge base for retrieval and outputting a list of drug recommendations.
具体实现过程中，终端101通过接收模块接收用户输入的语音信息或触控信息，具体的，该接收模块可以为触控屏或话筒，相应的，可以由触控屏接收用户输入的触控信息，还可以通过话筒接收用户输入的语音信息。以触控信息为例，对药品推荐过程进行示例说明，触控屏向用户推送症状输入界面，用户根据自身情况，从触控界面中选择符合自己症状、年龄、性别、发病部位、病史、药物过敏史等信息的描述。用户所选信息作为个人信息被存储在本地或服务器102，接收模块用户输入的个人信息发送至根据权威书籍构建的药品知识库进行检索，获得推荐药品列表，该药品列表中的药品通过内置于终端101的扬声器进行语音播报，或者通过显示屏向用户进行图片或文字显示。可选地，该药品知识库的检索过程还可以通过与终端101连接的服务器102完成。本实施例提供的药品推荐方法，简单易用，能够准确智能的为用户进行药品推荐，提升用户的购药用药体验。In the specific implementation process, the terminal 101 receives the voice information or touch information input by the user through the receiving module. Specifically, the receiving module can be a touch screen or a microphone. Correspondingly, the touch screen can receive the touch information input by the user. , and can also receive voice information input by the user through the microphone. Taking touch information as an example to illustrate the drug recommendation process, the touch screen pushes the symptom input interface to the user, and the user selects from the touch interface according to his own situation, age, gender, disease location, medical history, drug A description of information such as allergy history. The information selected by the user is stored locally or in the server 102 as personal information. The personal information input by the receiving module is sent to the drug knowledge base constructed based on authoritative books for retrieval, and a list of recommended drugs is obtained. The drugs in the drug list are passed through the built-in terminal The loudspeaker of 101 performs voice broadcast, or displays pictures or text to the user through the display screen. Optionally, the retrieval process of the drug knowledge base can also be completed through the server 102 connected to the terminal 101 . The drug recommendation method provided in this embodiment is simple and easy to use, can accurately and intelligently recommend drugs for users, and improves the user's experience in purchasing and administering drugs.
图2为本发明又一实施例提供的药品推荐方法的流程示意图。如图2所示，该方法包括：Fig. 2 is a schematic flowchart of a drug recommendation method provided by another embodiment of the present invention. As shown in Figure 2, the method includes:
201、接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史。201. Receive personal information input by a user; the personal information includes at least one of the following: symptoms, age, gender, disease location, medical history, and drug allergy history.
实际应用中，本实施例的执行主体可以为智能手机、平板、计算机、车载终端等终端设备。In practical applications, the execution subject of this embodiment may be a terminal device such as a smart phone, a tablet, a computer, or a vehicle-mounted terminal.
本实施例中，用户输入个人信息的方式可以有多种，可以以触控信息的形式输入，还可以以语音信息的形式进行输入。In this embodiment, there are many ways for the user to input personal information, such as input in the form of touch information, or input in the form of voice information.
若为触控信息的形式输入，可参照图1所示实施例的说明，此处不再赘述。If the input is in the form of touch information, reference may be made to the description of the embodiment shown in FIG. 1 , which will not be repeated here.
若为语音信息的形式输入，具体的，用户可以根据系统提供的范例句法，描述自己的症状、年龄、性别、发病部位、病史、药物过敏史等信息，语音数据数据转入数据解析模块进行解析处理。用户的语音输入信息先通过现有的语音识别技术转为文字。文字信息通过离线训练好的自然语言理解(Natural Language Understanding，NLU)模型(利用中文分词、句法分析及命名实体识别技术有监督训练)进行关键信息抽取，抽取出患者的症状、年龄、性别、发病部位、病史、药物过敏史等信息(没有的留空)，并存储该信息到本地或后台服务器中，以供后续步骤使用。If the input is in the form of voice information, specifically, users can describe their symptoms, age, gender, disease location, medical history, drug allergy history and other information according to the sample syntax provided by the system, and the voice data data is transferred to the data analysis module for analysis deal with. The user's voice input information is first converted into text through the existing voice recognition technology. Key information is extracted from the text information through the Natural Language Understanding (NLU) model trained offline (supervised training using Chinese word segmentation, syntactic analysis and named entity recognition technology), and the symptoms, age, gender, and onset of the patient are extracted. Site, medical history, drug allergy history and other information (leave blank if none), and store the information in the local or background server for use in subsequent steps.
例如，用户输入语音描述“我今天体温38度，有一些流鼻涕”。For example, the user enters a voice description "My body temperature is 38 degrees today, and I have some runny nose".
通过语音识别模块将该语音信息转化为文字后，将文字输入NLU模型，NLU模型对该文字进行关键信息抽取，获得关键信息“体温38度”，“有鼻涕”等症状信息。在后续步骤中，根据该症状信息在药品知识库中进行推理计算，获得第一药品列表。After the speech information is converted into text through the speech recognition module, the text is input into the NLU model, and the NLU model extracts key information from the text, and obtains key information such as "body temperature 38 degrees", "nasal mucus" and other symptom information. In a subsequent step, reasoning calculations are performed in the drug knowledge base according to the symptom information to obtain the first list of drugs.
202、根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表；其中，所述药品知识库是根据药品书籍和/或网络问诊数据构建的。202. Search in the drug knowledge base according to the personal information, and obtain a first drug list according to the search result; wherein, the drug knowledge base is constructed based on drug books and/or online consultation data.
实际应用中，将用户输入的症状输入药品知识库中进行检索。根据药品知识库中各药品与该症状的匹配度生成匹配度由高到低的一系列药品作为检索结果。并选取预设排名内的药品，生成第一药品列表。例如可以选择排名前10的药品作为第一药品列表。In practical applications, the symptoms entered by the user are entered into the drug knowledge base for retrieval. According to the matching degree of each drug in the drug knowledge base and the symptom, a series of drugs with matching degrees from high to low are generated as retrieval results. And select the medicines in the preset ranking to generate the first medicine list. For example, the top 10 drugs may be selected as the first drug list.
可选地，根据所述个人信息确定用户的症状；通过词频-逆文本频率指数TF-IDF算法，在药品知识库中查找与所述用户的症状匹配的药品，获得第一药品列表。Optionally, the user's symptoms are determined according to the personal information; through the word frequency-inverse text frequency index TF-IDF algorithm, the drugs matching the user's symptoms are searched in the drug knowledge base to obtain the first drug list.
可以理解，不同的症状会根据其的常见程度分配不同的权重，一般常见症状所分配的比重较小，比较少出现(比较特殊)的症状所分配的比重较大。例如，身体发热是比较常见的症状，昏厥是比较少出现的症状，那么身体发热被分配的比重比较小，昏厥被分配的比重比较大。如果一个药品的治疗症状中包括身体发热，另一个药品的治疗症状包括昏厥，那么第二个药品与用户的匹配度大于第一个药品。也即第二个药品的排名要靠前。另外，药品所包含的用户症状的个数越多，该药品与用户的匹配度也越大。It can be understood that different symptoms will be assigned different weights according to their commonness, generally common symptoms will be assigned a smaller proportion, and relatively rare (more special) symptoms will be assigned a larger proportion. For example, body fever is a relatively common symptom, and fainting is a relatively rare symptom, so the proportion assigned to body fever is relatively small, and the proportion assigned to fainting is relatively large. If one medicine treats symptoms that include body fever and another medicine treats symptoms that include fainting, then the second medicine is more likely to match the user than the first medicine. That is to say, the ranking of the second drug should be higher. In addition, the more the number of user symptoms contained in the drug, the greater the degree of matching between the drug and the user.
203、根据预设的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；其中，所述药品推理库是根据药品推荐规则和所述药品知识库，通过推理引擎构建的；所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。203. According to the preset drug reasoning library, screen the drugs in the first drug list to obtain a second drug list, so as to push the second drug list to the user; wherein, the drug reasoning library is based on The drug recommendation rules and the drug knowledge base are constructed through a reasoning engine; the drug recommendation rules are established according to contraindications of drugs, contraindicated groups, and drug interaction attributes.
本实施例中，所述药品推理库是根据药品推荐规则和所述药品知识库进行构建的，能够起到对药品推荐质量的控制作用。可选地，所述药品推荐规则可以是由医学专家制定的规则，具体的，医学专家根据药品的禁忌症、禁忌人群以及药物原理等属性制定该推荐规则。In this embodiment, the drug reasoning database is constructed according to the drug recommendation rules and the drug knowledge base, which can control the quality of drug recommendation. Optionally, the drug recommendation rule may be a rule formulated by a medical expert. Specifically, the medical expert formulates the recommendation rule according to attributes such as contraindications of the drug, contraindicated groups, and drug principles.
可以理解，为了用户的安全，为用户推荐更加合理的药品，需要对根据症状匹配度从药品知识库中检索到的第一药品列表进行进一步筛选。以防止用户购买与用户的当前身体状况不符的药品，例如孕期患者的禁忌药品。It can be understood that in order to recommend more reasonable medicines to users for the safety of users, it is necessary to further screen the first medicine list retrieved from the medicine knowledge base according to the matching degree of symptoms. To prevent users from purchasing medicines that are inconsistent with the user's current physical condition, such as contraindicated medicines for pregnant patients.
可选地，可以从所述第一药品列表中筛选排序前三的药品作为所述第二药品列表。Optionally, the top three drugs may be selected from the first drug list as the second drug list.
本实施例提供的药品推荐方法，通过接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；根据所述个人信息，在根据药品书籍和/或网络问诊数据构建的药品知识库中进行检索，并根据检索结果，获得第一药品列表；通过根据药品推荐规则和所述药品知识库构建的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；能够在保证用户的用药安全的前提下，准确的向用户推荐适合的药品，进而提升用户的用药体验。The drug recommendation method provided in this embodiment receives the personal information input by the user; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, drug allergy history; according to the personal information, in Retrieve in the drug knowledge base constructed according to drug books and/or network consultation data, and obtain the first list of drugs according to the retrieval results; The drugs in the first drug list are screened to obtain the second drug list, so as to push the second drug list to the user; on the premise of ensuring the user's medication safety, it is possible to accurately recommend suitable drugs to the user, thereby improving User experience with medication.
图3为本发明又一实施例提供的药品推荐方法的流程示意图。如图3所示，该方法包括：Fig. 3 is a schematic flowchart of a drug recommendation method provided by another embodiment of the present invention. As shown in Figure 3, the method includes:
301、接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史。301. Receive personal information input by a user; the personal information includes at least one of the following: symptoms, age, gender, disease location, medical history, and drug allergy history.
本实施例中步骤301与上述实施例中步骤201相类似，此处不再赘述。Step 301 in this embodiment is similar to step 201 in the above embodiment, and will not be repeated here.
302、根据药品书籍和/或网络问诊数据构建药品知识库。302. Construct a drug knowledge base according to drug books and/or network consultation data.
本实施例中，该步骤具体可以包括：In this embodiment, this step may specifically include:
对所述药品书籍进行信息抽取，通过结构化处理，确定抽取到的各药品与其治疗症状的关联关系，以构建第一知识库；Carrying out information extraction on the medicine books, and determining the relationship between the extracted medicines and their treatment symptoms through structured processing, so as to build a first knowledge base;
获取网络问诊数据，并通过挖掘算法，确定所述网络问诊数据中各药品与其治疗症状的关联关系，以构建第二知识库；Obtaining online medical consultation data, and determining the relationship between each drug in the online medical consultation data and its treatment symptoms through a mining algorithm, so as to construct a second knowledge base;
将所述第一知识库与所述第二知识库进行融合，获得所述药品知识库。The first knowledge base is fused with the second knowledge base to obtain the drug knowledge base.
针对第一知识库的构建，所述药品书籍可以是卫生组织或者专家推荐的权威医学书籍。具体的，对所述药品书籍，进行结构化处理，并利用现有知识库构建技术，如：SPO抽取、实体关联、实体归一等，建立完善准确的第一知识库，可以将权威书籍进行拍照，获得图像，并进行图像转文字处理。进而依次经过信息抽取、知识融合和知识加工的步骤构建第一知识库。第一知识库是由实体-关系-实体的三元组构成，例如症状实体与药品实体之间的关联，构成一个三元组。For the construction of the first knowledge base, the drug books may be authoritative medical books recommended by health organizations or experts. Specifically, carry out structural processing on the drug books, and use the existing knowledge base construction technology, such as: SPO extraction, entity association, entity normalization, etc., to establish a complete and accurate first knowledge base, and authoritative books can be Take photos, get images, and perform image-to-word processing. Then build the first knowledge base through the steps of information extraction, knowledge fusion and knowledge processing in sequence. The first knowledge base is composed of entity-relationship-entity triplets, for example, the association between the symptom entity and the drug entity constitutes a triplet.
其中，信息抽取是指从各种类型的数据源中提取出实体、属性以及实体间的相互关系，在此基础上形成本体化的知识表达，具体可以包括对半结构化数据(网页、百科)和非结构化数据(如图片、音频、视频)记性实体提取、关系提取和属性提取；知识融合是指在获得新知识之后，需要对其进行整合，以消除矛盾和歧义，比如某些实体可能有多种表达，某个特定称谓也许对应于多个不同的实体等，具体可以包括结构化数据(关系数据库)与第三方数据库进行数据整合后进行知识表示；知识加工是指对于经过融合的新知识，需要经过质量评估之后(部分需要人工参与甄别)，才能将合格的部分加入到知识库中，以确保知识库的质量，具体可以包括实体对齐、本体构建、知识更新、质量评估等功能模块。Among them, information extraction refers to the extraction of entities, attributes, and interrelationships between entities from various types of data sources, and on this basis to form ontological knowledge expressions, which can specifically include semi-structured data (web pages, encyclopedias) and unstructured data (such as pictures, audio, video) memory entity extraction, relationship extraction and attribute extraction; knowledge fusion refers to the need to integrate new knowledge after obtaining it to eliminate contradictions and ambiguities, such as some entities may There are many expressions, and a specific title may correspond to multiple different entities, etc. Specifically, it can include knowledge representation after data integration of structured data (relational database) and third-party databases; knowledge processing refers to the fusion of new Knowledge needs to be evaluated for quality (some need to be manually screened) before the qualified part can be added to the knowledge base to ensure the quality of the knowledge base. Specifically, it can include functional modules such as entity alignment, ontology construction, knowledge update, and quality assessment. .
可以理解，由于构建第一知识库所能采用的权威的药品书籍的数据量比较小，同时考虑到医药行业的准确性要求比较高，所以可以由一些医学专家在知识库构建过程中进行标注，以保证准确性，It can be understood that due to the relatively small data volume of authoritative drug books that can be used to build the first knowledge base, and considering the relatively high accuracy requirements of the pharmaceutical industry, some medical experts can mark them during the knowledge base construction process. To ensure accuracy,
另外，由于构建第一知识库时在图像转文字过程中会有一些损耗，(会出现一些错别字，比如说有一些段落出现错行等)，需要人力将其变成结构化的数据，因此药品书籍的处理过程复杂，此外药品书籍所能提供的药品数据有限，所以可以获取其他数据对其进行扩充，例如可以挖掘在网络中的医患问答语句，构建第二知识库。In addition, since there will be some loss in the process of image-to-text conversion when building the first knowledge base (some typos will appear, for example, there will be wrong lines in some paragraphs, etc.), manpower is required to turn it into structured data, so the drug The processing process of books is complicated. In addition, the drug data provided by drug books is limited, so other data can be obtained to expand it. For example, doctor-patient question-and-answer sentences in the network can be mined to build a second knowledge base.
最后将第一知识库和第二知识库的内容进行合并融合，获得所述药品知识库。从而能够提供准确全面的药品数据。Finally, the contents of the first knowledge base and the second knowledge base are merged to obtain the drug knowledge base. So as to provide accurate and comprehensive drug data.
303、根据药品推荐规则和所述药品知识库，通过推理引擎构建药品推理库。所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。303. According to the drug recommendation rules and the drug knowledge base, construct a drug reasoning base through a reasoning engine. The drug recommendation rule is established according to the contraindications of the drug, contraindicated population and drug interaction attributes.
本实施例中，可以专门分析药品知识库中的药品禁忌症、禁忌人群、药品相互作用等属性，并人工构建药品推荐规则，以规避推荐风险(建立的规则比如：患者是否怀孕，不能吃什么药，如果推荐药品中包含禁忌药品，则需要排除)。利用现有规则引擎技术，输入规则库和药品知识库，以建立专门的药品质量控制系统，即所述药品推理库。In this embodiment, attributes such as drug contraindications, contraindicated groups, and drug interactions in the drug knowledge base can be specifically analyzed, and drug recommendation rules can be manually constructed to avoid recommendation risks (rules established such as: whether the patient is pregnant, what not to eat If the recommended drugs contain contraindicated drugs, they need to be excluded). Utilize the existing rule engine technology, input the rule base and drug knowledge base, to establish a special drug quality control system, that is, the drug reasoning base.
304、根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表。304. Search the drug knowledge base according to the personal information, and obtain a first drug list according to the search result.
305、根据预设的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户。305. According to the preset drug inference library, screen the drugs in the first drug list to obtain a second drug list, so as to push the second drug list to the user.
本实施例中步骤304和步骤305与上述实施例中步骤202和步骤203相类似，此处不再赘述。Step 304 and step 305 in this embodiment are similar to step 202 and step 203 in the above embodiment, and will not be repeated here.
306、将所述第二药品列表向用户进行显示或播报。306. Display or broadcast the second drug list to the user.
可选地，可以通过扬声器进行语音播报，或者通过显示屏向用户展示推荐药品的图片和/或文字信息。用户点击药品图片，能够进一步查看药品的成分以及专家提供的用药注意事项。Optionally, a voice announcement can be made through a speaker, or pictures and/or text information of recommended medicines can be shown to the user through a display screen. Users can click on the picture of the drug to further view the ingredients of the drug and the precautions for medication provided by experts.
本实施例提供的药品推荐方法，通过根据药品书籍和/或网络问诊数据采用结构化处理技术构建药品知识库；并且根据药品推荐规则和所述药品知识库构建药品推理库，能够根据所述个人信息，在根据药品书籍和/或网络问诊数据构建的药品知识库中进行检索，并根据检索结果，获得第一药品列表；通过根据药品推荐规则和所述药品知识库构建的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；能够在保证用户的用药安全的前提下，准确的向用户推荐适合的药品，进而提升用户的用药体验。In the drug recommendation method provided in this embodiment, a drug knowledge base is constructed by using structured processing technology based on drug books and/or network consultation data; and a drug reasoning base is constructed according to drug recommendation rules and the drug knowledge base, which can Personal information is searched in the drug knowledge base constructed based on drug books and/or online consultation data, and according to the search results, the first list of drugs is obtained; through the drug reasoning base constructed based on drug recommendation rules and the drug knowledge base , screening the drugs in the first drug list to obtain a second drug list, so as to push the second drug list to the user; under the premise of ensuring the user's medication safety, it is possible to accurately recommend suitable drugs to the user Drugs, thereby improving the user's medication experience.
图4为本发明又一实施例提供的药品推荐设备的结构示意图。如图4所示，该药品推荐设备40包括：接收模块401、检索模块402以及筛选模块403。Fig. 4 is a schematic structural diagram of a drug recommendation device provided by another embodiment of the present invention. As shown in FIG. 4 , the drug recommendation device 40 includes: a receiving module 401 , a retrieval module 402 and a screening module 403 .
接收模块401，用于接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；The receiving module 401 is used to receive personal information input by the user; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, and drug allergy history;
本实施例中，用户输入个人信息的方式可以有多种，可以以触控信息的形式输入，还可以以语音信息的形式进行输入。In this embodiment, there are many ways for the user to input personal information, such as input in the form of touch information, or input in the form of voice information.
若为触控信息的形式输入，可参照图1所示实施例的说明，此处不再赘述。If the input is in the form of touch information, reference may be made to the description of the embodiment shown in FIG. 1 , which will not be repeated here.
若为语音信息的形式输入，具体的，用户可以根据系统提供的范例句法，描述自己的症状、年龄、性别、发病部位、病史、药物过敏史等信息，语音数据数据转入数据解析模块进行解析处理。用户的语音输入信息先通过现有的语音识别技术转为文字。文字信息通过离线训练好的自然语言理解(Natural Language Understanding，NLU)模型(利用中文分词、句法分析及命名实体识别技术有监督训练)进行关键信息抽取，抽取出患者的症状、年龄、性别、发病部位、病史、药物过敏史等信息(没有的留空)，并存储该信息到本地或后台服务器中，以供后续步骤使用。If the input is in the form of voice information, specifically, users can describe their symptoms, age, gender, disease location, medical history, drug allergy history and other information according to the sample syntax provided by the system, and the voice data data is transferred to the data analysis module for analysis deal with. The user's voice input information is first converted into text through the existing voice recognition technology. Key information is extracted from the text information through the Natural Language Understanding (NLU) model trained offline (supervised training using Chinese word segmentation, syntactic analysis and named entity recognition technology), and the symptoms, age, gender, and onset of the patient are extracted. Site, medical history, drug allergy history and other information (leave blank if none), and store the information in the local or background server for use in subsequent steps.
例如，用户输入语音描述“我今天体温38度，有一些流鼻涕”。For example, the user enters a voice description "My body temperature is 38 degrees today, and I have some runny nose".
通过语音识别模块将该语音信息转化为文字后，将文字输入NLU模型，NLU模型对该文字进行关键信息抽取，获得关键信息“体温38度”，“有鼻涕”等症状信息。在后续步骤中，根据该症状信息在药品知识库中进行推理计算，获得第一药品列表。After the speech information is converted into text through the speech recognition module, the text is input into the NLU model, and the NLU model extracts key information from the text, and obtains key information such as "body temperature 38 degrees", "nasal mucus" and other symptom information. In a subsequent step, reasoning calculations are performed in the drug knowledge base according to the symptom information to obtain the first list of drugs.
检索模块402，用于根据所述个人信息，在药品知识库中进行检索，并根据检索结果，获得第一药品列表；其中，所述药品知识库是根据药品书籍和/或网络问诊数据构建的；The retrieval module 402 is configured to search in the drug knowledge base according to the personal information, and obtain the first drug list according to the search results; wherein, the drug knowledge base is constructed based on drug books and/or network consultation data of;
实际应用中，将用户输入的症状输入药品知识库中进行检索。根据药品知识库中各药品与该症状的匹配度生成匹配度由高到低的一系列药品作为检索结果。并选取预设排名内的药品，生成第一药品列表。例如可以选择排名前10的药品作为第一药品列表。In practical applications, the symptoms entered by the user are entered into the drug knowledge base for retrieval. According to the matching degree of each drug in the drug knowledge base and the symptom, a series of drugs with matching degrees from high to low are generated as retrieval results. And select the medicines in the preset ranking to generate the first medicine list. For example, the top 10 drugs may be selected as the first drug list.
可选地，根据所述个人信息确定用户的症状；通过词频-逆文本频率指数TF-IDF算法，在药品知识库中查找与所述用户的症状匹配的药品，获得第一药品列表。Optionally, the user's symptoms are determined according to the personal information; through the word frequency-inverse text frequency index TF-IDF algorithm, the drugs matching the user's symptoms are searched in the drug knowledge base to obtain the first drug list.
可以理解，不同的症状会根据其的常见程度分配不同的权重，一般常见症状所分配的比重较小，比较少出现(比较特殊)的症状所分配的比重较大。例如，身体发热是比较常见的症状，昏厥是比较少出现的症状，那么身体发热被分配的比重比较小，昏厥被分配的比重比较大。如果一个药品的治疗症状中包括身体发热，另一个药品的治疗症状包括昏厥，那么第二个药品与用户的匹配度大于第一个药品。也即第二个药品的排名要靠前。另外，药品所包含的用户症状的个数越多，该药品与用户的匹配度也越大。It can be understood that different symptoms will be assigned different weights according to their commonness, generally common symptoms will be assigned a smaller proportion, and relatively rare (more special) symptoms will be assigned a larger proportion. For example, body fever is a relatively common symptom, and fainting is a relatively rare symptom, so the proportion assigned to body fever is relatively small, and the proportion assigned to fainting is relatively large. If one medicine treats symptoms that include body fever and another medicine treats symptoms that include fainting, then the second medicine is more likely to match the user than the first medicine. That is to say, the ranking of the second drug should be higher. In addition, the more the number of user symptoms contained in the drug, the greater the degree of matching between the drug and the user.
筛选模块403，用于根据预设的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；其中，所述药品推理库是根据药品推荐规则和所述药品知识库，通过推理引擎构建的；所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。The screening module 403 is configured to screen the drugs in the first drug list according to a preset drug reasoning library to obtain a second drug list, so as to push the second drug list to the user; wherein, the drug The reasoning base is constructed through the reasoning engine according to the drug recommendation rules and the drug knowledge base; the drug recommendation rules are established according to the contraindications of the drugs, contraindicated groups and drug interaction attributes.
本实施例中，所述药品推理库是根据药品推荐规则和所述药品知识库进行构建的，能够起到对药品推荐质量的控制作用。可选地，所述药品推荐规则可以是由医学专家制定的规则，具体的，医学专家根据药品的禁忌症、禁忌人群以及药物原理等属性制定该推荐规则。In this embodiment, the drug reasoning database is constructed according to the drug recommendation rules and the drug knowledge base, which can control the quality of drug recommendation. Optionally, the drug recommendation rule may be a rule formulated by a medical expert. Specifically, the medical expert formulates the recommendation rule according to attributes such as contraindications of the drug, contraindicated groups, and drug principles.
可以理解，为了用户的安全，为用户推荐更加合理的药品，需要对根据症状匹配度从药品知识库中检索到的第一药品列表进行进一步筛选。以防止用户购买与用户的当前身体状况不符的药品，例如孕期患者的禁忌药品。It can be understood that in order to recommend more reasonable medicines to users for the safety of users, it is necessary to further screen the first medicine list retrieved from the medicine knowledge base according to the matching degree of symptoms. To prevent users from purchasing medicines that are inconsistent with the user's current physical condition, such as contraindicated medicines for pregnant patients.
可选地，可以从所述第一药品列表中筛选排序前三的药品作为所述第二药品列表。Optionally, the top three drugs may be selected from the first drug list as the second drug list.
本发明实施例提供的药品推荐设备，通过接收模块401接收用户输入的个人信息；所述个人信息包括以下中至少一项：症状、年龄、性别、发病部位、病史、药物过敏史；检索模块402根据所述个人信息，在根据药品书籍和/或网络问诊数据构建的药品知识库中进行检索，并根据检索结果，获得第一药品列表；筛选模块403通过根据药品推荐规则和所述药品知识库构建的药品推理库，对所述第一药品列表中的药品进行筛选，获得第二药品列表，以将所述第二药品列表推送给用户；能够在保证用户的用药安全的前提下，准确的向用户推荐适合的药品，进而提升用户的用药体验。The drug recommendation device provided by the embodiment of the present invention receives the personal information input by the user through the receiving module 401; the personal information includes at least one of the following: symptoms, age, gender, disease site, medical history, and drug allergy history; the retrieval module 402 According to the personal information, search in the drug knowledge base constructed according to drug books and/or network consultation data, and obtain the first list of drugs according to the search results; The drug reasoning library constructed by the library screens the drugs in the first drug list to obtain the second drug list, so as to push the second drug list to the user; it can accurately Recommend suitable medicines to users, thereby improving the user's medication experience.
图5为本发明又一实施例提供的药品推荐设备的结构示意图。如图5所示，该药品推荐设备40还包括：第一构建模块404、语音识别模块405、第二构建模块406。Fig. 5 is a schematic structural diagram of a drug recommendation device provided by another embodiment of the present invention. As shown in FIG. 5 , the drug recommendation device 40 further includes: a first building block 404 , a voice recognition module 405 , and a second building block 406 .
可选地，所述检索模块402具体用于：Optionally, the retrieval module 402 is specifically configured to:
根据所述个人信息确定用户的症状；determine the user's symptoms based on said personal information;
通过词频-逆文本频率指数TF-IDF算法，在药品知识库中查找与所述用户的症状匹配的药品，获得第一药品列表。Through the word frequency-inverse text frequency index TF-IDF algorithm, the medicines matching the user's symptoms are searched in the medicine knowledge base, and the first medicine list is obtained.
可选地，所述设备还包括：Optionally, the device also includes:
第一构建模块404，用于对所述药品书籍进行信息抽取，通过结构化处理，确定抽取到的各药品与其治疗症状的关联关系，以构建第一知识库；The first building module 404 is used to extract information from the drug books, and determine the relationship between the extracted drugs and their treatment symptoms through structural processing, so as to build a first knowledge base;
获取网络问诊数据，并通过挖掘算法，确定所述网络问诊数据中各药品与其治疗症状的关联关系，以构建第二知识库；Obtaining online medical consultation data, and determining the relationship between each drug in the online medical consultation data and its treatment symptoms through a mining algorithm, so as to construct a second knowledge base;
将所述第一知识库与所述第二知识库进行融合，获得所述药品知识库。The first knowledge base is fused with the second knowledge base to obtain the drug knowledge base.
可选地，所述接收模块401具体用于：Optionally, the receiving module 401 is specifically configured to:
接收用户输入的语音信息，并将所述语音信息作为该用户的个人信息。The voice information input by the user is received, and the voice information is used as the user's personal information.
可选地，所述设备，还包括：Optionally, the device also includes:
语音识别模块405，用于通过语音识别算法对该语音信息进行识别，获得文字信息；A speech recognition module 405, configured to recognize the speech information through a speech recognition algorithm to obtain text information;
将所述文字信息输入自然语言理解NLU模型，通过所述NLU模型对所述文字信息进行关键信息抽取，获得信息抽取结果；The text information is input into a natural language understanding NLU model, and the key information is extracted from the text information through the NLU model to obtain an information extraction result;
所述检索模块具体用于：The retrieval module is specifically used for:
根据所述信息抽取结果，在药品知识库中进行检索以及相关性计算，获得第一药品列表。According to the information extraction result, search and correlation calculation are performed in the drug knowledge base to obtain the first drug list.
可选地，所述接收模块401具体用于：接收用户输入的触控信息，并将所述触控信息作为该用户的个人信息。Optionally, the receiving module 401 is specifically configured to: receive touch information input by a user, and use the touch information as personal information of the user.
可选地，所述设备还包括：第二构建模块406，用于根据药品推荐规则和所述药品知识库，通过推理引擎构建的；所述药品推荐规则是根据药品的禁忌症、禁忌人群和药品相互作用属性建立的。Optionally, the device further includes: a second construction module 406, configured to construct through a reasoning engine according to the drug recommendation rules and the drug knowledge base; the drug recommendation rules are based on drug contraindications, contraindicated groups and Drug interaction properties established.
本发明实施例提供的药品推荐设备，可用于执行上述的方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。The drug recommendation device provided by the embodiment of the present invention can be used to implement the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not repeat them here.
图6为本发明又一实施例提供的药品推荐设备的硬件结构示意图。如图6所示，本实施例提供的药品推荐设备60包括：至少一个处理器601和存储器602。该药品推荐设备60还包括通信部件603。其中，处理器601、存储器602以及通信部件603通过总线604连接。Fig. 6 is a schematic diagram of a hardware structure of a drug recommendation device according to another embodiment of the present invention. As shown in FIG. 6 , the drug recommendation device 60 provided in this embodiment includes: at least one processor 601 and a memory 602 . The medicine recommending device 60 also includes a communication part 603 . Wherein, the processor 601 , the memory 602 and the communication unit 603 are connected through a bus 604 .
在具体实现过程中，至少一个处理器601执行所述存储器602存储的计算机执行指令，使得至少一个处理器601执行如上药品推荐设备60所执行的药品推荐方法。In a specific implementation process, at least one processor 601 executes the computer-executed instructions stored in the memory 602 , so that at least one processor 601 executes the drug recommendation method performed by the drug recommendation device 60 above.
当本实施例的药品知识库中的检索过程由服务器执行时，该通信部件603可以将用户输入的个人信息发送给服务器。When the search process in the drug knowledge base of this embodiment is executed by the server, the communication component 603 can send the personal information input by the user to the server.
处理器601的具体实现过程可参见上述方法实施例，其实现原理和技术效果类似，本实施例此处不再赘述。For the specific implementation process of the processor 601, reference may be made to the foregoing method embodiments, and the implementation principles and technical effects thereof are similar, and details are not repeated here in this embodiment.
在上述的图6所示的实施例中，应理解，处理器可以是中央处理单元(英文：Central Processing Unit，简称：CPU)，还可以是其他通用处理器、数字信号处理器(英文：Digital Signal Processor，简称：DSP)、专用集成电路(英文：Application SpecificIntegrated Circuit，简称：ASIC)等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合发明所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。In the above-mentioned embodiment shown in FIG. 6, it should be understood that the processor can be a central processing unit (English: Central Processing Unit, referred to as: CPU), and can also be other general-purpose processors, digital signal processors (English: Digital Signal Processor, referred to as: DSP), application specific integrated circuit (English: Application Specific Integrated Circuit, referred to as: ASIC), etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, and the like. The steps of the method disclosed in conjunction with the invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
存储器可能包含高速RAM存储器，也可能还包括非易失性存储NVM，例如至少一个磁盘存储器。The memory may include high-speed RAM memory, and may also include non-volatile storage NVM, such as at least one disk memory.
总线可以是工业标准体系结构(Industry Standard Architecture，ISA)总线、外部设备互连(Peripheral Component，PCI)总线或扩展工业标准体系结构(ExtendedIndustry Standard Architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，本申请附图中的总线并不限定仅有一根总线或一种类型的总线。The bus may be an Industry Standard Architecture (Industry Standard Architecture, ISA) bus, a Peripheral Component Interconnect (Peripheral Component, PCI) bus, or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus, etc. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, the buses in the drawings of the present application are not limited to only one bus or one type of bus.
本申请还提供一种计算机可读存储介质，所述计算机可读存储介质中存储有计算机执行指令，当处理器执行所述计算机执行指令时，实现如上药品推荐设备执行的药品推荐方法。The present application also provides a computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the drug recommendation method performed by the above-mentioned drug recommendation device is implemented.
上述的计算机可读存储介质，上述可读存储介质可以是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。可读存储介质可以是通用或专用计算机能够存取的任何可用介质。The above-mentioned computer-readable storage medium, the above-mentioned readable storage medium can be realized by any type of volatile or non-volatile storage device or their combination, 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 Disk. Readable storage media can be any available media that can be accessed by a general purpose or special purpose computer.
一种示例性的可读存储介质耦合至处理器，从而使处理器能够从该可读存储介质读取信息，且可向该可读存储介质写入信息。当然，可读存储介质也可以是处理器的组成部分。处理器和可读存储介质可以位于专用集成电路(Application Specific IntegratedCircuits，简称：ASIC)中。当然，处理器和可读存储介质也可以作为分立组件存在于设备中。An exemplary readable storage medium is coupled to the processor such the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium may be located in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by program instructions and related hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910534894.5ACN110289068A (en) | 2019-06-20 | 2019-06-20 | Drug recommendation method and equipment |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910534894.5ACN110289068A (en) | 2019-06-20 | 2019-06-20 | Drug recommendation method and equipment |
| Publication Number | Publication Date |
|---|---|
| CN110289068Atrue CN110289068A (en) | 2019-09-27 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910534894.5APendingCN110289068A (en) | 2019-06-20 | 2019-06-20 | Drug recommendation method and equipment |
| Country | Link |
|---|---|
| CN (1) | CN110289068A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111048173A (en)* | 2019-12-19 | 2020-04-21 | 博奥生物集团有限公司 | Method and device for pushing medication data |
| CN111312359A (en)* | 2020-02-03 | 2020-06-19 | 广东省第二人民医院（广东省卫生应急医院） | Method and device for intelligent recommendation of medication regimen |
| CN111403043A (en)* | 2020-03-09 | 2020-07-10 | 武汉联影医疗科技有限公司 | IoT-based resource recommendation method and server |
| CN111627515A (en)* | 2020-05-29 | 2020-09-04 | 上海商汤智能科技有限公司 | Medicine recommendation method and device, electronic equipment and medium |
| CN111933302A (en)* | 2020-10-09 | 2020-11-13 | 平安科技（深圳）有限公司 | Medicine recommendation method and device, computer equipment and storage medium |
| CN112053763A (en)* | 2020-08-19 | 2020-12-08 | 北京左医健康技术有限公司 | Online medication consultation method, online medication consultation device and intelligent terminal |
| CN112116978A (en)* | 2020-09-17 | 2020-12-22 | 陕西师范大学 | Method, system and device for recommending rheumatic immune drugs |
| CN112133416A (en)* | 2020-09-14 | 2020-12-25 | 微医云(杭州)控股有限公司 | Method, apparatus, electronic device and storage medium for determining replacement medicament |
| CN112242189A (en)* | 2020-10-10 | 2021-01-19 | 北京小乔机器人科技发展有限公司 | Online voice medicine finding method |
| CN113076301A (en)* | 2021-03-31 | 2021-07-06 | 北京搜狗科技发展有限公司 | Knowledge base construction method, information query method, device and equipment |
| CN113140278A (en)* | 2020-01-20 | 2021-07-20 | 阿里健康信息技术有限公司 | Data processing method, terminal device, server and storage medium |
| CN113223657A (en)* | 2021-06-01 | 2021-08-06 | 联仁健康医疗大数据科技股份有限公司 | Medicine information processing method and device, electronic equipment and storage medium |
| CN113556649A (en)* | 2020-04-23 | 2021-10-26 | 百度在线网络技术（北京）有限公司 | Broadcasting control method and device of intelligent sound box |
| CN113658659A (en)* | 2021-08-20 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Medical information processing method and device, computer equipment and storage medium |
| CN113782144A (en)* | 2021-09-10 | 2021-12-10 | 江西中医药大学 | Traditional Chinese medicine preparation recommending and customizing method, electronic equipment and storage medium |
| CN113903423A (en)* | 2021-11-18 | 2022-01-07 | 北方健康医疗大数据科技有限公司 | Recommended methods, devices, equipment and media for medication regimens |
| WO2022041729A1 (en)* | 2020-08-31 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Medication recommendation method, apparatus and device, and storage medium |
| CN114334073A (en)* | 2020-09-28 | 2022-04-12 | 卫宁健康科技集团股份有限公司 | Medicine distribution mode recommendation method and device |
| CN115101166A (en)* | 2022-07-19 | 2022-09-23 | 康键信息技术（深圳）有限公司 | Recommended method and device for drug information, storage medium, and computer equipment |
| WO2022227176A1 (en)* | 2021-04-29 | 2022-11-03 | 平安科技（深圳）有限公司 | Drug information pushing method and apparatus, computer device, and storage medium |
| CN118230897A (en)* | 2024-05-24 | 2024-06-21 | 杭州中宝科技有限公司 | A drug information generation method and terminal |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040093331A1 (en)* | 2002-09-20 | 2004-05-13 | Board Of Regents, University Of Texas System | Computer program products, systems and methods for information discovery and relational analyses |
| CN107799160A (en)* | 2017-10-26 | 2018-03-13 | 医渡云（北京）技术有限公司 | Medication aid decision-making method and device, storage medium, electronic equipment |
| CN109102855A (en)* | 2018-07-03 | 2018-12-28 | 北京康夫子科技有限公司 | Drug recommended method |
| CN109378045A (en)* | 2018-09-26 | 2019-02-22 | 北京理工大学 | Drug decision support method based on drug knowledge graph reasoning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040093331A1 (en)* | 2002-09-20 | 2004-05-13 | Board Of Regents, University Of Texas System | Computer program products, systems and methods for information discovery and relational analyses |
| CN107799160A (en)* | 2017-10-26 | 2018-03-13 | 医渡云（北京）技术有限公司 | Medication aid decision-making method and device, storage medium, electronic equipment |
| CN109102855A (en)* | 2018-07-03 | 2018-12-28 | 北京康夫子科技有限公司 | Drug recommended method |
| CN109378045A (en)* | 2018-09-26 | 2019-02-22 | 北京理工大学 | Drug decision support method based on drug knowledge graph reasoning |
| Title |
|---|
| 王小胜: "基于相似和冲突关系挖掘的药品推荐系统研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111048173A (en)* | 2019-12-19 | 2020-04-21 | 博奥生物集团有限公司 | Method and device for pushing medication data |
| CN111048173B (en)* | 2019-12-19 | 2024-04-05 | 博奥生物集团有限公司 | Medication data pushing method and device |
| CN113140278B (en)* | 2020-01-20 | 2025-05-06 | 阿里健康信息技术有限公司 | Data processing method, terminal device, server and storage medium |
| CN113140278A (en)* | 2020-01-20 | 2021-07-20 | 阿里健康信息技术有限公司 | Data processing method, terminal device, server and storage medium |
| CN111312359B (en)* | 2020-02-03 | 2023-12-29 | 广东省第二人民医院（广东省卫生应急医院） | Intelligent recommendation method and device for medication scheme |
| CN111312359A (en)* | 2020-02-03 | 2020-06-19 | 广东省第二人民医院（广东省卫生应急医院） | Method and device for intelligent recommendation of medication regimen |
| CN111403043A (en)* | 2020-03-09 | 2020-07-10 | 武汉联影医疗科技有限公司 | IoT-based resource recommendation method and server |
| CN113556649B (en)* | 2020-04-23 | 2023-08-04 | 百度在线网络技术（北京）有限公司 | Broadcasting control method and device of intelligent sound box |
| CN113556649A (en)* | 2020-04-23 | 2021-10-26 | 百度在线网络技术（北京）有限公司 | Broadcasting control method and device of intelligent sound box |
| CN111627515A (en)* | 2020-05-29 | 2020-09-04 | 上海商汤智能科技有限公司 | Medicine recommendation method and device, electronic equipment and medium |
| CN112053763A (en)* | 2020-08-19 | 2020-12-08 | 北京左医健康技术有限公司 | Online medication consultation method, online medication consultation device and intelligent terminal |
| WO2022041729A1 (en)* | 2020-08-31 | 2022-03-03 | 康键信息技术（深圳）有限公司 | Medication recommendation method, apparatus and device, and storage medium |
| CN112133416A (en)* | 2020-09-14 | 2020-12-25 | 微医云(杭州)控股有限公司 | Method, apparatus, electronic device and storage medium for determining replacement medicament |
| CN112116978B (en)* | 2020-09-17 | 2023-01-31 | 陕西师范大学 | Method, system and device for recommending rheumatism immunity medicine |
| CN112116978A (en)* | 2020-09-17 | 2020-12-22 | 陕西师范大学 | Method, system and device for recommending rheumatic immune drugs |
| CN114334073A (en)* | 2020-09-28 | 2022-04-12 | 卫宁健康科技集团股份有限公司 | Medicine distribution mode recommendation method and device |
| CN111933302A (en)* | 2020-10-09 | 2020-11-13 | 平安科技（深圳）有限公司 | Medicine recommendation method and device, computer equipment and storage medium |
| WO2021179694A1 (en)* | 2020-10-09 | 2021-09-16 | 平安科技（深圳）有限公司 | Drug recommendation method, apparatus, computer device, and storage medium |
| CN112242189A (en)* | 2020-10-10 | 2021-01-19 | 北京小乔机器人科技发展有限公司 | Online voice medicine finding method |
| CN113076301A (en)* | 2021-03-31 | 2021-07-06 | 北京搜狗科技发展有限公司 | Knowledge base construction method, information query method, device and equipment |
| CN113076301B (en)* | 2021-03-31 | 2025-02-07 | 北京搜狗科技发展有限公司 | A method for building a knowledge base, an information query method, a device and an apparatus |
| WO2022227176A1 (en)* | 2021-04-29 | 2022-11-03 | 平安科技（深圳）有限公司 | Drug information pushing method and apparatus, computer device, and storage medium |
| CN113223657A (en)* | 2021-06-01 | 2021-08-06 | 联仁健康医疗大数据科技股份有限公司 | Medicine information processing method and device, electronic equipment and storage medium |
| CN113658659B (en)* | 2021-08-20 | 2023-07-21 | 深圳平安智慧医健科技有限公司 | Medical information processing method, medical information processing device, computer equipment and storage medium |
| CN113658659A (en)* | 2021-08-20 | 2021-11-16 | 平安国际智慧城市科技股份有限公司 | Medical information processing method and device, computer equipment and storage medium |
| CN113782144A (en)* | 2021-09-10 | 2021-12-10 | 江西中医药大学 | Traditional Chinese medicine preparation recommending and customizing method, electronic equipment and storage medium |
| CN113903423A (en)* | 2021-11-18 | 2022-01-07 | 北方健康医疗大数据科技有限公司 | Recommended methods, devices, equipment and media for medication regimens |
| CN115101166A (en)* | 2022-07-19 | 2022-09-23 | 康键信息技术（深圳）有限公司 | Recommended method and device for drug information, storage medium, and computer equipment |
| CN118230897A (en)* | 2024-05-24 | 2024-06-21 | 杭州中宝科技有限公司 | A drug information generation method and terminal |
| Publication | Publication Date | Title |
|---|---|---|
| CN110289068A (en) | Drug recommendation method and equipment | |
| Milosevic et al. | A framework for information extraction from tables in biomedical literature | |
| CN112215008B (en) | Entity identification method, device, computer equipment and medium based on semantic understanding | |
| WO2020147758A1 (en) | Drug recommendation method and apparatus, medium, and electronic device | |
| KR102170206B1 (en) | Information Search System and Method using keyword and relation information | |
| CN108536852A (en) | Question and answer exchange method and device, computer equipment and computer readable storage medium | |
| US20150089409A1 (en) | System and method for managing opinion networks with interactive opinion flows | |
| US11847411B2 (en) | Obtaining supported decision trees from text for medical health applications | |
| WO2023040516A1 (en) | Event integration method and apparatus, and electronic device, computer-readable storage medium and computer program product | |
| US12243653B1 (en) | Generating structured data records using an extraction neural network | |
| US11928437B2 (en) | Machine reading between the lines | |
| Wei et al. | Online education recommendation model based on user behavior data analysis | |
| CN118675674A (en) | User portrait construction method and device | |
| Jung et al. | Building a specialized lexicon for breast cancer clinical trial subject eligibility analysis | |
| WO2024098636A1 (en) | Text matching method and apparatus, computer-readable storage medium, and terminal | |
| CN116701593A (en) | Chinese question answering model training method and related equipment based on GraphQL | |
| US12430327B2 (en) | Answer generation using machine reading comprehension and supported decision trees | |
| McRoy et al. | Toward automated classification of consumers’ cancer-related questions with a new taxonomy of expected answer types | |
| Alegre Sepulveda et al. | Twitter sentiment analysis for the estimation of voting intention in the 2017 Chilean elections | |
| CN118629573A (en) | Medical report interpretation method, system and related device | |
| Chen et al. | Detecting the association of health problems in consumer-level medical text | |
| CN116483987A (en) | Target group selection method, device, computer equipment and readable storage medium | |
| CN112214580B (en) | Article identification method, apparatus, computer device and storage medium | |
| AU2022201117A1 (en) | Frameworks and methodologies for enabling searching and/or categorisation of digitised information, including clinical report data | |
| Adesina et al. | Text messaging and retrieval techniques for a mobile health information system |
| 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 |