CN111897967A - A medical consultation recommendation method based on knowledge graph and social media - Google Patents
A medical consultation recommendation method based on knowledge graph and social mediaDownload PDFInfo
- Publication number
- CN111897967A CN111897967ACN202010639311.8ACN202010639311ACN111897967ACN 111897967 ACN111897967 ACN 111897967ACN 202010639311 ACN202010639311 ACN 202010639311ACN 111897967 ACN111897967 ACN 111897967A
- Authority
- CN
- China
- Prior art keywords
- medical
- disease
- entity
- department
- symptom
- 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.)
- Pending
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/35—Clustering; Classification
- G06F16/355—Creation or modification of classes or clusters
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Pathology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明涉及数据挖掘技术，具体涉及一种基于知识图谱和社交媒体的医疗问诊推荐方法。The invention relates to data mining technology, in particular to a method for recommending medical consultation based on knowledge graphs and social media.
背景技术Background technique
目前，人们对于移动医疗服务的需求越来越高。生活中，人们经常会察觉到身体出现某些症状，却不能及时找到对应的科室和服务质量较好的医院及医生。互联网医疗服务(如腾讯医疗、寻医问药、好大夫等)的出现一定程度上缓解了这一问题，然而多数医疗网站仅仅提供疾病科普以及在线预约等功能，少数网站提供疾病自诊的手段，然而其多数仅允许用户输入单个关键词，基于关键词匹配给出推荐疾病，给出的疾病推荐列表非常冗长，没有推荐意义，且其并未涉及到对于医生和医院的推荐。At present, people's demand for mobile medical services is getting higher and higher. In life, people often notice certain symptoms in their bodies, but they cannot find the corresponding departments and hospitals and doctors with better service quality in time. The emergence of Internet medical services (such as Tencent Medical, seeking medical advice, good doctors, etc.) has alleviated this problem to a certain extent. However, most medical websites only provide functions such as disease popularization and online appointment, and a few websites provide self-diagnosis methods for diseases. However, most of them only allow users to input a single keyword, and recommend diseases based on keyword matching. The given disease recommendation list is very long and has no recommendation significance, and it does not involve recommendations for doctors and hospitals.
目前，人们对于医疗知识图谱展开了广泛的研究。国外有Rotmensch、Wang等人从电子健康记录(EHR，Electronic Health Records)中抽取信息，构建了各种各样的医疗知识图谱，并将其应用到药物推荐、医疗诊断辅助系统等。而国内对于医疗知识图谱也展开了综述性研究，侯梦薇和袁凯琦等人介绍了医疗知识图谱构建的核心技术，并将其应用场景归纳为临床决策支持系统、医疗语义搜索引擎、医疗问答系统等。At present, extensive research has been carried out on the medical knowledge graph. Abroad, Rotmensch, Wang and others extracted information from Electronic Health Records (EHR, Electronic Health Records), constructed a variety of medical knowledge maps, and applied them to drug recommendation, medical diagnosis assistance systems, etc. Domestic research on medical knowledge graph has also been reviewed. Hou Mengwei, Yuan Kaiqi and others introduced the core technology of medical knowledge graph construction, and summarized its application scenarios into clinical decision support system, medical semantic search engine, medical question answering system, etc.
近年来，随着自然语言处理技术的发展，也有一些研究工作致力于从医疗评论中挖掘用户情感信息。Hao等人基于好大夫网站评论文本数据，采用了LDA(Latent DirichletAllocation，潜在迪利克雷分配)模型挖掘了评论的几个情感属性，并简单分析了在这个几个情感属性上的极性表现。何玲玲同样使用好大夫、阿亮医生网等线上评论文本数据，通过语义词典和语义框架手段，构建了评论的情感主题，并对情感极性及其强弱进行了分析。情感属性提取可以反应用户在特定方面的满意度，但是他们使用的方法具有一定的局限性，没有充分利用自然语言处理领域的前沿方法。In recent years, with the development of natural language processing technology, there are also some research works dedicated to mining user emotional information from medical reviews. Hao et al. used the LDA (Latent Dirichlet Allocation) model to mine several sentiment attributes of reviews based on the review text data of the good doctor website, and simply analyzed the polarity performance on these several emotional attributes. He Lingling also used online comment text data such as Haodafu and Dr.Aliang.com to construct the emotional theme of the comment by means of semantic dictionary and semantic framework, and analyzed the emotional polarity and its strength. Sentiment attribute extraction can reflect users' satisfaction in specific aspects, but the methods they use have certain limitations and do not fully utilize the cutting-edge methods in the field of natural language processing.
发明内容SUMMARY OF THE INVENTION
针对以上现有技术中存在的问题，本发明提出了一种基于知识图谱和社交媒体的医疗问诊推荐方法。In view of the above problems in the prior art, the present invention proposes a medical consultation recommendation method based on knowledge graph and social media.
本发明的基于知识图谱和社交媒体的医疗问诊推荐方法，包括以下步骤：The medical consultation recommendation method based on knowledge graph and social media of the present invention comprises the following steps:
1)获取互联网医疗中开放的结构化疾病信息，从中提取疾病及其相关信息，疾病的相关信息包括症状关键词、发病率、易患人群、并发症、就诊科室和症状描述，从易患人群中进一步抽取年龄和性别信息，构建“疾病—症状”的医疗知识图谱，医疗知识图谱包括五种实体和五种关系，五种实体为：疾病实体、科室实体、年龄实体、性别实体和症状关键词实体，其中疾病实体拥有症状描述属性和发病率属性，五种关系为：疾病实体与疾病实体之间存在并发症关系、疾病实体和症状关键词实体之间存在拥有关系、疾病实体和科室实体之间存在就诊科室关系、疾病实体和年龄实体之间存在易患年龄关系，疾病实体和性别实体之间存在易患性别关系；1) Obtain open structured disease information in Internet medical care, and extract diseases and related information from them. Disease-related information includes symptom keywords, incidence rates, susceptible groups, complications, visiting departments and symptom descriptions. The age and gender information is further extracted from , and the medical knowledge map of "disease-symptom" is constructed. The medical knowledge map includes five entities and five relationships. The five entities are: disease entity, department entity, age entity, gender entity and symptom key Word entity, in which the disease entity has the attribute of symptom description and the attribute of incidence, and the five relationships are: there is a complication relationship between the disease entity and the disease entity, there is an ownership relationship between the disease entity and the symptom keyword entity, the disease entity and the department entity There is a relationship between visiting departments, a relationship of susceptible age between disease entities and age entities, and a susceptible gender relationship between disease entities and gender entities;
2)对步骤1)构建的医疗知识图谱，使用距离翻译模型训练知识图谱嵌入，将医疗知识图谱中的实体和关系映射为向量空间中的表述，得到医疗知识图谱中疾病实体的嵌入向量信息；2) For the medical knowledge graph constructed in step 1), use the distance translation model to train the knowledge graph embedding, map the entities and relationships in the medical knowledge graph to representations in the vector space, and obtain the embedded vector information of disease entities in the medical knowledge graph;
3)获取互联网上开放的医疗评论数据，医疗评论数据包含医生名称、医生所属的就诊科室、就诊科室所属的医院以及对医生的患者评论文本；根据医疗服务质量评价指标，标注患者评论文本，使用自然语言处理模型对患者评论文本的每个指标维度进行情感极性分析，统计每个医生的好评率，根据医生与就诊科室的所属关系，对同一就诊科室的患者评论文本进行汇总，得到相应的就诊科室的好评率，并根据威尔逊区间法分别得到医生和就诊科室的威尔逊评分；3) Obtain open medical review data on the Internet. The medical review data includes the doctor's name, the medical department to which the doctor belongs, the hospital to which the medical department belongs, and the text of the patient's comment to the doctor; according to the medical service quality evaluation index, mark the text of the patient's comment and use The natural language processing model analyzes the sentiment polarity of each index dimension of the patient's comment text, counts the favorable rate of each doctor, and summarizes the patient's comment text in the same clinic according to the relationship between the doctor and the clinic to obtain the corresponding The favorable rate of the visiting department is obtained, and the Wilson score of the doctor and the visiting department is obtained according to the Wilson interval method;
4)用户输入的症状关键词、性别、年龄和症状描述信息中的包含症状关键词M种信息，即症状关键词是必须输入的信息，1≤M≤4，根据用户输入的M种信息查询医疗知识图谱，构建初始疾病实体备选集，根据医疗知识图谱中疾病实体的嵌入向量信息选择最为相似的疾病实体扩展备选集，挖掘用户潜在患有的疾病，最后根据用户输入的性别、年龄、症状关键词和症状描述中相应的M个方面的相似性筛选出推荐疾病，并根据相应疾病实体的就诊科室，推荐威尔逊评分最高的就诊科室所属的医院和医生：4) The symptom keywords, gender, age, and symptom description information input by the user contain M kinds of information about the symptom keywords, that is, the symptom keywords are the information that must be input, 1≤M≤4, according to the M kinds of information input by the user. Medical knowledge graph, construct the initial disease entity candidate set, select the most similar disease entity to expand the candidate set according to the embedding vector information of the disease entity in the medical knowledge graph, mine the diseases that the user potentially suffers from, and finally, according to the gender and age input by the user , symptom keywords and the similarity of the corresponding M aspects in the symptom description to screen out the recommended diseases, and according to the medical department of the corresponding disease entity, recommend the hospital and doctor to which the medical department with the highest Wilson score belongs:
a)构建初始疾病实体备选集：根据用户输入的症状关键词，查询医疗知识图谱，根据疾病实体和症状关键词实体之间的拥有关系，筛选出症状关键词最为相似的多个疾病实体，并且根据疾病实体拥有的发病率属性，选取发病率最高的多个疾病实体，得到初始疾病实体备选集；a) Construction of the initial disease entity candidate set: According to the symptom keywords input by the user, the medical knowledge graph is queried, and according to the ownership relationship between the disease entity and the symptom keyword entity, multiple disease entities with the most similar symptom keywords are screened out. And according to the morbidity attribute possessed by the disease entity, multiple disease entities with the highest morbidity are selected to obtain the initial disease entity candidate set;
b)扩充疾病实体备选集：基于医疗知识图谱中疾病实体的嵌入向量，选择与疾病实体备选集中每个疾病实体的嵌入向量的欧式距离最近的一个或多个疾病实体，即最为相似的疾病实体，对初始疾病实体备选集进行扩充，得到疾病实体扩展备选集，从而挖掘用户潜在患有的疾病；b) Expanding the disease entity candidate set: Based on the embedding vector of the disease entity in the medical knowledge graph, select one or more disease entities with the nearest Euclidean distance to the embedding vector of each disease entity in the disease entity candidate set, that is, the most similar disease entity. Disease entity, expand the initial disease entity candidate set, and obtain the disease entity expansion candidate set, so as to mine the diseases that the user may suffer from;
c)给出最终推荐疾病结果：根据性别、年龄、症状关键词和症状描述中的M个方面的相似性，从疾病实体扩展备选集中筛选出推荐结果，其中，性别、年龄的相似度基于字符串匹配，症状关键词的相似度基于集合交运算，症状描述先使用词频-逆文件频率(TF-IDF，Term Frequency–Inverse Document Frequency)模型得到其向量表述，最终的症状描述相似度以向量之间的余弦相似度衡量；最终选择M个方面的相似度之和最高的多种疾病实体作为推荐结果，并查找医疗知识图谱，根据疾病实体和科室实体之间存在就诊科室关系，分别给出每一疾病实体相应的就诊科室；c) Give the final recommended disease results: According to the similarity of M aspects in gender, age, symptom keywords and symptom descriptions, the recommended results are screened from the extended candidate set of disease entities, where the similarity of gender and age is based on String matching, the similarity of symptom keywords is based on the set intersection operation, the symptom description first uses the Term Frequency-Inverse Document Frequency (TF-IDF, Term Frequency-Inverse Document Frequency) model to obtain its vector representation, and the final symptom description similarity is expressed as a vector. The cosine similarity between the two is measured; finally, multiple disease entities with the highest sum of similarity in M aspects are selected as the recommendation results, and the medical knowledge map is searched. According to the relationship between the disease entity and the department entity, respectively The corresponding medical department for each disease entity;
d)分别针对每种疾病实体，根据步骤c)得到的最终推荐的每一疾病实体相应的就诊科室，按照步骤3)的威尔逊评分，选择各家医院在这类就诊科室中得分最高的医院，再选择所属的医院的就诊科室下得分最高的医生推荐给用户。d) for each disease entity respectively, according to the corresponding visiting department of each disease entity that is finally recommended in step c), and according to the Wilson score of step 3), select the hospital with the highest score in each hospital in this type of visiting department, Then select the doctor with the highest score under the department of the hospital to which you belong to recommend it to the user.
进一步，在步骤4)的d)中，根据步骤c)得到的最终推荐疾病实体的就诊科室，按照步骤3)的威尔逊评分，选择各家医院中在这类就诊科室中得分最高的多家医院，结合社交网站上排名顺序，选择这多家医院中排名最高的医院，再选择所属的医院的就诊科室下得分最高的医生推荐给用户。Further, in d) of step 4), according to the final recommendation department of the disease entity obtained in step c), according to the Wilson score of step 3), select multiple hospitals with the highest scores in this type of medical department in each hospital , combined with the ranking order on social networking sites, select the hospital with the highest ranking among the multiple hospitals, and then select the doctor with the highest score in the department of the hospital to which it belongs to recommend it to the user.
在步骤1)中出现的疾病和疾病实体，代指实际上是统一的，疾病实体为知识图谱中的表述，疾病则是对应生活中的表述，其他类似。Diseases and disease entities appearing in step 1) are actually unified, disease entities are representations in the knowledge map, diseases are representations corresponding to life, and others are similar.
在步骤2)中，训练知识图谱嵌入的模型为距离翻译模型中的一种。In step 2), the model for training the knowledge graph embedding is one of the distance translation models.
在步骤3)中，自然语言处理模型采用深度学习模型，如LSTM(Long Short-termMemory，长短时记忆网络)、BERT(Bidirectional Encoder Representations fromTransformers，互感器双向编码预表示模型)等中的一种。情感极性分析以及服务质量的评价信息，包括以下步骤：In step 3), the natural language processing model adopts a deep learning model, such as one of LSTM (Long Short-term Memory, long short-term memory network), BERT (Bidirectional Encoder Representations from Transformers, mutual inductor bidirectional encoding pre-representation model) and the like. Sentiment polarity analysis and service quality evaluation information, including the following steps:
a)根据医疗服务质量的评价指标，对患者评论文本进行情感极性人工标注，每个服务质量的评价指标维度标注的情感极性有三种：积极、中性和消极，人工标注的患者评论文本的数目不得少于6000条；a) According to the evaluation index of medical service quality, the sentiment polarity of patient comment text is manually marked. There are three kinds of sentiment polarity marked by the evaluation index dimension of each service quality: positive, neutral and negative. Manually marked patient comment text shall not be less than 6000;
b)将标注好的评论文本数据转换为数字化表示，输入自然语言处理模型进行训练；b) Convert the marked comment text data into a digital representation, and input the natural language processing model for training;
c)利用训练好的自然语言处理模型对剩余的评论文本数据进行情感极性分析，得到每个医生的好评率，医生的好评率即同一个医生的积极的患者评论文本的数目占患者评论文本的总数目的比例；c) Use the trained natural language processing model to analyze the sentiment polarity of the remaining review text data, and obtain the favorable rate of each doctor. The doctor's favorable rate is the number of positive patient review texts of the same doctor, which accounts for the proportion of the patient review texts. the proportion of the total;
d)根据医生与就诊科室的所属关系，对同一家医院的同一就诊科室的患者评论文本进行汇总，得到相应的医院的就诊科室的好评率，就诊科室的好评率即同一就诊科室的所有医生的积极的患者评论文本的数目占这个就诊科室的所有患者评论文本的总数目的比例；d) According to the affiliation between the doctor and the treating department, summarize the texts of the patients' comments in the same treating department of the same hospital, and obtain the favorable rate of the treating department of the corresponding hospital. The number of positive patient comment texts as a percentage of the total number of patient comment texts for this visiting department;
e)医生和就诊科室的在服务质量的评价指标维度上的威尔逊评分Score的计算公式为：e) The formula for calculating the Wilson Score on the dimension of service quality evaluation indicators for doctors and visiting departments is:
其中，p表示好评率，zα表示正态分布的分位数，取值范围是[1.6,6.0]，用于衡量评分可信度，可信度范围为90％～100％，n表示评论文本数据的总数量；Among them, p represents the favorable rate, zα represents the quantile of the normal distribution, the value range is [1.6, 6.0], which is used to measure the reliability of the rating, and the reliability range is 90% to 100%, and n represents the review. the total amount of text data;
f)根据上面的公式，给出每个医生的威尔逊评分以及每个就诊科室的威尔逊评分。f) According to the above formula, give the Wilson score of each doctor and the Wilson score of each visiting department.
参考的医疗服务质量评价指标来自于Berry等人提出的SERVQUAL(ServiceQuality，服务质量)模型，该模型分为五个方面，分别为Tangibles(即有形性，用于衡量服务提供商环境设施及服务人员外表等方面的表现)、Reliability(即可靠性，用于衡量服务提供商兑现承诺的能力)、Responsiveness(即响应性，用于衡量服务提供商帮助顾客迅速提高服务的愿望)、Assurance(即保证性，用于衡量服务人员的知识、礼节以及表达出自信和可信能力)、Empathy(即共情性，用于衡量服务提供商关心并为顾客提高个性化服务的愿望和能力)。本发明在实际应用的过程中根据医疗评论的特点做了一些微调，具体如下：The reference medical service quality evaluation index comes from the SERVQUAL (ServiceQuality, service quality) model proposed by Berry et al. appearance, etc.), Reliability (i.e. reliability, which is used to measure the service provider's ability to deliver on promises), Responsiveness (i.e., responsiveness, which is used to measure the service provider's desire to help customers quickly improve service), Assurance (i.e. assurance Sexuality, which is used to measure the knowledge, etiquette, and ability to express confidence and trustworthiness of service personnel), Empathy (that is, empathy, which is used to measure the desire and ability of service providers to care and improve personalized service for customers). In the process of practical application, the present invention has made some fine-tuning according to the characteristics of medical reviews, as follows:
1、由于医疗评论缺少对医院硬件设施的描述，删除了有形性评价维度；1. Due to the lack of description of hospital hardware facilities in medical reviews, the dimension of tangible evaluation was deleted;
2、由于在医疗评论中响应性和共情性表现内容过于相近，本发明将两者合二为一。2. Since the content of responsiveness and empathy in medical reviews are too similar, the present invention combines the two into one.
本发明的优点：Advantages of the present invention:
本发明基于互联网开放的疾病信息构建医疗知识图谱，结合社交媒体的医疗评论数据，根据医疗服务质量的评价指标对医生和医院的服务质量进行了自动化评价，并向用户提供推荐服务，一定程度上满足了用户日益增长的移动医疗服务需求。The present invention constructs a medical knowledge map based on disease information open on the Internet, combines medical review data of social media, and automatically evaluates the service quality of doctors and hospitals according to the evaluation index of medical service quality, and provides recommendation services to users. It meets the growing demands of users for mobile medical services.
相比于其他医疗问诊推荐，本发明具有以下优势：1)同时完成疾病自诊和医生医院推荐服务，为用户提供更好的服务质量；2)结合多方面的信息推荐疾病，避免单纯症状关键词匹配带来的推荐列表冗长、没有推荐意义等问题，同时，本发明利用了医疗知识图谱中的结构化信息，丰富推荐选项，更容易推荐出用户潜在的疾病；3)本发明基于患者评论文本数据，结合现有的医疗服务质量评价指标，分析得到了医生和医院的服务质量，为用户提供了更加开放易明的推荐服务。Compared with other medical consultation recommendations, the present invention has the following advantages: 1) simultaneously complete disease self-diagnosis and doctor hospital recommendation services, providing users with better service quality; 2) combining various information to recommend diseases, avoiding simple symptoms The recommendation list caused by keyword matching is lengthy and has no recommendation meaning. At the same time, the present invention utilizes the structured information in the medical knowledge graph to enrich the recommendation options, and it is easier to recommend potential diseases of the user; 3) The present invention is based on patients The review text data, combined with the existing medical service quality evaluation indicators, analyzes the service quality of doctors and hospitals, and provides users with more open and easy-to-understand recommendation services.
附图说明Description of drawings
图1为根据本发明的基于知识图谱和社交媒体的医疗问诊推荐方法得到的医疗知识图谱的示意图。FIG. 1 is a schematic diagram of a medical knowledge graph obtained by a medical consultation recommendation method based on a knowledge graph and social media according to the present invention.
具体实施方式Detailed ways
下面结合附图，通过具体实施例，进一步阐述本发明。Below in conjunction with the accompanying drawings, the present invention will be further described through specific embodiments.
本实施例的基于知识图谱和社交媒体的医疗问诊推荐方法，包括以下步骤：The method for recommending medical consultation based on knowledge graph and social media in this embodiment includes the following steps:
1)获取互联网医疗中开放的结构化疾病信息，从中提取疾病及其相关信息，疾病的相关信息包括症状关键词、发病率、易患人群、并发症、就诊科室和症状描述，从易患人群中进一步抽取年龄和性别信息，构建“疾病—症状”的医疗知识图谱，如图1所示，医疗知识图谱包括五种实体和五种关系，五种实体为：疾病实体、科室实体、年龄实体、性别实体和症状关键词实体，其中疾病实体拥有症状描述属性和发病率属性，五种关系为：疾病实体与疾病实体之间存在并发症关系、疾病实体和症状关键词实体之间存在拥有关系、疾病实体和科室实体之间存在就诊科室关系、疾病实体和年龄实体之间存在易患年龄关系，疾病实体和性别实体之间存在易患性别关系，在本实施例中，医疗知识图谱中包含实体15418个，关系85303个；1) Obtain open structured disease information in Internet medical care, and extract diseases and related information from them. Disease-related information includes symptom keywords, incidence rates, susceptible groups, complications, visiting departments and symptom descriptions. We further extract age and gender information from , and construct a “disease-symptom” medical knowledge graph. As shown in Figure 1, the medical knowledge graph includes five entities and five relationships. The five entities are: disease entity, department entity, and age entity. , gender entity and symptom keyword entity, in which disease entity has symptom description attribute and morbidity attribute, five relationships are: there is a complication relationship between disease entity and disease entity, and there is an ownership relationship between disease entity and symptom keyword entity , There is a visiting department relationship between a disease entity and a department entity, a susceptible age relationship exists between a disease entity and an age entity, and a susceptible gender relationship exists between a disease entity and a gender entity. In this embodiment, the medical knowledge graph contains 15,418 entities and 85,303 relationships;
2)对步骤1)构建的医疗知识图谱，采用TransD模型训练知识图谱嵌入，其中，参数为迭代次数150次，向量长度100，学习率为1.0，优化器为随机梯度下降法，最终训练得到的损失为6.807，将医疗知识图谱中的实体和关系映射为向量空间中的表述，得到医疗知识图谱中疾病实体的嵌入向量信息；2) For the medical knowledge graph constructed in step 1), the TransD model is used to train the knowledge graph embedding, where the parameters are the number of iterations 150 times, the vector length 100, the learning rate 1.0, the optimizer is the stochastic gradient descent method, and the final training result is obtained. The loss is 6.807, the entities and relationships in the medical knowledge graph are mapped to representations in the vector space, and the embedding vector information of disease entities in the medical knowledge graph is obtained;
3)获取互联网上开放的医疗评论数据，医疗评论数据包含医生名称、医生所属的就诊科室、就诊科室所属的医院以及对医生的患者评论文本；根据医疗服务质量评价指标，标注患者评论文本，使用自然语言处理模型对患者评论文本的每个指标维度进行情感极性分析，统计每个医生的好评率，根据医生与就诊科室的所属关系，对同一就诊科室的患者评论文本进行汇总，得到相应的就诊科室的好评率，并根据威尔逊区间法分别得到医生和就诊科室的威尔逊评分：3) Obtain open medical review data on the Internet. The medical review data includes the doctor's name, the medical department to which the doctor belongs, the hospital to which the medical department belongs, and the text of the patient's comment to the doctor; according to the medical service quality evaluation index, mark the text of the patient's comment and use The natural language processing model analyzes the sentiment polarity of each index dimension of the patient's comment text, counts the favorable rate of each doctor, and summarizes the patient's comment text in the same clinic according to the relationship between the doctor and the clinic to obtain the corresponding The favorable rate of the visiting department is obtained, and the Wilson score of the doctor and the visiting department is obtained according to the Wilson interval method:
a)根据医疗服务质量的评价指标，对患者评论文本进行情感极性人工标注，每个服务质量的评价指标维度标注的情感极性有三种：积极、中性和消极，人工标注患者评论文本6019条；a) According to the evaluation index of medical service quality, the sentiment polarity of the patient comment text is manually marked. There are three kinds of sentiment polarity marked by the evaluation index dimension of each service quality: positive, neutral and negative, and the patient comment text is manually marked 6019 strip;
b)将标注好的评论文本数据转换为数字化表示，输入BERT模型进行训练，其中，BERT模型加载了官方的预训练中文模型chinese_L-12_H-768_A-12，设计参数为迭代次数1次，序列长度为200，损失函数为分类交叉熵函数(categorical_crossentropy)，优化器为Adam(0.00001)；b) Convert the marked comment text data into a digital representation, and input the BERT model for training. The BERT model is loaded with the official pre-trained Chinese model chinese_L-12_H-768_A-12, and the design parameters are the number of iterations 1 and the sequence length is 200, the loss function is the categorical cross-entropy function (categorical_crossentropy), and the optimizer is Adam (0.00001);
c)利用训练好的自然语言处理模型对剩余的评论文本数据进行情感极性分析，得到每个医生的好评率，医生的好评率即同一个医生的积极的患者评论文本的数目占患者评论文本的总数目的比例；c) Use the trained natural language processing model to analyze the sentiment polarity of the remaining review text data, and obtain the favorable rate of each doctor. The doctor's favorable rate is the number of positive patient review texts of the same doctor, which accounts for the proportion of the patient review texts. the proportion of the total;
d)根据医生与就诊科室的所属关系，对同一医院的同一就诊科室的患者评论文本进行汇总，得到相应的就诊科室的好评率，就诊科室的好评率即同一就诊科室的所有医生的积极的患者评论文本的数目占这个就诊科室的所有患者评论文本的总数目的比例；d) According to the affiliation between the doctor and the treating department, summarize the comment texts of patients in the same treating department in the same hospital, and get the favorable rate of the corresponding treating department. The favorable rate of the treating department is the positive patients of all doctors in the same treating department The ratio of the number of comment texts to the total number of comment texts for all patients in this visiting department;
e)医生和就诊科室的在服务质量的评价指标维度上的威尔逊评分Score的计算公式为：e) The formula for calculating the Wilson Score on the dimension of service quality evaluation indicators for doctors and visiting departments is:
其中，p表示好评率，计算方法为积极评论占总评论数量的比重，zα表示正态分布的分位数，取值为2，得分可信度约为95％，n表示评论文本数据的总数量；Among them, p represents the favorable rating, the calculation method is the proportion of positive comments in the total number of comments, zα represents the quantile of the normal distribution, the value is 2, the score reliability is about 95%, and n represents the quantile of the comment text data. The total number;
f)根据上面的公式，给出每个医生的威尔逊评分以及每个就诊科室的威尔逊评分，存储在JSON(JavaScript Object Notation，JavaScript对象表示)文件中；f) According to the above formula, give the Wilson score of each doctor and the Wilson score of each visiting department, and store them in a JSON (JavaScript Object Notation, JavaScript object representation) file;
4)用户输入的症状关键词、性别、年龄和症状描述信息中的包含症状关键词M种信息，即症状关键词是必须输入的信息，1≤M≤4，根据用户输入的M种信息查询医疗知识图谱，构建初始疾病实体备选集，根据医疗知识图谱中疾病实体的嵌入向量信息选择最为相似的疾病实体扩展备选集，挖掘用户潜在患有的疾病，最后根据用户输入的性别、年龄、症状关键词和症状描述中相应的M个方面的相似性筛选出推荐疾病，并根据相应疾病实体的就诊科室，推荐威尔逊评分最高的就诊科室和医生，并给出所属的医院：4) The symptom keywords, gender, age, and symptom description information input by the user contain M kinds of information about the symptom keywords, that is, the symptom keywords are the information that must be input, 1≤M≤4, according to the M kinds of information input by the user. Medical knowledge graph, construct the initial disease entity candidate set, select the most similar disease entity to expand the candidate set according to the embedding vector information of the disease entity in the medical knowledge graph, mine the diseases that the user potentially suffers from, and finally, according to the gender and age input by the user , symptom keywords and the similarity of the corresponding M aspects in the symptom description to screen out the recommended diseases, and according to the medical department of the corresponding disease entity, recommend the medical department and doctor with the highest Wilson score, and give the hospital to which it belongs:
a)构建初始疾病实体备选集：根据用户输入的症状关键词，查询医疗知识图谱，根据疾病实体和症状关键词实体之间的拥有关系，筛选出症状关键词最为相似的多个疾病实体，并且根据疾病实体拥有的发病率属性，选取发病率最高的多个疾病实体，得到初始疾病实体备选集；a) Construction of the initial disease entity candidate set: According to the symptom keywords input by the user, the medical knowledge graph is queried, and according to the ownership relationship between the disease entity and the symptom keyword entity, multiple disease entities with the most similar symptom keywords are screened out. And according to the morbidity attribute possessed by the disease entity, multiple disease entities with the highest morbidity are selected to obtain the initial disease entity candidate set;
b)扩充疾病实体备选集：基于医疗知识图谱中疾病实体的嵌入向量，选择与疾病实体备选集中每个疾病实体的嵌入向量的欧式距离最近的一个或多个疾病实体，即最为相似的疾病实体，对初始疾病实体备选集进行扩充，得到疾病实体扩展备选集，从而挖掘用户潜在患有的疾病；b) Expanding the disease entity candidate set: Based on the embedding vector of the disease entity in the medical knowledge graph, select one or more disease entities with the nearest Euclidean distance to the embedding vector of each disease entity in the disease entity candidate set, that is, the most similar disease entity. Disease entity, expand the initial disease entity candidate set, and obtain the disease entity expansion candidate set, so as to mine the diseases that the user may suffer from;
c)给出最终推荐疾病结果：根据性别、年龄、症状关键词和症状描述中的M个方面的相似性，从疾病实体扩展备选集中筛选出推荐结果，其中，性别、年龄的相似度基于字符串匹配，症状关键词的相似度基于集合交运算，症状描述先使用词频-逆文件频率(TF-IDF，Term Frequency–Inverse Document Frequency)模型得到其向量表述，最终的症状描述相似度以向量之间的余弦相似度衡量；最终选择M个方面的相似度之和最高的多种疾病实体作为推荐结果，并查找医疗知识图谱，根据疾病实体和科室实体之间存在就诊科室关系，分别给出每一疾病实体相应的就诊科室；c) Give the final recommended disease results: According to the similarity of M aspects in gender, age, symptom keywords and symptom descriptions, the recommended results are screened from the extended candidate set of disease entities, where the similarity of gender and age is based on String matching, the similarity of symptom keywords is based on the set intersection operation, the symptom description first uses the Term Frequency-Inverse Document Frequency (TF-IDF, Term Frequency-Inverse Document Frequency) model to obtain its vector representation, and the final symptom description similarity is expressed as a vector. The cosine similarity between the two is measured; finally, multiple disease entities with the highest sum of similarity in M aspects are selected as the recommendation results, and the medical knowledge map is searched. According to the relationship between the disease entity and the department entity, respectively The corresponding medical department for each disease entity;
d)分别针对每种疾病实体，根据步骤c)得到的最终推荐的每一疾病实体相应的就诊科室，按照步骤3)威尔逊评分，选择各家医院中在这类就诊科室中得分最高的多家医院，在实际推荐的过程中，本发明还考虑了一些经验规则，比如优先推荐在好大夫网站统计中在全国名列前茅的医院，优先推荐类别更高的医院，如三甲医院等，再选择所属的就诊科室下得分最高的医生推荐给用户。d) For each disease entity, according to the final recommended medical department corresponding to each disease entity obtained in step c), and according to step 3) Wilson score, select multiple hospitals with the highest scores in this type of medical department. Hospitals, in the actual recommendation process, the present invention also considers some empirical rules, such as giving priority to recommending hospitals that are among the best in the country in the statistics of the good doctor website, and giving priority to recommending hospitals with higher categories, such as tertiary hospitals, etc., and then selecting the hospital to which they belong. The doctor with the highest score in the consultation department is recommended to the user.
最后需要注意的是，公布实施例的目的在于帮助进一步理解本发明，但是本领域的技术人员可以理解：在不脱离本发明及所附的权利要求的精神和范围内，各种替换和修改都是可能的。因此，本发明不应局限于实施例所公开的内容，本发明要求保护的范围以权利要求书界定的范围为准。Finally, it should be noted that the purpose of publishing the embodiments is to help further understanding of the present invention, but those skilled in the art can understand that various replacements and modifications can be made without departing from the spirit and scope of the present invention and the appended claims. It is possible. Therefore, the present invention should not be limited to the contents disclosed in the embodiments, and the scope of protection of the present invention shall be subject to the scope defined by the claims.
Claims (6)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010639311.8ACN111897967A (en) | 2020-07-06 | 2020-07-06 | A medical consultation recommendation method based on knowledge graph and social media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010639311.8ACN111897967A (en) | 2020-07-06 | 2020-07-06 | A medical consultation recommendation method based on knowledge graph and social media |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111897967Atrue CN111897967A (en) | 2020-11-06 |
Family
ID=73193027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010639311.8APendingCN111897967A (en) | 2020-07-06 | 2020-07-06 | A medical consultation recommendation method based on knowledge graph and social media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897967A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112530576A (en)* | 2020-11-30 | 2021-03-19 | 百度健康(北京)科技有限公司 | Online doctor-patient matching method and device, electronic equipment and storage medium |
| CN112528153A (en)* | 2020-12-22 | 2021-03-19 | 北京百度网讯科技有限公司 | Content recommendation method, device, equipment, storage medium and program product |
| CN112786194A (en)* | 2021-01-28 | 2021-05-11 | 北京一脉阳光医学信息技术有限公司 | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence |
| CN113111162A (en)* | 2021-04-21 | 2021-07-13 | 康键信息技术（深圳）有限公司 | Department recommendation method and device, electronic equipment and storage medium |
| CN113160954A (en)* | 2021-04-07 | 2021-07-23 | 泰康保险集团股份有限公司 | Medical resource allocation method and device, storage medium and electronic equipment |
| CN113220905A (en)* | 2021-05-27 | 2021-08-06 | 哈尔滨理工大学 | Service recommendation method fusing knowledge graph |
| CN113535901A (en)* | 2021-07-08 | 2021-10-22 | 北京航空航天大学 | E-commerce comment-based user-side commodity knowledge graph construction method |
| CN113611408A (en)* | 2021-08-20 | 2021-11-05 | 泰康保险集团股份有限公司 | Method, system, equipment and computer readable medium for interacting diagnosis and treatment information |
| CN113707335A (en)* | 2021-09-06 | 2021-11-26 | 挂号网（杭州）科技有限公司 | Method, device, electronic equipment and storage medium for determining target reception user |
| CN113764080A (en)* | 2021-01-29 | 2021-12-07 | 北京京东拓先科技有限公司 | Resource allocation method, device and storage medium |
| CN114093482A (en)* | 2021-11-19 | 2022-02-25 | 中南大学湘雅医院 | Mobile diagnosis and treatment oriented medical care patient matching method and system |
| CN114093472A (en)* | 2021-10-13 | 2022-02-25 | 阿里健康科技(杭州)有限公司 | Triage information display method and client for Internet medical treatment |
| CN114201591A (en)* | 2021-11-19 | 2022-03-18 | 北京三快在线科技有限公司 | Method, device, device and storage medium for generating evaluation content for consultation service |
| CN114220528A (en)* | 2021-12-28 | 2022-03-22 | 深圳科卫机器人科技有限公司 | Hospital department recommended method, device, computer equipment and storage medium |
| CN114547444A (en)* | 2022-02-14 | 2022-05-27 | 南京邮电大学 | An online medical recommendation system and its realization method |
| CN114664421A (en)* | 2022-03-25 | 2022-06-24 | 北京百度网讯科技有限公司 | Doctor-patient matching method and device, electronic equipment, medium and product |
| CN114676390A (en)* | 2022-05-27 | 2022-06-28 | 华南师范大学 | Searching method, system, device and storage medium for persons with similar psychological characteristics |
| CN114783580A (en)* | 2022-06-20 | 2022-07-22 | 武汉博科国泰信息技术有限公司 | Medical data quality evaluation method and system |
| CN114840777A (en)* | 2022-07-04 | 2022-08-02 | 杭州城市大脑有限公司 | Multi-dimensional endowment service recommendation method and device and electronic equipment |
| CN114912005A (en)* | 2021-02-08 | 2022-08-16 | 京东方科技集团股份有限公司 | Exercise recommended methods, devices, equipment and media |
| CN115346654A (en)* | 2022-07-14 | 2022-11-15 | 赵盛 | Intelligent service system based on internet |
| CN115376668A (en)* | 2022-08-30 | 2022-11-22 | 温州城市智慧健康有限公司 | Big data business analysis method and system applied to intelligent medical treatment |
| CN115512859A (en)* | 2022-11-21 | 2022-12-23 | 北京左医科技有限公司 | Internet-based in-clinic quality management method, management device and storage medium |
| CN115547471A (en)* | 2022-10-13 | 2022-12-30 | 上海清赟医药科技有限公司 | Medical information recommendation method based on SCRM |
| CN115862830A (en)* | 2023-02-21 | 2023-03-28 | 清华大学 | A data processing method, device and electronic equipment |
| CN116798656A (en)* | 2023-05-04 | 2023-09-22 | 华中科技大学同济医学院附属协和医院 | Remote medical treatment and grading monitoring platform based on cloud-terminal cooperation |
| CN116976435A (en)* | 2023-09-25 | 2023-10-31 | 浙江辰龙检测技术有限公司 | Knowledge graph construction method based on network security |
| CN117271799A (en)* | 2023-09-25 | 2023-12-22 | 中国电子科技集团公司第十研究所 | Knowledge graph-based multi-round question answering method and system |
| CN117334354A (en)* | 2023-10-16 | 2024-01-02 | 北京好医生云医院管理技术有限公司 | An online medical service method and system |
| CN117476163A (en)* | 2023-12-27 | 2024-01-30 | 万里云医疗信息科技（北京）有限公司 | Method, apparatus and storage medium for determining disease conclusion |
| CN118116620A (en)* | 2024-04-28 | 2024-05-31 | 支付宝(杭州)信息技术有限公司 | Medical question-answering method, device and electronic equipment |
| CN118155817A (en)* | 2024-04-26 | 2024-06-07 | 旭辉卓越健康信息科技有限公司 | A department and expert recommendation method and system based on GPT model |
| CN118471455A (en)* | 2023-08-07 | 2024-08-09 | 温州医科大学 | Intelligent recommending method, equipment and storage medium for hospital registration departments based on text mining technology |
| CN118588233A (en)* | 2024-08-06 | 2024-09-03 | 中国石油大学(华东) | A knowledge graph-driven drug recommendation method for neurodegenerative diseases |
| CN119092158A (en)* | 2024-11-08 | 2024-12-06 | 武汉盛博汇信息技术有限公司 | A hospital system interaction method based on data association matching |
| CN119694520A (en)* | 2025-02-24 | 2025-03-25 | 北京融威众邦科技股份有限公司 | A registration recommendation method and system based on multi-dimensional information |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110085307A (en)* | 2019-04-04 | 2019-08-02 | 华东理工大学 | A kind of intelligent hospital guide's method and system based on the fusion of multi-source knowledge mapping |
| CN110489566A (en)* | 2019-08-22 | 2019-11-22 | 上海软中信息系统咨询有限公司 | A kind of hospital guide's method of intelligence hospital guide's service robot |
| US20200185102A1 (en)* | 2018-12-11 | 2020-06-11 | K Health Inc. | System and method for providing health information |
- 2020
- 2020-07-06CNCN202010639311.8Apatent/CN111897967A/enactivePending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200185102A1 (en)* | 2018-12-11 | 2020-06-11 | K Health Inc. | System and method for providing health information |
| CN110085307A (en)* | 2019-04-04 | 2019-08-02 | 华东理工大学 | A kind of intelligent hospital guide's method and system based on the fusion of multi-source knowledge mapping |
| CN110489566A (en)* | 2019-08-22 | 2019-11-22 | 上海软中信息系统咨询有限公司 | A kind of hospital guide's method of intelligence hospital guide's service robot |
Cited By (45)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112530576A (en)* | 2020-11-30 | 2021-03-19 | 百度健康(北京)科技有限公司 | Online doctor-patient matching method and device, electronic equipment and storage medium |
| CN112528153A (en)* | 2020-12-22 | 2021-03-19 | 北京百度网讯科技有限公司 | Content recommendation method, device, equipment, storage medium and program product |
| CN112528153B (en)* | 2020-12-22 | 2024-03-08 | 北京百度网讯科技有限公司 | Content recommendation methods, devices, equipment, storage media and program products |
| CN112786194A (en)* | 2021-01-28 | 2021-05-11 | 北京一脉阳光医学信息技术有限公司 | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence |
| CN112786194B (en)* | 2021-01-28 | 2024-11-01 | 北京一脉阳光医学信息技术有限公司 | Medical image diagnosis guiding and guiding system, method and equipment based on artificial intelligence |
| CN113764080A (en)* | 2021-01-29 | 2021-12-07 | 北京京东拓先科技有限公司 | Resource allocation method, device and storage medium |
| CN114912005A (en)* | 2021-02-08 | 2022-08-16 | 京东方科技集团股份有限公司 | Exercise recommended methods, devices, equipment and media |
| CN113160954B (en)* | 2021-04-07 | 2023-08-01 | 泰康保险集团股份有限公司 | Medical resource allocation method and device, storage medium and electronic equipment |
| CN113160954A (en)* | 2021-04-07 | 2021-07-23 | 泰康保险集团股份有限公司 | Medical resource allocation method and device, storage medium and electronic equipment |
| CN113111162A (en)* | 2021-04-21 | 2021-07-13 | 康键信息技术（深圳）有限公司 | Department recommendation method and device, electronic equipment and storage medium |
| WO2022222943A1 (en)* | 2021-04-21 | 2022-10-27 | 康键信息技术（深圳）有限公司 | Department recommendation method and apparatus, electronic device and storage medium |
| CN113220905A (en)* | 2021-05-27 | 2021-08-06 | 哈尔滨理工大学 | Service recommendation method fusing knowledge graph |
| CN113535901B (en)* | 2021-07-08 | 2023-08-18 | 北京航空航天大学 | Method for constructing user side commodity knowledge graph based on e-commerce comments |
| CN113535901A (en)* | 2021-07-08 | 2021-10-22 | 北京航空航天大学 | E-commerce comment-based user-side commodity knowledge graph construction method |
| CN113611408A (en)* | 2021-08-20 | 2021-11-05 | 泰康保险集团股份有限公司 | Method, system, equipment and computer readable medium for interacting diagnosis and treatment information |
| CN113707335A (en)* | 2021-09-06 | 2021-11-26 | 挂号网（杭州）科技有限公司 | Method, device, electronic equipment and storage medium for determining target reception user |
| CN114093472A (en)* | 2021-10-13 | 2022-02-25 | 阿里健康科技(杭州)有限公司 | Triage information display method and client for Internet medical treatment |
| CN114201591A (en)* | 2021-11-19 | 2022-03-18 | 北京三快在线科技有限公司 | Method, device, device and storage medium for generating evaluation content for consultation service |
| CN114093482A (en)* | 2021-11-19 | 2022-02-25 | 中南大学湘雅医院 | Mobile diagnosis and treatment oriented medical care patient matching method and system |
| CN114220528A (en)* | 2021-12-28 | 2022-03-22 | 深圳科卫机器人科技有限公司 | Hospital department recommended method, device, computer equipment and storage medium |
| CN114547444A (en)* | 2022-02-14 | 2022-05-27 | 南京邮电大学 | An online medical recommendation system and its realization method |
| CN114664421A (en)* | 2022-03-25 | 2022-06-24 | 北京百度网讯科技有限公司 | Doctor-patient matching method and device, electronic equipment, medium and product |
| CN114676390A (en)* | 2022-05-27 | 2022-06-28 | 华南师范大学 | Searching method, system, device and storage medium for persons with similar psychological characteristics |
| CN114783580A (en)* | 2022-06-20 | 2022-07-22 | 武汉博科国泰信息技术有限公司 | Medical data quality evaluation method and system |
| CN114840777A (en)* | 2022-07-04 | 2022-08-02 | 杭州城市大脑有限公司 | Multi-dimensional endowment service recommendation method and device and electronic equipment |
| CN115346654A (en)* | 2022-07-14 | 2022-11-15 | 赵盛 | Intelligent service system based on internet |
| CN115376668A (en)* | 2022-08-30 | 2022-11-22 | 温州城市智慧健康有限公司 | Big data business analysis method and system applied to intelligent medical treatment |
| CN115376668B (en)* | 2022-08-30 | 2024-03-08 | 温州城市智慧健康有限公司 | Big data business analysis method and system applied to intelligent medical treatment |
| CN115547471A (en)* | 2022-10-13 | 2022-12-30 | 上海清赟医药科技有限公司 | Medical information recommendation method based on SCRM |
| CN115512859A (en)* | 2022-11-21 | 2022-12-23 | 北京左医科技有限公司 | Internet-based in-clinic quality management method, management device and storage medium |
| CN115862830A (en)* | 2023-02-21 | 2023-03-28 | 清华大学 | A data processing method, device and electronic equipment |
| CN116798656A (en)* | 2023-05-04 | 2023-09-22 | 华中科技大学同济医学院附属协和医院 | Remote medical treatment and grading monitoring platform based on cloud-terminal cooperation |
| CN118471455A (en)* | 2023-08-07 | 2024-08-09 | 温州医科大学 | Intelligent recommending method, equipment and storage medium for hospital registration departments based on text mining technology |
| CN117271799A (en)* | 2023-09-25 | 2023-12-22 | 中国电子科技集团公司第十研究所 | Knowledge graph-based multi-round question answering method and system |
| CN116976435B (en)* | 2023-09-25 | 2023-12-15 | 浙江辰龙检测技术有限公司 | Knowledge graph construction method based on network security |
| CN116976435A (en)* | 2023-09-25 | 2023-10-31 | 浙江辰龙检测技术有限公司 | Knowledge graph construction method based on network security |
| CN117271799B (en)* | 2023-09-25 | 2025-09-09 | 中国电子科技集团公司第十研究所 | Knowledge graph-based multi-round question answering method and system |
| CN117334354A (en)* | 2023-10-16 | 2024-01-02 | 北京好医生云医院管理技术有限公司 | An online medical service method and system |
| CN117476163A (en)* | 2023-12-27 | 2024-01-30 | 万里云医疗信息科技（北京）有限公司 | Method, apparatus and storage medium for determining disease conclusion |
| CN117476163B (en)* | 2023-12-27 | 2024-03-08 | 万里云医疗信息科技（北京）有限公司 | Method, apparatus and storage medium for determining disease conclusion |
| CN118155817A (en)* | 2024-04-26 | 2024-06-07 | 旭辉卓越健康信息科技有限公司 | A department and expert recommendation method and system based on GPT model |
| CN118116620A (en)* | 2024-04-28 | 2024-05-31 | 支付宝(杭州)信息技术有限公司 | Medical question-answering method, device and electronic equipment |
| CN118588233A (en)* | 2024-08-06 | 2024-09-03 | 中国石油大学(华东) | A knowledge graph-driven drug recommendation method for neurodegenerative diseases |
| CN119092158A (en)* | 2024-11-08 | 2024-12-06 | 武汉盛博汇信息技术有限公司 | A hospital system interaction method based on data association matching |
| CN119694520A (en)* | 2025-02-24 | 2025-03-25 | 北京融威众邦科技股份有限公司 | A registration recommendation method and system based on multi-dimensional information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111897967A (en) | A medical consultation recommendation method based on knowledge graph and social media | |
| CN110993081B (en) | A doctor online recommendation method and system | |
| Hu et al. | New doctors ranking system based on VIKOR method | |
| Chang et al. | Accelerating mixed methods research with natural language processing of big text data | |
| Hosseini et al. | Heteromed: Heterogeneous information network for medical diagnosis | |
| CN111666477B (en) | Data processing method, device, intelligent equipment and medium | |
| KR102088980B1 (en) | System and Method for Providing personalized hospital information | |
| US20200185102A1 (en) | System and method for providing health information | |
| Lee et al. | Personalized mortality prediction driven by electronic medical data and a patient similarity metric | |
| US20230161972A1 (en) | Privacy-preserving text insight mining in a closed domain | |
| WO2021139232A1 (en) | Medical knowledge graph-based triage method and apparatus, device, and storage medium | |
| CN107122469B (en) | Method and device for query recommendation ranking based on semantic similarity and timeliness frequency | |
| CN109460473A (en) | The electronic health record multi-tag classification method with character representation is extracted based on symptom | |
| US10936962B1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| CN101084502A (en) | System and method for digital content retrieval according to a defined purpose | |
| Ju et al. | Doctor recommendation model based on ontology characteristics and disease text mining perspective | |
| Li et al. | Overview of CCKS 2020 Task 3: named entity recognition and event extraction in Chinese electronic medical records | |
| US20210133627A1 (en) | Methods and systems for confirming an advisory interaction with an artificial intelligence platform | |
| Wu et al. | A sentiment analysis driven method based on public and personal preferences with correlated attributes to select online doctors | |
| CN118841158A (en) | Treatment scheme recommendation method, treatment scheme recommendation device, computer equipment and storage medium | |
| CN116313120A (en) | Model pre-training method, medical application task processing method and related devices thereof | |
| Zou et al. | AI-driven diagnostic assistance in medical inquiry: reinforcement learning algorithm development and validation | |
| Wang et al. | Automatic scoring of Chinese fill-in-the-blank questions based on improved P-means | |
| CN120373301A (en) | Intelligent diagnosis-dividing and guiding analysis method, device and system based on large language model | |
| Varshney et al. | Cdialog: A multi-turn covid-19 conversation dataset for entity-aware dialog generation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | Application publication date:20201106 |