CN113870998A - Interrogation method, device, electronic equipment and storage medium - Google Patents
Interrogation method, device, electronic equipment and storage mediumDownload PDFInfo
- Publication number
- CN113870998A CN113870998ACN202111152045.7ACN202111152045ACN113870998ACN 113870998 ACN113870998 ACN 113870998ACN 202111152045 ACN202111152045 ACN 202111152045ACN 113870998 ACN113870998 ACN 113870998A
- Authority
- CN
- China
- Prior art keywords
- information
- inquiry
- department
- consultation
- doctor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- 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)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本公开涉及人工智能技术领域，具体涉及智能推荐和深度学习技术领域，尤其涉及问诊方法、装置、电子设备和存储介质。The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of intelligent recommendation and deep learning, and in particular, to an inquiry method, apparatus, electronic device and storage medium.
背景技术Background technique
随着计算机技术以及互联网络的发展，患者就医问诊的可以通过在线问诊的方式实现，使患者能够更加便捷的获取到医生的诊断和治疗。With the development of computer technology and the Internet, patients' medical consultation can be realized through online consultation, so that patients can more conveniently obtain doctor's diagnosis and treatment.
线上问诊系统基于用户的主诉信息进行科室判断，并将用户分发到对应科室的医生进行进一步的诊疗。The online consultation system determines the department based on the user's main complaint information, and distributes the user to the doctors in the corresponding department for further diagnosis and treatment.
发明内容SUMMARY OF THE INVENTION
本公开提供了一种问诊方法、装置、电子设备和存储介质。The present disclosure provides a diagnosis method, device, electronic device and storage medium.
根据本公开的一方面，提供了一种问诊方法，包括：According to an aspect of the present disclosure, there is provided a method for consultation, comprising:
获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断；Obtain the consultation information of the consultation user, and determine whether the consultation information can be divided into different departments;
根据能否分科判断结果和所述问诊信息，确定目标问诊科室。According to the judgment result of whether it can be divided into different departments and the consultation information, the target consultation department is determined.
根据本公开的一方面，提供了一种问诊装置，包括：According to an aspect of the present disclosure, there is provided an interrogation device, comprising:
能否分科判断模块，用于获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断；a module for judging whether the consultation can be divided into different disciplines, which is used to obtain the consultation information of the consultation user, and to judge whether the consultation information can be classified into different disciplines;
分诊科室确定模块，用于根据能否分科判断结果和所述问诊信息，确定目标问诊科室。The triage department determination module is used for determining the target interrogation department according to the judgment result of whether the department can be divided and the interrogation information.
根据本公开的另一方面，提供了一种电子设备，包括：According to another aspect of the present disclosure, there is provided an electronic device, comprising:
至少一个处理器；以及at least one processor; and
与所述至少一个处理器通信连接的存储器；其中，a memory communicatively coupled to the at least one processor; wherein,
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本公开任一实施例所述的问诊方法，或执行本公开任一实施例所述的问诊方法。The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the consultation of any embodiment of the present disclosure method, or perform the diagnosis method described in any embodiment of the present disclosure.
根据本公开的另一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行本公开任一实施例所述的问诊方法，或执行本公开任一实施例所述的问诊方法。According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the medical consultation method according to any embodiment of the present disclosure , or execute the diagnosis method described in any embodiment of the present disclosure.
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现本公开任一实施例所述的问诊方法，或执行本公开任一实施例所述的问诊方法。According to another aspect of the present disclosure, there is provided a computer program product, including a computer program, the computer program, when executed by a processor, implements the diagnosis method described in any of the embodiments of the present disclosure, or executes any one of the embodiments of the present disclosure. The method of questioning described in the examples.
本公开实施例可以提高问诊模型生成的字体的准确率。The embodiment of the present disclosure can improve the accuracy of the font generated by the consultation model.
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.
附图说明Description of drawings
附图用于更好地理解本方案，不构成对本公开的限定。其中：The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present disclosure. in:
图1是根据本公开实施例提供的一种问诊方法的示意图；FIG. 1 is a schematic diagram of a diagnosis method provided according to an embodiment of the present disclosure;
图2是根据本公开实施例提供的一种问诊方法的示意图；FIG. 2 is a schematic diagram of a method for inquiring according to an embodiment of the present disclosure;
图3是根据本公开实施例提供的一种问诊方法的示意图；3 is a schematic diagram of a method for inquiring a diagnosis provided according to an embodiment of the present disclosure;
图4是根据本公开实施例提供的一种问诊方法的示意图；FIG. 4 is a schematic diagram of a method for inquiring according to an embodiment of the present disclosure;
图5是根据本公开实施例提供的一种问诊装置的示意图；FIG. 5 is a schematic diagram of a diagnosis apparatus provided according to an embodiment of the present disclosure;
图6是用来实现本公开实施例的问诊方法的电子设备的框图。FIG. 6 is a block diagram of an electronic device used to implement the consultation method of the embodiment of the present disclosure.
具体实施方式Detailed ways
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
图1是根据本公开实施例公开的一种问诊方法的流程图，本实施例可以适用于用户获取问诊信息对应的分诊科室的情况。本实施例方法可以由问诊装置来执行，该装置可采用软件和/或硬件的方式实现，并具体配置于具有一定数据运算能力的电子设备中，该电子设备可以是客户端设备或服务器设备，客户端设备例如手机、平板电脑、车载终端和台式电脑等。FIG. 1 is a flowchart of an inquiring method disclosed according to an embodiment of the present disclosure. This embodiment can be applied to a situation where a user obtains a triage department corresponding to inquiring information. The method of this embodiment may be performed by an interrogation device, which may be implemented in software and/or hardware, and is specifically configured in an electronic device with a certain data computing capability, and the electronic device may be a client device or a server device , client devices such as mobile phones, tablet computers, vehicle terminals and desktop computers.
S101，获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断。S101 , obtaining the consultation information of the consultation user, and determining whether the consultation information can be divided into different departments.
本公开实施例可以应用于在线问诊的应用场景中，或者还可以应用于导诊设备自助导诊的应用场景中。问诊用户是指需要分诊的用户，具体是需要根据主要症状及体征判断病情的轻重缓急及其隶属专科，并合理安排其就诊的科室和医生等诊疗信息的用户。问诊信息可以是描述问诊用户的待诊断疾病内容，可以包括下述至少一项：用户属性信息、症状信息和历史就诊信息，用户属性信息可以包括姓名、性别和年龄等。历史就诊信息可以包括病灶位置、既往疾病、历史用药以及历史就医资料(如医生诊断记录和医学影像资料等)等。问诊信息用于对问诊用户进行分诊，具体是分科和分配医生，其中，分科是指确定问诊用户隶属的问诊科室，分配医生是指在前述确定的问诊科室中确定问诊用户的推荐医生。The embodiments of the present disclosure may be applied to an application scenario of online consultation, or may also be applied to an application scenario of self-guided diagnosis by a diagnostic guidance device. Consultation users refer to users who need to be triaged, specifically, users who need to determine the priority of the disease and its affiliated specialties based on the main symptoms and signs, and reasonably arrange the departments and doctors for diagnosis and treatment information. The consultation information may describe the content of the to-be-diagnosed disease of the consultation user, and may include at least one of the following: user attribute information, symptom information and historical consultation information, and the user attribute information may include name, gender, age, and the like. The historical medical treatment information may include the location of the lesion, past diseases, historical medication, and historical medical treatment data (such as doctor's diagnosis records and medical imaging data, etc.). The inquiring information is used to triage the inquiring user, specifically the sub-discipline and assigning a doctor, where the sub-discipline refers to determining the inquiring department to which the inquiring user belongs, and the assigning a doctor refers to determining the inquiring department in the above-determined inquiring department. The user's recommended doctor.
问诊信息可以以文本、语音、图像或视频等至少一种方式输入。可以将语音转换为文本，进行图像识别，以识别图像中的文字，或是基于一些图像识别模型，对一些医学图像进行识别得到识别结果。其中，针对直接获取输入的文本，或者识别出的文本，可以进一步进行解析和意图识别，获取解析结果和意图识别结果。可以将文本输入到解析模型中，得到问诊信息中的特征信息作为解析结果，例如，文本长度、用户属性信息、基础疾病、症状和药品等至少一项信息，其中，解析模型包括双向长短期记忆网络(Long Short-Term Memory,LSTM)和softmax网络，或者包括双向LSTM网络和条件随机场网络(Conditional RandomField，CRF)。文本还用于输入至意图识别模型中，得到文本对应的意图识别结果，示例性的，文本为“治疗糖尿病最好的医院是什么医院？”，意图识别结果包括基础疾病为糖尿病，以及查询治疗糖尿病的排名高的问诊科室。此外，还可以将解析结果和意图识别结果，输入到预先建立的知识图谱中，进行倒排索引，获取关联的科室信息，知识图谱包括解析结果和意图识别结果与科室信息之间的对应关系。可以将解析结果、意图识别结果和关联的科室信息与问诊信息建立对应关系。The consultation information can be input in at least one way such as text, voice, image or video. The speech can be converted into text, and image recognition can be performed to recognize the text in the image, or some medical images can be recognized based on some image recognition models to obtain recognition results. Among them, for the directly acquired text or the recognized text, further parsing and intent recognition may be performed to obtain the parsing result and the intent recognition result. The text can be input into the parsing model, and the feature information in the consultation information can be obtained as the parsing result, for example, at least one piece of information such as text length, user attribute information, underlying diseases, symptoms, and medicines, where the parsing model includes bidirectional long-term and short-term information. Memory network (Long Short-Term Memory, LSTM) and softmax network, or including bidirectional LSTM network and conditional random field network (Conditional RandomField, CRF). The text is also used for input into the intent recognition model, and the intent recognition result corresponding to the text is obtained. For example, the text is "What is the best hospital for treating diabetes?" The intent recognition result includes that the underlying disease is diabetes, and the query treatment Diabetes' top-ranked consultation department. In addition, the analysis results and intent recognition results can also be input into the pre-established knowledge graph, and the inverted index can be performed to obtain the associated department information. The knowledge graph includes the corresponding relationship between the analysis results and the intent recognition results and the department information. A corresponding relationship can be established between the analysis result, the intent recognition result, and the associated department information and the consultation information.
能否分科判断是指根据问诊信息是否可以对问诊用户进行分科。实际上，问诊用户输入的问诊信息中主要问题越明确，越有利于进行分科。问题越模糊不清楚，越不利于分科。通过能否分科判断，可以在确定分科结果之前，预先对能否进行分科进行判断，根据能否分科判断结果，在进一步进行分科，可以提高分科的准确率。如前述，能否分科判断可以是将问诊信息对应的解析结果、意图识别结果和关联的科室信息作为输入，得到能否分科判断结果。Whether it is possible to determine whether the user can be divided into different departments refers to whether the user can be divided into different departments according to the information of the consultation. In fact, the clearer the main question in the consultation information input by the consultation user, the more favorable it is for the division. The more ambiguous the question, the less conducive to division. By judging whether the subjects can be divided into subjects, it is possible to judge whether the subjects can be divided into subjects in advance before the results of the subjects are determined. As mentioned above, the determination of whether or not to classify may be based on the analysis result corresponding to the consultation information, the result of intention recognition, and the associated department information as input to obtain the determination result of whether to classify.
能否分科判断可以是：将问诊信息输入至预先训练能否分科判断模型，得到能否分科判断模型输出的能否分科判断结果，其中，能否分科判断模型可以是一种分类模型，用于输出能分科或者不能分科的结果。能否分科判断模型可以是机器学习模型，具体是深度学习模型，示例性的，能否分科判断模型包括当前的逻辑斯蒂回归模型和神经网络模型(Neural Network，NN)。训练样本可以包括问诊信息和问诊信息对应的能否分科判断结果。或者，能否分科判断可以是：根据预先配置的模板包括各参数，检测问诊信息中是否包括各参数对应的内容，根据缺少内容的参数，确定能否分科判断结果。示例性的，缺少内容的参数包括参数A和参数B，确定能否分科判断结果为不能分科；缺少内容的参数包括参数A，确定能否分科判断结果为能分科。Whether it is possible to determine whether it can be divided into different categories can be: input the inquiry information into the pre-trained model to determine whether it can be divided into different categories, and get the results of whether or not to determine whether the model can be divided into different categories. The model can be a classification model, using In terms of outputting the results that can be divided into subjects or cannot be divided into subjects. The model for judging whether it can be divided into different disciplines may be a machine learning model, specifically a deep learning model. Exemplarily, the model for judging whether or not it can be divided into different disciplines includes the current logistic regression model and a neural network model (Neural Network, NN). The training sample may include the consultation information and the judgment result of whether the consultation information corresponds to whether the patient can be divided into different departments. Alternatively, the determination of whether or not to classify can be as follows: according to a pre-configured template including various parameters, detecting whether the content corresponding to each parameter is included in the consultation information, and determining whether to classify the judgment result according to the parameter with missing content. Exemplarily, the parameters lacking content include parameter A and parameter B, and the result of determining whether the subject can be divided is that the subject cannot be divided; the parameter lacking content includes parameter A, and the judgment result of determining whether the subject can be divided is that the subject can be divided.
S102，根据能否分科判断结果和所述问诊信息，确定目标问诊科室。S102: Determine the target consultation department according to the determination result of whether the department can be divided into different departments and the consultation information.
目标问诊科室可以是指问诊用户隶属的科室，目标问诊科室用于问诊用户选择该科室下的医生进行挂号，并进行疾病诊断。The target consultation department may refer to the department to which the consultation user belongs, and the target consultation department is used for the consultation user to select a doctor under the department for registration and disease diagnosis.
在能否分科判断结果为能分科的情况下，根据问诊信息，确定目标问诊科室；在能否分科判断结果为不能分科的情况下，提示用户增加信息，并对问诊信息进行更新，基于更新的问诊信息，确定目标问诊科室。或者，基于更新的问诊信息继续进行能否分科判断，并在不能分科的情况下，提示用户增加信息，持续对问诊信息进行更新，直至能否分科判断结果为能分科，再根据当前更新后的问诊信息，确定目标问诊科室。In the case that the result of the judgment of whether the department can be divided into a department is able to be divided into a department, the target department to be consulted is determined according to the inquiry information; in the case that the result of the judgment of whether the department can be divided into a department is not able to be divided into a department, the user is prompted to add information, and the inquiry information is updated. Based on the updated consultation information, the target consultation department is determined. Or, continue to judge whether it can be classified based on the updated consultation information, and if it cannot be classified, prompt the user to add information, and continue to update the consultation information until the result of whether the diagnosis can be classified is that it can be classified, and then based on the current update After the consultation information, determine the target consultation department.
在能否分科判断结果为能分科的情况下，根据问诊信息，确定目标问诊科室，可以是将问诊信息输入至预先训练的分科模型，得到分科模型输出的分科结果，即确定目标问诊科室，其中，分科模型可以是神经网络模型；或者预先建立问诊信息与问诊科室之间的对应关系，查询问诊信息对应的目标问诊科室。In the case that the result of whether the division can be divided into departments is able to be divided into departments, according to the inquiry information, the target consultation department can be determined, which can be input into the pre-trained division model, and the division result output by the division model can be obtained, that is, the target inquiry department is determined. Clinic department, wherein the sub-discipline model may be a neural network model; or a correspondence relationship between the consultation information and the consultation department is established in advance, and the target consultation department corresponding to the consultation information is queried.
现有技术中，在线上问诊的过程中，根据患者输入的问诊信息，确定分科结果，但患者提供的问诊信息模糊不清楚或不完整等，会导致分科结果不准确。In the prior art, during the online consultation process, the results of the sub-discipline are determined according to the consultation information input by the patient, but the consultation information provided by the patient is ambiguous or incomplete, etc., which may lead to inaccurate results of the sub-discipline.
根据本公开的技术方案，通过对问诊信息进行能否分科判断，并根据能否分科判断的结果和问诊信息，确定目标问诊科室，可以在问诊信息可以进行分科的情况下，确定目标问诊科室，提高问诊信息的准确性，使问诊信息更加清楚，从而提高分科的准确率。According to the technical solution of the present disclosure, by judging whether the inquiry information can be divided into different departments, and according to the result of whether the inquiry information can be divided into different departments and the inquiry information, the target inquiring department can be determined. Target consultation departments, improve the accuracy of consultation information, make the consultation information clearer, and improve the accuracy of sub-disciplines.
图2是根据本公开实施例公开的另一种问诊方法的流程图，基于上述技术方案进一步优化与扩展，并可以与上述各个可选实施方式进行结合。所将根据能否分科判断结果和所述问诊信息，确定目标问诊科室，具体化为：在能否分科判断结果为不能分科的情况下，与所述问诊用户进行人机交互，获取交互信息，并更新所述问诊信息；根据更新后的问诊信息，确定目标问诊科室。FIG. 2 is a flowchart of another diagnosis method disclosed according to an embodiment of the present disclosure, which is further optimized and expanded based on the above-mentioned technical solution, and can be combined with each of the above-mentioned optional embodiments. The institute will determine the target consultation department according to the judgment result of whether it can be divided into different departments and the information of the consultation, which is embodied as: in the case that the judgment result of whether it can be divided into different departments is not able to be divided into different departments, it will perform human-computer interaction with the consultation user to obtain information is exchanged, and the consultation information is updated; according to the updated consultation information, the target consultation department is determined.
S201，获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断。S201: Obtain the consultation information of the consultation user, and determine whether the consultation information can be divided into different departments.
S202，在能否分科判断结果为不能分科的情况下，与所述问诊用户进行人机交互，获取交互信息，并更新所述问诊信息。S202 , in the case that the result of the determination of whether it can be divided into a department is that it cannot be divided into a department, perform human-computer interaction with the inquiring user, acquire interaction information, and update the inquiring information.
能否分科判断结果为不能分科，表明问诊信息不足以确定目标问诊科室。与问诊用户进行人机交互，用于从问诊用户获取更多更详细的问诊信息，丰富问诊信息。具体的，人机交互过程为：向问诊用户提供问题，问诊用户针对问题提供答案。交互信息用于更新问诊信息。交互信息为预设问题以及问诊用户针对预设问题输入的答案。更新问诊信息可以是指，将交互信息添加到问诊信息中，对问诊信息进行修正。The judgment result of whether it can be divided into departments is that it cannot be divided into departments, indicating that the inquiry information is not enough to determine the target inquiry department. Human-computer interaction with the inquiring user is used to obtain more and more detailed inquiring information from the inquiring user and enriching the inquiring information. Specifically, the human-computer interaction process is: providing questions to the inquiring user, and the inquiring user providing answers to the questions. Interactive information is used to update consultation information. The interactive information is preset questions and answers input by the consultation user for the preset questions. Updating the consultation information may refer to adding interactive information to the consultation information, and revising the consultation information.
实际上，交互信息包括预设问题和对应的答案文本，通常不符合用户的用语习惯，而问诊信息通常是用户用语习惯输入的信息。根据交互信息更新问诊信息，可以是指将交互信息转换为与问诊信息的用语类型对应的信息，并与问诊信息进行融合，以更新问诊信息。示例性的，更新问诊信息可以包括：将交互信息输入至预先训练的文本生成模型，得到文本生成模型输出的问诊文本，并将问诊文本与问诊信息进行融合，其中，文本生成模型可以是神经网络模型，用于将初始信息转换为用户用语习惯的信息。或者，更新问诊信息可以包括：基于预设的文本模板，从交互信息中提取关键词，添加到文本模板对应的位置处，生成问诊文本，并于问诊信息进行融合。其中，在问诊信息为文本的情况下，融合是指将问诊文本与问诊信息拼接，在问诊信息为非文本的情况下，可以将问诊文本转换为问诊信息对应的类型的信息，并与问诊信息进行拼接。例如，交互信息为：既往疾病为糖尿病。问诊信息为：我连续3天头疼。更新后的问诊信息为：我有糖尿病，连续3天头疼。In fact, the interactive information includes preset questions and corresponding answer texts, which usually do not conform to the user's language habits, while the consultation information is usually information input by the user's language habits. Updating the consultation information according to the interactive information may refer to converting the interactive information into information corresponding to the term type of the consultation information, and merging with the consultation information to update the consultation information. Exemplarily, updating the consultation information may include: inputting the interaction information into a pre-trained text generation model, obtaining the consultation text output by the text generation model, and fusing the consultation text with the consultation information, wherein the text generation model It can be a neural network model, which is used to convert the initial information into the information of the user's language habits. Alternatively, updating the consultation information may include: extracting keywords from the interactive information based on a preset text template, adding them to positions corresponding to the text template, generating consultation text, and merging with the consultation information. Among them, in the case where the consultation information is text, fusion refers to splicing the consultation text with the consultation information, and in the case where the consultation information is non-text, the consultation text can be converted into a type corresponding to the consultation information. information, and spliced with the consultation information. For example, the interactive information is: the previous disease is diabetes. The inquiry information is: I have a headache for 3 consecutive days. The updated consultation information is: I have diabetes and have a headache for 3 consecutive days.
可选的，所述与所述问诊用户进行人机交互，获取交互信息，包括：获取问题信息，并根据所述问题信息与所述问诊用户进行人机交互；获取所述问诊用户基于所述问题信息提供的答案信息；根据所述问题信息和所述答案信息，确定交互信息。Optionally, the performing human-computer interaction with the inquiring user and acquiring the interaction information includes: acquiring problem information, and performing human-computer interaction with the inquiring user according to the problem information; acquiring the inquiring user based on the answer information provided by the question information; and determining the interaction information according to the question information and the answer information.
问题信息用于提供给问诊用户，并获取问诊用户提供答案信息，以确定交互信息。答案信息是指问诊用户针对问题信息回复的内容。可以从多个预设的问题中选择至少一个问题，作为问题信息，分别提供给问诊用户，并相应的，获取每个问题的答案，作为答案信息。问题信息可以包括多个关联问题，在问诊用户针对问题输入答案信息，选择该问题关联的问题作为下一问题，例如，问题1为：是否发烧？关联的问题2为：是否出现喉咙痛的症状？或者，还可以设置问题信息存在多个关联的问题信息，并根据答案信息，从多个关联的问题中确定下一问题。对此不做限定。The question information is used to provide the consultation user, and obtain the answer information provided by the consultation user to determine the interaction information. The answer information refers to the content that the inquiring user replies to the question information. At least one question can be selected from a plurality of preset questions as question information, respectively provided to the consultation user, and correspondingly, the answer of each question can be obtained as the answer information. The question information may include multiple associated questions. When the user enters answer information for the question, the question associated with the question is selected as the next question. For example, question 1 is: Do you have a fever? Related question 2 is: Are there any symptoms of sore throat? Alternatively, it is also possible to set the question information to have multiple associated question information, and determine the next question from the multiple associated questions according to the answer information. This is not limited.
根据至少一个问题，以及对应的答案确定交互信息。可以理解的是，有些问题为是否的判断类型问题，问题和答案组合在一起，可以确定问诊用户的症状或既往疾病，例如，问题为：是否存在头疼的症状，答案为：是，此时，问诊用户提供的信息为，存在头疼的症状。若只根据答案，无法确定问诊用户的真实意思。The interaction information is determined according to at least one question and the corresponding answer. It is understandable that some questions are of the type of judgment of whether or not. The questions and answers are combined to determine the symptoms or previous diseases of the inquiring user. For example, the question is: whether there is a headache symptom, and the answer is: yes, at this time. , the information provided by the inquiring user is that there is a headache. If only based on the answers, it is impossible to determine the true meaning of the user who asked the question.
通过预先配置的问题，与问诊用户进行人机交互，获取问诊用户针对问题信息提供的答案信息，将问题信息和答案信息，确定交互信息，可以准确完整获取问诊用户的真实问诊内容和真实既往疾病等信息，并基于交互信息更新问诊信息，丰富问诊信息的内容，提高问诊信息的代表性，从而，提高分科准确率。Through pre-configured questions, human-computer interaction with the inquiring user can be used to obtain the answer information provided by the inquiring user for the question information. And real past diseases and other information, and update the consultation information based on the interactive information, enrich the content of the consultation information, improve the representativeness of the consultation information, and thus improve the accuracy of the division.
可选的，所述获取问题信息，包括下述至少一项：根据所述问诊信息，查询对应的关联科室，并根据所述关联科室的伴随症状，确定对应的问题信息；根据所述问诊信息，查询对应的目标场景，并根据场景与问题信息的对应关系，查询所述目标场景对应的问题信息；以及基于预先训练的医患交互模型，生成问题信息。Optionally, the acquiring the problem information includes at least one of the following: query the corresponding associated department according to the consultation information, and determine the corresponding problem information according to the accompanying symptoms of the associated department; diagnosis information, query the corresponding target scene, and query the problem information corresponding to the target scene according to the corresponding relationship between the scene and the problem information; and generate the problem information based on the pre-trained doctor-patient interaction model.
关联科室可以是指能够诊疗问诊信息的科室。伴随症状可以是指关联科室能够诊疗的症状。根据问诊信息，查询对应的关联科室，可以是对问诊信息进行解析和意图识别，将解析结果和意图识别结果，输入到预先建立的知识图谱中，进行索引，获取关联的科室信息，确定关联科室，并从关联的科室信息中提取关联科室的伴随症状。将根据关联科室的伴随症状，确定对应的问题信息，可以是生成至少一个伴随症状的确认问题，作为问题信息。例如，将与不同关联科室对应的伴随症状作为候选项，例如生成“是否存在伴随症状”问题，以与问诊用户进行确认，得到对应的答案。The associated department may refer to a department that can diagnose and treat information. Accompanying symptoms may refer to symptoms that can be treated by related departments. According to the consultation information, query the corresponding associated department, which may be to parse the consultation information and identify the intention, input the analysis result and the intention identification result into the pre-established knowledge map for indexing, obtain the information of the associated department, and determine the Associate departments, and extract the accompanying symptoms of the associated departments from the associated department information. Corresponding problem information will be determined according to the accompanying symptoms of the associated department, which may be a confirmation problem of at least one accompanying symptom as the problem information. For example, the concomitant symptoms corresponding to different related departments are used as candidates, for example, the question of "whether there are concomitant symptoms" is generated, so as to confirm with the inquiring user and obtain the corresponding answer.
可以根据不能分科的情况，对应配置不同的场景。可以预先采集多个问诊信息，并获取每个问诊信息的解析结果和意图识别结果，并对问诊信息进行分类，或者人工分类，每一类定义为一个场景。根据问诊信息查询对应的目标场景，可以是对问诊信息进行类型确定，具体可以采用聚类算法或分类模型等。人工编辑不同场景的问询过程涉及的问题信息，建立场景和问题信息的对应关系，通过问诊信息与场景的匹配来进行不同问询过程涉及的问题信息的选择。Different scenarios can be configured according to the situation that cannot be divided into subjects. Multiple consultation information can be collected in advance, and the analysis results and intent recognition results of each consultation information can be obtained, and the consultation information can be classified or manually classified, and each category is defined as a scene. According to the target scene corresponding to the inquiry information query, the type of the inquiry information may be determined, and specifically, a clustering algorithm or a classification model may be used. Manually edit the problem information involved in the inquiry process of different scenarios, establish the corresponding relationship between the scene and the problem information, and select the problem information involved in the different inquiry process by matching the inquiry information and the scene.
前两种是基于问诊信息确定对应的问题信息。最后一种基于医患交互模型生成问题，生成的问题与问诊信息不存在对应关系。可以预先采集历史医患对话，并将医生的问话作为输入，将患者回话作为输出，训练医患交互模型。使医患交互模型学习医生问询逻辑，通过医患交互模型产生候选项，即问题，作为问题信息。示例性的，医患交互模型包括基于隐空间(Latent Space)的端到端的预训练对话生成模型(Plato)，序列到序列模型(Sequence to Sequence，Seq2Seq)或特征生成预训练模型(Diag Generative Pre-Training，DiagGPT)等。The first two are based on the inquiry information to determine the corresponding problem information. The last problem is generated based on the doctor-patient interaction model, and the generated problem does not have a corresponding relationship with the consultation information. The historical doctor-patient dialogue can be collected in advance, the doctor's questioning as input, and the patient's reply as output to train the doctor-patient interaction model. Make the doctor-patient interaction model learn the doctor's query logic, and generate candidate items, that is, questions, as question information through the doctor-patient interaction model. Exemplarily, the doctor-patient interaction model includes an end-to-end pre-trained dialogue generation model (Plato) based on a latent space (Latent Space), a sequence-to-sequence model (Sequence to Sequence, Seq2Seq) or a feature generation pre-training model (Diag Generative Pre -Training, DiagGPT) etc.
可以选择其中的至少一种方式生成问题，在采用至少两种方式的情况下，可以对不同方式得到的问题信息进行融合，剔除相似重复的问题，得到问题信息。At least one of the methods can be selected to generate the problem, and in the case of adopting at least two methods, the problem information obtained by different methods can be fused, and the similar and repeated problems can be eliminated to obtain the problem information.
通过多种方式生成问题，可以丰富问题的内容，增加问题的覆盖范围，提高问题的代表性，从而提高问诊用户提供的答案的代表性，以及丰富问诊信息。Generating questions in various ways can enrich the content of the questions, increase the coverage of the questions, and improve the representativeness of the questions, thereby improving the representativeness of the answers provided by the inquiring users and enriching the inquiring information.
S203，根据更新后的问诊信息，确定目标问诊科室。S203: Determine the target consultation department according to the updated consultation information.
根据更新后的问诊信息，确定目标问诊科室，可以是在问诊信息中添加内容，以更加丰富更加准确的问诊信息，确定目标问诊科室，可以提高问诊科室的确定准确率。According to the updated consultation information, the target consultation department is determined, which can be by adding content to the consultation information to enrich and more accurate consultation information. Determine the target consultation department, which can improve the accuracy of the determination of the consultation department.
可选的，所述根据更新后的问诊信息，确定目标问诊科室，包括：将更新后的问诊信息输入预先训练的科室分类模型中，得到第一分类结果；和/或根据所述更新后的问诊信息，在预先建立的标准信息与科室之间的对应关系中，确定第二分类结果；根据所述第一分类结果和所述第二分类结果，确定目标问诊科室。Optionally, determining the target consultation department according to the updated consultation information includes: inputting the updated consultation information into a pre-trained department classification model to obtain a first classification result; and/or according to the In the updated consultation information, a second classification result is determined in the correspondence between the pre-established standard information and the department; the target consultation department is determined according to the first classification result and the second classification result.
第一分类结果为基于科室分类模型确定的目标问诊科室。第二分类结果为基于检索方式确定的目标问诊科室。The first classification result is the target consultation department determined based on the department classification model. The second classification result is the target consultation department determined based on the retrieval method.
科室分类模型用于根据问诊信息，确定问诊信息对应的目标问诊科室。训练样本包括问诊信息和对应的问诊科室。例如，科室分类模型为预先训练的神经网络模型，示例性的，科室分类模型包括预训练模型和softmax模型、预训练模型和文本卷积神经网络模型(Text Convolutional Neural Networks，Textcnn)或预训练模型和LSTM模型等。The department classification model is used to determine the target consultation department corresponding to the consultation information according to the consultation information. The training samples include consultation information and corresponding consultation departments. For example, the department classification model is a pre-trained neural network model. Exemplarily, the department classification model includes a pre-trained model and a softmax model, a pre-trained model and a text convolutional neural network model (Text Convolutional Neural Networks, Textcnn) or a pre-trained model and LSTM models, etc.
标准信息用于与问诊信息进行相似度检索，从而确定问诊信息对应的目标问诊科室。标准信息可以是对问诊信息进行抽象定义的信息，可以将标准信息理解为，对多个问诊信息进行分类，在每类中提取共同的特征，抽象定义，得到的信息，作为该类的标准信息。标准信息与科室之间的对应关系用于确定问诊信息对应的目标问诊科室。通过检索方式，查询问诊信息对应的标准信息，并将该对应的标准信息对应的目标问诊科室，确定为问诊信息对应的目标问诊科室。检索方式可以是近似最邻近检索方式(Approximate NearestNeighbor，ANN)，示例性的，可以将标准信息与科室进行人工构建入库，将问诊信息与标准信息进行ANN相似度索引检索，得到相似的标准信息对应的科室。The standard information is used for similarity retrieval with the consultation information, so as to determine the target consultation department corresponding to the consultation information. Standard information can be information that abstractly defines consultation information. Standard information can be understood as classifying multiple consultation information, extracting common features in each category, abstracting definitions, and obtaining information as the type of information. Standard information. The correspondence between the standard information and the department is used to determine the target consultation department corresponding to the consultation information. By means of retrieval, the standard information corresponding to the consultation information is queried, and the target consultation department corresponding to the corresponding standard information is determined as the target consultation department corresponding to the consultation information. The retrieval method can be the approximate nearest neighbor retrieval method (Approximate Nearest Neighbor, ANN). Exemplarily, the standard information and the department can be manually constructed and stored, and the inquiry information and the standard information can be searched by ANN similarity index to obtain similar standards. Information corresponding to the department.
在问诊信息更新的情况下，前述问诊信息可以替换为更新后的问诊信息。When the consultation information is updated, the aforementioned consultation information may be replaced with the updated consultation information.
在仅得到第一分类结果的情况下，第二分类结果为空，根据第一分类结果和第二分类结果，确定目标问诊科室，实际是将第一分类结果确定为目标问诊科室。在仅得到第二分类结果的情况下，第一分类结果为空，根据第一分类结果和第二分类结果，确定目标问诊科室，实际是将第二分类结果，确定为目标问诊科室。在得到第一分类结果和第二分类结果的情况下，可以将第一分类结果和第二分类结果进行融合，确定目标问诊科室。其中，融合方式可以是基于第二分类结果对第一分类结果进行修正。第二分类结果的优先级高于第一分类结果的优先级，或者还可以直接将第二分类结果确定为目标问诊科室。When only the first classification result is obtained, the second classification result is empty, and the target consultation department is determined according to the first classification result and the second classification result, and the first classification result is actually determined as the target consultation department. If only the second classification result is obtained, the first classification result is empty, and the target consultation department is determined according to the first classification result and the second classification result, and the second classification result is actually determined as the target consultation department. In the case where the first classification result and the second classification result are obtained, the first classification result and the second classification result may be fused to determine the target consultation department. The fusion method may be to modify the first classification result based on the second classification result. The priority of the second classification result is higher than the priority of the first classification result, or the second classification result can also be directly determined as the target consultation department.
通过计算第一分类结果和/或第二分类结果，并根据第一分类结果和第二分类结果确定目标问诊科室，采用多种方式进行分科，融合分类结果确定目标问诊科室，可以提高分科准确率。By calculating the first classification result and/or the second classification result, and determining the target consultation department according to the first classification result and the second classification result, using various methods to divide the department, and combining the classification results to determine the target consultation department, it is possible to improve the classification of departments. Accuracy.
根据本公开的技术方案，通过在能否分科判断结果为不能分科的情况下，与问诊用户进行人机交互，引导问诊用户更完整的描述自身情况，获取交互信息，并更新问诊信息，可以增加问诊信息的内容，提高问诊信息的完整性，使问诊信息的更加精确，并以更新后的问诊信息，确定目标问诊科室，可以提高目标问诊科室的准确率，从而提高分科准确率。According to the technical solution of the present disclosure, in the case that the judgment result of whether it can be divided into a department is that it cannot be divided into a department, human-computer interaction is performed with the inquiring user, so as to guide the inquiring user to describe their own situation more completely, obtain the interaction information, and update the inquiring information. , which can increase the content of the consultation information, improve the integrity of the consultation information, make the consultation information more accurate, and determine the target consultation department with the updated consultation information, which can improve the accuracy of the target consultation department. This improves the accuracy of classification.
图3是根据本公开实施例公开的另一种问诊方法的流程图，基于上述技术方案进一步优化与扩展，并可以与上述各个可选实施方式进行结合。将问诊方法优化为：获取所述目标问诊科室对应的至少一个备选医生信息；根据所述问诊信息和各所述备选医生信息，对各所述备选医生信息进行排序；根据排序结果，确定推荐医生信息。FIG. 3 is a flowchart of another diagnosis method disclosed according to an embodiment of the present disclosure, which is further optimized and expanded based on the above-mentioned technical solution, and can be combined with each of the above-mentioned optional embodiments. The inquiry method is optimized as follows: obtaining at least one candidate doctor information corresponding to the target inquiry department; sorting the candidate doctor information according to the inquiry information and each candidate doctor information; Sort the results to determine the recommended doctor information.
S301，获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断。S301: Obtain the consultation information of the consultation user, and determine whether the consultation information can be divided into different departments.
S302，根据能否分科判断结果和所述问诊信息，确定目标问诊科室。S302: Determine the target consultation department according to the judgment result of whether it can be divided into different departments and the consultation information.
S303，获取所述目标问诊科室对应的至少一个备选医生信息。S303: Obtain at least one candidate doctor information corresponding to the target consultation department.
备选医生信息可以是指隶属于目标问诊科室的医生的信息。The candidate doctor information may refer to information of a doctor belonging to the target consultation department.
备选医生信息用于筛选推荐医生信息，提供给问诊用户，以建议问诊用户针对性挂号，最终实现分诊目的。其中，备选医生信息不局限于一个医院中，可以从多个医院中，选择与目标问诊科室相同或相似的备选科室，并确定隶属于该备选科室的至少一个备选医生，采集各备选科室的各医生的信息，形成科室与医生信息的对应关系。医生信息可以包括下述至少一项：医生的职业科室、擅长疾病、疾病治疗方式和服务时间等。可以根据医生信息中的职业科室，建立医生信息与科室之间的对应关系。根据目标问诊科室，查询对应的科室，并确定对应的医生信息，作为备选医生信息。The candidate doctor information is used to screen the recommended doctor information and provide it to the inquiring user, so as to suggest the inquiring user to register in a targeted manner, and finally achieve the purpose of triage. Wherein, the candidate doctor information is not limited to one hospital, and a candidate department that is the same as or similar to the target consultation department can be selected from multiple hospitals, and at least one candidate doctor belonging to the candidate department is determined to collect the information. The information of each doctor in each candidate department forms the corresponding relationship between the department and the doctor's information. The doctor's information may include at least one of the following: the doctor's occupational department, expertise in disease, disease treatment method, service time, and the like. The correspondence between the doctor information and the department can be established according to the occupational department in the doctor information. According to the target consultation department, the corresponding department is inquired, and the corresponding doctor information is determined as the candidate doctor information.
S304，根据所述问诊信息和各所述备选医生信息，对各所述备选医生信息进行排序。S304: Sort each candidate doctor information according to the consultation information and each candidate doctor information.
根据问诊信息和备选医生信息，可以确定问诊信息与各备选医生信息之间的匹配程度，并根据匹配程度对备选医生信息进行排序。在不能分科的情况下，可以根据更新后的问诊信息和备选医生信息，对备选医生信息进行排序。通过对问诊信息更新，澄清问诊用户的就诊意图，并将更新的问诊信息进行复制，分别和每个备选医生信息进行组合，得到至少一个输入信息，输入至预先训练的线性回归模型中，获取线性回归模型输出的得分，并根据得分，对对应的输入信息中备选医生信息进行排序。线性回归模型用于模拟问诊信息和医生信息与问诊信息和医生信息之间的匹配程度之间的线性关系，其中，训练样本包括问诊信息中提取的问诊特征信息、医生信息中提取的医生特征信息，以及问诊信息和医生信息之间的匹配得分。其中，特征信息可以以向量形式表示，问诊特征信息可以包括前述的解析结果和意图识别结果等。医生特征信息可以包括医生信息中的关键词，其中，可以基于预先训练的文本识别模型从医生信息中提取医生特征信息，或者可以根据预设的模板，从医生信息中提取医生特征信息。According to the consultation information and the candidate doctor information, the matching degree between the consultation information and each candidate doctor information can be determined, and the candidate doctor information can be sorted according to the matching degree. In the case where it is not possible to divide the subjects, the candidate doctor information can be sorted according to the updated consultation information and the candidate doctor information. By updating the consultation information, clarify the consultation intention of the consultation user, copy the updated consultation information, and combine it with the information of each candidate doctor to obtain at least one input information, which is input to the pre-trained linear regression model , obtain the score output by the linear regression model, and sort the candidate doctor information in the corresponding input information according to the score. The linear regression model is used to simulate the linear relationship between the consultation information and the doctor's information and the degree of matching between the consultation information and the doctor's information, wherein the training samples include the consultation feature information extracted from the consultation information, and the matching score between the consultation information and the doctor information. The feature information may be represented in the form of a vector, and the consultation feature information may include the aforementioned analysis results and intent recognition results. The doctor characteristic information may include keywords in the doctor information, wherein the doctor characteristic information may be extracted from the doctor information based on a pre-trained text recognition model, or the doctor characteristic information may be extracted from the doctor information according to a preset template.
S305，根据排序结果，确定推荐医生信息。S305, according to the sorting result, determine the recommended doctor information.
推荐医生信息用于推荐给问诊用户，以建议问诊用户选择推荐医生进行诊疗，实现精准分诊，提高诊疗效果。根据排序结果，可以是从中筛选排名靠前的备选医生信息，确定为推荐医生信息。示例性的，可以将第一名备选医生信息确定为推荐医生信息；或者可以将第1-3名备选医生信息确定为推荐医生信息。此外还有其他情况，不做具体限制。The recommended doctor information is used to recommend to the inquiring user, so as to suggest that the inquiring user chooses the recommended doctor for diagnosis and treatment, realizes accurate triage, and improves the diagnosis and treatment effect. According to the sorting result, the top-ranked candidate doctor information may be screened therefrom and determined as the recommended doctor information. Exemplarily, the first candidate doctor information may be determined as the recommended doctor information; or the first to third candidate doctor information may be determined as the recommended doctor information. In addition, there are other situations that do not impose specific restrictions.
可选的，所述根据所述问诊信息和各所述备选医生信息，对各所述备选医生信息进行排序，包括：在预先建立的标准信息与严重程度的对应关系中，查询所述问诊信息对应的严重程度；根据所述问诊信息、对应的严重程度和各所述备选医生信息，对各所述备选医生信息进行排序。Optionally, the sorting of the candidate doctor information according to the consultation information and the candidate doctor information includes: in the pre-established correspondence between the standard information and the severity, querying all the candidate doctor information. Describe the severity corresponding to the consultation information; sort the candidate doctor information according to the consultation information, the corresponding severity, and the candidate doctor information.
标准信息可以参考前述描述。严重程度是指问诊用户的病情严重程度，严重程度可以包括严重和不严重；或者还可以包括极度严重、重度严重、中度严重、低度严重和不严重。标准信息与严重程度的对应关系用于确定问诊信息对应的严重程度。通过检索方式，查询问诊信息对应的标准信息，并将该对应的标准信息对应的严重程度，确定为问诊信息对应的严重程度。检索方式可以是ANN，示例性的，可以将标准信息与严重程度进行人工构建入库，将问诊信息与标准信息进行ANN相似度索引检索，得到相似的标准信息对应的严重程度。Standard information can refer to the foregoing description. Severity refers to the severity of the condition of the inquiring user, and the severity may include severe and non-severe; or may also include extremely severe, severely severe, moderately severe, low-severity, and non-severe. The correspondence between the standard information and the severity is used to determine the severity corresponding to the consultation information. By means of retrieval, the standard information corresponding to the consultation information is queried, and the severity corresponding to the corresponding standard information is determined as the severity corresponding to the consultation information. The retrieval method can be ANN. For example, the standard information and severity can be manually constructed and stored in the database, and the ANN similarity index retrieval can be performed on the consultation information and the standard information to obtain the severity corresponding to the similar standard information.
在不能分科的情况下，通过对问诊信息更新，澄清问诊用户的就诊意图和病情严重程度，并将更新的问诊信息和严重程度进行复制，分别和每个备选医生信息进行组合，得到至少一个输入信息，输入至预先训练的线性回归模型中，获取线性回归模型输出的得分，并根据得分，对对应的输入信息中备选医生信息进行排序。具体的，将严重程度添加到问诊特征信息中，即问诊特征信息可以包括前述的解析结果、意图识别结果和严重程度等。将问诊特征信息进行复制，分别和每个备选医生信息的医生特征信息进行组合，得到至少一个输入信息，输入至预先训练的线性回归模型中，获取线性回归模型输出的得分，并根据得分，对对应的输入信息中备选医生信息进行排序。In the case where it is not possible to divide the department, by updating the consultation information, clarify the consultation intention and the severity of the patient's condition, and copy the updated consultation information and severity, and combine them with the information of each candidate doctor respectively. Obtain at least one input information, input it into a pre-trained linear regression model, obtain a score output by the linear regression model, and sort the candidate doctor information in the corresponding input information according to the score. Specifically, the severity is added to the consultation feature information, that is, the consultation feature information may include the aforementioned analysis result, intent identification result, severity, and the like. Copy the consultation feature information, combine it with the doctor feature information of each candidate doctor information, obtain at least one input information, input it into the pre-trained linear regression model, obtain the score output by the linear regression model, and according to the score , sort the candidate doctor information in the corresponding input information.
此外，在基于标准信息与严重程度的对应关系中，查询问诊信息对应的严重程度，在查询结果为空的情况下，可以为问诊用户预先分配低等级的医生，进行病情问询和疾病的初步诊断，进行病情严重程度的判断，得到该医生确定的严重程度；或者，还可以获取问诊用户输入的严重程度。其中，低等级的医生是和高等级的医生相对，高等级的医生可以是指专家级别的医生；低等级的医生可以是门诊级别的医生；或者，高等级的医生可以是指三甲医院的医生；低等级的医生可以是二甲医院的医生。In addition, based on the correspondence between the standard information and the severity, the severity corresponding to the inquiry information can be queried. If the query result is empty, a low-level doctor can be pre-assigned to the inquiring user to conduct disease inquiries and diseases. The initial diagnosis is made, the severity of the condition is judged, and the severity determined by the doctor is obtained; or, the severity input by the inquiring user can also be obtained. Among them, low-level doctors are opposite to high-level doctors. High-level doctors can refer to specialist-level doctors; low-level doctors can be outpatient-level doctors; or high-level doctors can refer to doctors in tertiary hospitals ; A low-ranking doctor can be a doctor in a second-class hospital.
通过确定问诊用户的严重程度，可以通过问诊用户的病情的严重程度，来进行医生推荐，在分科的基础上，进一步实现分级诊疗，提高分诊的准确率，提供推荐医生，提高分诊推荐的准确率，提高用户体验。By determining the severity of the inquiring user, a doctor can be recommended based on the severity of the inquiring user's condition. On the basis of sub-discipline, the hierarchical diagnosis and treatment can be further realized, the accuracy of triaging can be improved, the recommended doctor can be provided, and the triage can be improved. Recommended accuracy and improve user experience.
根据本公开的技术方案，通过获取问诊信息对应的至少一个备选医生信息，并基于问诊信息，从备选医生信息中筛选出推荐医生信息，可以合理利用医疗资源，为问诊用户提供合适的医生，实现分级诊疗，提高分针准确率。According to the technical solution of the present disclosure, by acquiring at least one candidate doctor information corresponding to the consultation information, and selecting the recommended doctor information from the candidate doctor information based on the consultation information, medical resources can be reasonably utilized to provide consultation users with Appropriate doctors can achieve hierarchical diagnosis and treatment and improve the accuracy of minute needles.
图4是根据本公开实施例公开的另一种问诊方法的流程图，是一种问诊方法的具体应用场景。FIG. 4 is a flowchart of another method for inquiring according to an embodiment of the present disclosure, which is a specific application scenario of the method for inquiring.
S401，获取问诊用户的问诊信息。S401. Obtain the consultation information of the consultation user.
S402，对所述问诊信息进行能否分科判断，如果能分科，则执行S403；否则执行S404。S402, judge whether the inquiry information can be divided into different subjects, if it can be divided into different subjects, then execute S403; otherwise, execute S404.
S403，根据所述问诊信息，确定目标问诊科室，执行S405。S403, according to the consultation information, determine the target consultation department, and execute S405.
S404，与所述问诊用户进行人机交互，获取交互信息，并更新所述问诊信息。S404, perform human-computer interaction with the inquiring user, obtain interaction information, and update the inquiring information.
用户作答，与问诊信息进行拼接融合，得到更新后的问诊信息。The user answers, splices and fuses with the consultation information, and obtains the updated consultation information.
S405，在预先建立的标准信息与严重程度的对应关系中，查询所述问诊信息对应的严重程度，并判断能否查询到严重程度；如果能，则执行S406；否则执行S407。S405, in the pre-established correspondence between the standard information and the severity, query the severity corresponding to the consultation information, and determine whether the severity can be queried; if yes, execute S406; otherwise, execute S407.
S406，为问诊用户分配低级别医生，并通过低级别医生问询诊断，获取严重程度。S406, assign a low-level doctor to the inquiring user, and obtain the severity by inquiring about the diagnosis through the low-level doctor.
S407，根据严重程度、所述问诊信息和所述目标问诊科室对应的至少一个备选医生信息，确定推荐医生信息为推荐权威三甲医生。S407, according to the severity, the consultation information, and at least one candidate doctor information corresponding to the target consultation department, determine that the recommended doctor information is a recommended authoritative top-three doctor.
根据所述问诊信息、对应的严重程度和各所述备选医生信息，对各所述备选医生信息进行排序。根据排序结果，确定推荐医生信息。在严重程度为严重的情况下，推荐医生信息为目标问诊科室的权威三甲医生。The candidate doctor information is sorted according to the consultation information, the corresponding severity, and the candidate doctor information. According to the sorting result, the recommended doctor information is determined. In the case of severe severity, the recommended doctor information is the authoritative top three doctors in the target department.
通过预先判断能否分科，在不能分科的情况下，通过人机交互，更新问诊信息，引导问诊用户更完整表述自己的基本情况，可以增加问诊信息的内容，提高问诊信息的完整性，使问诊信息的更加精确，提高分科准确率，并通过获取问诊信息的严重程度，以及获取目标问诊科室对应的至少一个备选医生信息，筛选推荐医生信息，提供给问诊用户，可以合理利用医疗资源，为问诊用户提供合适的医生，实现分级诊疗，提高分针准确率。By pre-judging whether it can be divided into subjects, in the case of not being able to be divided into subjects, through human-computer interaction, update the consultation information, and guide the consultation users to more completely express their basic situation, which can increase the content of the consultation information and improve the integrity of the consultation information. By obtaining the severity of the consultation information and obtaining at least one candidate doctor information corresponding to the target consultation department, the information of recommended doctors can be screened and provided to the consultation users. , which can rationally use medical resources, provide suitable doctors for inquiring users, realize hierarchical diagnosis and treatment, and improve the accuracy of minute needles.
根据本公开的实施例，图5是本公开实施例中的问诊装置的结构图，本公开实施例适用于用户获取问诊信息对应的分诊科室的情况。该装置采用软件和/或硬件实现，并具体配置于具备一定数据运算能力的电子设备中。According to an embodiment of the present disclosure, FIG. 5 is a structural diagram of an interrogation apparatus in an embodiment of the present disclosure, and the embodiment of the present disclosure is applicable to a situation where a user obtains a triage department corresponding to the interrogation information. The device is implemented by software and/or hardware, and is specifically configured in an electronic device with a certain data computing capability.
如图5所示的一种问诊装置500，包括：能否分科判断模块501和[108]分诊科室确定模块502；其中，As shown in FIG. 5 , an
能否分科判断模块501，用于获取问诊用户的问诊信息，并对所述问诊信息进行能否分科判断；Whether it is possible to classify the
分诊科室确定模块502，用于根据能否分科判断结果和所述问诊信息，确定目标问诊科室。The triage
根据本公开的技术方案，通过对问诊信息进行能否分科判断，并根据能否分科判断的结果和问诊信息，确定目标问诊科室，可以在问诊信息可以进行分科的情况下，确定目标问诊科室，提高问诊信息的准确性，使问诊信息更加清楚，从而提高分科的准确率。According to the technical solution of the present disclosure, by judging whether the inquiry information can be divided into different departments, and according to the result of whether the inquiry information can be divided into different departments and the inquiry information, the target inquiring department can be determined. Target consultation departments, improve the accuracy of consultation information, make the consultation information clearer, and improve the accuracy of sub-disciplines.
进一步的，所述分诊科室确定模块502，包括：问诊信息更新单元，用于在能否分科判断结果为不能分科的情况下，与所述问诊用户进行人机交互，获取交互信息，并更新所述问诊信息；分诊科室再确定单元，用于根据更新后的问诊信息，确定目标问诊科室。Further, the triage
进一步的，所述问诊信息更新单元，包括：人机交互子单元，用于获取问题信息，并根据所述问题信息与所述问诊用户进行人机交互；答案信息获取子单元，用于获取所述问诊用户基于所述问题信息提供的答案信息；交互信息确定单元，用于根据所述问题信息和所述答案信息，确定交互信息。Further, the inquiry information updating unit includes: a human-computer interaction sub-unit for acquiring question information, and performing human-computer interaction with the inquiring user according to the question information; an answer information acquiring sub-unit for Acquiring answer information provided by the inquiring user based on the question information; an interaction information determining unit, configured to determine interaction information according to the question information and the answer information.
进一步的，所述人机交互子单元，用于下述至少一项：根据所述问诊信息，查询对应的关联科室，并根据所述关联科室的伴随症状，确定对应的问题信息；根据所述问诊信息，查询对应的目标场景，并根据场景与问题信息的对应关系，查询所述目标场景对应的问题信息；以及基于预先训练的医患交互模型，生成问题信息。Further, the human-computer interaction subunit is used for at least one of the following: query the corresponding associated department according to the consultation information, and determine the corresponding problem information according to the accompanying symptoms of the associated department; Describe the consultation information, query the corresponding target scene, and query the problem information corresponding to the target scene according to the corresponding relationship between the scene and the problem information; and generate the problem information based on the pre-trained doctor-patient interaction model.
进一步的，所述问诊装置500，还包括：分科医生获取模块，用于获取所述目标问诊科室对应的至少一个备选医生信息；医生排序模块，用于根据所述问诊信息和各所述备选医生信息，对各所述备选医生信息进行排序；医生推荐模块，用于根据排序结果，确定推荐医生信息。Further, the inquiring
进一步的，所述医生排序模块，包括：严重程度确定单元，用于在预先建立的标准信息与严重程度的对应关系中，查询所述问诊信息对应的严重程度；严重程度排序单元，用于根据所述问诊信息、对应的严重程度和各所述备选医生信息，对各所述备选医生信息进行排序。Further, the doctor ranking module includes: a severity determination unit, used for inquiring the severity corresponding to the inquiry information in the pre-established correspondence between the standard information and the severity; a severity ranking unit, used for The candidate doctor information is sorted according to the consultation information, the corresponding severity, and the candidate doctor information.
进一步的，所述分诊科室确定模块502，包括：模型分类单元，用于将更新后的问诊信息输入预先训练的科室分类模型中，得到第一分类结果；和/或搜索分类单元，用于根据所述更新后的问诊信息，在预先建立的标准信息与科室之间的对应关系中，确定第二分类结果；分类融合单元，用于根据所述第一分类结果和所述第二分类结果，确定目标问诊科室。Further, the triage
上述问诊装置可执行本公开任意实施例所提供的问诊方法，具备执行问诊方法相应的功能模块和有益效果。The above-mentioned interrogation device can execute the interrogation method provided by any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to executing the interrogation method.
本公开的技术方案中，所涉及的用户个人信息的收集、存储、使用、加工、传输、提供和公开等处理，均符合相关法律法规的规定，且不违背公序良俗。In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved are all in compliance with relevant laws and regulations, and do not violate public order and good customs.
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
图6示出了可以用来实施本公开的实施例的示例电子设备600的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。FIG. 6 shows a schematic block diagram of an example
如图6所示，设备600包括计算单元601，其可以根据存储在只读存储器(ROM)602中的计算机程序或者从存储单元608加载到随机访问存储器(RAM)603中的计算机程序，来执行各种适当的动作和处理。在RAM 603中，还可存储设备600操作所需的各种程序和数据。计算单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O)接口605也连接至总线604。As shown in FIG. 6 , the
设备600中的多个部件连接至I/O接口605，包括：输入单元606，例如键盘、鼠标等；输出单元607，例如各种类型的显示器、扬声器等；存储单元608，例如磁盘、光盘等；以及通信单元609，例如网卡、调制解调器、无线通信收发机等。通信单元609允许设备600通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。Various components in the
计算单元601可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元601的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元601执行上文所描述的各个方法和处理，例如问诊方法或问诊方法。例如，在一些实施例中，问诊方法或问诊方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元608。在一些实施例中，计算机程序的部分或者全部可以经由ROM 602和/或通信单元609而被载入和/或安装到设备600上。当计算机程序加载到RAM 603并由计算单元601执行时，可以执行上文描述的问诊方法或问诊方法的一个或多个步骤。备选地，在其他实施例中，计算单元601可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行问诊方法或问诊方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a distributed system server, or a server combined with blockchain.
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in different orders. As long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, there is no limitation herein.
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure should be included within the protection scope of the present disclosure.
Claims (17)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152045.7ACN113870998B (en) | 2021-09-29 | 2021-09-29 | Medical consultation method, device, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152045.7ACN113870998B (en) | 2021-09-29 | 2021-09-29 | Medical consultation method, device, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113870998Atrue CN113870998A (en) | 2021-12-31 |
| CN113870998B CN113870998B (en) | 2025-07-04 |
Family
ID=79000517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111152045.7AActiveCN113870998B (en) | 2021-09-29 | 2021-09-29 | Medical consultation method, device, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870998B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114566264A (en)* | 2022-01-28 | 2022-05-31 | 北京泽桥医疗科技股份有限公司 | 3D model and content intelligent recommended doctor online timely application feedback system |
| CN116936058A (en)* | 2023-09-14 | 2023-10-24 | 北京健康有益科技有限公司 | Intelligent diagnosis guiding method and system based on deep learning and knowledge graph |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109300535A (en)* | 2018-07-06 | 2019-02-01 | 北京康夫子科技有限公司 | Hospital guide's method, hospital guide's device and machine readable storage medium |
| CN110993081A (en)* | 2019-12-03 | 2020-04-10 | 济南大学 | A method and system for online recommendation of doctors |
| 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 |
| WO2021114736A1 (en)* | 2020-07-07 | 2021-06-17 | 平安科技（深圳）有限公司 | Medical consultation assistance method and apparatus, electronic device, and medium |
- 2021
- 2021-09-29CNCN202111152045.7Apatent/CN113870998B/enactiveActive
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109300535A (en)* | 2018-07-06 | 2019-02-01 | 北京康夫子科技有限公司 | Hospital guide's method, hospital guide's device and machine readable storage medium |
| CN110993081A (en)* | 2019-12-03 | 2020-04-10 | 济南大学 | A method and system for online recommendation of doctors |
| WO2021114736A1 (en)* | 2020-07-07 | 2021-06-17 | 平安科技（深圳）有限公司 | Medical consultation assistance method and apparatus, electronic device, and medium |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 崔浩;刘丰源;: "智能导诊服务机器人的设计与实现", 计算机应用与软件, no. 07, 12 July 2020 (2020-07-12)* |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114566264A (en)* | 2022-01-28 | 2022-05-31 | 北京泽桥医疗科技股份有限公司 | 3D model and content intelligent recommended doctor online timely application feedback system |
| CN116936058A (en)* | 2023-09-14 | 2023-10-24 | 北京健康有益科技有限公司 | Intelligent diagnosis guiding method and system based on deep learning and knowledge graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113870998B (en) | 2025-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118627628B (en) | A large language model knowledge question answering method and system integrating multimodal knowledge graph | |
| CN104699741B (en) | Method and apparatus for improving answers to input questions | |
| US20200050949A1 (en) | Digital assistant platform | |
| CN113345577B (en) | Diagnosis and treatment auxiliary information generation method, model training method, device, equipment and storage medium | |
| CN112015917A (en) | Data processing method and device based on knowledge graph and computer equipment | |
| US12106054B2 (en) | Multi case-based reasoning by syntactic-semantic alignment and discourse analysis | |
| CN110517767B (en) | Auxiliary diagnosis method, auxiliary diagnosis device, electronic equipment and storage medium | |
| CN111326251B (en) | Question output method and device and electronic equipment | |
| US20220035998A1 (en) | Obtaining supported decision trees from text for medical health applications | |
| US12321357B2 (en) | System and method for improved state identification and prediction in computerized queries | |
| US20240420587A1 (en) | Drug knowledge quiz method, apparatus, electronic device and medium | |
| RU2718978C1 (en) | Automated legal advice system control method | |
| CN112579750A (en) | Similar medical record retrieval method, device, equipment and storage medium | |
| CN116719840A (en) | A medical information push method based on structured processing of medical records | |
| CN113870998A (en) | Interrogation method, device, electronic equipment and storage medium | |
| US20230359932A1 (en) | Classification process systems and methods | |
| CN120067243A (en) | Method, device and equipment for generating reply information based on large language model | |
| US20220293253A1 (en) | Systems and methods using natural language processing to improve computer-assisted coding | |
| CN113407813B (en) | Method for determining candidate information, method for determining query result, device and equipment | |
| US20230325422A1 (en) | Hybrid artificial intelligence system for semi-automatic patent claims analysis | |
| CN118230971A (en) | Medical information extraction method, device, electronic device and storage medium | |
| CN117932075A (en) | Causal graph generation method and system based on knowledge graph | |
| CN114664421A (en) | Doctor-patient matching method and device, electronic equipment, medium and product | |
| CN114117082A (en) | Method, apparatus and medium for correction of data to be corrected | |
| JP2019061522A (en) | Document recommendation system, document recommendation method and document recommendation program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |