阅读说明：本技术 基于自然语音交互的疾病症状信息采集系统 (Disease symptom information acquisition system based on natural voice interaction ) 是由 汤文巍 章智云 于 2019-12-17 设计创作，主要内容包括：本发明提供一种基于自然语音交互的疾病症状信息采集系统,包括：客户端子系统、服务端子系统,客户端子系统和服务端子系统进行集成并通过互联网将两个子系统进行连接以完成相互通讯和数据处理；所述客户端子系统包括麦克风部件、网络通讯部件B、扩音器部件,所述服务端子系统包括网络通讯部件C、语音转换文字部件、自然语义信息提取部件、自然语言交互部件、文字合成语音部件,本发明采用人机自然语音交互的方式,可以更简单方便的完成用户症状和疾病信息的采集。用户多医生少的情况下,采用本系统后,可以节省大量的医生与用户问诊沟通的时间,提高医生的工作效率和用户的就诊效率。(The invention provides a disease symptom information acquisition system based on natural voice interaction, which comprises: the system comprises a client subsystem and a service terminal system, wherein the client subsystem and the service terminal system are integrated and are connected through the Internet to complete mutual communication and data processing; the client subsystem comprises a microphone component, a network communication component B and a loudspeaker component, and the service terminal system comprises a network communication component C, a voice conversion character component, a natural semantic information extraction component, a natural language interaction component and a character synthesis voice component. Under the condition that the user has more doctors and less doctors, by adopting the system, a large amount of time for inquiring and communicating between the doctors and the user can be saved, and the working efficiency of the doctors and the diagnosis efficiency of the user are improved.)

1. A disease symptom information acquisition system based on natural voice interaction comprises: client subsystem, service terminal system, its characterized in that: the client subsystem and the service terminal system are integrated and are connected through the Internet to complete mutual communication and data processing; the client subsystem comprises a microphone component, a network communication component B and a loudspeaker component, the service terminal system comprises a network communication component C, a voice conversion character component, a natural semantic information extraction component, a natural language interaction component and a character synthesis voice component, a user awakens the client subsystem through an awakening language and describes own diseases and symptoms by using the natural language according to voice guidance played by the client subsystem, and the service terminal system completes extraction of the information of the diseases and symptoms described by the user through analysis and processing of voice data streams provided by the client subsystem.

2. The system according to claim 1, wherein the system comprises: the microphone component of the client subsystem is in a monitoring state by default, a user wakes up the client subsystem through a wake-up word, the client subsystem plays guide voice through the loudspeaker component, and then the microphone component enters the monitoring state; the user describes own diseases and symptoms by natural language according to the prompt of the guide voice; the client subsystem collects the user voice data stream through the microphone component and submits the user voice data stream to the network communication component B in real time; the network communication component B transmits the voice data stream to a network communication component C of the service terminal system through the Internet, and the client subsystem enters a waiting state; the network communication part C in the service terminal system submits the received voice data stream to the voice conversion character part in real time.

3. The system according to claim 1, wherein the system comprises: the voice conversion character part converts the natural voice data stream into natural language text information, and then submits the natural language text information to the natural semantic information extraction part in real time.

4. The system according to claim 1, wherein the system comprises: the natural semantic information extraction component firstly extracts the information related to the user symptoms and diseases based on natural semantic analysis, and the information is as follows: personal information: sex, age; the main complaint information is as follows: symptom name, disease name, time of occurrence of symptom, severity of symptom; life habit information: whether smoking is frequent, whether drinking is frequent, and whether staying up all night; and finally submitting the data to a natural language interaction component.

5. The system according to claim 1, wherein the system comprises: the natural language interaction component generates a guide language to be replied to the user according to the current missing information by combining the transmitted extracted information with the context rule of the inquiry; the generated guide language is then submitted to a text-to-speech component.

6. The system according to claim 1, wherein the system comprises: the character synthesis voice component converts the received text information into a corresponding voice data stream and submits the voice data stream to the network communication component C, and the network communication component C transmits the voice data stream to the client subsystem in real time through the Internet.

7. The system according to claim 1, wherein the system comprises: and the network communication component B of the client subsystem enters a playing state after receiving the guide voice data stream returned by the service terminal system, plays the received voice data stream to a user for listening through the loudspeaker component, and then the microphone component enters a monitoring state again to acquire the voice of the user again.

Technical Field

The invention relates to the technical field of voice recognition processing, in particular to a disease symptom information acquisition system based on natural voice interaction.

Background

At present, the disease symptom information acquisition mode is generally a process that a doctor communicates with a user through inquiry, and the doctor asks questions and the user answers to record the symptoms and the disease information of the user. This approach has the following drawbacks: 1. different doctors have different experiences, so that incomplete information acquisition is easy to cause; 2. the working efficiency of the doctor is limited and cannot meet the requirements of a large number of users.

Disclosure of Invention

The technical problem to be solved by the present invention is to provide a disease symptom information collecting system based on natural voice interaction, so as to solve the problems proposed in the background art.

The technical problem solved by the invention is realized by adopting the following technical scheme: disease symptom information acquisition system based on natural voice interaction includes: the system comprises a client subsystem and a service terminal system, wherein the client subsystem and the service terminal system are integrated and are connected through the Internet to complete mutual communication and data processing; the client subsystem comprises a microphone component, a network communication component B and a loudspeaker component, the service terminal system comprises a network communication component C, a voice conversion character component, a natural semantic information extraction component, a natural language interaction component and a character synthesis voice component, a user awakens the client subsystem through an awakening language and describes own diseases and symptoms by using the natural language according to voice guidance played by the client subsystem, and the service terminal system completes extraction of the information of the diseases and symptoms described by the user through analysis and processing of voice data streams provided by the client subsystem.

The microphone component of the client subsystem is in a monitoring state by default, a user wakes up the client subsystem through a wake-up word, the client subsystem plays guide voice through the loudspeaker component, and then the microphone component enters the monitoring state; the user describes his disease and symptoms in natural language according to the guidance voice prompt. The client subsystem collects the user voice data stream through the microphone component and submits the user voice data stream to the network communication component B in real time; the network communication component B transmits the voice data stream to a network communication component C of the service terminal system through the Internet, and the client subsystem enters a waiting state; the network communication part C in the service terminal system submits the received voice data stream to the voice conversion character part in real time.

The voice conversion character part converts the natural voice data stream into natural language text information, and then submits the natural language text information to the natural semantic information extraction part in real time.

The natural semantic information extraction component firstly extracts the information related to the user symptoms and diseases based on natural semantic analysis, and the information is as follows: personal information: sex, age; the main complaint information is as follows: symptom name, disease name, time of occurrence of symptom, severity of symptom; life habit information: whether smoking is frequent, whether drinking is frequent, and whether staying up all night; and finally submitting the data to a natural language interaction component.

And the natural language interaction component generates a guide language to be replied to the user according to the current missing information by combining the transmitted extracted information with the context rule of the inquiry. The generated guide language is then submitted to a text-to-speech component.

The character synthesis voice component converts the received text information into a corresponding voice data stream and submits the voice data stream to the network communication component C, and the network communication component C transmits the voice data stream to the client subsystem in real time through the Internet.

And the network communication component B of the client subsystem enters a playing state after receiving the guide voice data stream returned by the service terminal system, plays the received voice data stream to a user for listening through the loudspeaker component, and then the microphone component enters a monitoring state again to acquire the voice of the user again.

Compared with the prior art, the invention has the beneficial effects that: the invention adopts a man-machine natural voice interaction mode, and can more simply and conveniently finish the collection of user symptoms and disease information. Under the condition that the user has more doctors and less doctors, by adopting the system, a large amount of time for inquiring and communicating between the doctors and the user can be saved, and the working efficiency of the doctors and the diagnosis efficiency of the user are improved.

Drawings

FIG. 1 is a schematic diagram of the architecture of the present invention.

Detailed Description

In the description of the present invention, it should be noted that unless otherwise specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected, mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements.

As shown in fig. 1, the disease symptom information collecting system based on natural voice interaction includes: the system comprises a client subsystem and a service terminal system, wherein the client subsystem and the service terminal system are integrated and are connected through the Internet to complete mutual communication and data processing; the client subsystem comprises a microphone component, a network communication component B and a loudspeaker component, the service terminal system comprises a network communication component C, a voice conversion character component, a natural semantic information extraction component, a natural language interaction component and a character synthesis voice component, a user awakens the client subsystem through an awakening language and describes own diseases and symptoms by using the natural language according to voice guidance played by the client subsystem, and the service terminal system completes extraction of the information of the diseases and symptoms described by the user through analysis and processing of voice data streams provided by the client subsystem. The microphone component of the client subsystem is in a monitoring state by default, a user wakes up the client subsystem through a wake-up word, the client subsystem plays guide voice through the loudspeaker component, and then the microphone component enters the monitoring state; the user describes his disease and symptoms in natural language according to the guidance voice prompt. The client subsystem collects the user voice data stream through the microphone component and submits the user voice data stream to the network communication component B in real time; the network communication component B transmits the voice data stream to a network communication component C of the service terminal system through the Internet, and the client subsystem enters a waiting state; the network communication part C in the service terminal system submits the received voice data stream to the voice conversion character part in real time. The voice conversion character part converts the natural voice data stream into natural language text information, and then submits the natural language text information to the natural semantic information extraction part in real time.