CN117672549A - IVR-based AI doctor remote inquiry method and system - Google Patents
IVR-based AI doctor remote inquiry method and system Download PDFInfo
- Publication number
- CN117672549A CN117672549A CN202311644061.7A CN202311644061A CN117672549A CN 117672549 A CN117672549 A CN 117672549A CN 202311644061 A CN202311644061 A CN 202311644061A CN 117672549 A CN117672549 A CN 117672549A
- Authority
- CN
- China
- Prior art keywords
- voice
- text
- ivr
- inquiry
- server
- 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
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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention provides an IVR-based AI doctor remote inquiry method, which comprises the following steps: creating a voice session channel according to the number of the user terminal, and acquiring user voice data; executing a voice-to-text instruction according to the user voice data to obtain a text problem, wherein the voice-to-text instruction comprises submitting a voice server to execute a voice-to-text request according to the user voice data; executing an AI inquiry instruction according to the text question to obtain an AI text answer, wherein the AI inquiry instruction comprises submitting an AI server to execute an inquiry request according to the text question and the user terminal number; executing a text-to-speech instruction according to the AI text answer to obtain a consultation result speech file; and executing a playing instruction according to the inquiry result voice file, and sending voice data to the user terminal. Solves the problems that the remote inquiry of people with vision impairment lacks a communication channel with doctors and realizes a platform.
Description
Technical Field
The invention belongs to the field of IVR and computers, and particularly relates to an AI doctor remote consultation method and system based on IVR.
Background
In the modern medical field, artificial Intelligence (AI) is increasingly used. The AI doctor question and answer system can provide convenient medical consultation and suggestion for the user. However, conventional doctor question-answering systems typically require a user to interact literally via the internet, which has limitations for some users who cannot access the internet or are unfamiliar with using the internet, such as lack of communication channels and implementation platforms for remote questions by visually impaired people.
Disclosure of Invention
The embodiment aims to provide an IVR-based AI doctor remote inquiry method and system, which solve the problems that the remote inquiry of visually impaired people lacks a communication channel with doctors and a platform is realized.
The invention provides an IVR-based AI doctor remote inquiry method, which comprises the following steps:
creating a voice session channel according to the number of the user terminal, and acquiring user voice data;
executing a voice text conversion instruction according to the user voice data to obtain a text problem, wherein the voice text conversion instruction comprises submitting a voice text conversion server to execute a voice text conversion request according to the user voice data;
executing an AI inquiry instruction according to the text question to obtain an AI text answer, wherein the AI inquiry instruction comprises submitting an AI server to execute an inquiry request according to the text question and the user terminal number;
executing a text-to-speech instruction according to the AI text answer to obtain a consultation result speech file;
executing a terminal playing instruction according to the inquiry result voice file, wherein the terminal playing instruction comprises sending voice data to the user terminal according to the voice session channel.
Further, creating a voice session channel according to the number of the user terminal includes: executing a link creation instruction according to the user terminal number to create a voice session channel;
if the voice conversation channel is successfully established, playing an IVR voice guiding instruction according to the conversation channel;
and acquiring user inquiry requirements including AI inquiry and manual inquiry according to the IVR voice guiding instruction.
Further, a voice session channel is created, including process creation or thread creation.
Further, obtaining user voice data includes: and executing the voice recording of the user according to the voice session channel to acquire the inquiry voice file.
Further, acquiring the inquiry voice file further comprises executing the user voice data encoding instruction.
Further, the text problem is obtained, and the method further comprises the steps of executing text noise removal and correcting misspelling instructions according to the text problem.
Further, the acquired AI text answer format includes JSON strings.
Further, the AI text answer executes a text-to-speech instruction to obtain a query result speech file, and further includes parsing the JSON result string to obtain a speech file download address.
The invention also provides an AI doctor remote consultation system based on IVR, which comprises a user terminal, an IVR server, a voice-to-text server, a text-to-voice server and an AI consultation server; the IVR server is used for: receiving a call instruction, acquiring a user terminal number and creating a voice session channel;
the user terminal is used for acquiring user voice input and key input;
the voice-to-text server is used for responding to a voice-to-text request initiated by the IVR server;
the text-to-speech server is used for responding to a text-to-speech request initiated by the IVR server and providing a download address of the text-to-speech file, and the download address is used for the IVR server to acquire the text-to-speech file in a download mode;
the AI inquiry server is used for responding to the AI text inquiry request initiated by the IVR server.
Further, the IVR server is further configured to play the query result according to the voice session channel.
The IVR-based AI doctor remote inquiry method and system solve the problems that the remote inquiry of visually impaired people lacks a communication channel with doctors and realizes a platform
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1: the method step diagram of the IVR-based AI doctor remote inquiry method provided by the embodiment of the invention;
fig. 2: the invention provides a remote consultation system framework diagram of an IVR-based AI doctor;
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.
An IVR-based AI doctor remote inquiry method (see fig. 1) comprising:
s1100: according to the user terminal number, a voice session channel is created, user voice data is obtained, in this embodiment, an IVR server responds to a dial-in service request of dialing a special service number by a user through an exchange or a base station of an operator, for example 96xxx, obtains a terminal number of the dial-in user according to a data interaction protocol of the exchange of the operator, creates the voice session channel according to the dial-in terminal number, and establishes an IVR temporary session. The IVR server can use a creating thread mode and a creating process mode to create the voice session channel, and the creating thread mode consumes little system resources. The IVR temporary session in this step includes playing a preset IVR voice flow file according to the voice session channel and obtaining a user key input according to the IVR voice flow, where the IVR voice flow includes a voice content provided by a playing system, for example: the method comprises the steps of performing manual inquiry by a key 1 and AI inquiry by a key 2, further executing a delay instruction and waiting for a user to input a key to acquire user inquiry requirements, wherein an IVR voice flow file is prerecorded by an operator and placed at a corresponding disk position of an IVR server, the voice file format comprises wav, MP3, wma and other formats, the IVR server comprises a board card and an IVR flow execution program, the flow execution program comprises execution codes written in a language C, and step S1200;
s1200: according to the user voice data, executing a voice transfer text instruction to acquire a text problem, wherein the voice transfer text instruction comprises submitting a voice server to execute a voice transfer text request according to the user voice data, in the step, if a user inputs an AI inquiry for a number 2 key according to a user key, the IVR server plays a preset AI-IVR voice flow file according to the voice session channel, wherein the voice request comprises please speak your inquiry requirement after hearing a voice, the IVR server executes a start recording operation to acquire the voice data of the user through the voice session channel, and further converts the voice data into a waveform file, wherein the waveform file comprises a waveform file in a wav format, and further executes an encoding instruction to acquire an encoding file, the encoding instruction executes wav file compression for network transmission, and the encoding instruction comprises an A rate encoding, a U rate encoding, a G729 encoding, a G encoding, a GSM encoding, a G723 encoding, an MP3 encoding, an OGG encoding and the like, and the voice transfer text instruction is further executed by the IVR server according to the encoding file and a user terminal number, and the voice transfer text instruction comprises the IVR server initiates the voice transfer text request to the text request according to the user terminal number and the user terminal number. The technique also enables recognition of different accents and speech rates, ensuring accurate conversion of speech to text. Step S1300 is performed;
s1300: the AI inquiry instruction is executed according to the text question to obtain an AI text answer, the AI inquiry instruction comprises submitting an AI server to execute an inquiry request according to the text question and the user terminal number, the AI server is a third party server in the embodiment, the AI inquiry uses an interface mode to obtain an inquiry answer from the AI server, the executing AI inquiry instruction further comprises the IVR server executing the text question preformatted instruction to format the text question into a JSON format question, the JSON format question further comprises removing noise, correcting spelling errors and the like to improve the accuracy of the question, the further IVR server initiates the AI inquiry request according to the JSON format question, and the AI inquiry server analyzes the question and generates the text answer in the embodiment: the AI inquiry server uses natural language processing and machine learning algorithms to analyze and understand the user's questions, retrieve matching medical knowledge and databases, and generate corresponding text answers. The step of obtaining the AI text answer includes obtaining a return result string in JSON format. Step S1400 is performed;
s1400: according to the AI text answer, executing a text-to-speech instruction to obtain a consultation result speech file, wherein in the step, an IVR server obtains a JSON format word string of an AI text from an AI consultation server, and further executing to perform JSON format decoding to obtain the consultation result word string; the IVR server further executes a text-to-speech instruction, the text-to-speech instruction comprises that the IVR server initiates a text-to-speech request to the text-to-speech server according to the inquiry result string and the user terminal number to obtain a speech file, and the speech file is downloaded to a local disk of the IVR server from an address returned by the text-to-speech server in an address mode. In this step, the IVR server uses text-to-speech synthesis technology to convert the text answers into natural and smooth speech content. The synthesized speech content may be adjusted according to the user's preferences, such as speech rate, pitch, mood, etc. Step S1500 is performed;
s1500: and executing a playing instruction according to the voice file of the inquiry result, sending voice data to the user terminal, and executing the playing of the voice file by the IVR server according to the voice session channel. The voice file in this embodiment is read by the IVR server and decoded into PCM format, where the voice file in this embodiment is in a rate a coding format, and the voice format includes a rate a, a rate U, or GSM, which are not limited in this embodiment. The method further comprises the step of executing a recording waiting instruction after playing the voice file, wherein the recording waiting instruction is used for receiving a follow-up inquiry instruction which is continuously executed by a user in a voice mode. The recording waiting instruction comprises a prompt guiding voice IVR flow file which is played after the recording file is played, wherein the prompt guiding voice IVR flow file comprises a prompt instruction that the content is an answer result of an AI doctor, and a user can continue to ask questions after hearing dripping sounds, and can hear answers of the AI doctor through a telephone and further communicate or ask questions.
The embodiment also provides an AI doctor remote consultation system based on IVR, wherein the (see figure 2) system comprises a user terminal, an IVR server, a voice-to-text server, a text-to-voice server and an AI consultation server; the IVR server is used for: receiving a call instruction, acquiring a user terminal number and creating a voice session channel;
the user terminal is used for acquiring user voice input and key input;
the voice-to-text server is used for responding to a voice-to-text request initiated by the IVR server;
the text-to-speech server is used for responding to the text-to-speech request initiated by the IVR server and providing a download address of the text-to-speech file, and is used for acquiring the text-to-speech file by the IVR server in a download mode;
the AI inquiry server is used for responding to an AI text inquiry request initiated by the IVR server;
the IVR server is further configured to play the inquiry result according to the voice session channel and execute a subsequent IVR voice command acquisition after the inquiry result is played, including playing the inquiry result, waiting until the user voice is subsequently input, and continuing to execute the user voice command in real time, where the voice command further includes detecting whether the user hangs up in real time, and if the user hangs up, executing resource recovery of the voice session channel, including releasing memory resources, releasing thread resources, and disconnecting session connection between the IVR server and the AI inquiry server.
The voice-to-text server, the text-to-voice server and the AI inquiry server are third party servers.
The IVR-based AI doctor remote inquiry method and system solve the problems that the remote inquiry of visually impaired people lacks a communication channel with doctors and a platform is realized.
The above embodiments of the present invention are only examples, and are not intended to limit the scope of the present invention, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An IVR-based AI doctor remote inquiry method, comprising:
creating a voice session channel according to the number of the user terminal, and acquiring user voice data;
executing a voice text conversion instruction according to the user voice data to obtain a text problem, wherein the voice text conversion instruction comprises submitting a voice text conversion server to execute a voice text conversion request according to the user voice data;
executing an AI inquiry instruction according to the text question to obtain an AI text answer, wherein the AI inquiry instruction comprises submitting an AI server to execute an inquiry request according to the text question and the user terminal number;
executing a text-to-speech instruction according to the AI text answer to obtain a consultation result speech file;
executing a terminal playing instruction according to the inquiry result voice file, wherein the terminal playing instruction comprises sending voice data to the user terminal according to the voice session channel.
2. The IVR-based AI doctor remote inquiry method of claim 1, wherein creating a voice session channel from a user terminal number includes: executing a link creation instruction according to the user terminal number to create a voice session channel;
if the voice conversation channel is successfully established, playing an IVR voice guiding instruction according to the conversation channel;
and acquiring user inquiry requirements including AI inquiry and manual inquiry according to the IVR voice guiding instruction.
3. The IVR-based AI doctor remote interrogation method of claim 2, wherein the creating a voice session channel includes process creation or thread creation.
4. The IVR-based AI doctor remote inquiry method of claim 1, wherein the acquiring user voice data includes: and executing the voice recording of the user according to the voice session channel to acquire the inquiry voice file.
5. The IVR-based AI doctor remote interrogation method of claim 4, wherein the obtaining an interrogation voice file further includes executing the user voice data encoding instructions.
6. The IVR-based AI doctor remote interrogation method of claim 1, wherein the obtaining text questions further includes performing text de-noising, correcting misspellings instructions based on the text questions.
7. The IVR-based AI doctor remote inquiry method of claim 1, wherein the acquired AI text answer format includes JSON strings.
8. The IVR-based AI doctor remote consultation method according to claim 1, further comprising analyzing JSON result strings to obtain a voice file download address by executing a text-to-voice instruction to obtain a consultation result voice file according to the AI text answer.
9. An IVR-based AI doctor remote inquiry system is characterized by comprising a user terminal, an IVR server, a voice-to-text server, a text-to-voice server and an AI inquiry server; the IVR server is used for: receiving a call instruction, acquiring a user terminal number and creating a voice session channel;
the user terminal is used for acquiring user voice input and key input;
the voice-to-text server is used for responding to a voice-to-text request initiated by the IVR server;
the text-to-speech server is used for responding to a text-to-speech request initiated by the IVR server and providing a download address of the text-to-speech file, and the download address is used for the IVR server to acquire the text-to-speech file in a download mode;
the AI inquiry server is used for responding to the AI text inquiry request initiated by the IVR server.
10. The IVR-based AI doctor remote inquiry system of claim 9, wherein the IVR server is further configured to play the inquiry results according to the voice conversation path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311644061.7A CN117672549A (en) | 2023-11-30 | 2023-11-30 | IVR-based AI doctor remote inquiry method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311644061.7A CN117672549A (en) | 2023-11-30 | 2023-11-30 | IVR-based AI doctor remote inquiry method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117672549A true CN117672549A (en) | 2024-03-08 |
Family
ID=90069310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311644061.7A Pending CN117672549A (en) | 2023-11-30 | 2023-11-30 | IVR-based AI doctor remote inquiry method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117672549A (en) |
-
2023
- 2023-11-30 CN CN202311644061.7A patent/CN117672549A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111246027B (en) | Voice communication system and method for realizing man-machine cooperation | |
| CN111739519B (en) | Speech recognition-based dialogue management processing method, device, equipment and medium | |
| CN110751943A (en) | Voice emotion recognition method and device and related equipment | |
| EP1602102B1 (en) | Management of conversations | |
| US7644000B1 (en) | Adding audio effects to spoken utterance | |
| US7711105B2 (en) | Methods and apparatus for processing foreign accent/language communications | |
| CN100424632C (en) | Semantic object synchronous understanding for highly interactive interface | |
| CN111128126A (en) | Multi-language intelligent voice conversation method and system | |
| US8457973B2 (en) | Menu hierarchy skipping dialog for directed dialog speech recognition | |
| CN113362828A (en) | Method and apparatus for recognizing speech | |
| KR20160077190A (en) | Natural expression processing method, processing and response method, device, and system | |
| CN107133709B (en) | Quality inspection method, device and system for customer service | |
| CN110138654B (en) | Method and apparatus for processing speech | |
| US20080147395A1 (en) | Using an automated speech application environment to automatically provide text exchange services | |
| US20190121860A1 (en) | Conference And Call Center Speech To Text Machine Translation Engine | |
| US20010056345A1 (en) | Method and system for speech recognition of the alphabet | |
| EP1382032B1 (en) | Web-based speech recognition with scripting and semantic objects | |
| US7885391B2 (en) | System and method for call center dialog management | |
| CN117672549A (en) | IVR-based AI doctor remote inquiry method and system | |
| CN109616116B (en) | Communication system and communication method thereof | |
| RU2763691C1 (en) | System and method for automating the processing of voice calls of customers to the support services of a company | |
| CN113763921B (en) | Method and device for correcting text | |
| CN115602172A (en) | An intelligent outbound call method and system | |
| CN115050351A (en) | Method and device for generating timestamp and computer equipment | |
| US20060265225A1 (en) | Method and apparatus for voice recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |