Method and system for automatically judging telephone state of virtual number by intelligent outbound robot

Abstract

The invention discloses a method and system for an intelligent outbound robot to automatically judge the telephone state of a virtual number, and the method comprises the steps: enabling the intelligent outbound robot to call out the virtual number, and receiving a communication command of a virtual telephone platform; after the intelligent outbound robot receives a communication receiving command of the virtual telephone platform, voice recognition is started; if the voice recognition system of the intelligent outbound robot does not detect human voice within preset time, the intelligent outbound robot actively hangs up; and if the voice recognition system of the intelligent outbound robot detects answering voice, performing voice interaction with a user. According to the method and the system, the processing efficiency of the outbound virtual number of the robot can be greatly improved, the occupation of line and system loads is reduced, and the generation of invalid dialogue data is avoided.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent telephone voice robots, and mainly relates to a method and system for an intelligent outbound calling robot to automatically identify the telephone status of a virtual number. Background Art

[0002] A virtual number is a phone number that does not rely on a traditional physical SIM card. It is a digital ID based on network technology that can be generated and used through software or online services. As a telephone bridging method that hides the user's real mobile phone number, virtual numbers effectively protect user privacy concerns and are widely used in taxi-hailing, food delivery and other fields.

[0003] Enterprise outbound call robot is an automatic telephone calling system based on artificial intelligence technology, which can simulate real people to communicate with users by voice. Enterprises usually have the need for outbound call virtual numbers for enterprise outbound call robot systems.

[0004] In the outbound call robot system in the prior art, the virtual number is usually provided by the cloud communication service provider. The process of the robot calling the virtual number is generally as follows:

[0005] Robot outbound calls;

[0006] The service provider's telephone system receives the outbound call request; at this point, the outbound call is already connected for the robot;

[0007] The service provider performs secondary dialing and calls the real phone number mapped by the user.

[0008] The signaling of whether the real phone is connected during the second dialing will not be transmitted to the robot system again through the service provider. As a result, the robot system in the prior art cannot effectively determine whether the call is actually answered by the user through the signaling when calling the virtual number, and thus cannot effectively guide the robot to interact with the user in multiple rounds of voice, resulting in many invalid outbound interactions. Summary of the invention

[0009] In order to solve the above-mentioned problems existing in the prior art, the present invention adopts voice recognition technology. When the telephone robot calls a virtual number, it is first connected by the virtual telephone platform. At this time, the connection command is only for the platform to connect. The telephone robot starts voice recognition and waits for the user's mobile phone to answer. If the user answers, the human voice activity is detected. If the human voice is detected, it is considered that the user has answered. Otherwise, if the human voice is not detected within a predetermined timeout period, it is considered that the user has not answered, and the call is hung up, thereby realizing automatic judgment of the connection of the virtual number user.

[0010] The present invention provides a method for an intelligent outbound calling robot to automatically identify the telephone status of a virtual number, comprising the following steps:

[0011] The intelligent outbound calling robot calls the virtual number and receives the answering command from the virtual telephone platform;

[0012] After receiving the answering command from the virtual telephone platform, the intelligent outbound calling robot starts voice recognition;

[0013] If the voice recognition system of the intelligent outbound call robot does not detect a human voice within a predetermined time, the intelligent outbound call robot will actively hang up; if the voice recognition system of the intelligent outbound call robot detects a human voice, it will interact with the user by voice.

[0014] Furthermore, after the intelligent outbound calling robot makes an outbound call to the virtual number, the virtual number service provider receives an incoming call event of the virtual number and connects the call. At the same time, the virtual number service provider sends a connection command to the intelligent outbound calling robot and dials the user's real phone number for a second time.

[0015] Furthermore, the voice interaction with the user includes: starting prompt playback, collecting user voice input, voice recognition of the user's voice, converting it into text and performing semantic understanding, performing corresponding voice playback or other responses based on the semantic understanding results, repeating multiple rounds of interaction with the user to complete the call task.

[0016] Furthermore, the speech recognition system includes a speech recognition engine; the speech recognition engine adopts a deep neural network, uses a large amount of human voice corpus for training, filters non-human voice interference, and can accurately judge human speech.

[0017] The present invention provides an intelligent outbound call robot system, comprising an outbound call module, a speech recognition module, a speech synthesis module, and a conversation management module;

[0018] The outbound calling module is used to call a virtual number to a virtual number service provider and receive a call receiving command sent by the virtual number service provider;

[0019] The voice recognition module is used to start detecting human voice after the outbound call module receives the receiving signal;

[0020] If the voice recognition module does not detect a human voice within a predetermined time, it is considered that the virtual number service provider's secondary dialing is not answered by the user, and the outbound call module hangs up; if the voice recognition module detects a human voice, the voice recognition result is transferred to the session management module;

[0021] The session management module is used to manage and control the voice interaction process with the user;

[0022] The speech synthesis module is used to convert text information into spoken speech output according to the instructions of the conversation management module.

[0023] The present invention uses voice recognition to determine whether the user answers the call. The voice recognition engine uses a deep neural network to train a large amount of human voice data, which can accurately determine the human voice and filter out non-human voice interference such as environmental noise. Compared with the conventional telephone robot system that does not have voice to determine whether the virtual number is connected, it can more accurately determine whether the user's call is actually connected. This method can greatly improve the processing efficiency of the robot's outbound calls to virtual numbers, reduce the occupation of lines and system loads, and avoid the generation of invalid conversation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] For a more complete understanding of the present invention, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

[0025] Figure 1 A schematic flow chart of a method for automatically determining the status of a virtual number phone by an intelligent outbound calling robot provided by the present invention;

[0026] Figure 2 Schematic diagram of the intelligent outbound call robot system provided by the present invention. DETAILED DESCRIPTION

[0027] In order to make the problems, technical solutions and technical effects to be solved by the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments and obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0028] Before describing the exemplary embodiments of the present invention in more detail, it should be noted that although the flowchart of the present invention describes the operations as a sequential processing mode, many of the operation steps can be implemented in parallel or simultaneously, and the order of the operations can also be rearranged as needed. In addition, the processing can be terminated when the operation is completed, but there can also be additional steps not included in the drawings.

[0029] In the following description, the terms "first, second, third", etc. are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first, second, third", etc. can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0030] Embodiment 1

[0031] The present invention provides a method for an intelligent outbound calling robot to automatically identify the status of a virtual number phone. Figure 1 , the method comprises the following steps:

[0032] Step S01: The intelligent outbound calling robot calls a virtual number and receives a call-answering command from the virtual telephone platform.

[0033] After the intelligent outbound call robot calls the virtual number, the virtual number service provider receives the incoming call event of the virtual number and connects the call. At the same time, the virtual number service provider sends a connection command to the intelligent outbound call robot. However, the connection is only answered by the service provider's telephone system, not by the user.

[0034] After receiving the call from the intelligent outbound calling robot and answering the call, the virtual number service provider dials the user's real phone number for the second time.

[0035] Step S02: After receiving the answering command from the virtual telephone platform, the intelligent outbound call robot starts voice recognition; if the voice recognition system of the intelligent outbound call robot does not detect a human voice within a predetermined time, the intelligent outbound call robot actively hangs up; if the voice recognition system of the intelligent outbound call robot detects a human voice, it interacts with the user.

[0036] The speech recognition system is first used to detect human voice. If the speech recognition system of the intelligent outbound call robot does not detect human voice within a predetermined time, it is considered that the virtual number service provider's secondary dialing is not answered by the user, and the intelligent outbound call robot actively hangs up; if the speech recognition system of the intelligent outbound call robot detects a human voice, it interacts with the user.

[0037] After detecting the answering voice, the speech recognition system starts playing prompts, collects user voice input, recognizes the user's voice, converts it into text and performs semantic understanding, plays corresponding voice or other responses based on the semantic understanding results, and repeats multiple rounds of interactions with the user to complete the call task.

[0038] The method of the present invention uses voice recognition to determine whether the user answers the call and speaks, and the voice recognition system includes a voice recognition engine.

[0039] Preferably, the speech recognition engine uses a deep neural network, uses a large amount of human voice data for training, filters non-human voice interference such as environmental noise, and can accurately determine human speech. Compared with conventional telephone robot systems that do not use voice to determine whether a virtual number is connected, it can more accurately determine whether the user's phone is actually connected.

[0040] Embodiment 2

[0041] The present invention provides an intelligent outbound call robot system, as shown in the accompanying drawings of the specification Figure 2 As shown, the intelligent outbound call robot system includes an outbound call module, a speech recognition module, a speech synthesis module, and a session management module.

[0042] The outbound calling module is used to call a virtual number to a virtual number service provider and receive a call receiving command sent by the virtual number service provider.

[0043] The voice recognition module is used to start detecting human voice after the outbound call module receives the receiving signal.

[0044] The speech recognition module includes a speech recognition engine, which uses a deep neural network, uses a large amount of human voice data for training, filters non-human voice interference such as environmental noise, and can accurately determine whether a person is speaking. Compared with conventional telephone robot systems that do not use voice to determine whether a virtual number is connected, it can more accurately determine whether the user's call is actually connected.

[0045] If the voice recognition module does not detect a human voice within a predetermined time, it is considered that the virtual number service provider's secondary dialing is not answered by the user, and the outbound call module hangs up; if the voice recognition module detects an answering human voice, the result of the voice recognition is transferred to the session management module.

[0046] The session management module is used to manage and control the voice interaction process with the user, including session initialization, intent recognition, dialogue management, context understanding, multi-round dialogue processing, exception handling, user intent confirmation, data collection and analysis, and other functions.

[0047] The speech synthesis module is used to convert text information into spoken speech output according to the instructions of the conversation management module.

[0048] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, no matter from which aspect, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the description of the above embodiments, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for an intelligent outbound calling robot to automatically determine the telephone status of a virtual number, comprising the following steps: The intelligent outbound calling robot calls the virtual number and receives the answering command from the virtual telephone platform; After receiving the answering command from the virtual telephone platform, the intelligent outbound calling robot starts voice recognition; If the voice recognition system of the intelligent outbound call robot does not detect a human voice within a predetermined time, the intelligent outbound call robot will actively hang up; if the voice recognition system of the intelligent outbound call robot detects a human voice, it will interact with the user by voice.

2. The method according to claim 1, characterized in that After the intelligent outbound calling robot makes an outbound call to the virtual number, the virtual number service provider receives an incoming call event of the virtual number and connects the call. At the same time, the virtual number service provider sends a connection command to the intelligent outbound calling robot and dials the user's real phone number for a second time.

3. The method according to claim 1, characterized in that The voice interaction with the user includes: starting prompt playback, collecting user voice input, voice recognition of the user's voice, converting it into text and performing semantic understanding, performing corresponding voice playback or other responses based on the semantic understanding results, repeating multiple rounds of interaction with the user to complete the call task.

4. The method according to claim 1, characterized in that The speech recognition system includes a speech recognition engine; the speech recognition engine adopts a deep neural network, uses a large amount of human voice corpus for training, filters non-human voice interference, and can accurately judge human speech.

5. An intelligent outbound call robot system, comprising an outbound call module, a speech recognition module, a speech synthesis module, and a conversation management module; in, The outbound calling module is used to call a virtual number to a virtual number service provider and receive a call receiving command sent by the virtual number service provider; The voice recognition module is used to start detecting human voice after the outbound call module receives the receiving signal; If the voice recognition module does not detect a human voice within a predetermined time, it is considered that the virtual number service provider's secondary dialing is not answered by the user, and the outbound call module hangs up; if the voice recognition module detects a human voice, the voice recognition result is transferred to the session management module; The session management module is used to manage and control the voice interaction process with the user; The speech synthesis module is used to convert text information into spoken speech output according to the instructions of the conversation management module.

6. The system according to claim 5, characterized in that The virtual number service provider receives the incoming call event of the virtual number of the outbound call module and answers the call. At the same time, the virtual number service provider sends a call answering command to the outbound call module and dials the user's real phone number for a second time.

7. The system according to claim 5, characterized in that The conversation management module, the speech recognition module, and the speech synthesis module are used to start prompt playback, collect user voice input, recognize user voice, convert it into text and perform semantic understanding, perform corresponding voice playback or other responses based on the semantic understanding results, and repeat multiple rounds of interactions with the user to complete the call task.

8. The system according to claim 5, characterized in that The speech recognition module includes a speech recognition engine; the speech recognition engine adopts a deep neural network, uses a large amount of human voice corpus for training, filters non-human voice interference, and can accurately judge human speech.

Images