CN115002283A - Virtual digital man-machine telephone answering system and method - Google Patents
Virtual digital man-machine telephone answering system and method Download PDFInfo
- Publication number
- CN115002283A CN115002283A CN202210840722.2A CN202210840722A CN115002283A CN 115002283 A CN115002283 A CN 115002283A CN 202210840722 A CN202210840722 A CN 202210840722A CN 115002283 A CN115002283 A CN 115002283A
- Authority
- CN
- China
- Prior art keywords
- call
- virtual digital
- service
- video
- conversation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/42212—Call pickup
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/487—Arrangements for providing information services, e.g. recorded voice services or time announcements
- H04M3/493—Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
- H04M3/4936—Speech interaction details
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/54—Arrangements for diverting calls for one subscriber to another predetermined subscriber
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Human Computer Interaction (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a virtual digital man-telephone answering system, wherein a user use interface is arranged at the front end, and a conversation control subsystem and a communication interaction center are arranged at the rear end; the dialogue control subsystem is integrated with a communication network voice service, a 5G video access service, an audio and video communication exchange service, a client audio and video interaction flow service, an ASR/TTS service and an NLP intention identification service; the communication interaction center is in butt joint with an operator network, and whether the call number label is answered by a person or not is judged to be transferred to the virtual digital person or not; the virtual digital person discriminates the call scenes based on the conversation control subsystem, so that different scene conversations are switched, call contents are recorded in the form of audio, video and characters at the same time, and the call contents are sent to the mobile phone of the user after the call is finished. The virtual digital man-machine telephone answering system and the method thereof are adopted to automatically identify the conversation scene, the feedback forms are flexible and various, the user can be effectively prevented from missing important calls, and the use experience of the user is improved.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a virtual digital man-machine telephone answering system and a virtual digital man-machine telephone answering method.
Background
At present, two methods for realizing the communication response scheme are mainly available. Firstly, when an external telephone is accessed, the system provides recording and message leaving functions and forwards the recording and message leaving functions to a client; and secondly, the virtual robot performs man-machine interaction, converts the voice of the opposite user into a text and records the text, and then replies the set response voice to the opposite user.
The two schemes have the following problems: 1) the method is not friendly to the users of the mobile phone, only can feed back the incoming call content in a text or voice form, and cannot present the incoming call content to the virtual image of the client in an image and video mode; 2) in the incoming call process, a specific scene cannot be identified, and balance points of 'call answering required', 'harassing call receiving afraid' and 'easy missed call receiving' cannot be found.
Disclosure of Invention
The invention aims to provide a virtual digital man-machine telephone answering system and a virtual digital man-machine telephone answering method, which are used for solving the problems that the existing communication automatic answering mode is rigid, poor in reliability, incapable of identifying a conversation scene and easy to leak important telephones.
In order to achieve the above object, the present invention provides a technical solution,
a virtual digital man-telephone answering system, the front end sets up the user interface, the back end sets up the dialogue control subsystem and communication interaction center; the dialogue control subsystem is integrated with a communication network voice service, a 5G video access service, an audio and video communication exchange service, a client audio and video interaction flow service, an ASR/TTS service and an NLP intention identification service; the communication interaction center is in butt joint with an operator network, and whether the call number label is answered by a person or not is judged to be transferred to the virtual digital person or not; the virtual digital person discriminates the call scenes based on the conversation control subsystem, so that different scene conversations are switched, call contents are recorded in the form of audio, video and characters at the same time, and the call contents are sent to the mobile phone of the user after the call is finished.
Preferably, the communication interaction center establishes a soft switch and a signaling protocol based on the SIP server to realize the transfer of the incoming call session.
Preferably, the virtual digital person simulates the response mode of the real person by calling the fixed virtual character, and displays the graphic image.
Preferably, the communication interaction center establishes a harassment interception list according to the big data, and filters the incoming call number according to the harassment interception list.
Corresponding to the system, the invention also provides a virtual digital man-machine response method, which comprises the following steps,
s1: starting up and waiting; initializing a telephone answering system and monitoring events;
s2: judging an incoming call; the communication interaction center identifies the incoming call number; if the incoming call number is in the harassment interception list, ending the call; otherwise, switching judgment is carried out, namely S3 is carried out;
s3: switching judgment; judging the waiting answering time by the communication interaction center; if the waiting answering time does not exceed the threshold value, waiting for the called user of the local machine to answer; otherwise, automatically switching to the virtual digital person, namely entering S4;
s4: intelligent response; the virtual digital man calls the virtual role, then identifies the conversation content by means of ASR/TTS technology and NLP technology, judges the conversation scene and carries out multi-turn conversation;
s5: recording the call; the virtual digital person arranges the conversation content in the form of audio, video and characters, and sends the conversation content to the mobile phone of the user after the conversation is finished.
Preferably, the step of S4 specifically includes,
s41: the conversation control subsystem judges the incoming call mode to determine whether to start the video call mode of the virtual digital person;
s42: the dialogue control subsystem carries out VAD detection on the audio data and automatically separates each section of audio file;
s43: the digital robot converts the voice into text based on ASR technology;
s44: the digital robot identifies the text based on an NLP intention identification technology and switches different scene dialogues;
s45: the digital robot performs text-to-speech conversion based on TTS technology and performs multiple rounds of conversations with the caller.
The virtual digital man-machine telephone answering system and the method have the following advantages that:
1. a virtual digital human intelligent response system aiming at individual users is created, and the requirements of specific market scale are met. The video call function of the virtual digital person is realized by means of artificial intelligent images and natural language processing technology.
2. The purpose of preventing harassment is as follows: according to the user setting, the product can actively intercept the incoming call blacklist user, also can identify a specific scene in the process of receiving the incoming call instead of the incoming call, and call the virtual digital human image to perform specific reply or hang up.
3. After the conversation is finished, the virtual digital person response system sends conversation contents to a mobile phone of a user in various forms such as audio, characters, video and the like, and the information acquisition efficiency is improved.
Drawings
FIG. 1 is an overall configuration diagram of a virtual digital man phone answering system according to the present invention;
FIG. 2 is a response flow diagram of the virtual digital personal telephone response system of the present invention;
FIG. 3 is a front end functional block diagram of a virtual digital man phone answering system in accordance with the present invention;
FIG. 4 is a flow chart of front end applet client configuration management in accordance with the present invention;
FIG. 5 is a front-end public function block diagram of the present invention;
FIG. 6 is a block diagram of a front-end background information management function of the present invention;
FIG. 7 is a block diagram of an artificial intelligence enabled platform for foreground invocation in the present invention;
FIG. 8 is a diagram of the virtual digital man phone answering system architecture of the present invention;
FIG. 9 is a diagram of a platform for deploying a virtual digital personal telephone answering system in accordance with the present invention;
fig. 10 is a diagram of a deployment scenario for SIP servers in the present invention.
Detailed Description
The technical scheme of the invention is further explained by combining the drawings and the embodiment.
Example 1
The virtual digital man-phone answering system shown in fig. 1 is divided into two parts, the back end is a conversation control subsystem and a communication interaction center, and the front end is a customer using interface.
The dialogue control subsystem integrates services of AI capability butt joint, such as communication network voice service, 5G video access service, audio and video communication exchange service, client audio and video interaction flow service, ASR/TTS (automatic speech recognition technology/text-to-speech conversion) and the like. The audio and video exchange service needs to be developed for the second time based on a soft exchange Freeswitch project. The conversation control system and the communication interaction center are the core of a virtual digital human response system, comprise the core 5G digital human video, voice recognition, natural semantic understanding, voice synthesis, conversation management and other complete AI capabilities, and are comprehensively responsible for the management of conversation contents in the process of answering a call by a user so as to realize intelligent response.
The communication interaction center is connected with an operator network, a user calls and then transfers to the communication interaction center, the system judges whether the call is transferred to the conversation robot, and the communication interaction center has the functions of number line resource management, number routing, recording management and the like. Under the scenes of unavailable answering or on-hook and the like, when the virtual digital person helps the user to answer the incoming call, multiple rounds of conversations corresponding to the scenes can be made according to the content of the incoming call, if the incoming call scene is identified as real estate, the virtual digital person can continuously inquire information such as a building address and a selling price, and the user is helped not to miss important information. After the call is finished, the virtual digital person transcribes the call content into characters/audio/video and sends the characters/audio/video to the mobile phone of the user, and therefore information acquisition efficiency is improved.
As shown in fig. 3-7, the front-end client interface is provided for use by the user. After the general user opens the service, the general user can set the service, check the incoming call record, receive the incoming call push ticket in the WeChat applet, the public number, the webpage and the like. The user configures the applet end as shown in figure 4.
As shown in fig. 8, the present system is built using the following framework model. The technical architecture comprises 4 layers: user interface layer, capability layer, storage layer. The user interface layer (Web), provides the user interface through HTML Web pages and VUE front end frameworks. And the service layer adopts a SPRING BOOT framework based on a micro-service technology, a DUBBO framework based on distributed RPC and an FS system supporting voice interaction to realize service logic. The capability layer realizes speech recognition, dialogue generation and speech synthesis through processing engines such as natural language processing NLP, automatic speech recognition ASR, speech synthesis TTS and the like; the service of the virtual digital human adopts a method of calling the fixed virtual role to call the existing virtual digital human interface subsystem. And calling the image of the digital virtual human, simulating a response system of a real human, and displaying the graphic image. And the storage layer is provided with a MySQL database, an elastic search storage and a distributed cluster memory database Redis to support the storage and the quick query of voice data.
As shown in fig. 9, the platform deployment of the system mainly includes two major aspects, namely, a service application layer and a communication interaction layer. The business application layer mainly completes foreground interface configuration and core service. The communication interaction layer completes 5G video service access by means of a communication platform and introduces a third-party technology. Specifically, the communication platform completes call forwarding/pushing through the soft switch cluster, introduces AI services such as ASR, TTS and the like by means of the interface cluster, and builds other services required by the system by means of the middleware cluster.
As shown in fig. 10, the soft switch cluster service of the communication platform is mainly implemented by means of SIP servers. The SIP server establishes a soft switch and signaling protocol to establish, configure and terminate sessions between two endpoints on the network. It can also be used for instant messaging, online information or file transfer. Typically, the SIP server does not participate in the media processing process. In SIP networks, media generally always uses end-to-end negotiation. In some special cases or service processes, such as Music On Hold, the SIP server may actively participate in media negotiation.
Example 2
The virtual digital man-phone answering method as shown in fig. 2, includes,
s1: starting up and waiting; initializing a telephone answering system and monitoring events;
s2: judging an incoming call; the communication interaction center identifies the incoming call number; if the incoming call number is in the harassment interception list, ending the call; otherwise, switching judgment is carried out, namely S3 is carried out;
s3: switching judgment; the communication interaction center judges the waiting answering time; if the waiting time does not exceed the threshold value, waiting for the called user of the local machine to answer; otherwise, automatically switching to the virtual digital person, namely entering S4;
s4: intelligent response; the virtual digital man calls the virtual role, then recognizes the conversation content by means of ASR/TTS technology and NLP technology, judges the conversation scene and carries out multi-turn conversation; the steps are specifically as follows, and the steps are as follows,
s41: the conversation control subsystem judges the incoming call mode to determine whether to start the video call mode of the virtual digital person;
s42: the dialogue control subsystem carries out VAD detection on the audio data and automatically separates each section of audio file;
s43: the digital robot converts the voice into text based on ASR technology;
s44: the digital robot identifies the text based on an NLP intention identification technology and switches different scene dialogues;
s45: the digital robot performs text-to-speech conversion based on TTS technology and performs multiple rounds of conversations with the caller.
S5: recording the call; the virtual digital person arranges the conversation content in the form of audio, video and characters, and sends the conversation content to the mobile phone of the user after the conversation is finished.
The above is a specific embodiment of the present invention, but the scope of the present invention should not be limited thereto. Any changes or substitutions which can be easily made by those skilled in the art within the technical scope of the present invention disclosed herein shall be covered by the protection scope of the present invention, and therefore the protection scope of the present invention shall be subject to the protection scope defined by the appended claims.
Claims (6)
1. A virtual digital man-telephone answering system is characterized in that a user using interface is arranged at the front end, and a conversation control subsystem and a communication interaction center are arranged at the rear end; the dialogue control subsystem is integrated with a communication network voice service, a 5G video access service, an audio and video communication exchange service, a client audio and video interaction flow service, an ASR/TTS service and an NLP intention identification service; the communication interaction center is in butt joint with an operator network, and whether the call number label is answered by a person or not is judged to be transferred to the virtual digital person or not; the virtual digital person discriminates the call scenes based on the conversation control subsystem, so that different scene conversations are switched, call contents are recorded in the form of audio, video and characters at the same time, and the call contents are sent to the mobile phone of the user after the call is finished.
2. The telephone answering system according to claim 1, wherein the communication interaction center establishes a soft switch and a signaling protocol based on the SIP server to effect the transfer of the incoming call session.
3. The telephone answering system according to claim 1, wherein the virtual digital person simulates a real person's answering mode by calling a fixed virtual character, and performs display of a graphic image.
4. The telephone answering system according to claim 1, wherein the communication interaction center establishes a harassment interception list according to the big data, and filters the incoming telephone numbers according to the harassment interception list.
5. A virtual digital man-machine answering method, comprising,
s1: starting up and waiting; initializing a telephone answering system and monitoring events;
s2: judging an incoming call; the communication interaction center identifies the incoming call number; if the incoming call number is in the harassment interception list, ending the call; otherwise, switching judgment is carried out, namely S3 is carried out;
s3: switching judgment; judging the waiting answering time by the communication interaction center; if the waiting answering time does not exceed the threshold value, waiting for the called user of the local machine to answer; otherwise, automatically switching to the virtual digital person, namely entering S4;
s4: intelligent response; the virtual digital man calls the virtual role, then recognizes the conversation content by means of ASR/TTS technology and NLP technology, judges the conversation scene and carries out multi-turn conversation;
s5: recording the call; the virtual digital person arranges the conversation content in the form of audio, video and characters, and sends the conversation content to the mobile phone of the user after the conversation is finished.
6. The telephone answering method according to claim 5, wherein the step S4 specifically includes,
s41: the conversation control subsystem judges the incoming call mode to determine whether to start the video call mode of the virtual digital person;
s42: the dialogue control subsystem carries out VAD detection on the audio data and automatically separates each section of audio file;
s43: the digital robot converts the voice into text based on ASR technology;
s44: the digital robot identifies the text based on an NLP intention identification technology and switches different scene dialogues;
s45: the digital robot performs text-to-speech conversion based on TTS technology and performs multiple rounds of conversations with the caller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210840722.2A CN115002283A (en) | 2022-07-18 | 2022-07-18 | Virtual digital man-machine telephone answering system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210840722.2A CN115002283A (en) | 2022-07-18 | 2022-07-18 | Virtual digital man-machine telephone answering system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115002283A true CN115002283A (en) | 2022-09-02 |
Family
ID=83020977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210840722.2A Pending CN115002283A (en) | 2022-07-18 | 2022-07-18 | Virtual digital man-machine telephone answering system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115002283A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116319632A (en) * | 2022-11-28 | 2023-06-23 | 浪潮通信信息系统有限公司 | Operation and maintenance management system and method for automatic business processing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109246310A (en) * | 2018-11-03 | 2019-01-18 | 天津深思维科技有限公司 | It is a kind of that auxiliary system is answered based on intelligent sound technology |
| CN111294463A (en) * | 2020-02-06 | 2020-06-16 | 广州市讯飞樽鸿信息技术有限公司 | Intelligent response method, system and device |
| CN112489645A (en) * | 2020-11-05 | 2021-03-12 | 北京中凯信通信息技术有限公司 | Intelligent voice interaction method, system and storage medium |
| CN112565529A (en) * | 2020-11-05 | 2021-03-26 | 北京中凯信通信息技术有限公司 | Intelligent telephone answering method, system and storage medium |
-
2022
- 2022-07-18 CN CN202210840722.2A patent/CN115002283A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109246310A (en) * | 2018-11-03 | 2019-01-18 | 天津深思维科技有限公司 | It is a kind of that auxiliary system is answered based on intelligent sound technology |
| CN111294463A (en) * | 2020-02-06 | 2020-06-16 | 广州市讯飞樽鸿信息技术有限公司 | Intelligent response method, system and device |
| CN112489645A (en) * | 2020-11-05 | 2021-03-12 | 北京中凯信通信息技术有限公司 | Intelligent voice interaction method, system and storage medium |
| CN112565529A (en) * | 2020-11-05 | 2021-03-26 | 北京中凯信通信息技术有限公司 | Intelligent telephone answering method, system and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116319632A (en) * | 2022-11-28 | 2023-06-23 | 浪潮通信信息系统有限公司 | Operation and maintenance management system and method for automatic business processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110891124B (en) | System for artificial intelligence pick-up call | |
| US6519326B1 (en) | Telephone voice-ringing using a transmitted voice announcement | |
| US7890638B2 (en) | Communication between a real world environment and a virtual world environment | |
| CN101873391B (en) | Join-us call-log and call-answer messages | |
| US7142643B2 (en) | Method and system for unifying phonebook for varied hearing disabilities | |
| CN111131638A (en) | Intelligent outbound voice robot system and outbound method | |
| JP2001103161A (en) | Transmission of advertisement utilizing ring-back period in elecric communication exchange system | |
| AU1374401A (en) | Telephone based access to instant messaging | |
| CN100521714C (en) | Method for realizing calling number additional label and customized information presenting in communication network | |
| CN104580630A (en) | Callback type call communication method and system | |
| CN112565529A (en) | Intelligent telephone answering method, system and storage medium | |
| CN109246316B (en) | Incoming call processing method and system | |
| CN112040073B (en) | Intelligent directory assistance server, directory assistance system and directory assistance method | |
| CN111741171B (en) | 5G enhanced video color ring back tone service system and implementation method thereof | |
| CN111402881B (en) | Intelligent dialogue robot system and method for realizing intelligent dialogue | |
| CN104580762A (en) | Method and device for realizing call forwarding according to language | |
| CN113194203A (en) | Communication system, answering and dialing method and communication system for hearing-impaired people | |
| CN115002283A (en) | Virtual digital man-machine telephone answering system and method | |
| CN101951390B (en) | Sequenced telephony applications upon call disconnect method and apparatus | |
| CN101202795B (en) | Method and system for audio frequency content user recording | |
| CN101552952B (en) | A broadcast call implementation method and system | |
| US20120072530A1 (en) | System For Providing Multi-Phased, Multi-Modal Access To Content Through Voice And Data Devices | |
| CN101610488B (en) | Internet communication tool uniformly coding and dialing system and internet communication tool uniformly coding and dialing method | |
| CN105991846A (en) | Owner calling method, device, server and system | |
| US20130093830A1 (en) | Systems and methods for accepting video calls on voice telephones at call centers or other locations |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Xin Inventor after: Chen Xintong Inventor after: Zheng Changshui Inventor before: Zheng Changshui Inventor before: Li Xin |