A native voice intelligent outbound call model and system thereof

Abstract

The application discloses a kind of original voice intelligent outbound model and system thereof, including ICE module, Freeswitch module, ISE module and user interface, external interface, internal interface, system logic and system physical structure;ICE module includes, process management, call rule management, call list, call import and call dialogue information;Freeswitch module includes, dialing, session routing and recording;ISE module includes interactive process control.The beneficial effects of the application are as follows: call rules are configured through interface, the first call dials the customer's own phone, if the first call is not connected, then dial the contactor's phone the second time, configure the process of each dialing, support adding, deleting, modifying and inquiring, interface configuration interactive process, view the results and call related information of all calls that meet the conditions, import call information, display call related information in the form of chart, can interact with customers independently and store recording.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence call technology, specifically to a native voice intelligent outbound call model and system. Background Technology

[0002] In recent years, the explosive growth of artificial intelligence has attracted widespread attention from all sectors of society. In order to promote the integration and innovation of artificial intelligence and the call center industry and comprehensively improve the intelligence level of call centers, we will carry out intelligent outbound calling projects to accelerate the improvement of call center work efficiency. Summary of the Invention

[0003] The purpose of this invention is to provide a native voice intelligent outbound calling model and system to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a native voice intelligent outbound calling model and system thereof, including an ICE module, a Freeswitch module, an ISE module, a user interface, an external interface, an internal interface, system logic, and a system physical structure; The ICE module includes process management, call rule management, call list, call import, and call dialogue information; the Freeswitch module includes dialing, session routing, and recording; and the ISE module includes interactive flow control.

[0005] Further optimized, the user interface includes the ICE-WEB system, which interacts with the server via a browser.

[0006] Further optimized, the external interface includes Freeswitch interface to digital trunk gateway, and Freeswitch interface to ASR and TTS, which respectively initiate calls through the digital trunk gateway and call the two engines through the MRCP v2 protocol.

[0007] Further optimized, the internal interfaces include ICE, Freeswitch, and ISE, which are respectively used to call Freeswitch to initiate a call, route a session to ISE, and call ASR and TTS through interaction with Freeswitch.

[0008] In a further optimized version, the system logic involves operating the ICE engine via ICE-WEB, configuring call rules and corresponding call flows, importing specified call information and specifying the corresponding call rules via ICE-WEB, processing the call information using the call rules to generate the final call content, initiating a call by calling FreeSwitch, determining whether the call is connected, ending the session if the call is not connected, and transferring the session to the ISE engine if the call is connected. The ISE engine executes the corresponding flow, sending requests for recognition and audio synthesis to FreeSwitch as needed, and FreeSwitch invoking ASR and TTS based on the received requests.

[0009] In a further optimized form, the physical structure of the system consists of E1, digital relay gateway, ICE-WEB, MongoDB, Redis, ICE, Freeswitch, ISE, ASR, and TTS.

[0010] Further optimized, the E1 is used to connect to the operator, the digital trunk gateway is used to process and forward SIP requests, the ICE-WEB is used for the web interaction interface of the ICE engine, the MongoDB is used to store the data generated in the system, and the Redis session is used for data sharing.

[0011] Further optimized, the ICE is used for the call strategy and control engine, the Freeswitch is used for telephone switching, the ISE is used for the process control engine, the ASR is used for the speech-to-text engine, and the TTS is used for the text-to-speech engine. Beneficial effects

[0012] The native voice intelligent outbound calling model and system provided by this invention can configure calling rules through an interface, such as dialing the customer's phone number on the first call, and dialing the contact person's phone number on the second call if the first call fails. The process of each call can also be configured, and it supports adding, deleting, modifying and querying. The interaction process can be configured through the interface, and the results of all calls that meet the conditions and call-related information can be viewed. The content of the robot's interaction with the user can be viewed, and the interaction recordings can be listened to. Call information can be imported, and call-related information can be displayed in the form of charts. Call operations can be initiated, and the robot can interact autonomously with the customer and store recordings. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the rule management process of the present invention; Figure 2 This is a schematic diagram of the process management of the present invention; Figure 3This is a schematic diagram of the call task flow of the present invention; Figure 4 This is a schematic diagram of the call processing flow of the present invention; Figure 5 This is a schematic diagram of the intelligent interaction process of the present invention; Figure 6 This is a schematic diagram of the system structure of the present invention; Figure 7 This is a schematic diagram showing the functional requirements and system module relationships of the present invention; Figure 8 This is a schematic diagram of the system logic interface structure of the present invention; Figure 9 This is a schematic diagram of the ICE-Freeswitch-ISE calling logic of the present invention; Figure 10 This is a schematic diagram of the Freeswitch-ASR call logic of the present invention; Figure 11 This is a schematic diagram of the Freeswitch-TTS calling logic of the present invention; Figure 12 This is a schematic diagram of the Freeswitch relay call logic of the present invention; Figure 13 This is a schematic diagram of the physical structure of the system of the present invention; Figure 14 This is a schematic diagram of the structure definition of the dial_call_rule table in this invention; Figure 15 This is a schematic diagram of the structure definition of the dial_already_flow_info table in this invention; Figure 16 This is a schematic diagram of the structure definition of the dial_flows table in this invention; Figure 17 This is a schematic diagram of the structure definition of the dial_flow_log table in this invention; Figure 18 This is a schematic diagram of the structure definition of the dial_flow_record table in this invention. Detailed Implementation

[0014] The following are specific embodiments of the present invention, which are described in conjunction with the accompanying drawings to further illustrate the technical solutions of the present invention. However, the present invention is not limited to these embodiments. Example

[0015] like Figure 1-18 As shown, a native voice intelligent outbound calling model and its system include an ICE module, a Freeswitch module, an ISE module, a user interface, an external interface, an internal interface, system logic, and a system physical structure. The ICE module includes process management, call rule management, call list, call import, and call dialogue information; the Freeswitch module includes dialing, session routing, and recording; and the ISE module includes interactive flow control.

[0016] In this embodiment, the user interface includes the ICE-WEB system, which interacts with the server via a browser.

[0017] External interfaces include Freeswitch for connecting to digital trunk gateways, and Freeswitch for connecting to ASR and TTS, which respectively initiate calls through the digital trunk gateway and call these two engines through the MRCP v2 protocol.

[0018] The internal interfaces include ICE, Freeswitch, and ISE, which are used to call Freeswitch to initiate a call, route a session to ISE, and call ASR and TTS through interaction with Freeswitch, respectively.

[0019] The system logic is as follows: ICE-WEB operates the ICE engine, configures call rules and corresponding call flows, imports specified call information and corresponding call rules through ICE-WEB, ICE processes the call information according to the call rules to generate the final call content, ICE calls FreeSwitch to initiate the call, ICE determines whether the call is connected, if the call is not connected, the session ends; if the call is connected, the session is transferred to the ISE engine, the ISE engine executes the corresponding flow, and the ISE sends requests to FreeSwitch for recognition and audio synthesis as needed, and FreeSwitch calls ASR and TTS based on the received requests.

[0020] The system's physical architecture consists of E1, digital trunk gateway, ICE-WEB, MongoDB, Redis, ICE, Freeswitch, ISE, ASR, and TTS.

[0021] E1 is used to connect to the operator, the digital trunk gateway is used to process and forward SIP requests, ICE-WEB is used for the web interface of the ICE engine, MongoDB is used to store the data generated in the system, and Redis:session is used for data sharing.

[0022] ICE is used for call strategy and control engine, Freeswitch is used for telephone switching, ISE is used for process control engine, ASR is used for speech-to-text engine, and TTS is used for text-to-speech engine.

[0023] The ICE-WEB system uses a browser to interact with the server, querying and modifying data such as processes, call rules, call results, and call dialogue by querying the database server. Freeswitch connects to a digital trunk gateway and initiates calls through the digital trunk gateway; Freeswitch interfaces with ASR and TTS, calling these two engines via the MRCP v2 protocol; ICE invokes FreeSwitch to initiate the call; Freeswitch routes the session to ISE; ISE invokes ASR and TTS through interaction with FreeSwitch; Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A native voice intelligent outbound calling model and system thereof, characterized in that: This includes the ICE module, Freeswitch module, ISE module, user interface, external interface, internal interface, system logic, and system physical structure. The ICE module includes process management, call rule management, call list, call import, and call dialogue information; the Freeswitch module includes dialing, session routing, and recording. The ISE module includes interactive flow control.

2. The native voice intelligent outbound calling model and system according to claim 1, characterized in that: The user interface includes the ICE-WEB system, which uses a browser to interact with the server.

3. The native voice intelligent outbound calling model and system according to claim 1, characterized in that: The external interfaces include Freeswitch interface to digital trunk gateway, and Freeswitch interface to ASR and TTS, which respectively initiate calls through the digital trunk gateway and call the two engines through the MRCP v2 protocol.

4. The native voice intelligent outbound calling model and system according to claim 1, characterized in that: The internal interfaces include ICE, Freeswitch, and ISE, which are used to call Freeswitch to initiate a call, route a session to ISE, and call ASR and TTS through interaction with Freeswitch, respectively.

5. The native voice intelligent outbound calling model and system according to claim 1, characterized in that: The system logic is as follows: the ICE engine is operated through ICE-WEB, the call rules and corresponding call flow are configured, the specified call information is imported through ICE-WEB and the corresponding call rules are specified, ICE processes the call information through the call rules to generate the final call content, ICE calls freeswitch to initiate the call, ICE determines whether the call is connected, and if the call is not connected, the session is terminated. If the call is connected, the session is transferred to the ISE engine. The ISE engine executes the corresponding process. According to the process requirements, the ISE sends requests to FreeSWITCH for recognition and audio synthesis. FreeSWITCH then calls ASR and TTS based on the received requests.

6. The native voice intelligent outbound calling model and system according to claim 1, characterized in that: The system's physical structure consists of E1, digital relay gateway, ICE-WEB, MongoDB, Redis, ICE, Freeswitch, ISE, ASR, and TTS.

7. The native voice intelligent outbound calling model and system according to claim 6, characterized in that: The E1 is used to connect to the operator, the digital trunk gateway is used to process and forward SIP requests, the ICE-WEB is used for the web interface of the ICE engine, the MongoDB is used to store the data generated in the system, and the Redis session is used for data sharing.

8. The native voice intelligent outbound calling model and system according to claim 6, characterized in that: The ICE is used for call strategy and control engine, the Freeswitch is used for telephone switching, the ISE is used for process control engine, the ASR is used for speech-to-text engine, and the TTS is used for text-to-speech engine.

Images