Cloud customer service system and method of artificial intelligence era

Abstract

The invention relates to a cloud customer service system and method in an artificial intelligence era, the system is composed of a multi-channel customer access platform, a call center service platform and a manual seat / mobile seat, supports a plurality of access modes such as PSTN, IMS, WeChat official account, WEB, APP, QQ and the like, and realizes unified queuing and distribution of customers. The call center service platform is integrated with a CallManager module, a ChatServer module and other modules, and core functions and management are achieved. The system further comprises an intelligent outbound robot and an intelligent voice quality inspection module, and automatic outbound interaction is achieved through ASR and NLP technologies. In addition, the system supports a secondary development interface, and has good expansibility and customization capability. According to the invention, the defects of an existing call center system in the aspects of multi-channel access, intelligent call-out, voice quality inspection and the like are effectively overcome, the intelligent level and service quality of customer service are remarkably improved, and the requirements of enterprises for an efficient customer service system are met.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence and cloud computing technology, and in particular relates to a cloud customer service system and method in the era of artificial intelligence. Background Art

[0002] With the rapid development of the internet and mobile internet, the ways in which customers and businesses interact are becoming increasingly diverse. Traditional call center systems primarily support PSTN telephone access, but have significant shortcomings when handling internet access (such as WeChat official accounts, web-based online customer service, and mobile app customer service). Furthermore, traditional call center systems face numerous challenges in terms of agent management, service quality monitoring, and business expansion. With the development of big data, cloud computing, and artificial intelligence technologies, intelligent customer service has become an important means of improving the quality and efficiency of customer service. However, existing technologies still have shortcomings in multi-channel access, intelligent outbound calling, and voice quality inspection, and are unable to meet the needs of businesses for efficient and intelligent customer service systems. Summary of the Invention

[0003] (1) Purpose of the invention

[0004] In order to overcome the above shortcomings, the purpose of the present invention is to provide a cloud customer service system and method in the era of artificial intelligence to solve the above technical problems.

[0005] (2) Technical solution

[0006] To achieve the above objectives, the technical solutions provided by this application are as follows:

[0007] A cloud customer service system in the era of artificial intelligence, including:

[0008] Multi-channel customer access platform, supporting PSTN ordinary telephone, IMS soft switch, WeChat official account, WEB online customer service, mobile APP customer service, QQ marketing account access channels, and unified queuing and allocation of customers;

[0009] The call center service platform, including CallManager, ChatServer services, ICM services, IVR services, AM services, CCM services, CCDC services, REC services, and agent CRM, is used to implement the core functions and management of the call center;

[0010] Manual agents / mobile agents support PC agents and mobile agents. Agents log in to the WEB version of the agent system to perform various business functions.

[0011] Preferably, the multi-channel customer access platform includes:

[0012] Voice gateway, used to connect to traditional PSTN trunk lines to implement incoming and outgoing voice calls;

[0013] WeChat access gateway module enables docking with the WeChat public account platform, supporting two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information;

[0014] QQ access gateway module, which enables docking with the QQ marketing platform and supports two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information;

[0015] The SBC module and ChatServer module enable the connection between WEB online customer service and APP customer service channels, supporting two-way transmission of text, emoticons, images, video files, location information, as well as real-time voice and video calls.

[0016] Preferably, the call center service platform includes:

[0017] The intelligent voice quality inspection module, through a combination of "in-process monitoring and post-process quality inspection", enables intelligent analysis and automated quality inspection of all data generated during the service process;

[0018] The intelligent outbound call robot module uses ASR automatic speech technology and NLP semantic understanding technology to realize automatic outbound calls and voice interaction based on preset speech processes.

[0019] Preferably, the intelligent voice quality inspection module includes:

[0020] Quality inspection rule management unit, used to set and manage quality inspection rules for customer service businesses in different industries;

[0021] A voice set management unit, used to create and manage target voice sets to be quality-checked;

[0022] The quality inspection task management unit is used to create and start quality inspection tasks, combining speech sets with quality inspection rules for analysis;

[0023] The quality inspection result display unit is used to display the analysis results of the quality inspection task, including the conversation content, rule matching status, and supports manual re-listening and scoring adjustment.

[0024] Preferably, the intelligent outbound call robot module includes:

[0025] A conversation flow design tool that provides questionnaire-based conversation design capabilities, including conversation nodes, global context, and FAQ design.

[0026] The outbound call campaign management unit supports the creation of outbound call campaigns, including the import of batch outbound call numbers, the customization of outbound call strategies, and the generation and management of outbound call tasks;

[0027] Call list import function, supports importing the number list of outbound call activities through Excel files;

[0028] The outbound call task execution monitoring unit displays the status of outbound call tasks in real time, including preparation, calling, waiting, and end status;

[0029] The outbound call statistics report unit provides call detail query and call report query functions for statistics and analysis of the effectiveness of outbound call activities.

[0030] Preferably, the manual seats / mobile seats include:

[0031] The agent console provides call center service functions, including login / logout, busy / idle setting, break / cancel break, post-processing and completion, active answering, accepting assignment, rejection, hold and retrieve, soft hang-up, internal calling, outgoing calling, transfer, and invitation;

[0032] The customer management module supports batch import of customer information, manual addition of individual customers, and modification of customer information. It also serves as the basic data source for the "customer information pop-up screen" when agents answer customer calls.

[0033] Customer service workstation, which enables pop-up screen for customer information and viewing of recent service records;

[0034] The work order management module supports creating new customer service work orders, viewing work order lists, viewing work order details, work order flow allocation, and work order reminders;

[0035] The Internet customer service function supports unified queuing, unified allocation, and multimedia conversation services for customers accessing through WeChat official accounts, WEB website online customer service, mobile app customer service, and QQ marketing accounts, and realizes multi-channel unified work order and multimedia customer service record management;

[0036] The real-time video customer service function supports agents with video call capabilities to conduct one-way or two-way video conversations with customers, and record the entire service process. It also supports agents to take photos at the workbench and save them to the customer service work order.

[0037] Preferably, the system supports secondary development interfaces, including:

[0038] PC agent secondary development interface, providing JavaScript-based agent call development component JSPB, supporting seamless integration with third-party agent application systems;

[0039] Mobile APP secondary development interface, providing SDK secondary development package, supports rapid integration of customer service functions within existing APP applications;

[0040] IVR process secondary development interface supports direct data access mode and custom communication interface, realizing data connection between IVR business process and third-party backend application system;

[0041] The secondary development interface of mobile agent provides call center APP outbound call interface and direct call back interface based on the "dual call mode", and supports telephone service integration of third-party clients.

[0042] Preferably, the method comprises the following steps:

[0043] Create an outbound call campaign and set the campaign name, type, participating agents, start time, end time, and valid period parameters;

[0044] Import outbound call number lists and import in batches via Excel files;

[0045] Set outbound call activity strategies, including the number of failed retries, failed retry interval, maximum number of concurrent outbound calls, outbound call display number, and predicted call multiple;

[0046] Start the outbound call robot, execute each outbound call task in sequence according to the set strategy and speech process, and interact with the customer by voice;

[0047] Monitor the real-time status of outbound call tasks, including preparation, calling, waiting, and end status;

[0048] Analyze and compile statistics on the effectiveness of outbound calling activities, and generate call details and call reports.

[0049] Preferably, the method comprises the following steps:

[0050] Create quality inspection rules and set corresponding quality inspection indicators and rules according to industry customer service business needs;

[0051] Create a voice set and import the target recordings that need quality inspection from the recording list in the customer service system;

[0052] Start the quality inspection task, combine the voice set with the quality inspection rules, and use ASR intelligent speech recognition technology to conduct a full analysis of the service recordings;

[0053] View quality inspection results, including conversation content and rule matching, and support manual re-listening and scoring adjustments;

[0054] Conduct service quality assessment and formulate improvement measures based on quality inspection results.

[0055] Beneficial effects:

[0056] 1. Saving Human Resources: By analyzing business scenarios, many tasks suitable for robot outbound calls can be assigned to outbound call robots. This can significantly save human agent resources, allowing valuable human resources to be better utilized in inbound customer service scenarios. Furthermore, compared to the salary costs of human agents, outbound call robots are more economical and less expensive.

[0057] 2. Adapt to business flexibility: Traditional agent human resources lack flexibility, while outbound call robots can be added or removed at any time as business volume changes, truly "on demand";

[0058] 3. Satisfy large concurrency: In addition to the convenience of robots being able to scale up or down at any time, robot seats do not require physical workplaces. As long as the hardware server resources are sufficient, it can meet the needs of any business concurrency, no matter how large the scale.

[0059] 4. More standardized business processes: Since the outbound call robot is executed through a pre-configured unified speech process, the business standardization of the interaction process between the robot and the customer can be guaranteed, and the arbitrariness of the manual outbound call process can be avoided to the greatest extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following is a detailed description of the present invention with reference to the accompanying drawings. Figure 1 , the present invention is further described in detail. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present invention.

[0062] A cloud customer service system in the era of artificial intelligence, including:

[0063] Multi-channel customer access platform, supporting PSTN ordinary telephone, IMS soft switch, WeChat official account, WEB online customer service, mobile APP customer service, QQ marketing account access channels, and unified queuing and allocation of customers;

[0064] The call center service platform, including CallManager, ChatServer services, ICM services, IVR services, AM services, CCM services, CCDC services, REC services, and agent CRM, is used to implement the core functions and management of the call center;

[0065] Manual agents / mobile agents support PC agents and mobile agents. Agents log in to the WEB version of the agent system to perform various business functions.

[0066] Preferably, the multi-channel customer access platform includes:

[0067] Voice gateway, used to connect to traditional PSTN trunk lines, or directly connect to the operator / virtual operator's SIP soft switch platform through the SBC-IMS network management system to implement inbound and outbound voice call functions;

[0068] WeChat access gateway module enables docking with the WeChat public account platform, supporting two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information;

[0069] QQ access gateway module, which enables docking with the QQ marketing platform and supports two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information;

[0070] The SBC module and ChatServer module enable the connection between WEB online customer service and APP customer service channels, supporting two-way transmission of text, emoticons, images, video files, location information, as well as real-time voice and video calls.

[0071] The SBC module is a border gateway controller. With the SBC, all internet terminals (such as mobile agents and WebCall clients) can seamlessly access the cloud call center platform. Its functions primarily include SIP messaging, firewall penetration for audio and video RTP media streams, and codec conversion for audio and video media.

[0072] Preferably, the call center service platform includes:

[0073] The intelligent voice quality inspection module, through a combination of "in-process monitoring and post-process quality inspection", enables intelligent analysis and automated quality inspection of all data generated during the service process;

[0074] The intelligent outbound call robot module uses ASR automatic speech technology and NLP semantic understanding technology to realize automatic outbound calls and voice interaction based on preset speech processes.

[0075] Preferably, the intelligent voice quality inspection module includes:

[0076] Quality inspection rule management unit, used to set and manage quality inspection rules for customer service businesses in different industries;

[0077] A voice set management unit, used to create and manage target voice sets to be quality-checked;

[0078] The quality inspection task management unit is used to create and start quality inspection tasks, combining speech sets with quality inspection rules for analysis;

[0079] The quality inspection result display unit is used to display the analysis results of the quality inspection task, including the conversation content, rule matching status, and supports manual re-listening and scoring adjustment.

[0080] Preferably, the intelligent outbound call robot module includes:

[0081] A conversation flow design tool that provides questionnaire-based conversation design capabilities, including conversation nodes, global context, and FAQ design.

[0082] The outbound call campaign management unit supports the creation of outbound call campaigns, including the import of batch outbound call numbers, the customization of outbound call strategies, and the generation and management of outbound call tasks;

[0083] Call list import function, supports importing the number list of outbound call activities through Excel files;

[0084] The outbound call task execution monitoring unit displays the status of outbound call tasks in real time, including preparation, calling, waiting, and end status;

[0085] The outbound call statistics report unit provides call detail query and call report query functions for statistics and analysis of the effectiveness of outbound call activities.

[0086] Preferably, the manual seats / mobile seats include:

[0087] The agent console provides call center service functions, including login / logout, busy / idle setting, break / cancel break, post-processing and completion, active answering, accepting assignment, rejection, hold and retrieve, soft hang-up, internal calling, outgoing calling, transfer, and invitation;

[0088] The customer management module supports batch import of customer information, manual addition of individual customers, and modification of customer information. It also serves as the basic data source for the "customer information pop-up screen" when agents answer customer calls.

[0089] Customer service workstation, which enables pop-up screen for customer information and viewing of recent service records;

[0090] The work order management module supports creating new customer service work orders, viewing work order lists, viewing work order details, work order flow allocation, and work order reminders;

[0091] The Internet customer service function supports unified queuing, unified allocation, and multimedia conversation services for customers accessing through WeChat official accounts, WEB website online customer service, mobile app customer service, and QQ marketing accounts, and realizes multi-channel unified work order and multimedia customer service record management;

[0092] The real-time video customer service function supports agents with video call capabilities to conduct one-way or two-way video conversations with customers, and record the entire service process. It also supports agents to take photos at the workbench and save them to the customer service work order.

[0093] Preferably, the system supports secondary development interfaces, including:

[0094] PC agent secondary development interface, providing JavaScript-based agent call development component JSPB, supporting seamless integration with third-party agent application systems;

[0095] Mobile APP secondary development interface, providing SDK secondary development package, supports rapid integration of customer service functions within existing APP applications;

[0096] IVR process secondary development interface supports direct data access mode and custom communication interface, realizing data connection between IVR business process and third-party backend application system;

[0097] The secondary development interface of mobile agent provides call center APP outbound call interface and direct call back interface based on the "dual call mode", and supports telephone service integration of third-party clients.

[0098] An intelligent outbound calling method for a cloud customer service system comprises the following steps:

[0099] Create an outbound call campaign and set the campaign name, type, participating agents, start time, end time, and valid period parameters;

[0100] Import outbound call number lists and import in batches via Excel files;

[0101] Set outbound call activity strategies, including the number of failed retries, failed retry interval, maximum number of concurrent outbound calls, outbound call display number, and predicted call multiple;

[0102] Start the outbound call robot, execute each outbound call task in sequence according to the set strategy and speech process, and interact with the customer by voice;

[0103] Monitor the real-time status of outbound call tasks, including preparation, calling, waiting, and end status;

[0104] Analyze and compile statistics on the effectiveness of outbound calling activities, and generate call details and call reports.

[0105] An intelligent voice quality inspection method for a cloud customer service system comprises the following steps:

[0106] Create quality inspection rules and set corresponding quality inspection indicators and rules according to industry customer service business needs;

[0107] Create a voice set and import the target recordings that need quality inspection from the recording list in the customer service system;

[0108] Start the quality inspection task, combine the voice set with the quality inspection rules, and use ASR intelligent speech recognition technology to conduct a full analysis of the service recordings;

[0109] View quality inspection results, including conversation content and rule matching, and support manual re-listening and scoring adjustments;

[0110] Conduct service quality assessment and formulate improvement measures based on quality inspection results.

[0111] This invention provides a cloud customer service system for the AI ​​era. By organically integrating a multi-channel customer access platform, a call center service platform, and both human agents and mobile agents, it achieves comprehensive, all-media customer access and efficient service management. The system supports multiple access channels, including PSTN telephones, IMS soft switches, WeChat public accounts, online customer service, mobile app customer service, and QQ marketing accounts. It enables unified queuing and allocation of customers, and provides differentiated services based on customer priority.

[0112] The call center service platform integrates multiple functional modules, including CallManager, ChatServer, ICM, IVR, AM, CCM, CCDC, REC, and agent CRM, enabling core call center functions and management. Human agents and mobile agents are supported, and agents can log in to the web-based agent system to access various business functions.

[0113] The present invention also provides an intelligent outbound call robot module and an intelligent voice quality inspection module. The intelligent outbound call robot module utilizes ASR automatic speech processing and NLP semantic understanding technology to implement automated outbound calls and voice interaction based on pre-set speech flow. The intelligent voice quality inspection module combines in-service monitoring with post-service quality inspection to perform comprehensive intelligent analysis and automated quality inspection of data generated during the service process.

[0114] The cloud customer service system of the present invention also supports secondary development interfaces, including PC agent secondary development interface, mobile APP secondary development interface, IVR process secondary development interface and mobile phone agent secondary development interface, providing flexibility for system expansion and customization.

[0115] Through the above technical solution, the present invention can effectively solve the problems existing in the existing call center system in multi-channel access, intelligent outbound calls, voice quality inspection, etc., improve the intelligence level and service quality of the customer service system, and meet the customer service needs of enterprises in the era of artificial intelligence.

[0116] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A cloud customer service system in the era of artificial intelligence, characterized by: include: Multi-channel customer access platform, supporting PSTN ordinary telephone, IMS soft switch, WeChat official account, WEB online customer service, mobile APP customer service, QQ marketing account access channels, and unified queuing and allocation of customers; The call center service platform, including CallManager, ChatServer services, ICM services, IVR services, AM services, CCM services, CCDC services, REC services, and agent CRM, is used to implement the core functions and management of the call center; Manual agents / mobile agents support PC agents and mobile agents. Agents log in to the WEB version of the agent system to perform various business functions.

2. The cloud customer service system in the artificial intelligence era according to claim 1 is characterized in that: The multi-channel customer access platform includes: Voice gateway, used to connect to traditional PSTN trunk lines to implement incoming and outgoing voice calls; WeChat access gateway module enables docking with the WeChat public account platform, supporting two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information; QQ access gateway module, which enables docking with the QQ marketing platform and supports two-way transmission of text, emoticons, voice intercom, pictures, video files, and location information; The SBC module and ChatServer module enable the connection between WEB online customer service and APP customer service channels, supporting two-way transmission of text, emoticons, images, video files, location information, as well as real-time voice and video calls.

3. The cloud customer service system in the artificial intelligence era according to claim 1 is characterized in that: The call center service platform includes: The intelligent voice quality inspection module combines in-process monitoring with post-process quality inspection to achieve intelligent analysis and automated quality inspection of all data generated during the service process. The intelligent outbound call robot module uses ASR automatic speech technology and NLP semantic understanding technology to realize automatic outbound calls and voice interaction based on preset speech processes.

4. The cloud customer service system in the artificial intelligence era according to claim 3 is characterized in that: The intelligent voice quality inspection module includes: Quality inspection rule management unit, used to set and manage quality inspection rules for customer service businesses in different industries; A voice set management unit, used to create and manage target voice sets to be quality-checked; The quality inspection task management unit is used to create and start quality inspection tasks, combining speech sets with quality inspection rules for analysis; The quality inspection result display unit is used to display the analysis results of the quality inspection task, including the conversation content, rule matching status, and supports manual re-listening and scoring adjustment.

5. The cloud customer service system in the artificial intelligence era according to claim 3 is characterized in that: The intelligent outbound call robot module includes: A conversation flow design tool that provides questionnaire-based conversation design capabilities, including conversation nodes, global context, and FAQ design. The outbound call campaign management unit supports the creation of outbound call campaigns, including the import of batch outbound call numbers, the customization of outbound call strategies, and the generation and management of outbound call tasks; Call list import function, supports importing the number list of outbound call activities through Excel files; The outbound call task execution monitoring unit displays the status of outbound call tasks in real time, including preparation, calling, waiting, and end status; The outbound call statistics report unit provides call detail query and call report query functions for statistics and analysis of the effectiveness of outbound call activities.

6. The cloud customer service system in the artificial intelligence era according to claim 1, characterized in that: The manual seats / mobile seats include: The agent console provides call center service functions, including login / logout, busy / idle setting, break / cancel break, post-processing and completion, active answering, accepting assignment, rejection, hold and retrieve, soft hang-up, internal calling, outgoing calling, transfer, and invitation; The customer management module supports batch import of customer information, manual addition of individual customers, and modification of customer information. It also serves as the basic data source for the "customer information pop-up screen" when agents answer customer calls. Customer service workstation, which enables pop-up screen for customer information and viewing of recent service records; The work order management module supports creating new customer service work orders, viewing work order lists, viewing work order details, work order flow allocation, and work order reminders; The Internet customer service function supports unified queuing, unified allocation, and multimedia conversation services for customers accessing through WeChat official accounts, WEB website online customer service, mobile app customer service, and QQ marketing accounts, and realizes multi-channel unified work order and multimedia customer service record management; The real-time video customer service function supports agents with video call capabilities to conduct one-way or two-way video conversations with customers, and record the entire service process. It also supports agents to take photos at the workbench and save them to the customer service work order.

7. The cloud customer service system in the artificial intelligence era according to claim 1 is characterized in that: The system supports secondary development interfaces, including: PC agent secondary development interface, providing JavaScript-based agent call development component JSPB, supporting seamless integration with third-party agent application systems; Mobile APP secondary development interface, providing SDK secondary development package, supports rapid integration of customer service functions within existing APP applications; IVR process secondary development interface supports direct data access mode and custom communication interface, realizing data connection between IVR business process and third-party backend application system; The secondary development interface of mobile agent provides call center APP outbound call interface and direct call-back interface based on the "dual call mode", and supports telephone service integration of third-party clients.

8. An intelligent outbound calling method based on the cloud customer service system according to claims 1 to 7, characterized in that: The following steps are involved: Create an outbound call campaign and set the campaign name, type, participating agents, start time, end time, and valid period parameters; Import outbound call number lists and import in batches via Excel files; Set outbound call activity strategies, including the number of failed retries, failed retry interval, maximum number of concurrent outbound calls, outbound call display number, and predicted call multiple; Start the outbound call robot, execute each outbound call task in sequence according to the set strategy and speech process, and interact with the customer by voice; Monitor the real-time status of outbound call tasks, including preparation, calling, waiting, and end status; Analyze and compile statistics on the effectiveness of outbound calling activities, and generate call details and call reports.

9. An intelligent voice quality inspection method based on the cloud customer service system according to claims 1 to 7, characterized in that: The following steps are involved: Create quality inspection rules and set corresponding quality inspection indicators and rules according to industry customer service business needs; Create a voice set and import the target recordings that need quality inspection from the recording list in the customer service system; Start the quality inspection task, combine the voice set with the quality inspection rules, and use ASR intelligent speech recognition technology to conduct a full analysis of the service recordings; View quality inspection results, including conversation content and rule matching, and support manual re-listening and scoring adjustments; Conduct service quality assessment and formulate improvement measures based on quality inspection results.

Images