CN117499536A - Call processing method and device, electronic equipment and storage medium - Google Patents

Call processing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117499536A
CN117499536A CN202310735851.XA CN202310735851A CN117499536A CN 117499536 A CN117499536 A CN 117499536A CN 202310735851 A CN202310735851 A CN 202310735851A CN 117499536 A CN117499536 A CN 117499536A
Authority
CN
China
Prior art keywords
user
agent
call
voice message
callback
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
Application number
CN202310735851.XA
Other languages
Chinese (zh)
Inventor
夏福森
蒋宁
吴海英
刘磊
杨锋
杨砚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mashang Xiaofei Finance Co Ltd
Original Assignee
Mashang Xiaofei Finance Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Mashang Xiaofei Finance Co Ltd filed Critical Mashang Xiaofei Finance Co Ltd
Priority to CN202310735851.XA priority Critical patent/CN117499536A/en
Publication of CN117499536A publication Critical patent/CN117499536A/en
Pending legal-status Critical Current

Links

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
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing
    • H04M3/523—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing with call distribution or queueing
    • H04M3/5232—Call distribution algorithms
    • H04M3/5235—Dependent on call type or called number [DNIS]
    • 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
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/53—Centralised arrangements for recording incoming messages, i.e. mailbox systems
    • H04M3/533—Voice mail systems
    • H04M3/53366—Message disposing or creating aspects

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The application discloses a call processing method, a call processing device, electronic equipment and a storage medium, which are used for timely responding to a user message, reducing the repeated incoming line rate and improving the user satisfaction. The method comprises the following steps: in the process that a user initiates a call to a first seat, if a voice message function is triggered, receiving voice message information of the user; carrying out intention recognition on the voice message information to obtain a message intention; determining the urgency of the voice message information based on the message intent; and responding to the voice message information based on a target agent response strategy matched with the emergency degree in preset multiple agent response strategies, wherein the multiple agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.

Description

Call processing method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of call technologies, and in particular, to a call processing method, a call processing device, an electronic device, and a storage medium.
Background
With the development of communication technology, users can apply various services to agents online through hotline telephones or intelligent terminal equipment, and enterprises automatically realize service consultation and handling by using information technology (Information Technology, IT), so that the enterprise cost is reduced. However, the utilization of the agents by enterprises often does not reach the most scientific rationalization, so that the user experience is poor, the single rate is reduced, the labor cost is increased, and particularly in the peak business period, the users often cannot quickly connect the agents.
At present, when a user cannot connect with an agent, the user usually automatically enters a message mode to leave a message, and after that, the agent listens to the message of the user through tuning, so that the user's appeal is clarified and the call is returned. However, the response timeliness of the mode is low, the user's appeal cannot be solved once, the appeal one-time resolution is low, the problem that some users repeatedly enter wires because the appeal cannot respond in time easily occurs, the repeated wire inlet rate is high, a large amount of communication resources are occupied, and the user satisfaction is low.
Disclosure of Invention
The embodiment of the application aims to provide a call processing method, a call processing device, electronic equipment and a storage medium, which are used for realizing timely response to a user message, reducing the repeated incoming line rate and improving the one-time problem solving rate and the user satisfaction.
In order to achieve the above purpose, the embodiment of the present application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a call processing method, including:
in the process that a user initiates a call to a first seat, if a voice message function is triggered, receiving voice message information of the user;
carrying out intention recognition on the voice message information to obtain a message intention;
determining the urgency of the voice message information based on the message intent;
and responding to the voice message information based on a target agent response strategy matched with the emergency degree in preset multiple agent response strategies, wherein the multiple agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
In a second aspect, an embodiment of the present application provides a call processing apparatus, including:
the receiving unit is used for receiving voice message information of the user if the voice message function is triggered in the process that the user initiates a call to the first seat;
The recognition unit is used for carrying out intention recognition on the voice message information to obtain a message intention;
a determining unit for determining an urgency degree of the voice message information based on the message intention;
and the response unit is used for responding to the voice message information based on a target agent response strategy matched with the emergency degree in a plurality of preset agent response strategies, wherein the plurality of agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method of the first aspect.
The above-mentioned at least one technical scheme that this application embodiment adopted can reach following beneficial effect: in the process that a user initiates a call to an agent, if a voice message function is triggered, receiving voice message information of the user, obtaining a message intention by carrying out intention recognition on the voice message information, and determining the urgency of the voice message information based on the message intention; further, a plurality of agent response strategies are preset, specifically, a response strategy of calling back is initiated by a first agent with low call idle degree or a response strategy of transferring a call to a second agent with high call idle degree is included, and as the response timeliness of different response strategies is different, the response is carried out by matching the corresponding target agent response strategy with the voice message information according to the emergency degree of the voice message information, the effect of pertinently responding to the user message according to the light and heavy emergency can be achieved, the user appeal is solved more timely and effectively, the one-time problem solving rate is improved, the times of repeated incoming lines due to incapacitation of the user appeal are reduced, and the user satisfaction is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
Fig. 1 is an application scenario schematic diagram of a call processing method according to an embodiment of the present application;
fig. 2 is a flow chart of a call processing method according to an embodiment of the present application;
fig. 3 is a flow chart of a call processing method according to another embodiment of the present application;
fig. 4 is a flow chart of a call processing method according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a call processing device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes, technical solutions and advantages of the present application, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein. Furthermore, in the present specification and claims, "and/or" means at least one of the connected objects, and the character "/" generally means a relationship in which the associated object is an "or" before and after.
Partial conceptual description:
PSTN: public Switched Telephone Network, public switched telephone network, a telephone network commonly used in our daily life. PSTN provides an analog dedicated channel that is connected between channels via a number of telephone exchanges. When two hosts or router devices need to be connected through PSTN, the network access side (i.e. subscriber loop side) at both ends must use a Modem (Modem) to perform analog/digital, digital/analog conversion of the signal.
Call Center (Call Center): places where contacts and transactions are interacted with by telephone, such as services, sales, emergency events, etc., also include manual services, self-service services, etc.
kamailio: the precursor to kamailio is an opener, which is commonly used to implement clusters with the term load balancing media servers (e.g., freswitch) when used in large concurrency, as a sip proxy. In the embodiment of the application, kamailio is used for freeswitch load balancing. The kamailio can be simultaneously implemented as a proxy server, a registration server, and a redirection server, and in the embodiment of the application, is used as a bridge for interfacing the call center and the gateway.
agent (agent): the seat or seat representation is generally composed of a seat computer, seat software, seat headset, service personnel and the like. The call center seat realizes the relevant control function through seat software and hardware equipment so as to achieve the purpose of customer service.
As described in the background art, at present, after recording the user message, the user message is stored, and after that, the user message is heard by the seat, so as to define the user's appeal and call back the user. However, the response timeliness of the mode is low, so that the requirement of a user cannot be solved once, the requirement of the user is low in one-time solution rate, the problem that some users cannot solve in time or cannot solve once due to the requirement of the user to repeatedly enter wires easily occurs, the repeated wire inlet rate is high, a large amount of communication resources are occupied, and the user satisfaction degree is low.
In view of this, an embodiment of the present application aims to provide a call processing method, in a process of a user initiating a call to an agent, if a voice message function is triggered, receiving voice message information of the user, performing intention recognition on the voice message information to obtain a message intention, and determining an emergency degree of the voice message information based on the message intention; further, a plurality of agent response strategies are preset, specifically, a response strategy of calling back is initiated by a first agent with low call idle degree or a response strategy of transferring a call to a second agent with high call idle degree is included, and as the response timeliness of different response strategies is different, the response is carried out according to the urgent degree of voice message information and the target agent response strategy of corresponding response timeliness is matched with the voice message information, the effect of pertinently responding to user messages according to the urgent degree of the voice message information can be achieved, the user complaint can be solved more timely and effectively, the one-time resolution of the problem is improved, the times of repeated incoming lines due to the fact that the user complaint cannot be solved are reduced, and the user satisfaction is improved.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
First, an application scenario of the call processing method provided in the embodiment of the present application will be described with reference to fig. 1. It should be understood that the application of the call processing method provided in the embodiment of the present application to the scenario shown in fig. 1 is only an exemplary illustration, and should not be construed as limiting the application scenario of the method.
As shown in fig. 1, one practical application scenario to which the call processing method provided in the embodiment of the present application is applicable includes: internet call centers (ICC, internet Call Center), agents and subscribers.
ICC is a call center located on the internet. ICC completes the call control process based on advanced session initiation protocol (Session Initiation Procotol, SIP), realizes soft switching based on SIP/RTP (Real-time Transport Protocol ), and is developed and completed based on open source software. ICC can support high-capacity high-concurrency calling/calling scene high-reliability and flexible expansion by utilizing a docker container technology and a kubernetes cloud native technology through middleware. While using the kafka, spark stream calculations to process the large amount of data generated by the call. In the aspect of expandability, ICC is integrated with scientific and technological elements such as artificial intelligence, voice recognition, natural language learning and the like to realize the intelligentization of a call center.
The ICC may include a number of components or functional modules such as an interactive voice response (Interactive Voice Response, IVR) component, a computer telephony integration (Computer Telephony Integration, CTI) middleware, a routing communications component (e.g., a freeswitch), a load balancing component (e.g., a kamailio), a seat bench, a file management system, a voice-to-text module, and an intent recognition module.
In ICC, IVR component is a powerful telephone automatic service component, and can use prerecorded voice or voice synthesized by text-to-voice technology to make automatic response so as to provide a menu navigation function. The IVR component can answer entertainment products of the communication electronic device according to the operation prompt, and can play related information according to content input by a user. IVR components have three main roles: firstly, primarily screening customer demands, and setting different keys to split customers; secondly, the increasing labor cost is reduced through self-service; thirdly, optimizing the business flow through IVR data analysis.
The load balancing component (such as kamailio) is a bridge where the ICC interfaces with the gateway, and is configured to perform load balancing processing on received call traffic, and distribute the call traffic to the corresponding routing communication component.
The routing communication component (such as a freswitch) is a cross-platform open source telephone switching platform and has strong scalability. The routing communication component is responsible for providing routing and interconnection communication for audio, text or any other form of media, and providing self-service IVR services, intelligent robot services; secondly, the routing communication component provides API (Application Programming Interface, application program interface, also called Application programming interface) and APP (Application program) to call CTI middleware (such as dialing a call, bridging a channel, hanging up a call, etc.); and sending ESL (Event Socket Library ) events to CTI to finish ACD, agent state switching, data report statistics and the like in the middle.
The CTI middleware is mainly communicated with the routing communication component, the IVR component and the seat workbench, receives ESL events (such as channel_ANSER, channel_BRIDGE and the like) from the routing communication component to switch the seat states, counts data reports, sends related websocket messages to inform the seat workbench to switch the seat turntable, receives custom ESL events (such as find_agent, ter_ IVR and the like) from the IVR component to switch the seat ACD and the like.
The voice-to-text module is used for providing a voice-to-text processing function. The intention recognition module is used for providing an intention recognition function.
Based on the ICC, a call can be made between the user and the agent. In one call scenario, a user dials an enterprise service line through a mobile terminal, and a call request enters ICC via the PSTN of the operator and the enterprise voice gateway. Generally, an enterprise receives traffic through an IVR component preset in advance, and a user selects a required service (such as complaint advice, repayment consultation, website inquiry and the like) according to a navigation menu played by the IVR component. If the user selects the manual service, the IVR component initiates a manual request (namely a self-defined find agent ESL message) to the CTI middleware through the routing communication component; after receiving the manual transfer request, the CTI middleware performs ACD (automatic call distribution), and if no free seat exists currently, the CTI middleware broadcasts waiting music to the user through the IVR. Often, in the service peak period, the phenomenon that no idle seat exists for a long time can occur, and after waiting for a preset time period, the CTI middleware instructs the IVR component to play a menu for the user to select whether to continue waiting, for example, playing 'respect users are good, the number of the current consultants is excessive, the user continues to wait for requesting to press 1, and the user ends requesting to hang up', etc.; if the user chooses to continue waiting, the IVR component continues to report the queuing voice to the user.
When the number of times of continuous waiting of the user reaches the preset number of times, the IVR component automatically enters a message leaving mode, and the number of times IVR component initiates a cancel request (such as a user-defined IVR _cancel_queue ESL message) to the CTI middleware through the route communication component so as to avoid poor user experience caused by the fact that the telephone is suddenly received by the seat in the process of leaving a message of the user. The IVR component also sends a start message (e.g., a start_leave_msg message, which carries a message ID, user ID, message record file name, etc.) to the CTI middleware to inform the CTI middleware that the message function is triggered and that the message starts. At the same time, the IVR component records the user's message by invoking a recording application (record app) of the routing communication component. After the message is finished, recording is stopped, the IVR component sends the voice message information of the user to the CTI middleware, or the IVR component uploads the voice message information of the user to the file management system, the CTI middleware acquires the voice message information of the user from the file management system, requests to invoke the intention recognition module through a hypertext transfer protocol (Hyper Text Transfer Protocol, HTTP) interface, carries out intention recognition on the message information of the user, and carries out corresponding response operation on the message information of the user according to the recognized message intention, so that the targeted response on the message of the user is realized, the one-time problem solving rate is improved, the times of repeated incoming lines due to the fact that the user cannot find the solution are reduced, and the user satisfaction is improved.
The call processing method provided in the embodiment of the present application will describe the call processing procedure of ICC in detail.
Referring to fig. 2, a flow chart of a call processing method according to an embodiment of the present application is provided, and the method can be applied to an Internet Call Center (ICC) shown in fig. 1. As shown in fig. 2, the method may include the steps of:
s202, in the process that the user initiates a call to the first seat, if the voice message function is triggered, receiving voice message information of the user.
In this embodiment of the present application, the first agent refers to an agent called by a user.
The condition that the voice message function is triggered can be set according to actual needs, for example, the number of times of calling the first seat reaches the preset number of times or the response of the first seat is not received after the preset time length is exceeded, and the like.
For example, in some call scenarios, a user dials an enterprise service hotline through a mobile terminal, an enterprise accepts telephone traffic through an IVR component, plays a navigation menu to the user, and if the user selects self-service handling service or hangs up according to the navigation menu, the call is ended after corresponding processing is executed according to the user selection.
If the user selects to transfer manual service according to the navigation menu, the IVR component sends a transfer manual request to the CTI middleware, and the CTI middleware responds to the transfer manual request to transfer the incoming call of the user to the idle first seat. If the first seat does not answer the call of the user beyond the preset time, the IVR component triggers a voice message function to allow the user to leave a message. Or after the IVR component requests the manual work through the CTI middleware, the phenomenon that no idle seat exists for a long time occurs, the CTI middleware triggers the IVR component to play a menu to the user for the user to select whether to continue waiting or not after waiting for a preset time, if the user selects to continue waiting, the IVR component continues to report queuing waiting voice to the user, and when the number of times of waiting for manual work by the user exceeds a preset number of times, the IVR component triggers a voice message function for the user to leave a message. After the voice message function is triggered, the IVR component may invoke a recording application (record app) of the routing communication component to receive the user message information.
Optionally, during the process of receiving the voice message, a situation that the user does not speak for a long time or pauses for a time may occur, and in order to avoid invalid messages, silence detection may be performed during the process of receiving the voice message. Specifically, in S202, voice message information of the user is received in real time, and an energy value of the voice message information received in real time is detected; if the duration of the voice message information which is received currently and is lower than the preset lower limit energy value reaches the preset silence duration, discarding the voice message information with the energy value lower than the preset lower limit energy value, and stopping receiving the voice message information.
For example, after triggering the voice message function, the IVR component invokes the recording application program of the routing communication component to start real-time recording until the recording duration reaches the preset message duration, and then the recording is finished. In addition, in the recording process, the energy value of the voice message information recorded in real time is detected, if the duration of the voice message information recorded currently to be lower than the preset lower limit energy value reaches 20 seconds, the voice message information with the energy value lower than the preset lower limit energy value is discarded, and recording is stopped.
It should be noted that, in the embodiment of the present application, the "real-time receiving" refers to that the time interval between two adjacent receiving steps is short, for example, the interval is 10ms, and the interval time may be set according to actual needs, which is not limited in the embodiment of the present application.
Optionally, in the process of receiving the voice message information of the user, the IVR component may also play a prompt to the user under the condition that the preset message duration is about to be reached, for example, 1 minute before stopping recording, for example, "about to reach the maximum message duration, please note", so that the user experience may be improved.
It can be understood that, because the energy value of the voice message information is changed along with time, the energy value of the voice message information during silence is low, by detecting the energy value in real time during the receiving process of the voice message information, and discarding the voice message information with the energy value lower than the preset lower limit energy value under the condition that the duration of the voice message information with the energy value lower than the preset lower limit energy value reaches the preset silence duration, invalid silence segments in the voice message information can be removed, and the validity of the voice message information is ensured. In addition, under the condition that the duration of the voice message information which is lower than the preset lower limit energy value reaches the preset silence duration, the user can be predicted to end the message, the function of automatically suspending the voice message can be achieved by stopping receiving the voice message information, manual operation of the user is not needed, the intelligent degree of the message is improved, and the user experience is improved.
Optionally, after receiving the voice message information of the user, the call processing method provided in the embodiment of the present application may further include: performing voice conversion text processing on voice message information of a user to obtain text content of the voice message information; and correspondingly storing the voice message information and the text content of the voice message information to a file management system.
The file management system may include components of the ICC having file storage and management functions, such as a file server, e.g., an object storage server. For example, after receiving the voice message information of the user, the IVR component may request the CTI middleware to call the ICC voice conversion text module to perform voice conversion text processing on the voice message information, so as to obtain corresponding text content, and correspondingly upload the voice message information and the text content thereof to the file management system for storage through a secure file transfer protocol (Secure File Transfer Protocol, SFTP). Or, the IVR component can also request the CTI middleware to call the voice-to-text module to perform voice-to-text processing on the voice message information received in real time in the process of receiving the voice message information of the user, so as to obtain real-time text content; after the voice message is received, the IVR component sends a message completion message to the CTI middleware, and after the CTI middleware receives the message completion message, the currently received voice message and the text content thereof are uploaded to the file management system for storage through the SFTP protocol.
In practical application, the user identification of the user to which the voice message information belongs, the incoming call information after desensitization processing, the message duration and other information can be uploaded to the file management system.
It can be understood that the voice message information and the text content thereof of the user are correspondingly stored in the file management system, so that the seat can conveniently retrieve the voice message information and the text content thereof when needed, and the seat callback efficiency is improved. For example, the agent may send a message viewing request to the file management system via the agent workstation, and the file management system returns the voice message information requested to be viewed by the agent and the text content thereof to the agent workstation in response to the message viewing request.
S204, intention recognition is carried out on the voice message information, and a message intention is obtained.
Specifically, various intention recognition methods commonly used in the art can be adopted to perform intention recognition on the voice message information, such as an intention recognition algorithm based on artificial intelligence, and the like, which are not described in detail. In practical application, the intention recognition can be directly carried out on the voice message information to obtain the message intention. Alternatively, the intention recognition may be performed on the text content of the voice message information to obtain the message intention.
In an actual call scenario, according to the call purpose, the message intention can be divided into two categories, namely inquiry service information and non-inquiry service information. The inquiry service information refers to information related to inquiring some services, such as self-service handling flow of consulting a certain service, inquiring network points, etc., which is meant to be a message; non-query business information is other intents besides business information query, such as complaints, clearing certificates, and the like.
In practical application, an intention recognition algorithm is preset in an intention recognition module of ICC, after voice message information of a user is received by an IVR component of ICC, the voice message information can be uploaded to a file management system, the voice message information is obtained from the file management system by CTI middleware, the intention recognition module is called, and the intention recognition module carries out intention recognition on the voice message information based on the preset intention recognition algorithm to obtain a message intention.
S206, determining the emergency degree of the voice message information based on the message intention.
The message intention and the emergency degree have a corresponding relationship, which can be preset according to actual service requirements, and the embodiment of the application is not limited to this. For example, table 1 below shows an example of correspondence between message intent and urgency.
TABLE 1
Message leaving intention Degree of emergency
Complaints of Not less than the preset upper limit value
Application delayed repayment and application staged repayment Between a preset lower limit value and a preset upper limit value
Opening clearing evidence, applying for presenting business A preset lower limit value is less than or equal to
S208, responding to the voice message information based on a target agent response strategy matched with the emergency degree in the preset various agent response strategies.
The plurality of agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring a call to the second agent, and the call idle degree of the second agent is higher than that of the first agent. The call idle degree of the agent is used for reflecting the idle condition of the agent.
Because the response timeliness of the response strategies of different agents is different, for example, the response timeliness of the response strategy of calling back initiated by the first agent is higher than that of the response strategy of switching the call to the second agent, the response is carried out for the target agent response strategy of matching the corresponding response timeliness for the voice message information according to the urgency degree of the voice message information, the effect of pertinently responding to the user message according to the light and heavy urgency can be achieved, the user appeal is more timely and effectively solved, the one-time problem solving rate is improved, the times of repeated incoming lines due to incapacity of solving the user complaint are reduced, and the user satisfaction is improved.
Specifically, in the case where the degree of urgency of the voice message information is greater than or equal to the first preset level, the target agent answer policy includes an answer policy to transfer the call to the second agent. Accordingly, the step S208 may include: marking switching priority for the user based on the emergency degree of the voice message information, wherein the switching priority is positively related to the emergency degree; and adding the user into a transit user queue based on the transit priority of the user, wherein the transit user queue is used for storing the users to be transited to the second agent, which are ordered according to the transit priority, and the second agent responds to the call of the user in the transit user queue.
For example, if the user's message is intended to be a complaint, the CTI middleware may determine that the urgency of the voice message is greater than or equal to a preset upper limit, and may further determine that the target answer policy includes an answer policy to transfer the call to the second agent. In this case, the CTI middleware may mark the forwarding priority of the user as the highest, so that the user has the "queue inserting" capability in the forwarding user queue and will be inserted into the first position of the forwarding user queue, so that when automatic call allocation is performed based on the forwarding user queue, the call of the user will be preferentially and most rapidly forwarded to the second agent with high call idle degree, and the second agent responds to the user of the user, so as to solve the user complaint in time, thereby reducing the complaint rate of the user and improving the satisfaction degree of the user.
Optionally, in the case that the urgency of the voice message is greater than or equal to the preset upper limit value, before the user is added to the transit user queue based on the transit priority of the user, transit guiding information may be played to the user, where the transit guiding information is used to guide the user to confirm that the call is initiated to the second seat. Accordingly, in response to a user's confirmation operation of the transit guidance information, the user is added to the transit user queue based on the transit priority of the user.
For example, if the user's message is intended to be complaint, the CTI middleware plays transfer guide information "your good, currently available idle agents, if you need to transfer immediately, please press 1" to guide the user to confirm that a call is initiated to the second agent; if the user selects to initiate a call to the second agent, the IVR component initiates a transfer manual request to the CTI middleware through the routing communication component again, and marks the transfer priority of the user as the highest priority; after receiving the manual transfer request, the CTI middleware inserts the user into the first position of the transfer user queue according to the transfer priority, so that under the condition that an idle seat appears, the call of the user is preferentially transferred to the idle seat.
It can be understood that before marking the transfer priority of the user, transfer guide information can be played to the user, so that the user can intuitively perceive timely response to the voice message, meanwhile, the attention of the user to the transfer waiting time can be reduced, the function of soothing the emotion of the user is achieved, and the possibility of complaint of the user is reduced.
Optionally, when the urgency of the voice message information is greater than or equal to a preset upper limit value, after the transfer guide information is played to the user, responding to a refusal operation of the user on the transfer guide information, adding the user to a callback user list, wherein the callback user list is used for recording the user to be callback by the first seat; marking corresponding callback priority for the user in a callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated; and pushing the marked callback user list to the first seat.
For example, if the user's message is intended to be complaint, the CTI middleware plays transfer guide information "your good, currently available idle agents, if you need to transfer immediately, please press 1" to guide the user to confirm that a call is initiated to the second agent; if the user chooses not to transfer the second seat or hang up, the IVR component initiates a callback request to the CTI middleware through the routing communication component; after receiving the manual request for transferring, the CTI middleware adds the user into a callback user list, marks higher callback priority on the user in the callback user list, and pushes the marked callback user list to the first seat, so that the user can be called back by the first seat preferentially, response timeliness of a user message is guaranteed, user requirements are timely solved, repeated incoming lines caused by the fact that the user message cannot be responded in time are avoided, and user satisfaction is improved.
Optionally, when the urgency of the voice message is greater than or equal to the preset upper limit value, before the user is added to the transit user queue based on the transit priority of the user, the message time of the voice message can be obtained; if the message leaving time belongs to the working period of the second agent, adding the user into a transit user queue based on the transit priority of the user; if the message leaving time belongs to the non-working period of the second agent, sending a call request to the second agent through the appointed communication number of the second agent, wherein the call request is used for requesting to establish a call between the user and the second agent.
The designated communication number of the second agent may be a mobile phone number reserved by the second agent. If the message leaving time belongs to the non-working period of the second agent, sending a call request to the second agent through the appointed communication number of the second agent, so that the second agent can be ensured to respond to the message of the user in time, and the problem can be solved for the user in time, thereby being beneficial to improving the satisfaction degree of the user.
If the emergency degree of the message intention is smaller than the preset upper limit value, the target agent response strategy comprises a response strategy of initiating callback by the first agent. Correspondingly, in the above step S208, the user is added to a callback user list, the callback user list is used for recording the users to be callback by the first agent, and each user in the callback user list corresponds to a message intention label; determining callback priority of each user in a callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated; sequencing each user according to the callback priority, pushing the sequenced callback user list to the first seat, and determining whether callback operation is performed or not by the first seat according to each sequenced user and the message intention label thereof. Wherein the user's message intention label is used to represent the user's message intention, for example, if the user's message intention is to specify a proof of statement, the user's message intention label may be to specify a proof of statement. Alternatively, the user's message intention label is used to indicate the urgency of the user's voice message, and if the user's message intention is to make a clear proof, the user's message intention label may be a non-urgent intention.
For example, if the message intent is clearing evidence that the urgency of such intent is not high, the CTI middleware may add the user to the callback user list and mark the user with a lower callback priority in the callback user list; if the message intention is to apply for deferred repayment, the intention usually appears when the user borrows is about to be overdue, the emergency degree is higher, the CTI middleware can add the user to a callback user list, and the callback priority of the user is marked as higher priority in the callback user list. Therefore, after the users in the callback user list are ordered according to the callback priority and the ordered callback priority is pushed to the first agent, the user with higher callback priority and urgent message intention can be called back by the first agent preferentially, so that the response timeliness to the message of the user is ensured, and the user satisfaction is improved.
Optionally, in order to ensure that the user can be called back by the first seat in time when the emergency degree of the voice message information is greater than or equal to the preset lower limit value, the alarm information carrying the user information of the user can be pushed to the administrator.
For example, taking the user message intention as an application delay repayment as an example, after determining that the target agent response policy is a response policy of a first agent initiating a callback, the CTI middleware pushes alarm information carrying user information of the user to an agent workbench of an administrator, and displays the alarm information to the administrator through the agent workbench, for example, displays the alarm information in a manner of a pop screen or a message prompt and the like, so that the administrator can prompt the first agent to timely callback to the user.
Optionally, before S206, the call processing method provided in the embodiment of the present application may further include: if the message intention is inquiring service information, inquiring a target answer matched with the message intention from a preset service knowledge base; the user's call is turned on and the target answer is played to the user, or a response message is sent to the user, the response message including the target answer.
The business knowledge base stores business information of various businesses, such as business introduction, business handling channels, business handling sites and the like of the various businesses.
For example, after the call intention recognition module recognizes the message intention, if the message intention is "query the website of the service 1 in the area a", the CTI middleware searches the target answers hitting the keywords from the preset service knowledge base based on the keywords of "service 1", "area a" and "website" in the message intention, for example, the website of the service 1 in the area a has website 1, website 2 and website 3, and calls the IVR component to connect the call of the user and play the target answer to the user, or sends a response message containing the target answer to the user.
It can be appreciated that in an actual call scenario, the IVR component typically covers most of the business self-service, and the user changes the navigation menu played by the IVR component to manual service, often because the user is unfamiliar with the use of the IVR navigation menu or does not know other self-service channels to seek help from the seat, and the answer to such questions often has a fixed answer; based on the method, under the condition that the message intention is identified as inquiring service information, the answer is inquired in the service knowledge base and fed back to the user, so that the function of timely and quickly responding to the user message can be achieved, the problem can be solved for the user in time, the one-time problem solving rate can be improved, the repeated incoming line rate can be reduced, and the user complaint rate can be reduced.
Referring to fig. 3, a flow chart of a call processing method according to another embodiment of the present application is provided, where the flow chart describes a scenario in which a user dials an enterprise service line through a mobile terminal in some call scenarios. As shown in fig. 3, the method comprises the steps of:
the enterprise accepts traffic through the IVR component and plays the navigation menu to the user.
If the user selects self-service handling service or hangs up according to the navigation menu, the call is ended after the corresponding processing is executed according to the user selection.
If the user selects to transfer manual service according to the navigation menu, the IVR component sends a transfer manual request to the CTI middleware, and the CTI middleware responds to the transfer manual request to transfer the incoming call of the user to the idle first seat.
If the user incoming call is successfully transferred to the first seat, the first seat answers the user incoming call, and user appeal is solved.
If the user fails to transfer the incoming call to the first seat or the user selects a message, the IVR component triggers a voice message function to receive voice message information of the user. And finishing after the user leaves the message.
After receiving the voice message information of the user, the IVR component requests the CTI middleware to call the ICC voice conversion text module to perform voice conversion text processing on the voice message information to obtain corresponding text content, and the voice message information and the text content thereof are uploaded to a file management system as voice message files for storage.
After obtaining the text content of the voice message, the ICC middleware invokes an intention recognition model to recognize the intention of the voice message according to the text content of the voice message.
If the recognized message intention indicates that the voice message information has the message intention for inquiring the service information, inquiring a target answer matched with the message intention from a preset service knowledge base; the user's call is turned on and the target answer is played to the user, or a response message is sent to the user, the response message including the target answer.
If the identified message intention does not contain query service information and the message intention indicates that the emergency degree of the voice message information is greater than or equal to a preset upper limit value, for example, the user has complaint intention, guiding secondary transfer, namely marking the transfer priority of the user as the highest based on the emergency degree of the voice message information, inserting the user into the first position of a transfer user queue, enabling the user incoming call to be preferentially transferred to a second seat with high idle degree, and solving the user complaint by the second seat.
If the identified message intention mark is smaller than or equal to a preset lower limit value, for example, the message intention is clearing evidence, etc., the user is added to a callback user list, and the first agent calls back the user in the callback user list according to the requirement afterwards.
If the identified message intention is smaller than a preset upper limit value and larger than a preset lower limit value, such as applying for delay repayment and the like, after the user is added to the callback user name, the conversation priority of each user in the callback user name is determined based on the urgency degree of voice message information, each user is ordered according to the callback priority, corresponding message intention labels are marked for the users in a callback list of the users, the ordered callback user list is pushed to a first seat, and whether callback operation is performed or not is determined by the first seat according to each user and the message intention labels after ordering.
Referring to fig. 4, a flow chart of a call processing method according to another embodiment of the present application is provided, where the flow chart describes an interaction process between components or functional modules, such as an IVR component, a routing communication component, a CTI middleware, a voice-to-text module, and an intention recognition module, in ICC. As shown in fig. 4, the method comprises the steps of:
firstly, after receiving a call request sent by a user through PSTN, the IVR component plays a navigation menu to the user.
If the user selects the manual service, the IVR component sends a manual request to the CTI middleware through the routing communication component.
After receiving the manual transfer request, the CTI middleware performs Automatic Call Distribution (ACD), if no free seat exists currently, the CTI middleware plays waiting music to the user through the IVR, and after waiting for a preset time period, the IVR component is triggered to play a menu to the user so as to enable the user to select whether to continue waiting or not; if the user chooses to continue waiting, the waiting music continues to be played.
If the user chooses not to wait continuously or the number of times of waiting continuously reaches the preset number of times, the IVR component automatically triggers a voice message function and invokes a recording application (record app) of the routing communication component to record the user message. In addition, the IVR component also sends a start message and a cancel queuing message to the CTI middleware to instruct the CTI middleware to cancel the transit first agent for the user.
After the message is finished, the IVR component uploads the message information of the user to the file management system and sends the message finishing message to the CTI middleware through the routing communication component.
After receiving the message completion message, the CTI middleware acquires the voice message information from the file management system, and the voice-to-text module performs voice-to-text processing on the voice message information to obtain corresponding text content, uploads the text content to the file management system and stores the text content corresponding to the voice message information.
The CTI middleware also calls an intention recognition module, and the intention recognition module carries out intention recognition on the voice message information based on a preset intention recognition algorithm to obtain a message intention.
If the message intention is to inquire the service information, the CTI middleware inquires a target answer matched with the message intention from a preset service knowledge base, and connects the call of the user through the IVR component and plays the target answer to the user or sends a response message containing the target answer to the user.
If the message intention does not contain the inquiry service information, the CTI middleware determines the emergency degree of the voice message information based on the message intention, selects a target seat response strategy matched with the emergency degree from a plurality of preset seat response strategies, and responds to the voice message information.
According to the call processing method provided by one or more embodiments of the application, when a user initiates a call to an agent, if a voice message function is triggered, voice message information of the user is received, the voice message information is subjected to intention recognition to obtain a message intention, and the emergency degree of the voice message information is determined based on the message intention; further, a plurality of agent response strategies are preset, specifically, a response strategy of calling back is initiated by a first agent with low call idle degree or a response strategy of transferring a call to a second agent with high call idle degree is included, and as the response timeliness of different response strategies is different, the response is carried out by matching the corresponding target agent response strategy with the voice message information according to the emergency degree of the voice message information, the effect of pertinently responding to the user message according to the light and heavy emergency can be achieved, the user appeal is solved more timely and effectively, the one-time problem solving rate is improved, the times of repeated incoming lines due to incapacitation of the user appeal are reduced, and the user satisfaction is improved.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The embodiment of the application also provides a call processing device. Referring to fig. 5, a schematic structural diagram of a call processing apparatus 500 according to an embodiment of the present application is provided, where the apparatus 500 may include:
a receiving unit 510, configured to receive, when a voice message function is triggered during a call initiated by a user to a first agent, voice message information of the user;
the recognition unit 520 is configured to perform intention recognition on the voice message information to obtain a message intention;
a determining unit 530 for determining an urgency level of the voice message information based on the message intention;
and a response unit 540, configured to respond to the voice message information based on a target agent response policy matching with the urgency degree in a preset multiple agent response policy, where the multiple agent response policy includes a response policy that the first agent initiates a callback and a response policy that the call is transferred to a second agent, and the call idle degree of the second agent is higher than the call idle degree of the first agent.
Optionally, in the case that the degree of urgency exceeds a preset upper limit value, the target agent response policy includes a response policy for forwarding the call to a second agent;
the answering unit 540 is specifically configured to:
marking a switching priority for the user based on the emergency level, the switching priority being positively correlated with the emergency level;
and adding the user to a transit user queue based on the transit priority of the user, wherein the transit user queue is used for storing users to be transited to the second agent, which are ordered according to the transit priority, and the second agent responds to the conversation of the user in the user queue.
Optionally, before adding the user to the transit user queue based on the transit priority of the user, the answering unit 540 is further configured to:
before adding the user to a transit user queue based on the transit priority of the user, playing transit guide information to the user, wherein the transit guide information is used for guiding the user to confirm to initiate a call to the second agent again;
and responding to the confirmation operation of the user on the transfer guide information, and adding the user into a transfer user queue based on the transfer priority of the user.
Optionally, the answering unit 540 is further configured to:
after the transfer guide information is played to the user, responding to the refusal operation of the user on the transfer guide information, adding the user into a callback user list, wherein the callback user list is used for recording the user to be callback by a first seat;
marking corresponding callback priority for the user in the callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated;
and pushing the marked callback user list to the first seat.
Optionally, the answering unit 540 is further configured to: before adding the user into a transit user queue based on the transit priority of the user, acquiring a message time corresponding to the voice message information;
and if the message leaving time belongs to the non-working period of the second agent, sending a call request to the second agent through the appointed communication number of the second agent, wherein the call request is used for requesting to establish a call between the user and the second agent.
Optionally, in the case that the degree of urgency is less than a preset upper limit value, the target agent response policy includes a response policy that the first agent initiates a callback;
The answering unit 540 is specifically configured to:
adding the user to a callback user list, wherein the callback user list is used for recording the users to be callback by a first seat, and each user in the callback user list corresponds to a message intention label;
determining callback priority of each user in the callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated;
and sequencing each user according to the callback priority, pushing the sequenced callback user list to the first seat, and determining whether to perform callback operation by the first seat according to each sequenced user and the message intention label thereof.
Optionally, the answering unit 540 is further configured to: before the determining unit 530 determines the urgency of the voice message information based on the message intention, if the message intention is to query service information, a target answer matched with the message intention is queried from a preset service knowledge base;
and connecting the call of the user and playing the target answer to the user, or sending a response message to the user, wherein the response message comprises the target answer.
It is obvious that the call processing apparatus provided in the embodiment of the present application can be used as an execution subject of the call processing method shown in fig. 2, for example, in the service recommendation method shown in fig. 2, the step S202 may be executed by the receiving unit 510 in the call processing apparatus shown in fig. 5, the step S204 may be executed by the identifying unit 520 in the call processing apparatus shown in fig. 5, and the step S206 may be executed by the determining unit 530 in the call processing apparatus shown in fig. 5; step S208 is performed by the answering unit 540 in the call processing apparatus shown in fig. 5.
According to another embodiment of the present application, each unit in the call processing apparatus shown in fig. 5 may be separately or completely combined into one or several other units, or some unit(s) thereof may be further split into a plurality of units with smaller functions, which may achieve the same operation without affecting the implementation of the technical effects of the embodiments of the present application. The above units are divided based on logic functions, and in practical applications, the functions of one unit may be implemented by a plurality of units, or the functions of a plurality of units may be implemented by one unit. In other embodiments of the present application, the call processing apparatus may also include other units, and in practical applications, these functions may also be implemented with assistance of other units, and may be implemented by cooperation of multiple units.
According to another embodiment of the present application, a call processing apparatus as shown in fig. 5 may be constructed by running a computer program (including program code) capable of executing the steps involved in the respective methods as shown in fig. 2 on a general-purpose computing device such as a computer including a processing element such as a central processing unit (Central Processing Unit, CPU), a random access storage medium (Random Access Memory, RAM), a Read-Only Memory (ROM), or the like, and a storage element, and implementing the call processing method of the present application. The computer program may be recorded on, for example, a computer readable storage medium, transferred to, and run in, an electronic device via the computer readable storage medium.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 6, at the hardware level, the electronic device includes a processor, and optionally an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry Standard Architecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one bi-directional arrow is shown in FIG. 6, but not only one bus or type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form a call processing device on a logic level. The processor is used for executing the programs stored in the memory and is specifically used for executing the following operations:
in the process that a user initiates a call to a first seat, if a voice message function is triggered, receiving voice message information of the user;
Carrying out intention recognition on the voice message information to obtain a message intention;
determining the urgency of the voice message information based on the message intent;
and responding to the voice message information based on a target agent response strategy matched with the emergency degree in preset multiple agent response strategies, wherein the multiple agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
The method executed by the call processing device disclosed in the embodiment shown in fig. 2 of the present application may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or by instructions in the form of software. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
The electronic device may further execute the method of fig. 2 and implement the functions of the call processing apparatus in the embodiments shown in fig. 2, 3 and 4, which are not described herein.
Of course, other implementations, such as a logic device or a combination of hardware and software, are not excluded from the electronic device of the present application, that is, the execution subject of the following processing flow is not limited to each logic unit, but may be hardware or a logic device.
The present embodiments also provide a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a portable electronic device comprising a plurality of application programs, enable the portable electronic device to perform the method of the embodiment of fig. 1, and in particular to:
in the process that a user initiates a call to a first seat, if a voice message function is triggered, receiving voice message information of the user;
carrying out intention recognition on the voice message information to obtain a message intention;
determining the urgency of the voice message information based on the message intent;
And responding to the voice message information based on a target agent response strategy matched with the emergency degree in preset multiple agent response strategies, wherein the multiple agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
In summary, the foregoing description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

Claims (10)

1. A call processing method, comprising:
in the process that a user initiates a call to a first seat, if a voice message function is triggered, receiving voice message information of the user;
carrying out intention recognition on the voice message information to obtain a message intention;
determining the urgency of the voice message information based on the message intent;
and responding to the voice message information based on a target agent response strategy matched with the emergency degree in preset multiple agent response strategies, wherein the multiple agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
2. The method according to claim 1, wherein the target agent answer policy includes an answer policy to transfer the call to a second agent in case the degree of urgency exceeds a preset upper limit;
the responding to the voice message information based on the target agent response strategy matched with the emergency degree in the preset various agent response strategies comprises the following steps:
marking a switching priority for the user based on the emergency level, the switching priority being positively correlated with the emergency level;
and adding the user to a transit user queue based on the transit priority of the user, wherein the transit user queue is used for storing users to be transited to the second agent, which are ordered according to the transit priority, and the second agent responds to the call of the user in the transit user queue.
3. The method of claim 2, wherein prior to adding the user to a transit user queue based on the transit priority of the user, the method further comprises:
the transfer guide information is played to the user and used for guiding the user to confirm to initiate a call to the second seat again;
The adding the user to a transit user queue based on the transit priority of the user includes:
and responding to the confirmation operation of the user on the transfer guide information, and adding the user into a transfer user queue based on the transfer priority of the user.
4. The method of claim 3, wherein after playing the diversion guide information to the user, the method further comprises:
responding to the refusal operation of the user on the transfer guide information, and adding the user into a callback user list, wherein the callback user list is used for recording the user to be callback by a first seat;
marking corresponding callback priority for the user in the callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated;
and pushing the marked callback user list to the first seat.
5. The method of claim 2, wherein prior to adding the user to a transit user queue based on the transit priority of the user, the method further comprises:
acquiring the message leaving time corresponding to the voice message information;
And if the message leaving time belongs to the non-working period of the second agent, sending a call request to the second agent through the appointed communication number of the second agent, wherein the call request is used for requesting to establish a call between the user and the second agent.
6. The method according to claim 1, wherein the target agent response policy includes a response policy for initiating a callback by the first agent in case the degree of urgency is less than a preset upper limit value;
the responding to the voice message information based on the target agent response strategy matched with the emergency degree in the preset various agent response strategies comprises the following steps:
adding the user to a callback user list, wherein the callback user list is used for recording the users to be callback by a first seat, and each user in the callback user list corresponds to a message intention label;
determining callback priority of each user in the callback user list based on the urgency degree of the voice message information, wherein the callback priority and the urgency degree are positively correlated;
and sequencing each user according to the callback priority, pushing the sequenced callback user list to the first seat, and determining whether to perform callback operation by the first seat according to each sequenced user and the message intention label thereof.
7. The method of claim 1, wherein prior to determining the urgency of the voice message based on the message intent, the method further comprises:
if the message intention is inquiring service information, inquiring a target answer matched with the message intention from a preset service knowledge base;
and connecting the call of the user and playing the target answer to the user, or sending a response message to the user, wherein the response message comprises the target answer.
8. A call processing apparatus, comprising:
the receiving unit is used for receiving voice message information of the user if the voice message function is triggered in the process that the user initiates a call to the first seat;
the recognition unit is used for carrying out intention recognition on the voice message information to obtain a message intention;
a determining unit for determining an urgency degree of the voice message information based on the message intention;
and the response unit is used for responding to the voice message information based on a target agent response strategy matched with the emergency degree in a plurality of preset agent response strategies, wherein the plurality of agent response strategies comprise a response strategy for initiating a callback by the first agent and a response strategy for transferring the call to a second agent, and the call idle degree of the second agent is higher than that of the first agent.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the call processing method of any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the call processing method according to any one of claims 1 to 7.
CN202310735851.XA 2023-06-20 2023-06-20 Call processing method and device, electronic equipment and storage medium Pending CN117499536A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310735851.XA CN117499536A (en) 2023-06-20 2023-06-20 Call processing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310735851.XA CN117499536A (en) 2023-06-20 2023-06-20 Call processing method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117499536A true CN117499536A (en) 2024-02-02

Family

ID=89669640

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310735851.XA Pending CN117499536A (en) 2023-06-20 2023-06-20 Call processing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117499536A (en)

Similar Documents

Publication Publication Date Title
JP6743246B2 (en) Real-time voice delivery to agent greetings
US10171665B2 (en) Contact center session preservation
US6587558B2 (en) System and method for virtual interactive response unit
US8787546B2 (en) Apparatus, system, and method for automated call initiation
US8774394B2 (en) System and method for eliminating hold time in a telecommunications network
US8351595B2 (en) Restoration of a caller to a previous place in an on-hold queue
US20130114801A1 (en) Customer-controlled recording
US7929686B2 (en) System and method for managing request priority in a telecommunications network
US10791218B2 (en) Sending progress update messages while a user is on hold
US20220109756A1 (en) Communications processing
CN109120804B (en) Outbound system based on response information identification
US10681215B1 (en) Multi-dimensional attribute-based routing
CN117499536A (en) Call processing method and device, electronic equipment and storage medium
CN110913085A (en) Method and device for positioning user requirements
CN115766942A (en) Customer service switching method, device, equipment and storage medium
KR100516556B1 (en) System for voice and text complex ars service
CN110198383B (en) Address detection method, system, device and storage medium
US11632466B2 (en) Systems and methods for communication processing
EP1718085A2 (en) Method for eliminating hold time in a telecommunications network
KR100699330B1 (en) Information Offering System and Method using real-time streaming transmitting

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