CN111901486A - Voice call processing method and device and electronic equipment - Google Patents
Voice call processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111901486A CN111901486A CN202010676849.6A CN202010676849A CN111901486A CN 111901486 A CN111901486 A CN 111901486A CN 202010676849 A CN202010676849 A CN 202010676849A CN 111901486 A CN111901486 A CN 111901486A
- Authority
- CN
- China
- Prior art keywords
- session
- text
- seat
- user
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 92
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000004044 response Effects 0.000 claims abstract description 25
- 230000001960 triggered effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 5
- 230000003993 interaction Effects 0.000 abstract description 31
- 230000008569 process Effects 0.000 abstract description 14
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 8
- 230000002452 interceptive effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/50—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
-
- 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
- H04M3/5141—Details of processing calls and other types of contacts in an unified manner
Landscapes
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application discloses a voice call processing method, belongs to the technical field of communication, and is beneficial to improving the call processing efficiency of a voice interaction system. The method comprises the following steps: creating a session interface of a session processed by a current seat of a seat client in real time; simultaneously displaying session interfaces of all sessions processed by the current seat in real time in a display area of a seat client; receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by a call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session; determining a seat reply text in response to a selection and/or editing operation on the displayed candidate reply text; the seat reply text is converted into first voice data through the call management module and is sent to the user side communication equipment, so that one seat can process multiple paths of calls at the same time, and the call processing efficiency of the voice interaction system is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of communication, and in particular relates to a voice call processing method and device, an electronic device and a computer-readable storage medium.
Background
The voice interaction system is widely applied to a customer service platform and other platforms needing to answer a large number of user calls. When receiving an incoming call of a user, a voice exchange module (such as a telephone exchange) of the voice interaction system transfers the incoming call of the user to a call management module, the call management module selects an idle seat to process the call data of the user, then the voice exchange module performs link connection between the user telephone and the selected seat telephone, and the selected seat performs voice interaction with the user to realize functions such as customer service. In the prior art, in the process of call processing of the user, a selected seat can only perform voice interaction with the user, and cannot simultaneously perform interaction with other users until the call processing is finished (such as a user hangs up a phone call, a seat hangs up a phone call, and the like), so that the number of calls accessed by a voice interaction system at the same time is limited under the condition that the number of seats is limited, for example, a voice interaction system with 100 seats can only process 100 calls at most at the same time.
In order to increase the number of incoming calls accessed by a voice interactive system at the same time, a common method in the prior art is to optimize a seat scheduling strategy of the voice interactive system and reduce the idle time of a seat and the incoming call waiting time of a user as much as possible. Or the service proficiency of the seat personnel is improved by training the seat personnel. However, the method in the prior art can only slightly improve the incoming call processing performance of the user who is processed within a period of time, and does not improve the incoming call processing performance of the concurrent incoming call of the voice interactive system.
It can be seen that there is still a need for improvement in the prior art voice interactive systems.
Disclosure of Invention
The embodiment of the application provides a voice call processing method, which can realize a multi-path parallel voice call processing method.
In order to solve the foregoing problem, in a first aspect, an embodiment of the present application provides a voice call processing method, including:
creating a session interface of a session processed by a current seat of a seat client in real time;
displaying a session interface of all sessions processed by the current seat in real time at the seat client;
receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by the call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session;
in response to a selection and/or editing operation on the displayed candidate reply text, determining a seat reply text;
and converting the seat reply text into first voice data through the call management module, and sending the first voice data to the user side communication equipment of the session.
In a second aspect, an embodiment of the present application provides a voice call processing apparatus, including:
the session interface creating unit is used for creating a session interface of each session processed by the current position of the position client in real time;
the conversation interface display unit is used for displaying the conversation interfaces of all the conversations processed by the current position in real time at the position client;
a session text and candidate reply text display unit, configured to receive a user session text corresponding to a specified session and at least one candidate reply text for the user session text, which are sent by the call management module, and display the user session text and the at least one candidate reply text on the session interface of the specified session;
the agent reply text determining unit is used for responding to the selection and/or editing operation of the displayed candidate reply text and determining an agent reply text;
and the voice data sending unit is used for converting the seat reply text into first voice data through the call management module and sending the first voice data to the user side communication equipment of the session.
In a third aspect, an embodiment of the present application provides a voice call processing method, including:
establishing a session associated with the calling request information according to the calling request information sent by a preset seat client; establishing a session associated with incoming call request information according to the incoming call request information sent by a preset voice exchange module;
sending the created session information of the session to the preset voice exchange module for storage;
responding to real-time voice data of an appointed conversation sent by the preset voice exchange module, converting the real-time voice data into a user conversation text, and then sending the user conversation text and at least one candidate reply text aiming at the user conversation text to an agent client logged in by an agent of the appointed conversation, wherein the real-time voice data is sent to the agent of the appointed conversation by a user end communication device of the appointed conversation; or,
and responding to the received seat reply text of the appointed conversation sent by the preset seat client, converting the seat reply text into first voice data, and sending the first voice data to the user side communication equipment of the appointed conversation through the preset voice exchange module.
The voice call processing method disclosed by the embodiment of the application comprises the steps of creating a session interface of a session processed by a current seat of a seat client in real time; displaying a session interface of all sessions processed by the current seat in real time at the seat client; receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by the call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session; in response to a selection and/or editing operation on the displayed candidate reply text, determining a seat reply text; the seat reply text is converted into first voice data by the call management module and is sent to the user side communication equipment of the conversation, so that one seat can process multi-channel conversation simultaneously, and the conversation processing efficiency of the voice interaction system is greatly improved.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a flowchart of a voice call processing method according to a first embodiment of the present application;
fig. 2 is a schematic structural diagram of an application system of a voice call processing method according to a first embodiment of the present application;
FIG. 3 is a schematic diagram of a seat client interface according to an embodiment of the present application;
FIG. 4 is a schematic view of a session interface according to an embodiment of the present application;
fig. 5 is a flowchart of a voice call processing method according to a second embodiment of the present application;
fig. 6 is a schematic structural diagram of a voice call processing apparatus according to a third embodiment of the present application;
fig. 7 is a schematic structural diagram of a voice call processing apparatus according to a fourth embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
As shown in fig. 1, a method for processing a voice call, disclosed in an embodiment of the present application, includes: step 110 to step 150.
The voice call processing method described in the embodiment of the present application is applied to the voice interaction system shown in fig. 2, and the voice interaction system includes: a call management module 210, a voice switching module 220, and several agent clients 230. All parts operate cooperatively, and receive incoming voice calls and make voice outgoing calls through information interaction.
The agent client 230 is in communication connection with the call management module 210, and is configured to create and display a session interface, and perform data interaction with the call management module 210 according to the operation of an agent person. For example, the agent client 230 is configured to establish one or more text sessions according to the information sent by the call management module 210, receive text information sent by the call management module 210 for each text session, and send the text information to the call management module 210 according to the operation of an agent. The agent client 230 may also create a session interface based on the operations of the agent personnel.
The voice switching module 220 is in communication connection with the call management module 210, and is configured to receive an incoming telephone call and forward received incoming telephone call data to the call management module 210; and sending voice data to a designated communication device according to the control or interface call sent by the call management module 210. The voice exchange module 220 may be: a telephone exchange, or a software module with telephony voice switching functionality.
The call management module 210 is configured to convert the voice incoming call sent by the voice exchange module 220 into a text session and send the text session to the corresponding seat client 230, and convert text information sent by the seat client 230 into voice data and send the voice data to the voice exchange module 220, so as to implement communication between seat personnel and user side personnel.
In some embodiments of the present application, creating a session interface for a session processed in real-time by a current position of a position client comprises: in response to receiving first information which is sent by a call management module and indicates to access a session, a seat client creates a session interface which is processed by a current seat in real time and is associated with a session identifier carried in the first information; or, in response to second information which is sent by the call management module and indicates that the session is successfully created when the session is created by the call management module, the agent client creates a session interface which is processed by the current agent in real time and is associated with the session identifier carried in the second information. Each session is associated with a session interface, and the session, the session interface and the session identifier are in one-to-one correspondence.
In an embodiment of the present application, after receiving an incoming call of a user, the voice switching module 220 sends incoming call request information indicating that there is an incoming call to the call management module 210, where the incoming call request information generally includes: incoming call telephone number, incoming call time, etc.
Thereafter, the call management module 210 creates a session associated with the incoming call request information, and generates a session identifier identifying the session. Meanwhile, the call management module 210 creates a session data structure associated with the session for storing session description information and session records associated with the incoming call request information. Wherein the description information includes but is not limited to: the system comprises an incoming call telephone number, incoming call time, call duration, incoming call user name and session records, wherein the session records comprise voice data and corresponding text information, and each piece of voice data sent to user side personnel by seat personnel has information such as playing state, playing progress, playing time and the like.
In some embodiments of the present application, after creating the session data structure associated with the incoming call request information, the call management module 210 stores description information (such as an incoming call phone number, an incoming call time, and the like) of the incoming call of this time, which is parsed from the incoming call request information, in the session data structure. Then, the call management module 210 allocates a seat person for the voice interaction to interact with the user-side person. The call management module 210 selects a seat person according to a preset seat scheduling policy, and sends first information indicating an access session to a seat client 230 on which the selected seat person logs, where the first information carries information such as a session identifier and session description information of the session. Meanwhile, the selected agent information is stored in the session data structure associated with the session, so that after the selected agent receives the first information through the agent client 230, a session which is processed in real time by the current agent of the agent client 230 and is associated with the session identifier carried in the first information is created; and displaying a session interface of all sessions processed by the current position in real time at the position client.
In some embodiments of the present application, the preset seat scheduling policy includes: and selecting the online seat personnel with the minimum number of real-time processing sessions and the number smaller than the preset maximum parallel processing session number threshold value. In other embodiments of the present application, the online position personnel may be further selected according to the number of real-time processing sessions by combining information such as session processing efficiency and service type of the position personnel.
After selecting a seat person, the call management module 210 generates first information according to the description information of the incoming call and a session identifier of a session created according to the incoming call, and sends the first information to the seat client 230 where the selected seat person logs in.
After receiving the first information indicating to access the session sent by the call management module 210, the agent client 230 creates a session interface according to the description information (such as the incoming call phone number, the incoming call time, the incoming call user's call title, and other information) and the session identifier carried in the first information. The session interface is associated with the description information and the session identifier carried in the first information.
After the agent client 230 successfully creates the session interface associated with the session identifier carried in the first information, the agent client 230 caches the association relationship between the session identifier and the session interface. The call management module 210 associates the agent person with the session through a session data structure, and stores the state of the current session as an ongoing state in the session data structure.
In other embodiments of the present application, the seat client 230 sends outgoing request information to the call management module 210 according to an operation of creating an outgoing call session triggered by a current seat, where the outgoing request information carries an identity of the seat person, an outgoing telephone number, and an identifier of the seat client. After receiving the outgoing call request information, the call management module 210 creates a session associated with the outgoing call request information, and generates a session identifier for identifying the session. Meanwhile, the call management module 210 creates a session data structure associated with the session for storing session description information and session records associated with the incoming call request information. Wherein the description information includes but is not limited to: information such as the calling telephone number, the calling time, the call duration, the calling user name, and the conversation record. Then, the call management module 210 generates second information indicating that the session has been successfully created according to the session identifier and the description information, and feeds back the second information to the agent client that sent the outgoing call request information. After receiving the second information, the agent client 230 creates a session that is processed by the current agent of the agent client 230 in real time and is associated with the session identifier carried in the second information; and displaying a session interface of all sessions processed by the current position in real time at the position client.
And 120, displaying a session interface of all sessions processed by the current position in real time at the position client.
Wherein the all sessions include: a session interface for the session associated with the first information; a session interface of the session associated with the second information.
In some embodiments of the present application, each time the agent client 230 receives a first message indicating an access session, a session interface is created at the agent client 230, and the created session interface is associated with the received first message. In other embodiments of the present application, each time the agent client 230 receives a piece of second information indicating that the session has been successfully created, a session interface is also created at the agent client 230, and the created session interface is associated with the received piece of second information.
In some embodiments of the present application, each session corresponds to a session identifier and a session interface. The session identifier may be an incoming call phone number, or may be an identifier code of another form.
The session can be one-to-one corresponding to the session interface created by the agent client 230 and the session data structure stored by the call management module 210 through the session identifier. As shown in fig. 3, when a certain seat client 230 receives a plurality of first messages and/or second messages sent by the call management module 210 in sequence, a plurality of session interfaces are created in a display area of an interface of the seat client 230. In some embodiments of the present application, each session interface created by the agent client 230 is tiled and displayed in different display areas of the interface of the agent client 230, such as the session interfaces 310-330.
In this embodiment of the present application, displaying, at the agent client, a session interface of all sessions processed by the current agent in real time includes: and simultaneously tiling and displaying the session interfaces of all the sessions processed by the current seat in real time in different display areas of the seat client. The different display areas are not completely overlapped, and the purpose of the different display areas is to enable a seat person to read each conversation interface displayed in the interface of the seat client 230 without hindrance.
In some embodiments of the present application, as shown in fig. 4, each session interface is at least used for displaying the description information (e.g., 410 in fig. 4) of the session corresponding to the session, wherein the description information includes, but is not limited to, one or more of the incoming call phone number, the incoming call user name, the incoming call user title, the call duration, and the historical incoming call times, and the session record (e.g., 420 in fig. 4); or information such as a calling telephone number, a calling user name, a call duration, a session record and the like.
In other embodiments of the present application, each of the session interfaces is further configured to display a session information editing interface. A session information edit box for the agent to edit reply information for the session is displayed, as in area 430 of fig. 4.
In other embodiments of the present application, a session information setting interface is further included in the session interface, such as the area 440 in fig. 4. Through the conversation interface, the seat personnel can set whether the voice data obtained by converting the text information can be interrupted or not when being played to the client.
In still other embodiments of the present application, a session list, such as 340 in fig. 3, may also be displayed in the agent client. The session list is used for displaying summary information (one or more items of information such as incoming call telephone number, incoming call time, call duration, incoming call user name or name) of the session. The session list may further include: the list of sessions and the list of historical sessions are processed in real time, and the agent client 230 may display a session interface or a session detail interface of a session selected by an agent through the session list according to the trigger of the agent. After the agent client 230 creates a session interface associated with the session identifier carried by the first information or the second information, the method further includes: adding the session which is processed by the current position in real time and is associated with the session identifier carried by the first information or the second information into a list of the real-time processing session of the current position; and refreshing and displaying the list in a display area of the seat client, wherein summary information of all the sessions is displayed in the list.
And the voice interaction processing is obtained by converting voice data output by the communication equipment of the user end personnel of the specified conversation.
After the session is established, the call management module 210 converts the acquired voice data (i.e., the voice information sent by the user-side person to the corresponding seat person) output by the communication device of the user-side person of each session in real time into text information, generates session information by combining the session identifier (e.g., the session identifier generated by the call management module or the incoming call number), the timestamp of the voice data, and other information, and then sends the generated session information to the seat client associated with the session (i.e., the seat processing the drawing session in real time).
For example, when the communication device of the user end person in session 1 outputs voice data, the call management module 210 may acquire the voice data output by the communication device of the user end person through the voice exchange module 220, convert the voice data into text information, and then generate a piece of session information according to the text information, the incoming phone number of session 1, the timestamp of the voice information, and other information, and send the session information to the seat client associated with session 1. After receiving the session information, the agent client associated with the session 1 determines a session interface corresponding to the session information according to a session identifier (such as an incoming call number) carried in the session information, and updates a session record displayed in the determined session interface according to information such as text information, a time stamp of voice information and the like carried in the session information.
In some embodiments of the present application, in order to improve the call processing efficiency of the voice interactive system, each agent client may process multiple ongoing sessions simultaneously, i.e. one agent may handle multiple ongoing sessions simultaneously, in order to guarantee the fluency of each session, while the call management module 210 is sending session information to the agent client 230, the candidate reply text for the session text carried in the session information may be sent to the agent client 230 at the same time, and displayed on the session interface by the agent client 230 (e.g. 450 in fig. 4), so that the agent person may reply to the user-side person directly using the candidate reply text, or the seat personnel can simply modify the candidate reply text and then send the modified text to reply the user side personnel, so that the information reply efficiency is improved.
In some embodiments of the present application, the candidate reply text is obtained by: and matching the user session text corresponding to the appointed session and the context information of the user session text from a preset session text library. For example, when the user end person of session 1 outputs the voice data of "my computer crashed" through a communication device (such as a telephone), the voice exchange module 220 sends the voice data to the call management module 210, the call management module 210 converts the voice data into text information, and identifies the intention of the user end person through an intention recognition engine in the prior art according to the last few session records of session 1, and then the call management module 210 filters one or more candidate reply texts matching the intention through a preset text library, and sends the determined candidate reply texts to the seat client 230 associated with session 1. The determined candidate reply text is, for example, "you can try to restart the computer" or "do you need to repair the computer? "etc. preset dialogistic text.
In some embodiments of the present application, the candidate reply text may contain only the text content of the spoken text. In other embodiments of the present application, the candidate reply text includes text position information of text content with a higher editing probability in the dialect text, and usually the text content with the higher editing probability in the dialect text is an entity word with a certain meaning, such as a name (e.g., "you"), a greeting (e.g., "good morning"), a proper noun (e.g., a computer, a wire speed), and the like.
In some embodiments of the present application, the text position information of the entity in the linguistic text may be described by entity information, for example, a candidate reply text may be described by a data structure containing the linguistic text and the entity information.
In other embodiments of the present application, the candidate reply text may also be generated according to a preset text protocol, for example, text content with a higher editing probability is identified by a special character (e.g., @ your @ candidate reply text @ computer @ required to be repaired.
In other embodiments of the present application, the entities may also be identified in other manners, which is not illustrated in this embodiment.
In other embodiments of the present application, the candidate reply text includes text content and entity information, where the entity information is used to indicate a text position corresponding to a text to be replaced in the text content, and the candidate reply text may also be obtained by: matching to obtain candidate reply texts to be replaced from a preset conversation text library according to the user conversation texts corresponding to the specified conversations and the context information of the user conversation texts; and then, replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain the candidate reply text.
Wherein, the replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain a candidate reply text, includes: and replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the user terminal personnel information, the session establishment time and one or more items of context information in the session record which are matched with the user session text to obtain the candidate reply text. When the user end person who still uses session 1 outputs the voice data of "my computer crashed" through a communication device (such as a telephone), the voice exchange module 220 sends the voice data to the call management module 210, the call management module 210 converts the voice data into text information, and identifies the intention of the user end person through an intention identification engine in the prior art according to the last few session records of session 1, and then the call management module 210 filters one or more candidate reply texts matching the intention through a preset language text library, for example, does the determined language text in the candidate reply texts "you can try to restart the computer" or "do you need to repair the computer? "; then, the seat client 230 replaces the entity (e.g., "you") in the candidate reply text according to the user information (e.g., the user called "mr. liu"), the session establishment time (e.g., am), and so on, and the replaced candidate reply text is, for example, "mr. liu can try to restart the computer" or "mr. liu needs to repair the computer? ".
When the text content of the entity is replaced, the text content can be determined by using a corresponding method in the prior art according to different description information of the entity in the candidate reply text, which is not described herein again.
In some embodiments of the present application, in order to prompt the position of the text content with the highest editing probability in each candidate reply text of the seat person, some text contents with the highest editing probability (such as title and time) are usually displayed in special formats such as different fonts or highlighting or underlining, so as to form a differentiated display effect in the eyes of the user (such as the seat person). The candidate reply text comprises text content and entity information, the entity information is used for indicating a text position corresponding to a text to be replaced in the text content, and the step of displaying the at least one candidate reply text on the session interface of the specified session comprises the following steps: and in the session interface of the specified session, according to the entity information in each candidate reply text, performing differentiated display on text contents in the corresponding candidate reply text at the text position indicated by the entity information. For example, after receiving a candidate reply text of a piece of session information for session 1 sent by the call management module 210, the agent client 230 parses the text position corresponding to each entity in the format of the candidate reply text, and displays the text at the text position in a specified format (such as highlight, underline, bold) different from the format adopted by other texts, so that the entity is highlighted, and the agent can locate and/or edit the entity text conveniently.
In some embodiments of the present application, the displaying, at the agent client, a session interface of all sessions processed by the current agent in real time further includes: within the conversation interface of the conversation, a first portal, 460 in fig. 4, is displayed for a voice call with a user-side person of the conversation.
Correspondingly, after the step of displaying, at the agent client, the session interface of all sessions processed in real time by the current agent, the method further includes: and responding to the triggering of the first entrance, and sending third information to the call management module, so that the call management module controls a preset voice exchange module to establish a communication link between the current seat and the user side personnel after receiving the third information. When the agent client 230 detects that the first entry for voice call with the user-side person of the session is triggered (e.g., 460 is checked), the agent client 230 sends a third message to the call management module 210. After receiving the third information, the call management module 210 controls the voice exchange module 220 to establish a communication link between the current seat and the user-side person, and then the seat person and the user-side person perform voice communication.
The first entrance for voice communication with the user end personnel of the conversation is arranged on the conversation interface, so that real-time connection of text conversation voice communication can be realized. For example, when a complex problem that text conversation cannot be solved occurs, a seat person operates a seat client to send information, and a call management module establishes a voice call link between a user person and the seat person through a voice interaction module to perform voice communication, so that user experience is further improved.
In some embodiments of the present application, the displaying, at the agent client, a session interface of all sessions processed by the current agent in real time further includes: a second entry is displayed in the session interface of the session for interrupting the start of the sending function when the first voice data is sent to the user end communication device of the session, for example, a selection control 440 is displayed in the session interface shown in fig. 4.
Correspondingly, after the agent client displays the session interfaces of all the sessions processed by the current agent in real time, the method further includes: and responding to the triggering of the second entrance, sending fourth information to the call management module, so that after receiving the fourth information, when the call management module obtains real-time voice data output by the user side communication equipment through a preset voice exchange module, if the recognition result of the real-time voice data indicates that the user side personnel expect to terminate receiving the first voice data, controlling the preset voice exchange module to stop sending the first voice data to the user side communication equipment. For example, after the agent client 230 detects that the selection control 440 in the session interface of session 1 is checked, the agent client 230 sends fourth information to the call management module 210, where the fourth information carries a session identifier (such as an incoming phone number of session 1) for determining which session to interrupt the first voice data sent by the session. After receiving the fourth information, the call management module 210 controls the voice switching module 220 to stop the first voice data corresponding to the session 1 currently being transmitted.
In some embodiments of the present application, after controlling the voice switching module 220 to stop sending the first voice data to the user end communication device, the call management module 210 records a sending progress of the first voice data, and stores the sending progress in a session data structure of the session.
In some embodiments of the present application, the agent person may select the displayed candidate reply text in the session interface of the agent client 230. After the agent client 230 detects the selection operation of the agent person on the candidate reply text, the selected candidate reply text is displayed in the reply text edit box. And the seat personnel takes the selected candidate reply text as a seat reply text by triggering a button such as a 'send' button arranged on the conversation interface.
In other embodiments of the present application, the human agent may further edit the candidate reply text displayed in the reply text edit box, for example, modify the user's name, and then use the selected candidate reply text as the human agent reply text by triggering a "send" button, for example, set in the conversation interface.
The agent client 230 determines the content in the reply text edit box as the agent reply text after detecting the confirmation operation of the agent on the content in the reply text edit box.
In some embodiments of the present application, taking a voice call-in scenario as an example, after the call management module 210 selects an online seat person, the session identifier of the successfully established session is fed back to the voice exchange module 220. The voice switching module 220 will store the binding relationship between the session identifier and the corresponding incoming call phone number and establish a corresponding voice data transmission link.
The agent client 230 determines the content in the reply text edit box as the agent reply text after detecting the confirmation operation of the agent on the content in the reply text edit box. Meanwhile, the agent client 230 sends the agent reply text to the call management module 210, the call management module 210 converts the agent reply text into first voice data, and then sends the first voice data obtained by conversion to the user-side communication device of the session. For example, the call management module 210 sends the first voice data and the session identification association of the session to the voice switching module 220. Then, the voice switching module 220 sends the received first voice data to the incoming call phone number bound to the session identifier according to the voice data transmission link corresponding to the binding relationship between the pre-stored session identifier and the corresponding incoming call phone number.
The technical scheme for the voice exchange module 220 to send the voice data to the designated phone number is the prior art, and is not described in this embodiment.
In the process of sending the first voice data by the voice exchange module 220, the call management module 210 may obtain a sending schedule of the first voice data, and store the sending schedule into a session data structure of the session. In some embodiments of the present application, the voice exchange module 220 may monitor the sending progress of the first voice data by sending an event notification through a data packet of the registered communication link, or may learn the sending progress of the first voice data by using other methods, which is not limited in this application. The voice switching module 220 further synchronizes the sending progress of the acquired first voice data to the call management module 210 in real time.
In some embodiments of the present application, converting the seat reply text into first voice data by the call management module, and sending the first voice data to the user-side communication device of the session includes sending the seat reply text to the call management module; and displaying the agent reply text and the sending progress of the agent reply text in a session interface of the session, wherein the sending progress of the agent reply text is determined according to the sending progress of the first voice data sent by the call management module. For example, after sending the agent reply text to the call management module, the agent client 230 displays the agent reply text in the session record, and displays a sending progress bar of the agent reply text below the agent reply text. The call management module 210 synchronizes the sending progress to the agent client 230 associated with the session in real time, and the agent client 230 updates the progress displayed by the progress bar according to the sending progress of the first voice data.
In some embodiments of the application, the sending progress of the seat reply text may also be displayed in other manners, and the specific form of the progress bar is not limited in the application.
In some embodiments of the present application, after displaying the agent reply text in the session interface of the session, the method further includes: displaying a third entry in a session interface of the session, wherein the third entry suspends the sending of the first voice data to the user side communication equipment of the session; and sending fifth information indicating that the first voice data is stopped being sent to user side communication equipment to the call management module in response to the third entry being triggered, so that the call management module controls the preset voice switching module to stop sending the first voice data to the user side communication equipment according to the fifth information. For example, a pause control, such as 470 in FIG. 4, is displayed in the progress bar. When the agent client 230 detects that a pause control (i.e., a third entry) shown in fig. 4 in the session interface of session 1 is clicked, fifth information is sent to the call management module 210, where the fifth information includes a session identifier of session 1. The call management module 210 controls the voice switching module 220 to stop sending the first voice data to the user end communication device of the session 1 according to the fifth information.
The voice call processing method disclosed by the embodiment of the application comprises the steps of creating a session interface of a session processed by a current seat of a seat client in real time; displaying a session interface of all sessions processed by the current seat in real time at the seat client; receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by the call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session; in response to a selection and/or editing operation on the displayed candidate reply text, determining a seat reply text; the seat reply text is converted into first voice data by the call management module and is sent to the user side communication equipment of the conversation, so that one seat can process multi-channel conversation simultaneously, and the conversation processing efficiency of the voice interaction system is greatly improved.
According to the voice call processing method disclosed by the embodiment of the application, a seat person can simultaneously answer multiple paths of calls by improving the data interaction process of the voice interaction system in the prior art and combining the voice recognition technology and the text-to-voice technology, so that the call processing efficiency of the voice interaction system is improved. By combining the voice recognition technology and the text-to-voice technology, a call center seat personnel does not need to answer incoming calls of all users, the content of the user speaking is automatically converted into a text through voice recognition by the system, the seat personnel can quickly know the content of the user speaking through reading the text, and meanwhile, the system can carry out natural language processing according to the text result of the voice recognition, so that reply dialogs which are possibly used are pushed to the seat personnel, the seat personnel can quickly select the prepared reply dialogs in advance to reply the user, the information processing efficiency can be further improved, and the user does not feel delay.
On the other hand, the seat personnel can stop playing at any time according to the feedback of the user by observing the playing state, and can also select to automatically stop playing the reply voice when the client speaks, so that the user experience can be further improved.
Example two
As shown in fig. 5, a method for processing a voice call disclosed in an embodiment of the present application includes: steps 510 to 540.
The voice call processing method described in this embodiment is applied to the voice interaction system shown in fig. 2.
In some embodiments of the present application, after receiving an incoming call of a user, the voice switching module 220 sends incoming call request information to the call management module 210, where the incoming call request information generally includes: incoming call telephone number, incoming call time, etc. Thereafter, the call management module 210 creates a session associated with the incoming call request information and generates a session identifier for the session, and at the same time creates a session data structure associated with the session.
For the specific implementation of creating a session according to the incoming call request information, generating a session identifier, and creating a session data structure, the call management module 210 refers to the related description in the first embodiment, and details are not repeated here.
In some embodiments of the present application, after creating a session associated with incoming request information according to incoming request information sent by a preset voice exchange module, the method further includes: the call management module sends first information to the preset seat client, so that in response to receiving the first information which is sent by the call management module and indicates to access the session, the seat client creates a session interface which is processed by the current seat in real time and is associated with the session identifier carried in the first information.
And then, the position client displays a session interface of all sessions processed by the current position in real time at the position client.
For a specific implementation of the call management module 210 selecting a seat person, generating first information indicating an access session, and sending the first information to a seat client on which the selected seat person logs, refer to first embodiment, which is not described herein again.
For a specific implementation of creating a session interface according to the first information and refreshing the session interface of each session in the display area, reference is made to embodiment one, and details are not described here.
In other embodiments of the present application, after receiving the outgoing call request information sent by the seat client 230, the call management module 210 creates a session associated with the outgoing call request information and generates a session identifier of the session. The call management module 210 simultaneously creates a session data structure associated with the session identification.
The specific implementation of the call management module 210 creating a session according to the outgoing call request information, generating a session identifier, and creating a session data structure is described in the first embodiment, and is not described herein again.
In some embodiments of the present application, after creating a session associated with the outgoing call request information according to outgoing call request information sent by a preset seat client, the method further includes: the call management module sends second information to the preset seat client, so that the seat client responds to the second information which is sent by the call management module and indicates that the session is successfully established when the session is established through the call management module, and the seat client establishes a session interface which is processed by the current seat in real time and is associated with the session identifier carried in the second information.
For a specific implementation of the call management module 210 selecting a seat person, generating second information indicating that a session is successfully created, and sending the second information to a seat client on which the selected seat person logs, reference is made to embodiment one, which is not described herein again.
For a specific implementation of creating a session interface according to the second information and refreshing the session interface of each session in the display area, reference is made to embodiment one, and details are not described here.
Wherein the session information includes: the conversation type information comprises one or more of conversation identification, user terminal personnel information (such as a user terminal telephone number), seat personnel information (such as a seat personnel telephone number and a seat personnel identity identification) and conversation type (such as incoming call and outgoing call).
In some embodiments of the present application, after creating a session associated with the outgoing call request information according to the incoming call request information sent by the preset voice exchange module 220, the call management module 210 feeds back the created session information of the session to the preset voice exchange module 220. The preset voice exchange module 220 stores the session information for data exchange.
In other embodiments of the present application, after creating a session associated with outgoing call request information according to outgoing call request information sent by a preset seat client, the call management module 210 sends the created session information of the session to the preset voice exchange module 220. The preset voice exchange module 220 stores the session information for data exchange.
After the preset voice exchange module 220 stores the session information, the preset voice exchange module 220 may forward the voice data sent by the user and the voice data sent by the seat client according to the stored session information.
After the session is established, the call management module 210 may obtain, through the voice exchange module 220, voice data (i.e., voice information sent by the user-side person to the corresponding seat person) output by the communication device of the user-side person of each session in real time, then, the call management module 210 converts the voice data into text information, determines one or more candidate reply texts of the text information in combination with context information of the session, and then sends the converted text information and the candidate reply texts to a seat client associated with the session (i.e., a seat client logged in by a seat person associated with a session identifier of the session).
For a specific implementation of the call management module 210 obtaining the real-time voice data output by the ue in the session through the voice exchange module 220, reference is made to the related description in the first embodiment, and details are not described in this embodiment again.
The candidate reply text comprises text content and entity information, the entity information is used for indicating a text position corresponding to a text to be replaced in the text content, and the agent client displays at least one candidate reply text on the session interface of the specified session after receiving the at least one candidate reply text of the user session text, wherein the candidate reply text comprises: and in the session interface of the specified session, according to the entity information in each candidate reply text, performing differentiated display on text contents in the corresponding candidate reply text at the text position indicated by the entity information.
In some embodiments of the present application, the candidate reply text is obtained by: matching the user session text corresponding to the designated session and the context information of the user session text from a preset session text library; or matching to obtain candidate reply texts to be replaced from a preset conversation text library according to the user conversation texts corresponding to the specified conversations and the context information of the user conversation texts; and then, replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain the candidate reply text.
For the method for determining candidate reply texts, reference is made to the first embodiment, which is not described in detail in this embodiment.
For a specific embodiment of refreshing and displaying a session interface of a corresponding session after the seat client receives at least one candidate reply text of the user session text, refer to embodiment one, which is not described in detail in this embodiment.
In some embodiments of the present application, the agent may edit the agent reply text through the conversation interface.
For a specific implementation manner of determining the seat reply text of a session according to an operation of a seat person on a certain session interface, reference is made to embodiment one, and details are not described in this embodiment.
And the seat client responds to the operation of the seat personnel and sends a seat reply text of the specified session to the call management module.
After receiving the seat reply text sent by the seat client, the call management module converts the seat reply text into first voice data, determines session information (such as a session identifier and a user terminal telephone number) associated with the session according to the session to which the seat reply text belongs, and then sends the first voice data and the session information to the voice exchange module. And the voice exchange module sends the first voice data to the user side communication equipment indicated by the session information through a pre-established communication link associated with the session information.
In some embodiments of the present application, the agent client displays, at the agent client, a session interface of all sessions processed by the current agent in real time, including: and displaying a first entrance for carrying out voice communication with the user side personnel of the conversation in the conversation interface of the conversation. Correspondingly, the seat client sends third information to the call management module in response to the first portal being triggered. And after receiving the third information, the call management module controls a preset voice exchange module to establish a communication link between the current seat and the user side personnel. For example, after the agent client 230 detects that the first entry for voice call with the user-side person of the session is triggered (e.g., 460 is checked), the agent client 230 sends a third message to the call management module 210. After receiving the third information, the call management module 210 controls the voice exchange module 220 to establish a communication link between the current seat and the user-side person, and then, the current seat and the user-side person perform a voice communication.
The first entrance for voice communication with the user end personnel of the conversation is arranged on the conversation interface, so that real-time connection of text conversation voice communication can be realized. For example, when a complex problem that text conversation cannot be solved occurs, a seat person operates a seat client to send information, and a call management module establishes a voice call link between a user person and the seat person through a voice interaction module to perform voice communication, so that user experience is further improved.
In some embodiments of the present application, the agent client displays, at the agent client, a session interface of all sessions processed by the current agent in real time, including: and displaying a second inlet for interrupting the starting of the sending function when the first voice data is sent to the user side communication equipment of the session in the session interface of the session, and sending fourth information to the call management module by the seat client in response to the triggering of the second inlet. After the first voice data is sent to the user-side communication device of the specified session through the preset voice exchange module, the method further includes: after receiving the fourth message, the call management module controls the preset voice exchange module to stop sending the first voice data to the user side communication device if the recognition result of the real-time voice data indicates that the user side personnel expect to stop receiving the first voice data when the real-time voice data output by the user side communication device is obtained through the preset voice exchange module. For example, after the agent client 230 detects that the selection control 440 in the session interface of session 1 is checked, the agent client 230 sends fourth information to the call management module 210, where the fourth information carries a session identifier (such as an incoming phone number of session 1) for determining which session to interrupt the first voice data sent by the session. After receiving the fourth information, the call management module 210 controls the voice switching module 220 to stop the first voice data corresponding to the session 1 currently being transmitted.
In some embodiments of the present application, a third entry for suspending sending of the first voice data to the user-side communication device of the session is displayed in a session interface of the session; in response to the third entry being triggered, the seat client sends fifth information to the call management module indicating to stop sending the first voice data to a user-side communication device. Correspondingly, after the first voice data is sent to the user-side communication device of the specified session through the preset voice exchange module, the method further includes: receiving fifth information indicating that the first voice data is stopped being sent to user side communication equipment; and the call management module controls the preset voice exchange module to stop sending the first voice data to the user side communication equipment according to the fifth information. For example, a pause control, such as 470 in FIG. 4, is displayed in the progress bar. When the agent client 230 detects that a pause control (i.e., a third entry) shown in fig. 4 in the session interface of session 1 is clicked, fifth information is sent to the call management module 210, where the fifth information includes a session identifier of session 1. The call management module 210 controls the voice switching module 220 to stop sending the first voice data to the user end communication device of the session 1 according to the fifth information.
According to the voice call processing method disclosed by the embodiment of the application, a session related to call request information is established according to the call request information sent by a preset seat client; establishing a session associated with incoming call request information according to the incoming call request information sent by a preset voice exchange module; sending the created session information of the session to the preset voice exchange module for storage; responding to real-time voice data of an appointed conversation sent by the preset voice exchange module, converting the real-time voice data into a user conversation text, and then sending the user conversation text and at least one candidate reply text aiming at the user conversation text to an agent client logged in by an agent of the appointed conversation, wherein the real-time voice data is sent to the agent of the appointed conversation by a user end communication device of the appointed conversation; or, in response to receiving a seat reply text of an appointed session sent by the preset seat client, converting the seat reply text into first voice data, and sending the first voice data to the user side communication equipment of the appointed session through the preset voice exchange module, so that each seat client can simultaneously access multiple sessions, and the conversation processing efficiency of the voice interaction system is improved.
According to the voice call processing method disclosed by the embodiment of the application, the voice passing process is converted into the text conversation, so that one seat client can process multiple incoming calls in parallel, and the call processing efficiency of the voice interaction system is effectively improved.
EXAMPLE III
As shown in fig. 6, a voice call processing apparatus disclosed in an embodiment of the present application includes:
a session interface creating unit 610, configured to create a session interface for each session processed in real time by the current seat of the seat client;
a session interface display unit 620, configured to display, at the agent client, session interfaces of all sessions processed in real time by the current agent;
a session text and candidate reply text display unit 630, configured to receive a user session text corresponding to a specified session and at least one candidate reply text for the user session text, which are sent by the call management module, and display the user session text and the at least one candidate reply text on the session interface of the specified session;
a position reply text determination unit 640, configured to determine a position reply text in response to a selection and/or editing operation on the displayed candidate reply text;
a voice data sending unit 650, configured to convert the seat reply text into first voice data through the call management module, and send the first voice data to the user-side communication device of the session.
In some embodiments of the present application, the candidate reply text includes text content and entity information, where the entity information is used to indicate a text position corresponding to a text to be replaced in the text content, and displaying the at least one candidate reply text on the session interface of the specified session includes:
and in the session interface of the specified session, according to the entity information in each candidate reply text, performing differentiated display on text contents in the corresponding candidate reply text at the text position indicated by the entity information.
In some embodiments of the present application, the candidate reply text is obtained by:
matching the user session text corresponding to the designated session and the context information of the user session text from a preset session text library; or,
matching to obtain candidate reply texts to be replaced from a preset conversation text library according to the user conversation texts corresponding to the specified conversations and the context information of the user conversation texts; and then, replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain the candidate reply text.
In some embodiments of the present application, the step of displaying, at the agent client, a session interface of all sessions processed by the current agent in real time further includes:
displaying a first entrance for voice communication with a user terminal person of the conversation in a conversation interface of the conversation;
after the step of displaying, at the agent client, the session interfaces of all sessions processed in real time by the current agent, the method further includes:
and responding to the triggering of the first entrance, and sending third information to the call management module, so that the call management module controls a preset voice exchange module to establish a communication link between the current seat and the user side personnel after receiving the third information.
In some embodiments of the present application, the step of displaying, at the agent client, a session interface of all sessions processed by the current agent in real time further includes:
displaying a second inlet for interrupting the starting of the sending function when the first voice data is sent to the user side communication equipment of the conversation in the conversation interface of the conversation;
after the step of displaying, at the agent client, the session interfaces of all sessions processed in real time by the current agent, the method further includes:
and responding to the triggering of the second entrance, sending fourth information to the call management module, so that after receiving the fourth information, when the call management module obtains real-time voice data output by the user side communication equipment through a preset voice exchange module, if the recognition result of the real-time voice data indicates that the user side personnel expect to terminate receiving the first voice data, controlling the preset voice exchange module to stop sending the first voice data to the user side communication equipment.
In some embodiments of the present application, the step of converting the seat reply text into the first voice data by the call management module and sending the first voice data to the user side communication device of the session includes,
sending the seat reply text to the call management module;
and displaying the agent reply text and the sending progress of the agent reply text in a session interface of the session, wherein the sending progress of the agent reply text is determined according to the sending progress of the first voice data sent by the call management module.
In some embodiments of the present application, after displaying the agent reply text in the session interface of the session, the method further includes:
displaying a third entry in a session interface of the session, wherein the third entry suspends the sending of the first voice data to the user side communication equipment of the session;
and sending fifth information indicating that the first voice data is stopped being sent to user side communication equipment to the call management module in response to the third entry being triggered, so that the call management module controls the preset voice switching module to stop sending the first voice data to the user side communication equipment according to the fifth information.
The voice call processing apparatus disclosed in the embodiment of the present application is used to implement the voice call processing method described in the first embodiment of the present application, and specific implementation manners of each module of the apparatus are not described again, and reference may be made to specific implementation manners of corresponding steps in the method embodiments.
The voice call processing device disclosed by the embodiment of the application establishes a session interface of a session processed by the current seat of the seat client in real time; displaying a session interface of all sessions processed by the current seat in real time at the seat client; receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by the call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session; in response to a selection and/or editing operation on the displayed candidate reply text, determining a seat reply text; the seat reply text is converted into first voice data by the call management module and is sent to the user side communication equipment of the conversation, so that one seat can process multi-channel conversation simultaneously, and the conversation processing efficiency of the voice interaction system is greatly improved.
The voice call processing device disclosed by the embodiment of the application realizes that one seat person simultaneously answers multiple paths of calls by improving the data interaction flow of the voice interaction system in the prior art and combining the voice recognition technology and the text-to-voice technology, thereby improving the call processing efficiency of the voice interaction system. By combining the voice recognition technology and the text-to-voice technology, a call center seat personnel does not need to answer incoming calls of all users, the content of the user speaking is automatically converted into a text through voice recognition by the system, the seat personnel can quickly know the content of the user speaking through reading the text, and meanwhile, the system can carry out natural language processing according to the text result of the voice recognition, so that reply dialogs which are possibly used are pushed to the seat personnel, the seat personnel can quickly select the prepared reply dialogs in advance to reply the user, the information processing efficiency can be further improved, and the user does not feel delay.
On the other hand, the seat personnel can stop playing at any time according to the feedback of the user by observing the playing state, and can also select to automatically stop playing the reply voice when the client speaks, so that the user experience can be further improved.
Example four
As shown in fig. 7, a voice call processing apparatus disclosed in an embodiment of the present application includes:
a session creating unit 710, configured to create a session associated with the outgoing call request information according to the outgoing call request information sent by a preset seat client; establishing a session associated with incoming call request information according to the incoming call request information sent by a preset voice exchange module;
a session information storage unit 720, configured to send the created session information of the session to the preset voice exchange module for storage;
a session text and candidate reply text sending unit 730, configured to, in response to receiving real-time voice data of an appointed session sent by the preset voice exchange module, convert the real-time voice data into a user session text, and then send the user session text and at least one candidate reply text for the user session text to an agent client that an agent of the appointed session logs in, where the real-time voice data is sent to the agent of the appointed session by the user-side communication device of the appointed session; or,
the voice data sending unit 740 is configured to, in response to receiving the seat reply text of the specified session sent by the preset seat client, convert the seat reply text into first voice data, and send the first voice data to the user-side communication device of the specified session through the preset voice exchange module.
The candidate reply text comprises text content and entity information, the entity information is used for indicating a text position corresponding to a text to be replaced in the text content, and the agent client displays at least one candidate reply text on the session interface of the specified session after receiving the at least one candidate reply text of the user session text, wherein the candidate reply text comprises: and in the session interface of the specified session, according to the entity information in each candidate reply text, performing differentiated display on text contents in the corresponding candidate reply text at the text position indicated by the entity information.
In some embodiments of the present application, the candidate reply text is obtained by: matching the user session text corresponding to the designated session and the context information of the user session text from a preset session text library; or matching to obtain candidate reply texts to be replaced from a preset conversation text library according to the user conversation texts corresponding to the specified conversations and the context information of the user conversation texts; and then, replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain the candidate reply text.
In some embodiments of the present application, the apparatus further comprises:
a second information sending unit (not shown in the figure), configured to, after creating a session associated with the call request information according to the call request information sent by a preset seat client, generate second information indicating that the session has been successfully created according to a session identifier of the session, and send the second information to the preset seat client, so that the seat client creates a session interface that is processed in real time by a current seat and is associated with the session identifier carried in the second information, in response to the second information indicating that the session has been successfully created and sent by the call management module when the session is created by the call management module.
A first information sending unit (not shown in the figure), configured to, after creating a session associated with incoming request information according to the incoming request information sent by a preset voice exchange module, generate first information indicating an access session according to a session identifier of the session, and send the first information to the preset seat client, so that in response to receiving the first information indicating an access session sent by the call management module, the seat client creates a session interface that is processed in real time by a current seat and is associated with the session identifier carried in the first information.
In some embodiments of the present application, the apparatus further comprises:
and a call link establishing unit (not shown in the figure) configured to, after receiving the third information sent by the agent client, control the preset voice exchange module to establish a call link between the current agent of the agent client and the user end person.
In some embodiments of the present application, the apparatus further comprises:
a first sending control unit (not shown in the figure), configured to, after receiving the fourth information sent by the seat client, when the preset voice exchange module obtains the real-time voice data output by the user-side communication device, if the recognition result of the real-time voice data indicates that the user-side person expects to terminate receiving the first voice data, control the preset voice exchange module to stop sending the first voice data to the user-side communication device.
In some embodiments of the present application, the apparatus further comprises:
a second sending control unit (not shown in the figure), configured to control the preset voice exchange module to stop sending the first voice data to the user side communication device according to fifth information sent by the seat client.
The voice call processing apparatus disclosed in this embodiment is used to implement the voice call processing method described in the second embodiment of this application, and specific implementation of each module of the apparatus is not described again, and reference may be made to specific implementation of corresponding steps in the method embodiment.
According to the voice call processing device disclosed by the embodiment of the application, a session related to call request information is established according to the call request information sent by a preset seat client; establishing a session associated with incoming call request information according to the incoming call request information sent by a preset voice exchange module; sending the created session information of the session to the preset voice exchange module for storage; responding to real-time voice data of an appointed conversation sent by the preset voice exchange module, converting the real-time voice data into a user conversation text, and then sending the user conversation text and at least one candidate reply text aiming at the user conversation text to an agent client logged in by an agent of the appointed conversation, wherein the real-time voice data is sent to the agent of the appointed conversation by a user end communication device of the appointed conversation; or, in response to receiving a seat reply text of an appointed session sent by the preset seat client, converting the seat reply text into first voice data, and sending the first voice data to the user side communication equipment of the appointed session through the preset voice exchange module, so that each seat client can simultaneously access multiple sessions, and the conversation processing efficiency of the voice interaction system is improved.
According to the voice call processing device disclosed by the embodiment of the application, voice is converted into text conversation through the process, so that a seat client can process multiple incoming calls in parallel, and the call processing efficiency of a voice interaction system is effectively improved.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
Correspondingly, the application also discloses an electronic device, which comprises a memory, a processor and a program code which is stored on the memory and can be run on the processor, wherein when the processor executes the program code, the voice call processing method of the first embodiment or the second embodiment is realized.
The voice call processing method and device provided by the present application are introduced in detail above, and a specific example is applied in the text to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and a core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Reference herein to "one embodiment," "an embodiment," or "one or more embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Moreover, it is noted that instances of the word "in one embodiment" are not necessarily all referring to the same embodiment.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A method for processing a voice call, comprising:
creating a session interface of a session processed by a current seat of a seat client in real time;
displaying a session interface of all sessions processed by the current seat in real time at the seat client;
receiving a user session text corresponding to a specified session and at least one candidate reply text aiming at the user session text, which are sent by the call management module, and displaying the user session text and the at least one candidate reply text on the session interface of the specified session;
in response to a selection and/or editing operation on the displayed candidate reply text, determining a seat reply text;
and converting the seat reply text into first voice data through the call management module, and sending the first voice data to the user side communication equipment of the session.
2. The method according to claim 1, wherein the candidate reply texts comprise text contents and entity information, the entity information is used for indicating a text position corresponding to a text to be replaced in the text contents, and the step of displaying the at least one candidate reply text in the session interface of the specified session comprises:
and in the session interface of the specified session, according to the entity information in each candidate reply text, performing differentiated display on text contents in the corresponding candidate reply text at the text position indicated by the entity information.
3. The method of claim 1, wherein the candidate reply text is obtained by:
matching the user session text corresponding to the designated session and the context information of the user session text from a preset session text library; or,
matching to obtain candidate reply texts to be replaced from a preset conversation text library according to the user conversation texts corresponding to the specified conversations and the context information of the user conversation texts; and then, replacing the text to be replaced at each text position indicated by the entity information in the candidate reply text to be replaced according to the context information of the user session text to obtain the candidate reply text.
4. The method according to any one of claims 1 to 3, wherein the step of displaying, at the agent client, a session interface for all sessions processed by the current agent in real time further comprises:
displaying a first entrance for voice communication with a user terminal person of the conversation in a conversation interface of the conversation;
after the step of displaying, at the agent client, the session interfaces of all sessions processed in real time by the current agent, the method further includes:
and responding to the triggering of the first entrance, and sending third information to the call management module, so that the call management module controls a preset voice exchange module to establish a communication link between the current seat and the user side personnel after receiving the third information.
5. The method according to any one of claims 1 to 3, wherein the step of displaying, at the agent client, a session interface for all sessions processed by the current agent in real time further comprises:
displaying a second inlet for interrupting the starting of the sending function when the first voice data is sent to the user side communication equipment of the conversation in the conversation interface of the conversation;
after the step of displaying, at the agent client, the session interfaces of all sessions processed in real time by the current agent, the method further includes:
and responding to the triggering of the second entrance, sending fourth information to the call management module, so that after receiving the fourth information, when the call management module obtains real-time voice data output by the user side communication equipment through a preset voice exchange module, if the recognition result of the real-time voice data indicates that the user side personnel expect to terminate receiving the first voice data, controlling the preset voice exchange module to stop sending the first voice data to the user side communication equipment.
6. The method according to any one of claims 1 to 3, wherein the step of converting the seat reply text into first voice data by the call management module and sending the first voice data to the user side communication device of the session comprises,
sending the seat reply text to the call management module;
and displaying the agent reply text and the sending progress of the agent reply text in a session interface of the session, wherein the sending progress of the agent reply text is determined according to the sending progress of the first voice data sent by the call management module.
7. The method of claim 6, wherein after displaying the agent reply text within a session interface of the session, further comprising:
displaying a third entry in a session interface of the session, wherein the third entry suspends the sending of the first voice data to the user side communication equipment of the session;
and sending fifth information indicating that the first voice data is stopped being sent to user side communication equipment to the call management module in response to the third entry being triggered, so that the call management module controls the preset voice switching module to stop sending the first voice data to the user side communication equipment according to the fifth information.
8. A method for processing a voice call, comprising:
establishing a session associated with the calling request information according to the calling request information sent by a preset seat client; establishing a session associated with incoming call request information according to the incoming call request information sent by a preset voice exchange module;
sending the created session information of the session to the preset voice exchange module for storage;
responding to real-time voice data of an appointed conversation sent by the preset voice exchange module, converting the real-time voice data into a user conversation text, and then sending the user conversation text and at least one candidate reply text aiming at the user conversation text to an agent client logged in by an agent of the appointed conversation, wherein the real-time voice data is sent to the agent of the appointed conversation by a user end communication device of the appointed conversation; or,
and responding to the received seat reply text of the appointed conversation sent by the preset seat client, converting the seat reply text into first voice data, and sending the first voice data to the user side communication equipment of the appointed conversation through the preset voice exchange module.
9. A voice call processing apparatus, comprising:
the session interface creating unit is used for creating a session interface of each session processed by the current position of the position client in real time;
the conversation interface display unit is used for displaying the conversation interfaces of all the conversations processed by the current position in real time at the position client;
a session text and candidate reply text display unit, configured to receive a user session text corresponding to a specified session and at least one candidate reply text for the user session text, which are sent by the call management module, and display the user session text and the at least one candidate reply text on the session interface of the specified session;
the agent reply text determining unit is used for responding to the selection and/or editing operation of the displayed candidate reply text and determining an agent reply text;
and the voice data sending unit is used for converting the seat reply text into first voice data through the call management module and sending the first voice data to the user side communication equipment of the session.
10. An electronic device comprising a memory, a processor, and program code stored on the memory and executable on the processor, wherein the processor implements the voice call processing method of any one of claims 1 to 8 when executing the program code.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010676849.6A CN111901486A (en) | 2020-07-15 | 2020-07-15 | Voice call processing method and device and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010676849.6A CN111901486A (en) | 2020-07-15 | 2020-07-15 | Voice call processing method and device and electronic equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111901486A true CN111901486A (en) | 2020-11-06 |
Family
ID=73192663
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010676849.6A Pending CN111901486A (en) | 2020-07-15 | 2020-07-15 | Voice call processing method and device and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111901486A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115426434A (en) * | 2022-08-15 | 2022-12-02 | 北京达佳互联信息技术有限公司 | Data processing method, device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6829243B1 (en) * | 1999-05-26 | 2004-12-07 | Nortel Networks Limited | Directory assistance for IP telephone subscribers |
CN101990305A (en) * | 2009-07-30 | 2011-03-23 | 中兴通讯股份有限公司 | Call method, call center, application server and terminal for realizing multi-session |
CN107295288A (en) * | 2016-04-01 | 2017-10-24 | 中兴通讯股份有限公司 | The realization method and system that a kind of split screen is attended a banquet |
CN109151231A (en) * | 2017-06-27 | 2019-01-04 | 中兴通讯股份有限公司 | The processing method of customer service system, the processing method of incoming call business and business |
CN110473550A (en) * | 2019-08-21 | 2019-11-19 | 北京小米智能科技有限公司 | Voice communication method, device and storage medium |
-
2020
- 2020-07-15 CN CN202010676849.6A patent/CN111901486A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6829243B1 (en) * | 1999-05-26 | 2004-12-07 | Nortel Networks Limited | Directory assistance for IP telephone subscribers |
CN101990305A (en) * | 2009-07-30 | 2011-03-23 | 中兴通讯股份有限公司 | Call method, call center, application server and terminal for realizing multi-session |
CN107295288A (en) * | 2016-04-01 | 2017-10-24 | 中兴通讯股份有限公司 | The realization method and system that a kind of split screen is attended a banquet |
CN109151231A (en) * | 2017-06-27 | 2019-01-04 | 中兴通讯股份有限公司 | The processing method of customer service system, the processing method of incoming call business and business |
CN110473550A (en) * | 2019-08-21 | 2019-11-19 | 北京小米智能科技有限公司 | Voice communication method, device and storage medium |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115426434A (en) * | 2022-08-15 | 2022-12-02 | 北京达佳互联信息技术有限公司 | Data processing method, device and storage medium |
CN115426434B (en) * | 2022-08-15 | 2023-10-31 | 北京达佳互联信息技术有限公司 | Data processing method, device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109413286B (en) | Intelligent customer service voice response system and method | |
CN109873909B (en) | Voice calling method, device and equipment and computer storage medium | |
US7606718B2 (en) | Apparatus and method for processing service interactions | |
US9992336B2 (en) | System for analyzing interactions and reporting analytic results to human operated and system interfaces in real time | |
US7471786B2 (en) | Interactive voice response system with partial human monitoring | |
US7573985B2 (en) | Systems and methods for facilitating communications involving hearing-impaired parties | |
US7315612B2 (en) | Systems and methods for facilitating communications involving hearing-impaired parties | |
CN110392168B (en) | Call processing method, device, server, storage medium and system | |
CN110035187A (en) | A method of realizing AI and operator attendance seamless switching in the phone | |
US20120196262A1 (en) | Methods and Systems for Obtaining Profile Information from Individuals Using Automation | |
CN110891124A (en) | System for artificial intelligence pick-up call | |
US20050071178A1 (en) | Data session notification means and method | |
CN112838978B (en) | System and method for real-time short message robot supporting man-machine cooperation | |
EP3138272B1 (en) | Voice call diversion to alternate communication method | |
CN112866086B (en) | Information pushing method, device, equipment and storage medium for intelligent outbound | |
CN112887194B (en) | Interactive method, device, terminal and storage medium for realizing communication of hearing-impaired people | |
US8085927B2 (en) | Interactive voice response system with prioritized call monitoring | |
JP2023126219A (en) | Method and apparatus for managing hold | |
CN104580762A (en) | Method and device for realizing call forwarding according to language | |
CN111901486A (en) | Voice call processing method and device and electronic equipment | |
WO2021109741A1 (en) | Serving method, apparatus, system and device, and storage medium | |
CN109005304A (en) | A kind of queuing strategy and device, computer readable storage medium | |
CN112333341A (en) | Intelligent voice robot system | |
RU2781493C1 (en) | Robotic question-answer system with a voice module "virtual assistant" | |
CN115086259A (en) | Reminding method and device for group chat information, computer equipment and storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201106 |
|
WD01 | Invention patent application deemed withdrawn after publication |