CN114567700A

CN114567700A - Interaction method, interaction device, electronic equipment and storage medium

Info

Publication number: CN114567700A
Application number: CN202210185699.8A
Authority: CN
Inventors: 张蕊莉; 牛国超; 李宇辉; 张稳龙
Original assignee: Yigu Network Technology Co ltd
Current assignee: Yigu Network Technology Co ltd
Priority date: 2022-02-28
Filing date: 2022-02-28
Publication date: 2022-05-31

Abstract

The embodiment of the invention discloses an interaction method, an interaction device, electronic equipment and a storage medium. The method comprises the following steps: when a call request sent by a user terminal is received, establishing call connection with the user terminal, and receiving a call interaction mode input by a user at the user terminal; if the call interaction mode is the intelligent interaction mode, acquiring current incoming line information of the user, and predicting the predicted call intention of the user according to the current incoming line information; and distributing virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user. The technical scheme of the embodiment of the invention solves the technical problems of low interaction efficiency and single interaction feedback form of the existing interaction method, improves the interaction efficiency and avoids the single interaction feedback form, thereby increasing the user experience.

Description

Interaction method, interaction device, electronic equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of computers, in particular to an interaction method, an interaction device, electronic equipment and a storage medium.

Background

Currently, the customer service of an enterprise generally acquires the requirements of a user, determines a corresponding answer according to the requirements of the user, and feeds the answer back to the user. However, the interaction method has the technical problems of low interaction efficiency and single feedback form of interaction, so that the user interaction demand experience is poor.

Disclosure of Invention

The embodiment of the invention provides an interaction method, an interaction device, electronic equipment and a storage medium, which are used for improving interaction efficiency and avoiding singleness of feedback forms of interaction, so that the technical effect of enhancing user experience is achieved.

In a first aspect, an embodiment of the present invention provides an interaction method, where the method includes:

when a call request sent by a user terminal is received, establishing call connection with the user terminal, and receiving a call interaction mode input by a user at the user terminal;

if the call interaction mode is the intelligent interaction mode, acquiring current incoming line information of the user, and predicting the predicted call intention of the user according to the current incoming line information;

and allocating virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

In a second aspect, an embodiment of the present invention further provides an interaction apparatus, where the apparatus includes:

the interactive mode receiving device is used for establishing a call connection with the user terminal and receiving a call interactive mode input by a user at the user terminal when receiving a call request sent by the user terminal;

the call intention prediction module is used for acquiring the current incoming line information of the user and predicting the call intention of the user according to the current incoming line information if the call interaction mode is the intelligent interaction mode;

and the interaction module is used for distributing virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:

one or more processors;

storage means for storing one or more programs;

when executed by the processor, cause the processor to implement the interaction method as provided by any of the embodiments of the invention.

In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the interaction method provided in any embodiment of the present invention.

According to the technical scheme of the embodiment of the invention, when the call request sent by the user terminal is received, the call connection with the user terminal can be established. And then receiving the call interaction mode input by the user at the user terminal based on the established call connection. And if the call interaction mode is the intelligent interaction mode, the current incoming line information of the user can be acquired. And then the predicted call intention of the user can be predicted according to the current incoming line information, and the interaction duration can be effectively shortened. After the predicted call intention of the user is predicted, virtual intelligent customer service corresponding to the call intention can be distributed to the user, and compared with the prior art, the phenomenon that the feedback form of interaction is single only through voice interaction in the prior art can be avoided. The virtual intelligent customer service corresponding to the call intention is distributed to the user, so that the virtual intelligent customer service can interact with the user, the technical problems that the interaction efficiency is low and the interaction feedback form is single in the existing interaction method are solved, the interaction efficiency is improved, the interaction feedback form is prevented from being single, and the technical effect of improving the user experience is achieved.

Drawings

In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.

Fig. 1 is a schematic flowchart of an interaction method according to an embodiment of the present invention;

fig. 2 is a schematic flowchart of an interaction method according to a second embodiment of the present invention;

fig. 3 is a schematic flowchart of an interaction method according to a third embodiment of the present invention;

fig. 4 is a schematic timing diagram of interaction based on an interaction method according to a fourth embodiment of the present invention;

fig. 5 is a schematic structural diagram of an interaction apparatus according to a fifth embodiment of the present invention;

fig. 6 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of an interaction method according to an embodiment of the present invention, where the embodiment is applicable to a case of intelligent interaction, the method may be executed by an interaction apparatus, the interaction apparatus may be implemented by software and/or hardware, and may be integrated in an electronic device such as a computer or a server.

As shown in fig. 1, the method of the present embodiment includes:

s110, when a call request sent by the user terminal is received, establishing call connection with the user terminal, and receiving a call interaction mode input by the user at the user terminal.

The user terminal may be a device having a call function. The user terminal may be, but is not limited to, a smartphone, a portable wearable device, a tablet computer, and a laptop computer. The call request may be a request generated after receiving a call instruction for making a call, which is input by a user at a user terminal, where the call instruction may be triggered by the user through a specified operation, and the specified operation may include, but is not limited to, a click or a slide type operation. The call request may be a video call request, or the like. The call request may be used to establish a call connection with the user terminal. The call request may carry an identification of the user terminal, which may include, but is not limited to, a number of the user terminal.

The call interaction mode may be an interaction mode determined based on a triggering operation of a user on a call interface of the user terminal. The triggering operation may be at least one of a click operation, a sliding operation, or a pressing operation. The call interaction mode may include a smart interaction mode and a non-smart interaction mode. The non-intelligent interaction mode may be a manual interaction mode.

Specifically, after receiving a call instruction for making a call, which is input by a user on a call interface of the user terminal. After receiving the call instruction, a call connection with the user terminal may be established based on the internet or the mobile internet. After determining that the call connection is successfully established with the user terminal, the call interaction mode input by the user on the call interface of the user terminal may be received, that is, the trigger operation input by the user on the call interface of the user terminal for selecting the call interaction mode may be received, and then the call interaction mode may be determined based on the trigger operation input by the user on the call interface of the user terminal for selecting the call interaction mode.

And S120, if the call interaction mode is the intelligent interaction mode, acquiring current incoming line information of the user, and predicting the call intention of the user according to the current incoming line information.

The current incoming line information can be understood as the incoming line information at the current moment, and the incoming line information can include but is not limited to a dialing number, dialing time, key operation information and the like. A line incoming message can be understood as a telephone line incoming operation. The predicted call intention may be an intention predicted from the current incoming line information. Alternatively, the predicted call intent may be a business intent.

Specifically, after receiving a call interaction mode input by a user, if the call interaction mode is an intelligent interaction mode, current incoming line information of the user can be acquired. And then the current incoming line information can be analyzed, so that the dialing number contained in the current incoming line information can be determined. After the dial number is determined, user portrait information and historical interaction data corresponding to the dial number may be obtained from the big data platform. Furthermore, the user's call intention can be predicted based on the user figure information and the historical interaction data corresponding to the dial number, and the predicted call intention can be used as the predicted call intention. The big data platform may be a server or a database which is pre-established and used for storing a large amount of user portrait information and historical interaction data.

And S130, distributing the virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

The virtual intelligent customer service can be understood as customer service with virtual character images. The virtual character can be a cartoon character image or a real person photo image. The gender of the virtual character may be male or female. Optionally, various virtual smart customer services may be stored in the big data platform. The virtual smart customer service may be used to interact with the user.

The virtual intelligent customer service in the embodiment of the invention can have facial micro-expressions. The facial micro expressions may be preset according to actual interaction conditions, for example, the micro expressions of the virtual smart customer service may include, but are not limited to, open eyes, closed eyes, and nodding when the virtual smart customer service is silent. The micro-expression of the virtual smart customer service when interacting with the user may include, but is not limited to, mouth opening. It should be noted that, in the embodiment of the present invention, the mouth opening and closing effect is generated based on the content of the virtual intelligent interactive customer report.

Specifically, after predicting the predicted call intention of the user, the virtual smart service matching the predicted call intention may be matched from a big data platform for storing at least one virtual smart service. After the virtual intelligent customer service matched with the predicted call intention is matched, the virtual intelligent customer service matched with the predicted call intention can be displayed on a display interface of the user terminal. Therefore, the interaction with the user can be carried out based on the virtual intelligent customer service of the display interface of the user terminal.

It should be noted that, in the embodiment of the present invention, displaying the virtual intelligent customer service matched with the predicted call intention on the display interface of the user terminal not only can prompt the interest of interaction, but also further improves the experience of the user from the perspective of interactive vision.

On the basis, if the call interaction mode is the non-intelligent interaction mode, historical interaction information of the user can be acquired. And further, according to the historical interaction information and the current seat detail information of the user, the corresponding call seat can be matched for the user, so that the call seat can interact with the user.

The historical interactive information can be understood as service requirement information existing in the historical call of the user. Current seat detail information may include, but is not limited to, number of free seats at the current time, skill, gender, performance. A call seat may be understood as a seat that interacts with a user.

Specifically, if the call interaction mode is a non-intelligent interaction mode, such as a manual interaction mode, historical interaction information of the user can be acquired from the big data platform, and information such as the number, skills, gender, performance and the like of idle seats at the current moment can be determined. After the historical interaction information of the user is obtained, the interaction intention of the user in the call process can be predicted based on the historical interaction information. And further, the user can be matched with the call seat matched with the interaction intention of the user based on the number, skill, gender and performance information of the idle seats at the current moment so as to enable the call seat to interact with the user.

Example two

Fig. 2 is a schematic flowchart of an interaction method provided in the second embodiment of the present invention, where on the basis of the foregoing embodiment, optionally, the enabling the virtual smart customer service to interact with the user includes: acquiring voice information input by the user, and performing recognition and voice-to-text processing on the voice information to generate voice text information of the voice information; and determining response text information corresponding to the voice text information, converting the response text information into audio streams, and displaying a picture of the audio streams by the virtual intelligent customer service on the user terminal. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.

As shown in fig. 2, the method of the embodiment may specifically include:

s210, when receiving a call request sent by a user terminal, establishing a call connection with the user terminal, and receiving a call interaction mode input by a user at the user terminal.

And S220, if the call interaction mode is the intelligent interaction mode, acquiring the current incoming line information of the user, and predicting the call intention of the user according to the current incoming line information.

And S230, distributing the virtual intelligent customer service corresponding to the call intention for the user.

S240, acquiring the voice information input by the user, identifying the voice information and performing voice-to-text processing to generate the voice text information of the voice information.

The voice information may be voice stream data input by a user at the user terminal. Recognizing speech may be understood as recognizing the information content contained in the speech information. The voice text information may be information that is voice-recognized by voice-stream data input by a user and stores the recognized contents in a text form.

Specifically, after the virtual intelligent customer service is distributed to the user, the virtual intelligent customer with the micro expression distributed to the user can be displayed on the display interface of the user terminal. After the display interface of the user terminal presents the virtual intelligent client with the micro expression, the voice information input by the user at the user terminal can be received. After receiving the voice information, the voice information input by the user can be identified through the existing voice identification technology, and the information content in the voice information is determined. And then the information content in the voice information can be stored in a text form by the existing voice-to-text technology, so that the voice text information corresponding to the voice information can be generated.

And S250, determining response text information corresponding to the voice text information, converting the response text information into audio streams, and displaying a picture of the audio streams of the virtual intelligent customer service on the user terminal.

Wherein the response text information may be understood as reply information generated based on the voice text information.

Specifically, after the voice text information of the voice information is generated, the voice text information may be analyzed, and then the response text information corresponding to the voice text information may be determined. After the response text information is determined, the response text information can be converted into an audio stream corresponding to the response text information through the existing text-to-speech technology, and a picture of the audio stream is displayed through a display interface of the user terminal through virtual intelligent customer service.

Optionally, the response text information corresponding to the speech text information is determined through the following steps:

step one, analyzing the voice text information, determining whether the voice text information meets the condition of multi-turn conversation, and if so, determining the target multi-turn conversation corresponding to the text information.

Wherein, the multi-turn conversation can be understood as that the virtual intelligent customer service has at least one conversation with the user in one complete conversation process. The multi-turn session may be a session in any session scenario, for example, the session scenario for the turn session may include, but is not limited to, a business transaction scenario, a transaction data query scenario, and a business information query scenario, etc. The target multi-turn conversation may be understood as one conversation corresponding to text information among a plurality of conversations.

Specifically, after the speech text information is obtained, the speech text information may be analyzed. And a conversation scene of the voice text information can be determined. And matching the conversation scene with the conversation scenes of the multiple rounds of conversations, and if the matching is not successful, determining that the voice text information does not meet the conditions of the multiple rounds of conversations. If the matching is successful, it can be determined that the speech text information meets the conditions of multiple turns of conversation. After the condition that the voice text information accords with the multiple rounds of conversations is determined, the multiple rounds of conversations corresponding to the conversation scenes of the voice text information can be used as the target multiple rounds of conversations.

And step two, taking preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation as response text information.

Specifically, after the target multi-turn conversation is determined, the preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation can be determined. And then the preset text content matched with the voice text information in the preset text contents corresponding to the target multi-turn conversation can be used as the response text information.

Optionally, the preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation is determined by the following method:

determining at least one keyword of preset text content corresponding to the target multi-turn conversation, and determining the keyword of the voice text information. And comparing the keywords of the voice text information with the keywords in the preset text content corresponding to the target multi-turn conversation. Thus, the alignment result can be obtained. And then, the preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation can be determined based on the comparison result. The preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation can be quickly and effectively determined through the processing.

In order to improve the interactive experience of the user, emotion analysis can be performed on the audio stream corresponding to the converted response text information, and then emotion analysis results can be obtained. And determining the micro expression of the virtual intelligent customer service playing the audio stream on the display interface of the user terminal based on the emotion analysis result. Therefore, the picture of the audio stream broadcasted by the virtual intelligent customer service with the micro expression is displayed on the display interface of the user terminal.

According to the technical scheme of the embodiment of the invention, the voice information input by the user is acquired, and then the voice information can be identified and converted into the text, so that the voice text information of the voice information is generated. After generating the voice text information of the voice information, the response text information corresponding to the voice text information may be determined. And then can convert the response text information into audio stream to the picture that the audio stream was reported in the virtual intelligent customer service that shows in user terminal has the micro expression, realized improving interactive efficiency and avoided interactive feedback form single, thereby reach the technological effect that increases user experience and feel.

EXAMPLE III

Fig. 3 is a flowchart of an interaction method provided by a third embodiment of the present invention, based on the foregoing embodiment, optionally after predicting the user's call intention of the user according to the current incoming line information, the interaction method of this embodiment may further include: and determining whether the predicted call intention is matched with the actual call intention of the user, and if so, executing the operation of allocating virtual intelligent customer service corresponding to the call intention for the user. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.

As shown in fig. 3, the method of the present embodiment may specifically include:

s310, when a call request sent by the user terminal is received, establishing a call connection with the user terminal, and receiving a call interaction mode input by the user at the user terminal.

And S320, if the call interaction mode is the intelligent interaction mode, acquiring the current incoming line information of the user, and predicting the predicted call intention of the user according to the current incoming line information.

S330, determining whether the predicted call intention is matched with the actual call intention of the user, and if so, executing S340; if not, go to S350.

The actual call intention can be understood as the real service requirement of the user in the current call process.

Specifically, after the predicted call intention is determined, a picture of audio stream data corresponding to the predicted call intention can be displayed on a display interface of the user terminal through a virtual intelligent customer service broadcast with a micro expression. After the broadcasting is finished, the voice information input by the user can be received. And then it can be determined whether the predicted call intention matches the actual call intention of the user based on the voice information input by the user. It can be understood that, while the display interface of the user terminal displays the broadcast picture, the speaker of the user terminal plays the content of the audio stream corresponding to the broadcast picture.

Alternatively, if it is determined that the predicted call intention does not match the actual call intention of the user based on the voice information input by the user, the actual call intention of the user may be acquired by:

and starting a preset virtual intelligent customer service, and acquiring the actual call intention of the user through the started virtual intelligent customer service.

The virtual intelligent customer service can be a service running on a user terminal. The virtual intelligent customer service can be used for acquiring the actual call intention of the user.

And S340, distributing the virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

And S350, determining the virtual intelligent customer service corresponding to the actual call intention, and distributing the virtual intelligent customer service corresponding to the actual call intention to the user.

Specifically, after it is determined that the predicted call intention does not match the actual call intention of the user, the actual call intention of the user may be acquired. And further matching virtual intelligent customer service corresponding to the actual call intention from the big data platform. And if the virtual intelligent customer service corresponding to the actual call intention exists in the big data platform, distributing the virtual intelligent customer service corresponding to the actual call intention to the user, and updating the virtual intelligent customer service displayed on the display interface of the user terminal to the virtual intelligent customer service corresponding to the actual call intention so as to enable the virtual intelligent customer service corresponding to the actual call intention to interact with the target user.

On the basis, if the virtual intelligent customer service corresponding to the actual call intention does not exist in the big data platform, the virtual intelligent customer service can be arranged for the user, or the data used for inputting the data used for creating the virtual intelligent customer service is received, the virtual intelligent customer service is created based on the data used for creating the virtual intelligent customer service, and the created virtual intelligent customer service is distributed to the user.

According to the technical scheme of the embodiment of the invention, whether the predicted call intention is matched with the actual call intention of the user is determined, if yes, the virtual intelligent customer service corresponding to the call intention is distributed to the user, so that the virtual intelligent customer service interacts with the user; if not, determining the virtual intelligent customer service corresponding to the actual call intention, and distributing the virtual intelligent customer service corresponding to the actual call intention to the user, so that the interaction efficiency is improved, the single feedback form of the interaction is avoided, and the technical effect of improving the user experience is achieved.

Example four

An alternative embodiment of the interaction method is provided in the fourth embodiment of the present invention, and specific implementation manners of the alternative embodiment may be seen in the following embodiments. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.

The method of the embodiment specifically comprises the following steps:

1. when an enterprise hot line number dialed by a client on the smart phone is received, a call connection with the smart phone is established, and a video call of an incoming call of the enterprise hot line number is received.

The method can be understood as the time when a call request sent by a user terminal is received when an enterprise hot line number dialed by a customer on the smart phone is received. A video call may be understood as a call interaction mode. Receiving a video call that is an incoming call to an enterprise hotline number may be understood as receiving a call interaction pattern input by a user at a user terminal.

2. And if the video call is an intelligent call, obtaining incoming line information of the client, and predicting the visiting intention of the client according to the incoming line information.

Wherein, the intelligent call can be understood as an intelligent interaction mode. The incoming line information may be understood as current incoming line information. The visiting intention can be understood as the predicted calling intention.

3. And allocating the digital person corresponding to the visiting intention to the client.

Wherein, the digital human can be understood as a virtual intelligent customer service.

Optionally, after the current visiting intention of the client is predicted according to the incoming line information, whether the current visiting intention is matched with the actual call intention of the client or not can be determined, and if yes, the operation of allocating the virtual intelligent customer service corresponding to the call intention to the client is executed. If not, determining the digital person corresponding to the actual call intention, and distributing the digital person corresponding to the actual call intention to the client.

Further, if it is determined that the visiting intention is not matched with the actual call intention of the client, a preset virtual intelligent customer service can be started, and the actual call intention of the user is obtained through the started virtual intelligent customer service.

4. And acquiring voice information input by a client, identifying the voice information and performing voice-to-text processing to generate voice text information of the voice information.

5. And analyzing the voice text information, determining whether the voice text information meets the condition of multi-turn conversations, and if so, determining the target multi-turn conversations corresponding to the text information.

And 6, taking preset text content matched with the voice text information in the preset text content corresponding to the target multi-turn conversation as response text information.

And 7, converting the response text information into audio streams, displaying a picture of the audio streams broadcasted by the virtual intelligent customer service on the smart phone, and playing the audio stream contents through the smart phone.

8. If the video call is manually serviced, personalized attributes of the customer can be obtained from the big data platform. And further, corresponding call seats can be matched for the client according to the personalized attributes of the client and the number, skills, gender and performance conditions of the current idle seats, so that the call seats and the client can interact.

The manual service can be understood as a non-intelligent interaction mode, and the acquisition of the personalized attributes of the customer from the big data platform can be understood as the acquisition of the historical interaction information of the user from the big data platform. Current seat detail information may include, but is not limited to, conditions such as the number of currently available seats, skills, gender, performance, etc.

It should be noted that the intelligent call and the manual service included in the video call in the embodiment of the present invention may be switched to each other, for example, the manual service may also be performed after the intelligent call is performed (see fig. 4), so as to implement the business interaction with the customer, and improve the interaction efficiency.

Compared with the prior art, the technical scheme of the embodiment of the invention can avoid the phenomenon of single interactive feedback form existing only through voice interaction. The digital person corresponding to the visiting intention is distributed to the client, so that the digital person and the client can interact, the technical problems that the interaction efficiency is low and the interaction feedback form is single in the existing interaction method are solved, the interaction efficiency is improved, the interaction feedback form is prevented from being single, and the technical effect of improving the user experience is achieved.

EXAMPLE five

Fig. 5 is a schematic structural diagram of an interaction apparatus according to a fifth embodiment of the present invention, where the interaction apparatus includes: an interaction mode receiving device 510, a call intention predicting module 520 and an interaction module 530.

The interactive mode receiving device 510 is configured to, when receiving a call request sent by a user terminal, establish a call connection with the user terminal, and receive a call interactive mode input by a user at the user terminal; a call intention prediction module 520, configured to, if the call interaction mode is an intelligent interaction mode, obtain current incoming line information of the user, and predict a call intention of the user according to the current incoming line information; an interaction module 530, configured to assign a virtual smart customer service corresponding to the call intention to the user, so that the virtual smart customer service interacts with the user.

According to the technical scheme of the embodiment of the invention, through the interactive mode receiving device, when the call request sent by the user terminal is received, the call connection with the user terminal can be established. And then receiving the call interaction mode input by the user at the user terminal based on the established call connection. Through the call intention prediction module, if the call interaction mode is the intelligent interaction mode, the current incoming line information of the user can be acquired. And then the predicted call intention of the user can be predicted according to the current incoming line information, and the interaction duration can be effectively shortened. After the predicted call intention of the user is predicted, the virtual intelligent customer service corresponding to the call intention can be distributed to the user through the interaction module, and compared with the prior art, the phenomenon that the feedback form of interaction is single only through voice interaction can be avoided. The virtual intelligent customer service corresponding to the call intention is distributed to the user, so that the virtual intelligent customer service can interact with the user, the technical problems that the interaction efficiency is low and the interaction feedback form is single in the existing interaction method are solved, the interaction efficiency is improved, the interaction feedback form is prevented from being single, and the technical effect of improving the user experience is achieved.

Optionally, the interaction module 530 is configured to obtain voice information input by the user, perform recognition and voice-to-text processing on the voice information, and generate voice text information of the voice information; and determining response text information corresponding to the voice text information, converting the response text information into audio streams, and displaying a picture of the audio streams by the virtual intelligent customer service on the user terminal.

Optionally, the interaction module 530 is configured to analyze the voice text information, determine whether the voice text information meets a condition of multiple rounds of conversations, and if so, determine a target multiple rounds of conversations corresponding to the text information; and taking preset text content matched with the voice text information in preset text content corresponding to the target multi-turn conversation as response text information.

Optionally, after the predicting the user's call intention of the user according to the current incoming line information, the apparatus further includes: and the predicted call intention determining module is used for determining whether the predicted call intention is matched with the actual call intention of the user, and if so, executing the operation of distributing virtual intelligent customer service corresponding to the call intention for the user.

Optionally, the predicted call intention determining module is further configured to determine, if the virtual intelligent customer service corresponding to the actual call intention is not available, the virtual intelligent customer service corresponding to the actual call intention, and allocate the virtual intelligent customer service corresponding to the actual call intention to the user.

Optionally, the apparatus further comprises: and the actual call intention acquisition module is used for starting a preset virtual intelligent customer service and acquiring the actual call intention of the user through the started virtual intelligent customer service.

Optionally, the apparatus further comprises: the non-intelligent interaction mode module is used for acquiring historical interaction information of the user if the call interaction mode is the non-intelligent interaction mode; and matching a corresponding call seat for the user according to the historical interaction information and the current seat detail information of the user so as to enable the call seat to interact with the user.

The device can execute the interaction method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the interaction method.

It should be noted that, the units and modules included in the interaction apparatus are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the embodiment of the invention.

EXAMPLE six

Fig. 6 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present invention. FIG. 6 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing any of the embodiments of the present invention. The electronic device 12 shown in fig. 6 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention. The device 12 is typically an electronic device that undertakes the processing of configuration information.

As shown in FIG. 6, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that couples the various components (including the memory 28 and the processing unit 16).

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

Electronic device 12 typically includes a variety of computer-readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer device readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown, but commonly referred to as a "hard drive"). Although not shown, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk-Read Only Memory (CD-ROM), Digital Video disk (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product 40, with program product 40 having a set of program modules 42 configured to carry out the functions of embodiments of the invention. Program product 40 may be stored, for example, in memory 28, and such program modules 42 include, but are not limited to, one or more application programs, other program modules, and program data, each of which examples or some combination may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, mouse, camera, etc., and display), one or more devices that enable a user to interact with electronic device 12, and/or any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), Wide Area Network (WAN), and/or a public Network such as the internet) via the Network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, Redundant processing units, external disk drive Arrays, disk array (RAID) devices, tape drives, and data backup storage devices, to name a few.

The processing unit 16 executes various functional applications and data processing by running programs stored in the memory 28, for example, to implement the interaction method provided by the above-described embodiment of the present invention, the method including:

when a call request sent by a user terminal is received, establishing call connection with the user terminal, and receiving a call interaction mode input by a user at the user terminal; if the call interaction mode is the intelligent interaction mode, acquiring current incoming line information of the user, and predicting the predicted call intention of the user according to the current incoming line information; and distributing virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

Of course, those skilled in the art can understand that the processor can also implement the technical solution of the interaction method provided by any embodiment of the present invention.

EXAMPLE seven

An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor, and is characterized in that, when the program is executed by the processor, for example, the interaction method provided in the foregoing embodiment of the present invention includes:

when a call request sent by a user terminal is received, establishing call connection with the user terminal, and receiving a call interaction mode input by a user at the user terminal; if the call interaction mode is the intelligent interaction mode, acquiring current incoming line information of the user, and predicting the predicted call intention of the user according to the current incoming line information; and allocating virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An interaction method, comprising:

2. The method of claim 1, wherein said causing said virtual smart customer service to interact with said user comprises:

acquiring voice information input by the user, and performing recognition and voice-to-text processing on the voice information to generate voice text information of the voice information;

and determining response text information corresponding to the voice text information, converting the response text information into audio streams, and displaying a picture of the audio streams by the virtual intelligent customer service on the user terminal.

3. The method of claim 2, wherein the determining the response text message corresponding to the speech text message comprises:

analyzing the voice text information, determining whether the voice text information meets the condition of multi-turn conversations, and if so, determining a target multi-turn conversation corresponding to the text information;

and taking preset text content matched with the voice text information in preset text content corresponding to the target multi-turn conversation as response text information.

4. The method of claim 1, wherein after predicting the user's user call intent from the current incoming line information, the method further comprises:

and determining whether the predicted call intention is matched with the actual call intention of the user, and if so, executing the operation of allocating virtual intelligent customer service corresponding to the call intention for the user.

5. The method of claim 4, further comprising:

if not, determining the virtual intelligent customer service corresponding to the actual call intention, and distributing the virtual intelligent customer service corresponding to the actual call intention to the user.

6. The method of claim 4, further comprising:

7. The method of claim 1, further comprising:

if the call interaction mode is a non-intelligent interaction mode, acquiring historical interaction information of the user;

and matching a corresponding call seat for the user according to the historical interaction information and the current seat detail information of the user so as to enable the call seat to interact with the user.

8. An interactive device, comprising:

the call intention prediction module is used for acquiring the current incoming line information of the user and predicting the call intention of the user according to the current incoming line information if the call interaction mode is an intelligent interaction mode;

and the interaction module is used for distributing the virtual intelligent customer service corresponding to the call intention for the user so as to enable the virtual intelligent customer service to interact with the user.

9. An electronic device, characterized in that the electronic device comprises:

one or more processors;

storage means for storing one or more programs;

when executed by the processor, cause the processor to implement the interaction method of any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the interaction method according to any one of claims 1 to 7.