Information interaction method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an information interaction method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: receiving an editing operation aiming at dialogue configuration information, and creating an intelligent agent according to the dialogue configuration information; wherein the conversation configuration information is used for configuring a rule followed by the intelligent agent when determining the conversation audio; in response to a release operation for the intelligent agent, determining a first call end, and establishing an association relationship between the first call end and the intelligent agent; wherein the first call audio of the first call end is determined by the intelligent agent. According to the technical scheme provided by the embodiment of the invention, the effects of creating the intelligent agent and binding and associating the intelligent agent with the call end through simple interaction operation are realized, the intelligent agent creation and intelligent agent binding process is simplified, and the effect of call interaction through the intelligent agent is further realized.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of computer processing, and in particular, to an information interaction method and device, electronic equipment, storage medium, and program product. BACKGROUND

[0002] With the continuous development of the Internet and communication technology, it is more and more common in various application platforms to solve problems or provide services for users through calls. When a user has a service demand, the user can initiate a call request to a call end that provides services. Then, the call end can provide the user with the required services.

[0003] In related technologies, a traditional call interaction method usually relies on interactive voice question and answer technology, which is based on a preset tree menu logic. A user needs to obtain the required services through a key or a simple voice instruction. However, this service obtaining process is relatively rigid and has certain limitations, and cannot handle complex natural languages, thereby resulting in low service accuracy and poor service quality, and affecting the service experience of the user. SUMMARY

[0004] The present disclosure provides an information interaction method and device, electronic equipment, storage medium, and program product, which achieves the effect of creating an agent and associating the agent with a call end through simple interaction operations, simplifies the agent creation and agent association process, and further implements the effect of call interaction through the agent.

[0005] In a first aspect, the embodiments of the present disclosure provide an information interaction method, which includes:

[0006] receiving an editing operation on dialogue configuration information, and creating an agent according to the dialogue configuration information; the dialogue configuration information is used to configure a rule followed by the agent when determining call audio;

[0007] in response to a publishing operation on the agent, determining a first call end, and establishing an association relationship between the first call end and the agent; wherein first call audio of the first call end is determined by the agent.

[0008] In a second aspect, the embodiments of the present disclosure further provide an information interaction device, which includes:

[0009] an agent creation module configured to receive an editing operation on dialogue configuration information, and create an agent according to the dialogue configuration information; the dialogue configuration information is used to configure a rule followed by the agent when determining call audio;

[0010] The agent publishing module is configured to, in response to a publishing operation for the agent, determine a first call end, and establish an association between the first call end and the agent, wherein a first call audio of the first call end is determined by the agent.

[0011] In a third aspect, the embodiments of the present disclosure further provide an electronic device, which comprises:

[0012] one or more processors;

[0013] a storage device configured to store one or more programs,

[0014] When the one or more programs are executed by the one or more processors, the one or more processors implement the information interaction method according to any of the embodiments of the present disclosure.

[0015] In a fourth aspect, the embodiments of the present disclosure further provide a storage medium containing computer executable instructions for executing the information interaction method according to any of the embodiments of the present disclosure when executed by a computer processor.

[0016] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product comprising a computer program for implementing the information interaction method according to any of the embodiments of the present disclosure when executed by a processor.

[0017] The technical scheme of the embodiment of the disclosure realizes the scene configuration of the intelligent agent by receiving the editing operation on the dialogue configuration information, creating the intelligent agent according to the dialogue configuration information, can create the intelligent agent based on the intelligent agent configuration operation, reduces the threshold of intelligent agent development, saves the intelligent agent creation cost, improves the reusability of the intelligent agent, and because the dialogue configuration information is used to configure the rule followed by the intelligent agent when determining the call audio, the created intelligent agent has the targeted ability, the response content of the intelligent agent can be accurately controlled through the dialogue configuration information, and the accuracy of the intelligent agent is improved. Further, in response to the publishing operation on the intelligent agent, the first call end is determined, and the association relationship between the first call end and the intelligent agent is established, which realizes the effect of associating the intelligent agent with the first call end through one-key publishing operation, reduces the technical threshold of the intelligent agent and call end binding operation, and ensures that the call response audio is automatically determined by the intelligent agent, improves the interaction efficiency and continuity, and improves the accuracy of the response audio. The technical scheme of the embodiment of the disclosure solves the problem that the service acquisition process in the related art is relatively rigid and has certain limitations, thereby causing low service accuracy and poor service quality, realizes the effect that the intelligent agent can be created and associated with the call end through simple interaction operation, reduces the operation threshold of intelligent agent creation and intelligent agent binding, simplifies the intelligent agent creation and intelligent agent binding process, and further realizes the effect of call interaction through the intelligent agent, improves the naturalness and fluency of the call, and improves the service response speed, the service quality and the service accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0018] The above and other features, advantages, and aspects of the embodiments of the disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the original and elements are not necessarily drawn according to the scale.

[0019] Figure 1 A flowchart of an information interaction method provided by an embodiment of the disclosure;

[0020] Figure 2 A flowchart of another information interaction method provided by an embodiment of the disclosure;

[0021] Figure 3 A signaling diagram of an intelligent agent creation method provided by an embodiment of the disclosure;

[0022] Figure 4 A signaling diagram of an information interaction method provided by an embodiment of the disclosure;

[0023] Figure 5 A structural diagram of an information interaction apparatus provided by an embodiment of the disclosure;

[0024] Figure 6 FIG. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail with reference to the drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather should be construed to encompass all modifications equivalent in meaning and scope to the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that each step described in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "comprising" and variations thereof as used in the present disclosure are open-ended, that is, "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related definitions of other terms will be given in the description below.

[0028] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the adjectives "one", "more" mentioned in the present disclosure are illustrative and not limiting, and those skilled in the art should understand that "one or more" should be understood unless otherwise explicitly stated in the context.

[0030] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.

[0031] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, use scenario, etc. of the personal information involved in the present disclosure should be informed to the user and the authorization of the user should be obtained in accordance with relevant laws and regulations.

[0032] For example, in response to receiving an active request of a user, a prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require obtaining and using personal information of the user. Thus, the user can autonomously select whether to provide the personal information to the software or hardware, such as an electronic device, an application program, a server or a storage medium, which performs the operation of the technical solution of the present disclosure according to the prompt information.

[0033] As an optional but non-limiting implementation manner, in response to receiving an active request of a user, the manner of sending a prompt information to the user may, for example, be a pop-up window manner, in which the prompt information can be presented in a text manner. In addition, the pop-up window can also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0034] It can be understood that the above notification and obtaining user authorization process is only illustrative and does not limit the implementation manner of the present disclosure. Other manners meeting relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0035] It can be understood that the data involved in the technical solution (including but not limited to the data itself, the obtaining or use of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0036] Figure 1 A flowchart of an information interaction method provided by the embodiment of the present disclosure is shown. The embodiment of the present disclosure is applicable to a scenario of interacting with a call end through an agent. The method can be executed by an information interaction device. The device can be implemented in the form of software and / or hardware. Optionally, the device can be implemented by an electronic device, which can be a mobile terminal, a PC terminal or a server.

[0037] As shown in FIG. 1, the method of the embodiment can specifically include the following steps. Figure 1

[0038] S110, receiving an editing operation on the dialogue configuration information, and creating an agent according to the dialogue configuration information; wherein the dialogue configuration information is used to configure a rule followed by the agent when determining a call audio.

[0039] Generally, in a scenario of performing an interactive service through a call (for example, querying a canteen menu, checking order information, etc.), in order to improve the quality of automatic service and improve the service efficiency and accuracy, an agent capable of performing a call task can be used to interact with a user end, so that the user end can be provided with a required interactive service through the call between the user end and the agent.

[0040] ​In the embodiments of the present disclosure, before the application of the agent, the agent that can meet the user demand can be created. At this time, the configuration information required for creating the agent can be used as the dialogue configuration information. The dialogue configuration information can refer to a core rule set used to define "how to determine the dialogue audio" of the agent in the dialogue process, and is an operation manual for the agent to perform the dialogue task. That is, the agent created according to the dialogue configuration information can make the agent follow the rules configured in the dialogue configuration information when determining the reply dialogue audio. The dialogue configuration information can include at least one rule followed by the agent when determining the dialogue audio, and optionally, at least one of role setting information of the agent, a knowledge base associated with the agent, and a preset dialogue rule. The role setting information can refer to a rule for defining the identity attribute and / or behavior style of the agent. Configuring the role setting information for the agent can make the interactive operation of the agent conform to the role expectation of a specific scene, and enhance the naturalness and pertinence of the dialogue. The knowledge base associated with the agent can be an information database that the agent can refer to when generating the dialogue audio, and the database stores factual and normative content related to the dialogue scene. The knowledge base can provide content support for the agent to ensure that the generated audio content is accurate and professional. The preset dialogue rule can be a flow rule that specifies how the agent processes the received dialogue audio and generates a response. Optionally, the presentation form of the preset dialogue rule can include a dialogue flowchart and / or dialogue text, etc. The preset dialogue rule can be composed of a plurality of information processing operations. The information processing operation can be understood as a specific execution step in the preset dialogue rule. The information processing operation is used to obtain a response audio for the received dialogue audio. That is, by sequentially executing the information processing operations in the preset dialogue rule, the response audio for the received dialogue audio can be obtained. Optionally, the information processing operations included in the preset dialogue rule can include a plurality of voice-to-text, semantic analysis, knowledge base retrieval, and text-to-speech, etc. The response audio can refer to the reply audio generated by the agent for the received dialogue audio.

[0041] In the embodiments of the present disclosure, the agent can refer to an automated entity running based on the dialogue configuration information, or can also be understood as a program or system module with dialogue audio processing capability. The agent can receive input information in the dialogue, and generate or determine feedback dialogue audio according to the dialogue configuration information. The agent can replace or assist human to complete the audio interaction decision in the dialogue, so as to improve the quality, efficiency and accuracy of the interactive service.

[0042] It should be noted that when editing the dialogue configuration information, one or more of the dialogue configuration information can be edited to obtain the edited dialogue configuration information, and the agent is created or updated according to the edited dialogue configuration information.

[0043] Optionally, in the absence of an already created agent, the role setting information of the agent, the knowledge base associated with the agent, and the preset dialogue rule can be edited to obtain edited dialogue configuration information, and the agent can be created according to the edited dialogue configuration information.

[0044] Optionally, in the presence of an already created agent, the role setting information of the agent, the knowledge base associated with the agent, and / or the preset dialogue rule can be edited to obtain edited dialogue configuration information, and the agent can be updated according to the edited dialogue configuration information.

[0045] In the embodiments of the present disclosure, in the case where the preset dialogue rule is in the form of dialogue text, the editing operation on the dialogue configuration information can include at least one of the following operation modes: in response to an information editing operation on the dialogue configuration item; in response to an input operation on the dialogue configuration information. The two operation modes can be described as follows.

[0046] Optionally, the editing operation on the dialogue configuration information includes: in response to an agent editing request, displaying a dialogue configuration interface including at least one dialogue configuration item; in response to an information editing operation on the dialogue configuration item, and determining edited dialogue configuration information according to the information editing operation.

[0047] The agent editing request can be initiated by the user end and can be a creation or modification instruction for the configuration rule of the agent. The agent editing request can be used to trigger the entry into the agent editing process. Optionally, the agent editing request includes at least one of the following: a preset intelligent editing control is triggered; the received audio information includes an audio trigger word associated with the agent editing; the received gesture action includes a trigger gesture action associated with the agent editing. The dialogue configuration interface can be an operation interface provided to the user end for visualizing the configuration of the agent rule. The user can complete the configuration of the agent rule through the dialogue configuration interface. The dialogue configuration item can be a specific configurable unit in the dialogue configuration interface. The information editing operation on the object configuration item is used to obtain the corresponding dialogue configuration information. Optionally, the object configuration item includes at least one of the following: a role configuration item, a knowledge base configuration item, and a preset dialogue rule configuration item. The information editing operation can be a specific operation performed by the user on the dialogue configuration item in the dialogue configuration interface. The information editing operation can include at least one of the following: an information input operation, an option selection operation, and an information upload operation.

[0048] In specific implementation, in a case where a control triggering operation for the preset intelligent editing control is received, a dialogue configuration interface including at least one dialogue configuration item can be displayed. Further, in a case where an information editing operation for the at least one dialogue editing item is received, the dialogue configuration information edited in response to the information editing operation and according to the information editing operation is determined.

[0049] Optionally, the editing operation for the dialogue configuration information is received, including: displaying an intelligent agent configuration session interface in response to an intelligent agent editing request; wherein the intelligent agent configuration session interface includes a dialogue input box; displaying the input information in the dialogue input box in response to a dialogue input operation for the dialogue input box; and taking the information displayed in the dialogue input box as the edited dialogue configuration information in response to a dialogue sending operation.

[0050] The intelligent agent configuration session interface can be a visual operation interface centered on session interaction displayed in response to the intelligent agent editing request. The intelligent agent configuration session interface can simulate a dialogue form to enable the user to complete intelligent agent configuration by inputting content. The dialogue input box can be an interactive area in the intelligent agent configuration session interface for the user to input text content, and is a core carrier for the user to deliver configuration requirements.

[0051] In specific implementation, in a case where a control triggering operation for the preset intelligent editing control is received, an intelligent agent configuration session interface including a dialogue input box can be displayed. Further, the input information can be displayed in the dialogue input box in response to a dialogue input operation for the dialogue input box. Further, in a case where a triggering operation for the sending control is received, the dialogue configuration information edited in response to the dialogue sending operation and according to the dialogue input box is determined.

[0052] In the embodiments of the present disclosure, the dialogue configuration information includes a preset dialogue rule, and in addition to presenting the preset dialogue rule in the form of dialogue text, the preset dialogue rule can also be presented in the form of a dialogue flowchart. In a case where the preset dialogue rule is presented in the form of a dialogue flowchart, the dialogue flowchart includes a plurality of dialogue configuration nodes, and the dialogue configuration nodes are used to indicate at least one information processing operation, and the information processing operation is used to obtain response audio for received call audio.

[0053] The dialogue flowchart can be a visual diagram that visually presents the preset dialogue rule in a graphical form. The dialogue flowchart can show the logical sequence, conditional judgment, operation execution and other steps of the dialogue rule through nodes and connection lines, similar to a flowchart or a mind map. The dialogue flowchart facilitates easier understanding and editing of complex preset dialogue rules. The dialogue configuration node can be a visual component used in a graphical configuration environment, which can be used to perform at least one information processing operation. The dialogue configuration node can allow a user to build a complete dialogue flowchart through dragging and connecting.

[0054] In the embodiments of the present disclosure, in the case where the preset dialogue rule is presented in the form of a dialogue flowchart, the editing operation on the dialogue configuration information can be completed by editing the dialogue configuration nodes and determining the connection relationship between the dialogue configuration nodes. Therefore, in the case where the preset dialogue rule is presented in the form of a dialogue flowchart, receiving an editing operation on dialogue configuration information includes: receiving a node editing operation on at least one dialogue configuration node through a preset graphical editing area, determining a plurality of dialogue configuration nodes and a connection relationship between the dialogue configuration nodes according to the node editing operation; and determining a dialogue flowchart according to the plurality of dialogue configuration nodes and the connection relationship in the graphical editing area. The advantage of this setting is that the dialogue nodes and the connection relationship are visually configured through the graphical editing area to generate a flowchart, which realizes intuitive editing and management of dialogue rules and reduces the configuration threshold of complex rules. Meanwhile, through the clear definition of nodes and connection relationship, the dialogue logic is clear and controllable, which facilitates subsequent modification, optimization and reuse of rules.

[0055] The graphical editing area can be understood as a visual interface that supports users to configure rules through graphical configuration nodes. The graphical editing area can be a visual editing interface provided by the system for creating and modifying a dialogue flowchart. A user can drag nodes, draw connection lines and edit node content in the graphical editing area to realize graphical configuration of a preset dialogue rule. That is, the graphical editing area provides a visual and easy-to-understand rule configuration environment for users to build a dialogue flowchart through dragging and placing graphical configuration nodes. The node editing operation can be understood as a specific operation of creating, modifying, deleting and / or associating a dialogue configuration node by a user in the graphical editing area. Optionally, the node editing operation includes at least one of a node creation operation, a node modification operation, a node deletion operation and a node connection operation. The connection relationship can be a logical association between different dialogue configuration nodes in a dialogue flowchart established through connection lines, which is used to define the sequence, conditional branching and other relationships of the dialogue flow. The connection relationship determines which dialogue configuration node the agent should enter next after completing the operation of a dialogue configuration node.

[0056] In the embodiments of the present disclosure, the manner of adding the dialogue configuration node in the graphical editing area can include at least one of the following: selected from pre-created optional configuration nodes; created in real time according to input configuration information.

[0057] In some embodiments, in the case of receiving an agent configuration request, an agent configuration interface is displayed in response to the agent configuration request, and the agent configuration interface includes a graphical editing area. Further, a node display operation is received through the graphical editing area, and a plurality of optional configuration nodes are displayed. Further, in response to a node selection operation on any optional configuration node, the selected optional configuration node is taken as a dialogue configuration node, and the dialogue configuration node is added to the graphical editing area. Further, a node connection operation on the dialogue configuration node can be received through the graphical editing area, and a connection relationship between the dialogue configuration nodes is determined according to the node connection operation. Further, in response to an editing completion instruction, a dialogue flowchart is determined according to the plurality of dialogue configuration nodes and the connection relationship thereof in the graphical editing area.

[0058] In some embodiments, in the case of receiving an agent configuration request, an agent configuration interface is displayed in response to the agent configuration request, and the agent configuration interface includes a graphical editing area. Further, in the case of receiving node configuration information through the graphical editing area, a configuration node can be created according to the node configuration information, the created configuration node is taken as a dialogue configuration node, and the dialogue configuration node is added to the graphical editing area. Further, a node connection operation on the dialogue configuration node can be received through the graphical editing area, and a connection relationship between the dialogue configuration nodes is determined according to the node connection operation. Further, in response to an editing completion instruction, a dialogue flowchart is determined according to the plurality of dialogue configuration nodes and the connection relationship thereof in the graphical editing area.

[0059] In the embodiments of the present disclosure, in the case of receiving an editing operation on the dialogue configuration information, the edited dialogue configuration information can be determined according to the editing operation. Further, an agent can be created according to the edited dialogue configuration information.

[0060] S120, in response to a publishing operation on the agent, a first call end is determined, and an association relationship between the first call end and the agent is established; wherein the first call audio of the first call end is determined by the agent.

[0061] The publishing operation can be a triggering operation of applying the agent to an actual call scene. The publishing operation can be used to convert the agent from a "configuration state" to an "available state", so that it has the ability to handle actual call tasks. Optionally, the publishing operation includes at least one of the following: triggering a preset agent publishing control; the received audio information includes an audio trigger word associated with the agent publishing; the received gesture action includes a trigger gesture action associated with the agent publishing. The first call end can be a party subject in the call, and the call audio output by the first call end in the call is determined by the agent. The first call end can be a service-providing end in the call process. Optionally, the first call end can be at least one of an entity device, a system account, or a virtual account. The first call end is used to call the second call end. The second call end can be a service-demanding end in the call process. That is, in the call process, the second call end proposes a service demand for a certain service, and the first call end can provide the second call end with the service upon receiving the service demand. It should be noted that the call audio received by the agent includes the second call audio input by the second call end, which is the input basis for the agent to determine the first call audio. The first call audio can be audio content output by the first call end to the second call end according to the dialogue configuration information and the received call audio. For example: the agent generates the voice "Hello, what can I do for you?", which is transmitted to the user through the first call end. At this time, the voice "Hello, what can I do for you?" is taken as the first call audio.

[0062] The association relationship can be a binding connection established between the first call end and the agent after the publishing operation. Through the association relationship, the response audio obtained by the agent can be transmitted to the second call end through the first call end. That is, the call audio determination task of the first call end is responsible for the agent associated with it, and the output of the agent can be directly used as the audio content of the first call end.

[0063] It should be noted that in the scenario of providing interactive services through calls, usually the second call end with service needs sends a call request to the first call end capable of providing interactive services. Further, in the case of establishing a communication connection between the second call end and the first call end, the first call end and the second call end can call. Further, in order to improve the service quality on the basis of improving the service efficiency, the agent can be used to provide services for the second call end, that is, the agent analyzes the call audio input by the second call end and determines the corresponding response audio. At this time, in order to enable the second call end to obtain the services provided by the agent through the call, an association relationship between the agent and the first call end can be established. Further, when the second call end has service needs, the corresponding interactive services provided by the agent can be obtained by establishing a communication connection with the first call end. Thus, the effect that the agent can be used to replace the automatic audio interaction between the first call end and the second call end can be realized when the second call end initiates a call request corresponding to the first call end and establishes a communication connection.

[0064] In actual application, when the agent is used to provide services for the second call end, usually the integration of multiple independent systems is required, and the agent, the language synthesis platform, the speech recognition service, and the relay connected with the call end need to be developed respectively. These components need to be seamlessly integrated, which requires professional technical personnel, and the configuration process is complicated, the debugging process is complex, the technical threshold is high, and ordinary business personnel may not be able to complete independently, which has certain limitations. Moreover, since the agent and the first call end are separated from each other, when calling, the business personnel often need to switch between the agent management end and the call management end, thereby causing the management and configuration to be disconnected.

[0065] In view of the above, in the embodiment of the present disclosure, the dialogue configuration information for creating the agent can be edited to obtain edited dialogue configuration information, and the agent is created according to the edited dialogue configuration information. Further, in the case of receiving a publishing operation for the agent, the first call end associated with the agent is determined in response to the publishing operation. Further, the agent can be bound to the first call end to establish an association relationship between the agent and the first call end. Further, when the second call end establishes a communication connection with the first call end, the agent can be used to provide interactive services for the second call end.

[0066] In the embodiment of the present disclosure, the determination method of the first call end can include at least one of the following: selecting from the existing optional call end; creating a new call end. The following can explain the two determination methods respectively.

[0067] Optionally, the first call end is determined by: displaying end identifiers of the plurality of call ends; and determining the first call end according to a selected end identifier in response to a selection operation on the selected end identifier. This has the advantage of supporting user selection of the first call end, enabling visualized and convenient selection of the call end, and ensuring accurate association of the first call end with the intelligent agent, thereby improving flexibility and operation efficiency of the intelligent agent and the call end binding.

[0068] The call end can be a terminal or an account entity with a call function available in the system. The call end can include an enabled call end and / or a non-enabled call end. The end identifier can be a symbol, name or code for uniquely identifying the call end. For example, assuming that the call end is a telecom call end, the end identifier can be a phone number. The end identifier can be displayed to the user in the interface, facilitating user identification and selection of the desired call end.

[0069] In some embodiments, the end identifiers of the plurality of call ends can be obtained and displayed in the display interface. Further, in a case where a selection operation on any end identifier is received, the call end corresponding to the selected end identifier can be taken as the first call end.

[0070] It should be noted that the selected end identifier can include one or more. In a case where the selected end identifier is one, the call end corresponding to the end identifier can be taken as the first call end, and a one-to-one correspondence between the intelligent agent and the first call end can be established. In a case where the selected end identifier is more than one, the call ends corresponding to the plurality of end identifiers can all be taken as the first call end, and a one-to-many correspondence between the intelligent agent and the plurality of first call ends can be established. Further, when the second call end communicates with any of the first call ends, the intelligent agent can be communicated with.

[0071] Optionally, the first call end is determined by: creating a call end associated with the intelligent agent, and taking the created call end as the first call end.

[0072] In other embodiments, the new call end associated with the intelligent agent can be created before or after the intelligent agent is created. Further, the created call end can be taken as the first call end.

[0073] In the embodiments of the present disclosure, the published agent can also be reconfigured, and the agent can be updated by the object configuration information obtained through the configuration, so that the updated agent can be more consistent with the service logic and user demand of the call end. Optionally, after the association relationship between the first call end and the agent is established, the method further includes: in response to an editing operation for the first call end, displaying at least part of the dialogue configuration information of the agent associated with the first call end; and in response to an editing operation for the at least part of the dialogue configuration information, updating the agent.

[0074] The editing operation can be an interactive operation initiated for the first call end to modify the associated configuration. The at least part of the dialogue configuration information can be configuration information that can be edited. The at least part of the dialogue configuration information includes all dialogue configuration information and / or part of the dialogue configuration information.

[0075] It should be noted that the first call end associated with the agent can include one or more. In the case where the first call end associated with the agent is one, when the editing operation for the first call end is received, all dialogue configuration information of the agent associated with the first call end can be displayed to edit all dialogue configuration information and update the agent. In the case where the first call end associated with the agent is multiple, configuration information common to multiple first call ends in the dialogue configuration information of the agent can not need to be displayed, and configuration information associated with the first call end in the dialogue configuration information (for example, knowledge base, preset dialogue rule, and role setting information, etc.) can be displayed as at least part of the dialogue configuration information that can be edited. Further, the editing operation can be input for the displayed at least part of the dialogue configuration information to update the agent. Thus, the updated agent can be more consistent with the application scenario, service logic and call interaction demand of the first call end.

[0076] In specific implementation, after the association relationship between the first call end and the agent is established, the published agent can also be reconfigured. When the editing operation for the first call end is received, at least part of the dialogue configuration information that can be edited can be obtained from the dialogue configuration information of the agent associated with the first call end, and the at least part of the dialogue configuration information is displayed. Further, when the editing operation for the at least part of the dialogue configuration information is received, the edited dialogue configuration information is obtained according to the editing operation, and the agent is updated according to the edited object configuration information.

[0077] The technical scheme of the embodiment of the present disclosure realizes the scene configuration of the intelligent agent by receiving the editing operation on the dialogue configuration information, creating the intelligent agent according to the dialogue configuration information, can create the intelligent agent based on the intelligent agent configuration operation, reduces the threshold of intelligent agent development, saves the intelligent agent creation cost, improves the reusability of the intelligent agent, and because the dialogue configuration information is used to configure the rule followed by the intelligent agent when determining the call audio, the created intelligent agent has the targeted ability, the response content of the intelligent agent can be accurately controlled through the dialogue configuration information, and the accuracy of the intelligent agent is improved. Further, in response to the publishing operation on the intelligent agent, the first call end is determined, and the association relationship between the first call end and the intelligent agent is established, the effect that the intelligent agent is associated with the first call end through one-key publishing operation is realized, the technical threshold of the intelligent agent binding operation is reduced, and the accuracy of the response audio is improved. The technical scheme of the embodiment of the present disclosure solves the problem that the service acquisition process in the related art is relatively rigid and has certain limitations, thereby causing low service accuracy and poor service quality, realizes the effect that the intelligent agent can be created and associated with the call end through simple interactive operation, reduces the operation threshold of intelligent agent creation and intelligent agent binding, simplifies the intelligent agent creation and intelligent agent binding process, and further realizes the effect that the call interaction is performed through the intelligent agent, improves the naturalness and fluency of the call, and improves the service response speed, the service quality and the service accuracy.

[0078] Figure 2 The flowchart of another information interaction method provided by the embodiment of the present disclosure is shown. The technical scheme of the embodiment is based on the above-mentioned embodiment, and after the association relationship between the first call end and the intelligent agent is established, the intelligent agent and the second call end can further perform call interaction, the second call audio of the second call end is received by the intelligent agent, the first call audio fed back to the second call end is determined, and further, the first call audio is fed back to the second call end. The specific implementation can be seen from the description of the embodiment. Among them, the same or similar technical features as the foregoing embodiments are not described herein. As shown in the Figure 2 The method of the embodiment can specifically include:

[0079] S210, receiving an editing operation on dialogue configuration information, and creating an intelligent agent according to the dialogue configuration information; the dialogue configuration information is used to configure the rule followed by the intelligent agent when determining the call audio.

[0080] S220, in response to a publishing operation on the intelligent agent, determining a first call end, and establishing an association relationship between the first call end and the intelligent agent; wherein the first call audio of the first call end is determined by the intelligent agent.

[0081] S230, in response to the call request for the first call end, determining a second call end and acquiring second call audio of the second call end.

[0082] In the embodiments of the present disclosure, after the association relationship between the first call end and the intelligent agent is established, the intelligent agent can be applied to perform the corresponding interaction task through the communication connection established between the first call end.

[0083] The call request can be understood as a call application initiated by the other call end to the first call end, for applying to establish a communication connection with the first call end. The call request for the first call end can be a call request initiated by the other call end based on the first call identifier of the first call end. The second call end can be a terminal or a user entity that initiates the call request, and is an object for calling the first call end. For example, assuming that the first call end is a customer service hotline of a platform, the second call end can be a user who dials the customer service hotline. The second call audio can be a voice signal output by the second call end during the call, which can at least include audio data describing service requirements.

[0084] In specific implementation, in the case that the call request for the first call end is received, the call request can be parsed to obtain the call identifier of the call end that initiates the call request, and the call end corresponding to the call identifier is taken as the second call end. Then, the communication connection between the first call end and the second call end is established. Further, in the communication process, the call audio input by the second call end can be collected, and then the second call audio of the second call end can be obtained.

[0085] S240, determining the first call audio according to the intelligent agent and the second call audio, and feeding back the first call audio to the second call end.

[0086] In the embodiments of the present disclosure, after obtaining the second call audio, the intelligent agent can be used to analyze and process the second call audio, and obtain the response audio of the second call audio. Then, the response audio is taken as the first call audio, and the first call audio is fed back to the second call end.

[0087] In the embodiments of the present disclosure, the way of determining the first call audio according to the intelligent agent and the second call audio can include at least one of the following, which will be described below.

[0088] Optionally, the third model is integrated in the intelligent agent, and the way of determining the first call audio according to the intelligent agent and the second call audio includes: inputting the second call audio into the third model to analyze and process the second call audio through the third model, and obtaining the first call audio.

[0089] The third model can be an algorithmic model with end-to-end audio processing capability, which can directly receive the second call audio as input, and directly output corresponding reply audio through built-in voice recognition, semantic understanding, reply generation, speech synthesis and other integrated logic. The third model can usually be a deep learning model.

[0090] In a specific implementation, after obtaining the second call audio of the second call end, the second call audio can be input into the agent. Further, the second call audio can be input into the third model. Then, the second call audio can be analyzed and processed by the third model, and the first call audio can be obtained. Further, the first call audio can be fed back to the second call end.

[0091] Optionally, the agent includes an audio recognition module, a call response module, and an audio synthesis module; the call response module includes a first model and a plurality of call response units; determining the first call audio according to the agent and the second call audio includes: converting the second call audio into second call text through the audio recognition module; determining a call content category according to the second call text and the first model, and in response to the call content category being a first category, determining first call text according to a call response unit associated with the call content category; and converting the first call text into the first call audio through the audio synthesis module. This arrangement has the advantage that: through the modular division of the agent (audio recognition, content classification, response generation, and audio synthesis), automatic processing of call audio from recognition to reply is achieved; by matching the response unit according to the content category, the reply is ensured to be accurately adapted to the demand, and the efficiency, professionalism, and scene adaptability of call interaction are improved.

[0092] The audio recognition module can be one of the core modules of the intelligent agent, and is configured to convert the received call audio into call text in the form of text. The audio recognition module can be a program or a system module with a speech-to-text function. The output of the audio recognition module can be used to provide input for subsequent text analysis. The call response module can be one of the core modules of the intelligent agent, and is configured to analyze the call text and determine a reply text according to the analysis result. The call response module includes a first model and a plurality of call response units. The first model can be an analysis model in the call response module, configured to perform semantic understanding and classification on the call text to determine the call content category to which the call text belongs. The first model can be a rule-based model, a machine learning model, or a deep learning model. The call response unit can be a reply logic module preset for different call content categories. Each call response unit corresponds to a specific category of call content and includes a dialogue rule, a reply template, or a processing flow for the category. The audio synthesis module can be one of the core sub-modules of the intelligent agent, configured to convert the call text in the form of text into a speech signal, so that it can be received by the second call terminal in the form of speech. The audio synthesis module can be a program or a system module with a text-to-speech function.

[0093] The second call text can be the text content obtained by performing audio recognition and audio conversion on the second call audio. The conversion of the second call audio into the second call text by the audio recognition module can convert audio signals that cannot be directly analyzed into structured text, facilitating subsequent semantic analysis and understanding by the model. The call content category can be a pre-classified subject or content type to which the received call audio belongs. The call content category can be used to distinguish different call scenarios or needs. For example, the call content category can include product consultation, order inquiry, complaint suggestion, after-sales problem, and artificial service, etc. The first category can be a category that does not require call transfer and can be directly responded to. For example, the first category can be all call content categories except the artificial service category. The first call text can be a reply text generated by the call response unit for the second call text, and is the response result output by the intelligent agent in the form of text. The first call text can be a response result in the form of text determined by the intelligent agent for the received second call audio.

[0094] In specific implementation, after the second call audio of the second call end is acquired, the second call audio can be input into the intelligent agent. Further, the second call audio can be converted into call text in the form of text by the audio recognition module in the intelligent agent, i.e., the second call text can be obtained. Further, the second call text can be input into the call response module, and the second call text is analyzed and processed by the first model in the call response module to determine the call content category of the second call text. Further, in the case where the determined call content category is the first category, the call response unit corresponding to the call content category is determined, and the second call text is input into the call response unit for analysis and processing, and the first call text is obtained. Further, the first call text can be input into the audio synthesis module, and the first call text is converted into response results in the form of audio by the audio synthesis module, i.e., the first call audio can be obtained. Further, the first call audio can be fed back to the second call end.

[0095] In the embodiments of the present disclosure, when the first call text is determined by the call response unit, at least two determination methods can be included: the first call text is acquired from the preset call text; and the first call text is generated by the second model. The two determination methods can be described as follows.

[0096] Optionally, the first call text is determined according to the call response unit associated with the call content category, including: the first call text is acquired from the preset call text associated with the call content category by the call response unit associated with the call content category. The advantage of this setting is that the reply text of the corresponding category is directly acquired from the preset call text, which realizes fast response in a simple scenario and reduces the calculation cost of real-time text generation; at the same time, the preset text ensures the standardization and accuracy of the reply content, and improves the efficiency and reliability of the call interaction.

[0097] The preset call text can be a standardized reply text set in advance for a specific scenario or demand. The preset call text can be directly called in a specific scenario to quickly generate a reply without real-time analysis and processing. For example, assuming that the call content category is an order query category, the preset "order query" process can be directly executed to determine the first call text "OK, what is your order number?" from the preset call text.

[0098] In specific implementation, the preset call text associated with the call content category can be acquired, and the reply text matched with the second call text can be acquired from the preset call text by the call response unit associated with the call content category, and the acquired reply text can be taken as the first call text.

[0099] Optionally, the call response unit is associated with a second model; and the first call text is determined according to the call response unit associated with the call content category, including: calling the second model through the call response unit associated with the call content category to generate the first call text through the second model. The advantage of this setting is that the reply text is dynamically generated by calling the second model, which realizes flexible response to complex or personalized call demands and breaks through the fixed limitations of preset text; at the same time, with the generation ability of the model, it is ensured that the reply content is consistent with the specific scene details, and the intelligence and adaptability of the call interaction are improved.

[0100] The second model can be an algorithm model integrated in the call response unit for dynamically generating reply text. The second model can have semantic understanding and text generation capabilities and can generate corresponding reply text according to the input call text. The second model can be a deep learning model trained through multiple rounds of sample dialogues, or it can be a rule model.

[0101] In specific implementation, the second model can be called through the call response unit associated with the call content category. Then, the second call text can be input into the second model to analyze and process the second call text through the second model and generate the first call text.

[0102] In this embodiment, generating the first call text through the second model can include at least one of the following generation methods: in the case where the second model is a deep learning model trained through multiple rounds of sample dialogues, the second model directly processes the second call text and generates the first call text; the second model queries the associated knowledge base and generates the first call text according to the query result. The following will describe these two generation methods respectively.

[0103] Optionally, generating the first call text through the second model includes: inputting the second call text into the second model to analyze and process the second call text through the second model and output the first call text.

[0104] Optionally, the call response unit is associated with a knowledge base; and generating the first call text through the second model includes: querying the knowledge base through the second model and generating the first call text according to the query result. The advantage of this setting is that the reply text is generated by querying the knowledge base through the second model, which ensures that the content generated by the model is supported by professional knowledge and ensures the accuracy and reliability of the reply; at the same time, the knowledge base provides specific basis for the model, avoids empty or incorrect replies, and improves the professionalism and information accuracy of the call interaction.

[0105] The knowledge base can be a database associated with the call response unit and storing professional information. The knowledge base can be used to provide the second model with a basis for generating a reply, ensuring the accuracy and professionalism of the reply. For example, assuming that the call response unit is a consultation response unit, the knowledge base associated with the call response unit can include product parameters, service policies, common question answers, and the like.

[0106] In the embodiments of the present disclosure, the first call text can be generated according to the query result in at least one of the following ways: directly taking the query result as the first call text; and integrating and analyzing the query result, and taking the integrated result as the first call text.

[0107] In some embodiments, the second model can query the knowledge base associated therewith according to the second call text, and obtain a query result matched with the second call text. Further, the query result can be input into the fourth model to integrate and analyze the query result by the fourth model, and obtain the first call text.

[0108] In the embodiments of the present disclosure, during the communication between the first call end and the second call end, the satisfaction degree of the second call end to the call audio fed back by the first call end can be low, and at this time, the second call end can have a demand for call transfer. Further, when it is determined that the call content category corresponding to the obtained second call audio is the second category, i.e., the call content category requiring call transfer, a call transfer operation can be performed to connect the second call end with a third call end, so that the third call end continues to provide corresponding interactive services for the second call end.

[0109] Optionally, the call response unit includes a call transfer unit, and the information interaction method further includes: in response to the call content category being the second category, generating a call transfer instruction by the call content category associated call transfer unit, and establishing a connection between the second call end and the third call end according to the call transfer instruction. The advantage of this setting is that by identifying the second category demand and triggering the call transfer, the flexible connection between the agent and the artificial or professional end is realized, and the complex demand that cannot be handled by the agent is solved; at the same time, the automatic transfer process ensures uninterrupted response, and improves the integrity of the call problem solving and the user experience.

[0110] The second category can be a content category that needs to trigger call transfer, is preset by the system, and is a demand type that cannot be independently processed by the intelligent agent. For example, the second category can be a category that needs human intervention. The call transfer unit can be a submodule of the call response unit for performing a call transfer operation. The call transfer unit can be configured to trigger and complete the operation of transferring the call from the current line to another line when the call content category is the second category. In the embodiments of the present disclosure, the call transfer unit can be configured to establish a new call connection after receiving a call transfer instruction, while disconnecting the original connection or maintaining a multi-end call state. The call transfer instruction can be an instruction signal generated by the call response unit to start the transfer process. The call transfer instruction can generally include the call identifier of the call end to which the call is transferred and the transfer reason, etc., to guide the call transfer unit to perform the call transfer operation. The third call end can be the call end to which the call is transferred, or it can also be understood as the call end that receives the transfer. The third call end can generally be a human customer service, a professional agent, or other terminals that handle specific problems.

[0111] In specific implementations, when it is determined that the call content category corresponding to the second call text is the second category, a call transfer instruction can be generated by the call content category associated call transfer unit. Further, the third call end to which the call is transferred can be determined according to the call transfer instruction, and the connection between the second call end and the third call end can be established according to the call transfer instruction.

[0112] For example, assuming that the call content category is a human service category, it is determined that it is the second category, and further, a call transfer instruction to transfer to a human customer service can be generated according to the call transfer unit. Further, the connection between the second call end and the human customer service end can be established according to the call transfer instruction.

[0113] The technical solution of the embodiments of the present disclosure realizes intelligent and automatic processing of call interaction by establishing an association between the first call end and the intelligent agent, determining the second call end in response to a call request for the first call end, obtaining the second call audio of the second call end, further determining the first call audio according to the intelligent agent and the second call audio, and feeding back the first call audio to the second call end. The whole process from obtaining the audio to generating the reply is connected, ensuring that the call response is timely and efficient, and improving the convenience and automation experience of call interaction.

[0114] In order to better understand the information interaction method provided by the embodiments of the present disclosure, the following is exemplarily described in conjunction with examples. Figure 3 The signaling diagram of the intelligent agent creation method provided by the embodiments of the present disclosure; Figure 4 The signaling diagram of the information interaction method provided by the embodiments of the present disclosure. Next, the information interaction method provided by the embodiments of the present disclosure will be described in conjunction with Figure 3 and Figure 4The information interaction method provided by the embodiments of the present disclosure is exemplarily described.

[0115] As shown in the figure, the intelligent agent creation method can specifically include: Figure 3

[0116] 1. Receiving, by the intelligent voice platform, an editing trigger operation of a user on an intelligent agent, triggering an intelligent agent editing process;

[0117] 2. Configuring role setting information for the intelligent agent;

[0118] 3. Configuring a business knowledge base for the intelligent agent;

[0119] 4. Configuring a business process required to be executed by the intelligent agent;

[0120] 5. Saving, by the intelligent voice platform, the configuration information of the intelligent agent;

[0121] 6. Receiving, by the intelligent voice platform, a telephone number configuration request input by the user, to pull a telephone number according to the telephone number configuration request;

[0122] 7. In the case where the intelligent voice platform receives the telephone number configuration request, obtaining available telephone numbers from the intelligent outbound platform;

[0123] 8. The intelligent outbound platform feeds back available telephone lists to the intelligent voice platform, and the telephone lists can include at least one available telephone number;

[0124] 9. The intelligent voice platform feeds back the telephone lists to the user, and in the case where the user inputs a number selection operation on any available telephone number, the selected available telephone number can be used as a telephone number associated with the intelligent agent;

[0125] 10. In response to a publishing operation of the intelligent agent, associating the intelligent agent with the selected telephone number;

[0126] 11. Saving, by the intelligent voice platform, the association relationship between the intelligent agent and the telephone number;

[0127] 12. Sending, by the intelligent voice platform, a notification to the intelligent outbound platform, to notify that the intelligent agent and the telephone number have been associated and bound;

[0128] 13. Recording, by the intelligent outbound platform, the binding relationship between the intelligent agent and the telephone number, and updating the state of the telephone number to an occupied state;

[0129] 14. Sending, by the intelligent outbound platform, reply information of successful binding to the intelligent voice platform;

[0130] 15. Sending, by the intelligent voice platform, the reply information of successful binding to the user.​

[0131] As Figure 4 shown, the information interaction method can specifically include:

[0132] 1. The call user (the user requesting the call) dials a phone to the intelligent outbound platform through the telecom operator;

[0133] 2. The telecom operator sends a call request to the intelligent outbound platform;

[0134] 3. The intelligent outbound platform judges whether the phone number dialed by the call user belongs to the intelligent voice dialogue;

[0135] 4. In the case of determining that it belongs to the intelligent voice dialogue, the intelligent outbound platform sends a connection request to the intelligent voice platform;

[0136] 5. In the case that the intelligent external platform receives the response information fed back by the intelligent voice platform, it is determined that the connection between the intelligent outbound platform and the intelligent voice platform is successful;

[0137] 6. The intelligent outbound platform sends a communication protocol to the intelligent voice platform to update the dialogue configuration;

[0138] 7. The intelligent voice platform returns the update result to the intelligent outbound platform;

[0139] 8. The intelligent voice platform feeds back the opening speech to the intelligent outbound platform;

[0140] 9. The intelligent outbound platform pushes the opening speech to the telecom operator;

[0141] 10. The telecom operator replies to the call user with the opening speech;

[0142] 11. The call user starts to speak and acquires the call audio of the user;

[0143] 12. The telecom operator sends the call audio of the user to the intelligent outbound platform;

[0144] 13. The intelligent outbound platform sends the call audio of the user to the intelligent voice platform;

[0145] 14. The intelligent voice platform generates a reply response audio according to the call audio of the user;

[0146] 15. The intelligent voice platform sends the generated response audio to the intelligent outbound platform;

[0147] 16. The intelligent outbound platform feeds back the generated response audio to the telecom operator;

[0148] 17. The telecom operator feeds back the response audio to the call user;

[0149] 18. The calling user starts to speak, and the user's call audio is obtained, for example, the call audio includes a need for manual service;

[0150] 19. The user's call audio is sent to the intelligent outbound call platform through the telecom operator;

[0151] 20. The user's call audio is sent to the intelligent voice platform through the intelligent outbound call platform;

[0152] 21. The intelligent voice platform performs semantic understanding on the user's call audio, and generates a transfer to manual instruction in the case that the user needs manual service;

[0153] 22. The intelligent voice platform issues the transfer to manual instruction;

[0154] 23. The intelligent voice platform issues the transfer to manual instruction to the intelligent outbound call platform;

[0155] 24. The intelligent outbound call platform processes the transfer to manual instruction, and determines the manual call end to which the call is transferred;

[0156] 25. An artificial access request is sent to the outbound call personnel;

[0157] 26. The outbound call personnel sends reply information to the intelligent outbound call platform;

[0158] 27. The intelligent outbound call platform feeds back the artificial reply information to the telecom operator;

[0159] 28. The telecom operator feeds back the artificial reply information to the calling user.

[0160] The technical scheme of the embodiment of the present disclosure encapsulates complex back-end technology through the "one-key publishing" function, so that business personnel without technical background can also create and put online a powerful voice customer service intelligent agent in a few minutes, realizes the popularization of technology, and greatly reduces the technical threshold. Moreover, through the innovative mixed intelligent reasoning engine, especially the application of preposed intention reasoning and fast reasoning link, for common and repetitive problems, the response speed can be shortened from several seconds to less than 1 second, almost eliminating the embarrassing pause in the call, making the human-computer dialogue as smooth and natural as a real person. Greatly reduce operating costs: Moreover, the fast reasoning link usually only involves simple database queries or interface calls, and its computing cost is much lower than calling large language models. By preferentially using the fast link, dependence on expensive intelligent agent computing power can be significantly reduced, thereby reducing overall operating costs. Both flexible and accurate: The present scheme does not completely abandon the model, but calls it when needed (such as processing open-domain problems or chatting). This hybrid mode not only guarantees the efficiency and accuracy of answering specific business problems (through the fast link), but also retains the flexibility and generalization ability to handle long-tail and complex problems (through the general model).

[0161] Figure 5 The structure diagram of an information interaction device provided by the embodiment of the present disclosure is shown in Figure 5 The device includes an intelligent agent creation module 310 and an intelligent agent publishing module 320. The intelligent agent creation module 310 is configured to receive an editing operation on dialogue configuration information, and create an intelligent agent according to the dialogue configuration information. The dialogue configuration information is used to configure rules followed by the intelligent agent when determining call audio. The intelligent agent publishing module 320 is configured to determine a first call end in response to a publishing operation on the intelligent agent, and establish an association relationship between the first call end and the intelligent agent. The first call audio of the first call end is determined by the intelligent agent.

[0162] The technical scheme of the embodiment of the present disclosure receives an editing operation on the dialogue configuration information through the intelligent agent creation module 310, creates an intelligent agent according to the dialogue configuration information, realizes the scene configuration of the intelligent agent, can create an intelligent agent based on the intelligent agent configuration operation, reduces the threshold of intelligent agent development, saves the intelligent agent creation cost, improves the reusability of the intelligent agent, and because the dialogue configuration information is used to configure the rule followed by the intelligent agent when determining the call audio, the created intelligent agent has the targeted ability, the response content of the intelligent agent can be accurately controlled through the dialogue configuration information, and the accuracy of the intelligent agent is improved. Further, the intelligent agent publishing module 320 responds to the publishing operation on the intelligent agent, determines the first call end, establishes the association relationship between the first call end and the intelligent agent, realizes the effect of associating the intelligent agent with the first call end through one-key publishing operation, reduces the technical threshold of the intelligent agent and call end binding operation, and ensures that the call response audio is automatically determined by the intelligent agent, improves the interaction efficiency and continuity, and improves the accuracy of the response audio. The technical scheme of the embodiment of the present disclosure solves the problem that the service acquisition process in the related art is relatively rigid and has certain limitations, thereby causing low service accuracy and poor service quality, realizes the effect that the intelligent agent can be created and associated with the call end through simple interaction operation, reduces the operation threshold of intelligent agent creation and intelligent agent binding, simplifies the intelligent agent creation and intelligent agent binding process, and further realizes the effect of call interaction through the intelligent agent, improves the naturalness and fluency of the call, and improves the service response speed, the service quality and the service accuracy.

[0163] On the basis of any optional technical scheme in the embodiments of the present disclosure, the intelligent agent publishing module 320 includes an identifier display unit and a call end determination unit. The identifier display unit is configured to display the end identifiers of the plurality of call ends. The call end determination unit is configured to determine the first call end according to the selected end identifier in response to the selection operation on at least one of the end identifiers.

[0164] On the basis of any optional technical scheme in the embodiments of the present disclosure, the apparatus further includes a dialogue configuration information display module and an intelligent agent updating module. The dialogue configuration information display module is configured to display at least part of the dialogue configuration information of the intelligent agent associated with the first call end in response to the editing operation on the first call end after the association relationship between the first call end and the intelligent agent is established. The intelligent agent updating module is configured to update the intelligent agent in response to the editing operation on at least part of the dialogue configuration information.

[0165] In any of the optional technical solutions in the embodiments of the present disclosure, the dialogue configuration information comprises preset dialogue rules; the preset dialogue rules are presented in the form of a dialogue flowchart; the dialogue flowchart comprises a plurality of dialogue configuration nodes; the dialogue configuration nodes are used to indicate at least one information processing operation for responding to the received call audio.

[0166] In any of the optional technical solutions in the embodiments of the present disclosure, the intelligent agent creation module 310 comprises a node connection relationship determination unit and a dialogue flowchart determination unit. The node connection relationship determination unit is configured to receive a node editing operation for at least one dialogue configuration node through a preset graphical editing area, determine a plurality of dialogue configuration nodes and a connection relationship between the dialogue configuration nodes according to the node editing operation; and the dialogue flowchart determination unit is configured to determine the dialogue flowchart according to the plurality of dialogue configuration nodes and the connection relationship thereof in the graphical editing area.

[0167] In any of the optional technical solutions in the embodiments of the present disclosure, the device further comprises a call audio acquisition module and a call audio determination module. The call audio acquisition module is configured to, after the association relationship between the first call end and the intelligent agent is established, determine a second call end in response to a call request for the first call end, and acquire second call audio of the second call end; and the call audio determination module is configured to determine first call audio according to the intelligent agent and the second call audio, and feed back the first call audio to the second call end.

[0168] In any of the optional technical solutions in the embodiments of the present disclosure, the intelligent agent comprises an audio recognition module, a call response module and an audio synthesis module; the call response module comprises a first model and a plurality of call response units; and the call audio determination module comprises an audio conversion submodule, a call text determination submodule and a call audio determination submodule. The audio conversion submodule is configured to convert the second call audio into second call text through the audio recognition module; the call text determination submodule is configured to determine a call content category according to the second call text and the first model, and determine first call text according to a call response unit associated with the call content category in response to the call content category being a first category; and the call audio determination submodule is configured to convert the first call text into first call audio through the audio synthesis module.

[0169] In any of the optional technical solutions in the embodiments of the present disclosure, the call text determination submodule comprises a call text acquisition unit. The call text acquisition unit is configured to acquire the first call text from a preset call text associated with the call content category through the call response unit associated with the call content category.

[0170] On the basis of any optional technical solution in the embodiments of the present disclosure, the call response unit is associated with a second model; the call text determination submodule comprises a call text generation unit. The call text generation unit is configured to call the second model through the call response unit associated with the call content category, and generate a first call text through the second model.

[0171] On the basis of any optional technical solution in the embodiments of the present disclosure, the call response unit is associated with a knowledge base; the call text generation unit is specifically configured to query the knowledge base through the second model and generate a first call text according to a query result.

[0172] On the basis of any optional technical solution in the embodiments of the present disclosure, the call response unit comprises a call switching unit; the information interaction device further comprises a call switching module. The call switching module is configured to, in response to the call content category being a second category, generate a call switching instruction through the call content category-associated call switching unit, and establish a connection between the second call end and a third call end according to the call switching instruction.

[0173] On the basis of any optional technical solution in the embodiments of the present disclosure, the dialogue configuration information comprises at least one of role setting information of the agent, a knowledge base associated with the agent, and a preset dialogue rule; the preset dialogue rule comprises a plurality of information processing operations, and the information processing operation is used to obtain a response audio for the received call audio.

[0174] The information interaction device provided in the embodiments of the present disclosure can execute the information interaction method provided in any of the embodiments of the present disclosure, and has the corresponding function modules and beneficial effects of executing the information interaction method.

[0175] It should be noted that each unit and module included in the above device is only divided according to the function logic, but is not limited to the above division, as long as the corresponding function can be implemented; in addition, the specific name of each functional unit is only for convenient distinction, and does not limit the protection scope of the embodiments of the present disclosure.

[0176] Reference will be made to the following description of the embodiments of the present disclosure with reference to the accompanying drawings. Figure 6 Fig. 6 shows a structural schematic diagram of an electronic device (such as a terminal device or a server) 600 suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure can include but is not limited to a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a vehicle-mounted terminal (such as a vehicle-mounted navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. Figure 6The electronic device shown is merely an example and should not bring any limitation to the functions and usage range of the embodiments of the present disclosure.

[0177] As shown in Figure 6 The electronic device 600 can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded into a random access memory (RAM) 603 from a storage device 608. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0178] Generally, the following devices can be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication devices 609 can allow the electronic device 600 to communicate with other devices wirelessly or through wires to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that all of the shown devices are not required to be implemented or possessed. More or fewer devices can be alternatively implemented or possessed.

[0179] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 609, or installed from the storage devices 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0180] The names of the messages or information exchanged between the plurality of devices in the embodiments of the present disclosure are only for illustrative purposes, and are not intended to limit the scope of the messages or information.

[0181] The electronic device provided by the embodiments of the present disclosure and the information interaction method provided by the above-mentioned embodiments belong to the same inventive concept, and the technical details not described in detail in the embodiments of the present disclosure can be referred to the above-mentioned embodiments, and the embodiments have the same beneficial effects as the above-mentioned embodiments.

[0182] The computer storage medium provided by the embodiments of the present disclosure stores a computer program, and the computer program is executed by a processor to implement the information interaction method provided by the above-mentioned embodiments.

[0183] It should be noted that the computer readable medium of the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the above two. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples of computer readable storage medium can include, but are not limited to, electrical connections with one or more conductive wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or component. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0184] According to one or more embodiments of the present disclosure, example one provides an information interaction method, comprising: receiving an editing operation on dialogue configuration information, and creating an agent according to the dialogue configuration information; the dialogue configuration information is used to configure rules followed by the agent when determining call audio; in response to a publishing operation on the agent, determining a first call end and establishing an association relationship between the first call end and the agent; wherein the first call audio of the first call end is determined by the agent.

[0185] According to one or more embodiments of the present disclosure, example two provides the method of example one, further comprising: optionally, the determination of the first call end comprises: displaying the end identifiers of a plurality of call ends; in response to a selection operation on at least one of the end identifiers, determining the first call end according to the selected end identifier.

[0186] According to one or more embodiments of the present disclosure, Example Three provides the method of Example One, further comprising: optionally, after the association between the first call terminal and the intelligent agent is established, further comprising: in response to an editing operation for the first call terminal, displaying at least part of the conversation configuration information of the intelligent agent associated with the first call terminal; and in response to an editing operation for at least part of the conversation configuration information, updating the intelligent agent.

[0187] According to one or more embodiments of the present disclosure, Example Four provides the method of Example One, further comprising: optionally, the conversation configuration information comprises a preset conversation rule; the preset conversation rule is in the form of a conversation flowchart; the conversation flowchart comprises a plurality of conversation configuration nodes; and the conversation configuration node is used to indicate at least one information processing operation for a response audio for a received call audio.

[0188] According to one or more embodiments of the present disclosure, Example Five provides the method of Example Four, further comprising: optionally, the receiving an editing operation for the conversation configuration information comprises: receiving a node editing operation for at least one conversation configuration node through a preset graphical editing area, determining a plurality of conversation configuration nodes and a connection relationship between the conversation configuration nodes according to the node editing operation; and determining the conversation flowchart according to the plurality of conversation configuration nodes and the connection relationship thereof in the graphical editing area.

[0189] According to one or more embodiments of the present disclosure, Example Six provides the method of Example One, further comprising: optionally, after the association between the first call terminal and the intelligent agent is established, further comprising: in response to a call request for the first call terminal, determining a second call terminal and obtaining a second call audio of the second call terminal; determining a first call audio according to the intelligent agent and the second call audio, and feeding back the first call audio to the second call terminal.

[0190] According to one or more embodiments of the present disclosure, Example Seven provides the method of Example Six, further comprising: optionally, the intelligent agent comprises an audio recognition module, a call response module, and an audio synthesis module; the call response module comprises a first model and a plurality of call response units; and the determining a first call audio according to the intelligent agent and the second call audio comprises: converting the second call audio into a second call text through the audio recognition module; determining a call content category according to the second call text and the first model, and in response to the call content category being a first category, determining a first call text according to a call response unit associated with the call content category; and converting the first call text into a first call audio through the audio synthesis module.

[0191] According to one or more embodiments of the present disclosure, Example Eight provides the method of Example Seven, further including: optionally, the call response unit associated with the call content category determines the first call text, including: through the call response unit associated with the call content category, obtaining the first call text from the preset call text associated with the call content category.

[0192] According to one or more embodiments of the present disclosure, Example Nine provides the method of Example Seven, further including: optionally, the call response unit is associated with a second model; the call response unit associated with the call content category determines the first call text, including: through the call response unit associated with the call content category, calling the second model to generate the first call text through the second model.

[0193] According to one or more embodiments of the present disclosure, Example Ten provides the method of Example Nine, further including: optionally, the call response unit is associated with a knowledge base; the first call text is generated through the second model, including: querying the knowledge base through the second model and generating the first call text according to the query result.

[0194] According to one or more embodiments of the present disclosure, Example Eleven provides the method of Example Seven, further including: optionally, the call response unit includes a call transfer unit; further including: in response to the call content category being a second category, generating a call transfer instruction through the call content category associated call transfer unit, and establishing a connection between the second call end and a third call end according to the call transfer instruction.

[0195] According to one or more embodiments of the present disclosure, Example Twelve provides the method of Example One, further including: optionally, the dialogue configuration information includes at least one of role setting information of the agent, a knowledge base associated with the agent, and a preset dialogue rule; the preset dialogue rule includes a plurality of information processing operations, and the information processing operation is used to obtain a response audio for the received call audio.

[0196] According to one or more embodiments of the present disclosure, Example Thirteen provides an information interaction device, including: an agent creation module, configured to receive an editing operation for dialogue configuration information, and create an agent according to the dialogue configuration information; the dialogue configuration information is used to configure a rule followed by the agent when determining a call audio; an agent publishing module, configured to determine a first call end in response to a publishing operation for the agent, and establish an association relationship between the first call end and the agent; wherein the first call audio of the first call end is determined by the agent.

[0197] In some embodiments, the client, server, or other computing machines utilized by the embodiments can communicate using any known or later developed form of computer readable media, including but not limited to wireless media (e.g., radio frequency, microwave, infrared, etc.), wired media (e.g., coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.), or any other form of computer readable medium. In some embodiments, the client, server, or other computing machines utilized by the embodiments can communicate using any current or future developed network protocol, such as the Hyper Text Transfer Protocol (HTTP) or the like, and can be interconnected with any form or medium of digital data communication (for example, a communication network) including the Internet, Intranet, Extranet, or the like.

[0198] The computer readable medium described above can be included in the electronic device described above; or can exist separately from the electronic device, and can be accessed via the electronic device.

[0199] The computer readable medium described above carries one or more programs, which when executed by the electronic device, cause the electronic device to: receive an editing operation for dialogue configuration information, create an agent according to the dialogue configuration information; the dialogue configuration information is used to configure rules followed by the agent when determining call audio; in response to a publishing operation for the agent, determine a first call end, and establish an association relationship between the first call end and the agent; wherein the first call audio of the first call end is determined by the agent.

[0200] Computer program code for carrying out operations of the present disclosure can be written in any of one or more programming languages, including but not limited to object oriented programming languages such as Java, Smalltalk, C++, or conventional procedural programming languages such as the "C" programming language or similar programming languages. The program code can 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 latter scenario, the remote computer can 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 can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0201] The computer program product of the first aspect can include one or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform the operations of the first aspect. The one or more non-transitory computer-readable media can include, for example, magnetic media such as one or more magnetic disks, magnetic tapes or cassettes; optical media such as one or more compact discs, optical discs or Blu-ray discs; magneto-optical media such as one or more floptical discs; solid state media such as one or more solid state drives or other flash memory arrays; or any suitable combination of these. The one or more non-transitory computer-readable media can be encoded with instructions that, when executed, cause one or more processors to perform the operations of the first aspect.

[0202] The modules or units described in the embodiments of the present disclosure can be implemented by software or by hardware. In some cases, the name of the module or unit does not constitute a limitation on the module or unit itself. For example, the agent creating module can also be described as a "module for creating an agent".

[0203] The functions described in the above description can be performed at least in part by one or more hardware logic components. For example, and without limitation, example types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Application-specific Integrated Circuits (ASICs), Application-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0204] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0205] The above description merely illustrates the preferred embodiments of the disclosure and a principle for applying the technologies. It is understood by those skilled in the art that the disclosed scope of the disclosure is not limited to the technical solutions formed by the specific combinations of the technical features described above, and should also cover other technical solutions formed by the combinations of the technical features described above or their equivalent features without departing from the disclosed concept. For example, the technical solutions formed by the mutual replacement of the above-described features and the technical features with similar functions disclosed in the disclosure (but not limited to) can be formed.

[0206] Further, although operations are depicted in a particular, sequential order, this should not be understood as requiring or implying that the operations are performed in the order illustrated or sequentially. In certain circumstances, multitasking and parallel processing can be advantageous. Likewise, although specific implementation details are included for the purpose of providing a thorough disclosure, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination.

[0207] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. An information exchange method, characterized in that, include: Receive editing operations on dialogue configuration information, and create an intelligent agent based on the dialogue configuration information; wherein, the dialogue configuration information is used to configure the rules followed by the intelligent agent when determining the call audio; In response to the publishing operation for the intelligent agent, a first calling terminal is identified, and an association relationship is established between the first calling terminal and the intelligent agent; wherein, the first calling audio of the first calling terminal is determined by the intelligent agent.

2. The information interaction method according to claim 1, characterized in that, The determination of the first call terminal includes: Displays the terminal identifiers of multiple callers; In response to a selection operation for at least one of the terminal identifiers, a first calling terminal is determined based on the selected terminal identifier.

3. The information interaction method according to claim 1, characterized in that, After establishing the association between the first call terminal and the intelligent agent, the method further includes: In response to an edit operation on the first call terminal, at least a portion of the dialogue configuration information of the agent associated with the first call terminal is displayed; The agent is updated in response to an edit operation on at least a portion of the dialogue configuration information.

4. The information interaction method according to claim 1, characterized in that, The dialogue configuration information includes preset dialogue rules; the preset dialogue rules are presented in the form of a dialogue flowchart; the dialogue flowchart includes multiple dialogue configuration nodes; the dialogue configuration nodes are used to indicate at least one information processing operation, and the information processing operation is used to obtain response audio for the received call audio.

5. The information interaction method according to claim 4, characterized in that, The receiving of editing operations for dialogue configuration information includes: The system receives node editing operations for at least one dialog configuration node through a preset graphical editing area, and determines multiple dialog configuration nodes and the connection relationships between the dialog configuration nodes based on the node editing operations. The dialogue flowchart is determined based on multiple dialogue configuration nodes and their connections in the graphical editing area.

6. The information interaction method according to claim 1, characterized in that, After establishing the association between the first call terminal and the intelligent agent, the method further includes: In response to a call request from the first caller, a second caller is identified, and the second call audio from the second caller is obtained. The first call audio is determined based on the intelligent agent and the second call audio, and the first call audio is fed back to the second call terminal.

7. The information interaction method according to claim 6, characterized in that, The intelligent agent includes an audio recognition module, a call response module, and an audio synthesis module; The call response module includes a first model and multiple call response units; Determining the first call audio based on the intelligent agent and the second call audio includes: The audio recognition module converts the second call audio into the second call text. The call content category is determined based on the second call text and the first model. In response to the call content category being the first category, the first call text is determined based on the call response unit associated with the call content category. The audio synthesis module converts the first call text into the first call audio.

8. The information interaction method according to claim 7, characterized in that, The step of determining the first call text based on the call response unit associated with the call content category includes: The first call text is obtained from the preset call text associated with the call content category through the call response unit associated with the call content category.

9. The information interaction method according to claim 7, characterized in that, The call response unit is associated with a second model; the step of determining the first call text based on the call response unit associated with the call content category includes: The second model is invoked through the call response unit associated with the call content category to generate the first call text.

10. The information interaction method according to claim 9, characterized in that, The call response unit is associated with a knowledge base; The generation of the first call text through the second model includes: The knowledge base is queried using the second model, and the first call text is generated based on the query results.

11. The information interaction method according to claim 7, characterized in that, The call response unit includes a call transfer unit; The information exchange method further includes: In response to the call content category being the second category, a call transfer instruction is generated by the call transfer unit associated with the call content category, and a connection is established between the second call terminal and the third call terminal according to the call transfer instruction.

12. The information interaction method according to claim 1, characterized in that, The dialogue configuration information includes at least one of the agent's role setting information, the knowledge base associated with the agent, and preset dialogue rules; the preset dialogue rules include multiple information processing operations, which are used to obtain response audio for the received call audio.

13. An information interaction device, characterized in that, include: The agent creation module is used to receive editing operations on dialogue configuration information and create an agent based on the dialogue configuration information. The dialogue configuration information is used to configure the rules that the agent follows when determining the call audio; The agent publishing module is used to respond to the publishing operation for the agent, determine the first call terminal, and establish the association between the first call terminal and the agent; wherein, the first call audio of the first call terminal is determined by the agent.

14. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the information interaction method as described in any one of claims 1-12.

15. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the information interaction method as described in any one of claims 1-12.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the information interaction method as described in any one of claims 1-12.

Images