Voice interaction response method and device, storage medium and electronic device

Abstract

The present invention discloses a voice interaction answering method and device, a storage medium and an electronic device. The method comprises: obtaining a target answering strategy matching the target interaction voice when a target interaction voice is identified from access traffic, wherein the target answering strategy is used to indicate a target answering process matching the target interaction voice; determining a target answering voice for answering the target interaction voice according to the target answering process; and playing the target answering voice. The present invention solves the technical problem of cumbersome voice answering interaction operation caused by the high difficulty in developing voice navigation function.

Description

Technical Field

[0001] The present invention relates to the field of voice interaction, and in particular to a voice interaction response method and device, a storage medium and an electronic device. Background Art

[0002] Traditional IVR (Interactive Voice Response) functions interact with users by pressing buttons. Users need to access menus level by level to reach the functions they want to access. Take phone bill inquiry as an example: press 1 to inquire about phone bills and points--press 1 to inquire about phone bills, press 2 to inquire about points--press 1 to inquire about this phone bill, press 2 to inquire about other phone bills--inquiring, please wait. However, it is more cumbersome to access the desired functions by repeatedly pressing buttons and accessing each level of menus level by level.

[0003] In order to overcome the cumbersome operation of traditional IVR, an intelligent voice navigation function has been developed. By interacting with the system through speaking, the user can directly enter the function corresponding to the voice, thereby simplifying the operation steps of accessing the menu step by step.

[0004] However, this intelligent voice navigation function is related to the manufacturer of call center products and the development tools they use. Developers need to master the manufacturer's development tools. In addition, code development is required for each function, and the entire development process is difficult. Before the intelligent voice function is developed, traditional IVR is still needed for function access.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide a voice interaction response method and device, a storage medium and an electronic device to at least solve the technical problem of cumbersome voice response interaction operations caused by the high difficulty in developing a voice navigation function.

[0007] According to one aspect of an embodiment of the present invention, a method for answering voice interaction is provided, comprising: when a target interactive voice is identified from an access call, obtaining a target answering strategy that matches the target interactive voice, wherein the target answering strategy is used to indicate a target answering process that matches the target interactive voice; determining a target answering voice for answering the target interactive voice according to the target answering process; and playing the target answering voice.

[0008] According to another aspect of an embodiment of the present invention, a voice interaction response device is also provided, including: an acquisition unit, used to acquire a target response strategy matching the target interaction voice when a target interaction voice is identified from access traffic, wherein the target response strategy is used to indicate a target response process matching the target interaction voice; a determination unit, used to determine a target response voice for responding to the target interaction voice according to the target response process; and a playback unit, used to play the target response voice.

[0009] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned voice interaction answering method when running.

[0010] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned voice interaction answering method through the computer program.

[0011] In an embodiment of the present invention, when a target interactive voice is identified from access traffic, a target answering strategy that matches the target interactive voice and is used to indicate a target answering process is obtained, and a target answering voice for answering the target interactive voice is determined according to the target answering process, thereby playing the target answering voice. By calling the target answering strategy when the target interactive voice is identified from the access traffic, the purpose of automatic voice answering according to the target answering voice that matches the target interactive voice as indicated by the target answering strategy is achieved, thereby achieving the technical effect of voice navigation through the answering voice determined by the target answering process indicated by the target answering strategy, and further solving the technical problem of cumbersome voice answering interaction operations caused by the high difficulty in developing the voice navigation function. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0013] Figure 1 is a schematic diagram of an application environment of an optional voice interaction answering method according to an embodiment of the present invention;

[0014] Figure 2 is a flow chart of an optional voice interaction answering method according to an embodiment of the present invention;

[0015] Figure 3 is a flow chart of an optional voice interaction answering method according to an embodiment of the present invention;

[0016] Figure 4 is a flow chart of an optional voice interaction answering method according to an embodiment of the present invention;

[0017] Figure 5 is a schematic diagram of description data of an optional voice interaction answering method according to an embodiment of the present invention;

[0018] Figure 6 is a schematic diagram of an interaction timing of an optional voice interaction answering method according to an embodiment of the present invention;

[0019] Figure 7 is a schematic structural diagram of an optional voice interaction answering device according to an embodiment of the present invention;

[0020] Figure 8 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to one aspect of an embodiment of the present invention, a method for answering a voice interaction is provided. Optionally, the method for answering a voice interaction may be applied to, but is not limited to, Figure 1In the environment shown in the figure, the terminal device 100 sends a call request to the server 120 through the network 110. The server 120 determines the target response voice that matches the target interactive voice in the call while processing the call request and accessing the call of the terminal device 100, and then sends the target response voice to the terminal device 100 through the network 110, so as to realize the use of the automatically determined target response voice to respond to the target interactive voice.

[0024] The response of the voice interaction implemented by the server 120 is not limited to being implemented by executing S102 to S106 in sequence. S102, obtain the target response strategy. When the target interactive voice is identified from the access traffic, obtain the target response strategy that matches the target interactive voice, and the target response strategy is used to indicate the target response process that matches the target interactive voice. S104, determine the target response voice. According to the target response process, determine the target response voice for responding to the target interactive voice. S106, play the target response voice.

[0025] Optionally, in this embodiment, the terminal device 100 may be a terminal device configured with a target client, which may include but is not limited to at least one of the following: a mobile phone (such as an Android phone, an IOS phone, etc.), a laptop, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, etc. The target client is not limited to a client capable of initiating voice communication, such as an audio client, a video client, a communication client, a browser client, an education client, etc. The network 110 may include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network, and a wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The server 120 may be a single server, or a server cluster consisting of multiple servers, or a cloud server. The above is only an example, and no limitation is made to this in this embodiment.

[0026] As an optional implementation, Figure 2 As shown, the above voice interaction response method includes:

[0027] S202, when a target interactive voice is identified from the access traffic, obtaining a target answering strategy that matches the target interactive voice, wherein the target answering strategy is used to indicate a target answering process that matches the target interactive voice;

[0028] S204, determining a target response voice for responding to the target interactive voice according to the target response process;

[0029] S206, play the target response voice.

[0030] The traffic is not limited to the voice calls initiated by the user through the terminal. The server is used to process the traffic initiated by the terminal with the target service. In the case where the traffic initiated by the terminal indicates a voice call with other terminals, the call center is used to realize the voice call connection between the terminal and other terminals. In the case where the traffic initiated by the terminal indicates interaction with the target service, the call center transfers the traffic to the server to interact with the terminal. The target service is not limited to the operator service of the terminal, but all operating services that provide self-service voice service functions, such as the voice account balance inquiry service provided by XX Bank and the voice medical expense inquiry service provided by XX Hospital.

[0031] Traffic interaction is not limited to physical interaction and voice interaction based on the terminal. Physical interaction is interaction based on physical operations received by the terminal, such as interaction using buttons on the terminal. Voice interaction is voice response interaction based on received voice commands by the terminal.

[0032] The target response process is not limited to the automatic voice response process triggered by the target interactive voice, and the target response process is not limited to but also includes the response voice of continuing the automatic voice response based on the interactive parameters after the target response voice. The automatic voice response to the voice interaction triggered by the target interactive voice is realized by calling the target response process indicated by the target response strategy.

[0033] In an embodiment of the present application, when a target interactive voice is identified from access traffic, a target answering strategy that matches the target interactive voice and is used to indicate a target answering process is obtained, and a target answering voice for answering the target interactive voice is determined according to the target answering process, thereby playing the target answering voice. By calling the target answering strategy when the target interactive voice is identified from the access traffic, the purpose of automatic voice answering according to the target answering voice that matches the target interactive voice as indicated by the target answering strategy is achieved, thereby achieving the technical effect of voice navigation through the answering voice determined by the target answering process indicated by the target answering strategy, and further solving the technical problem of cumbersome voice answering interaction operations caused by the high difficulty in developing the voice navigation function.

[0034] As an optional implementation manner, before obtaining the target answering strategy matching the target interactive voice, the method further includes:

[0035] S1, receiving access traffic using a general process file, wherein the general process file is used to call speech recognition to perform semantic recognition on interactive speech;

[0036] S2, when the semantic recognition result of the interactive voice hits the preset answer code, determine to recognize the target interactive voice from the access traffic.

[0037] The general process file is used to receive access calls. When the target interactive voice is identified, the target answering strategy is obtained by requesting to determine the target answering voice, so as to perform automatic voice answering using the target answering voice.

[0038] The general process file is not limited to a general interactive voice response (IVR) process file, and is used for general processing of incoming calls, including but not limited to: number release, timely call closing, and voice recognition. Voice recognition is used to perform semantic recognition on the voice in the incoming call, determine the meaning of the voice in the incoming call, and determine whether the interactive voice is recognized through the voice recognition result. The interactive voice is the voice that triggers the automatic voice response, and the triggering of the automatic voice response is not limited to the semantic recognition result hitting the answer code, thereby determining that the interactive voice is the target interactive voice that hits the specific answer code.

[0039] As an optional implementation, obtaining a target response strategy that matches the target interactive voice includes: obtaining a target response strategy that matches the target response code corresponding to the target interactive voice, wherein the preset response code includes the target response code, and the target response strategy is used to indicate the target response process for responding to the target response code.

[0040] When the general IVR process file calls up voice recognition to recognize the voice of the access call and the semantic recognition result hits the target answer code, the voice of the access call is determined to be the target interactive voice, thereby requesting to obtain the target answer strategy matching the target answer code.

[0041] The application of general IVR process files in voice interaction responses is not limited to: Figure 3As shown. The queuing machine 300 is used to queue and distribute all traffic, and the IVR server 310 is used to run the general process, that is, the general IVR process file, and use the general process to answer the traffic distributed to the IVR server. When the general process identifies the target interactive voice from the access traffic, it requests the answering strategy from the application server 320. The application server 320 is used for policy analysis and determination of the answering voice. The application server 320 is not limited to determining the current interactive state of the access traffic by analyzing the target interactive voice, thereby determining the answering voice based on the target answering strategy. The answering strategy used by the application server 320 is the answering strategy corresponding to the answering process submitted by the configuration tool 330. The configuration tool 330 is used for the process configuration of the answering process, and submits the configured answering process to the application server 320, so that the application server 320 performs the answering strategy analysis according to the answering process, thereby determining the answering voice for automatically answering the target interactive voice. The application server 320 sends the determined answering voice to the IVR server, so as to perform voice interaction with the user in the access traffic based on the answering voice through the general process in the IVR server.

[0042] In the embodiment of the present application, a universal IVR process file is utilized to process call access and universal processing of calls. When it is determined that the current request for the accessed call is to perform automatic voice response interaction, the application server performs policy analysis and determines the response voice through the request of the response strategy. This not only satisfies the universal IVR process file's ability to handle universal process processing of various types of calls, but also enables the voice response interaction to be executed according to the strategy through the configuration of the strategy and process, and has a higher degree of configurability.

[0043] As an optional implementation manner, before obtaining the target answering strategy matching the target interactive voice, the method further includes:

[0044] S1, receiving description data of a target response process configured for a target response code;

[0045] S2, parsing the description data to obtain each process node included in the target response process and the connection relationship between each process node;

[0046] S3, verifying the correctness of the target response process, wherein the correctness of the target response process includes the node correctness of each process node and the connection correctness of the connection relationship between each process node;

[0047] S4, when the correctness of the target response process is verified, the target response process is determined as a target response strategy that matches the target response code.

[0048] Optionally, the configuration of the response process is not limited to the selection of a visual process configuration page, and the configuration of the response process is implemented in the form of a node control. After the response process configuration is completed, the description data corresponding to the response process is automatically generated, and the description data is transmitted to the application server to realize the conversion from the visual response process to the response strategy.

[0049] When the response process is built based on the node control, the description data of the response process is not limited to node data and node relationship. Node data is used to record the parameters and other data of each node, and node relationship is used to indicate the connection relationship between each node, that is, the operation relationship between the process nodes of the response process.

[0050] When receiving the description data, the correctness verification of the description data is not limited to determining the response process corresponding to the description data that has passed the correctness verification as the target response strategy that matches the target response code. The correctness verification of the description data is not limited to determining the node type of the node, the validity and correctness of the node, the correctness of the connection between each node, and the correctness and completeness of the process. In the visual process configuration interface, different types of nodes are not limited to being represented by node controls of different shapes, so that the node type of the current node is clearly represented by the node shape, making the visual response process configuration more efficient.

[0051] Specifically, taking the node types of process nodes including start nodes, conditional judgment nodes, interactive nodes, jump nodes, etc., and the description data using JSON format as an example, the correctness verification of the description data is not limited to including:

[0052] 1. Format verification of description data, including but not limited to whether it is legal JSON data, whether the node data and node relationship data are not empty, and the correctness of the data format of the node data and node relationship;

[0053] 2. Verification of the node composition, individual nodes and node relationships in the description data, including but not limited to:

[0054] 1) Verify the correctness of the type and parameters of each node, including but not limited to the correctness of the node execution function and the correctness of the calling interface;

[0055] 2) There is only one starting node in the entire response process and at least one ending node (such as an interaction node or a jump node);

[0056] 3) There are no nodes that are independent of the response process, that is, there are no nodes that have no connection with any other nodes;

[0057] 4) Each non-terminal node (such as the start node, conditional judgment node) has a subsequent node;

[0058] 5) Each branch of each multi-branch node (such as a conditional judgment node) has a subsequent node;

[0059] 6) Each process branch has a process termination node (such as an interaction node or a jump node).

[0060] If the correctness verification of the description data fails, it is determined that the description data and the corresponding response process have defects, not limited to providing defect prompts, and the current defective response process is determined to be invalid, that is, it is not used as the response strategy corresponding to the response code. If the correctness verification of the description data passes, the description data and the response process are saved in the database and associated with the corresponding response code, so that the response process can be called through the response code to realize voice interactive response using the response process.

[0061] Take the configuration flow chart as Figure 4 As shown, the automatically generated description data corresponding to the flowchart is not limited to Figure 5 As shown. The answering process includes node 401: "Test scenario 6", node 402 "Determine whether it is nighttime", node 403 "Nighttime prompt" and node 404 "Welcome". The node structure of the answering process includes a starting node (circle), a conditional judgment node (diamond), and two interactive nodes (rectangles). The interactive nodes are not limited to being used to indicate the voice identifier used as the answering voice. Taking node 403 "Nighttime prompt" as an example, it is used to indicate that the voice corresponding to the "nighttime prompt" is used as the answering voice for voice interaction.

[0062] In the right Figure 5 When the correctness of the description data shown is verified, the parsing verification is not limited to including:

[0063] 1. Verify the data format and the correctness of the data format of node data and node relationships;

[0064] 2. Verification of the node composition, individual nodes and node relationships in the description data, including but not limited to:

[0065] 1) The correctness of the type and parameters of each node. Each node is configured and the configuration parameters match the node type.

[0066] 2) The entire response process has one and only one starting node: node 401: "Test scenario 6", and at least one ending node: node 403 "Night prompt" and node 404 "Welcome";

[0067] 3) There are no nodes outside the response process;

[0068] 4) Each non-terminal node (starting node: node 401, conditional judgment node: node 402) has a subsequent node;

[0069] 5) Conditional judgment node: Node 402 "Judge whether it is nighttime" has two branches, namely no (daytime) and yes (nighttime), and both branches have subsequent nodes: "Node 404 "Welcome" is the subsequent node of the no (daytime) branch in the conditional judgment node; Node 403 "Nighttime reminder" is the subsequent node of the yes (nighttime) branch in the conditional judgment node.

[0070] 6) Each process branch has a process termination node. Based on the two process branches divided by node 402 "determine whether it is night time", the process termination nodes of the two process branches (no (daytime), yes (nighttime)) are both "node 404 "welcome".

[0071] As an optional implementation manner, before receiving the description data of the target response process configured for the target response code, it also includes:

[0072] S1, display the node control template in the process configuration interface;

[0073] S2, build the target response process using the node control template;

[0074] S3: When the target response process is constructed, the description data of the target response process is generated.

[0075] The process configuration interface is not limited to the visual response process configuration interface in the configuration tool, and the target response process is constructed using the node control template. The target response process is not limited to the flowchart displayed in the process configuration interface.

[0076] As an optional implementation, using the node control template to construct a target response process includes:

[0077] S1, in response to a selection operation on a target node control template, adding a target node control to an initial response process displayed on a process configuration interface, wherein the initial response process at least includes a start node control, and the start node control is used to indicate a response code corresponding to the initial response process;

[0078] S2, establishing a connection relationship between the target node control and the candidate node control in the initial response process;

[0079] S3: When the initial response process includes at least one response node control, the initial response process is used as the target response process.

[0080] The target response flow includes a start node for identifying the response flow. Adding the target node control to the initial response flow is not limited to establishing a connection relationship between the target node control and an existing node in the initial response flow, thereby adding the target node control to the initial response flow.

[0081] When the target node control is added to the initial response process, the node parameters are configured for the target node control, and the node parameters are used to indicate the specific process processing logic of the target node. The node parameters are related to the node type. For example, the starting node is used to identify the response process, which is not limited to setting the response code, process name and other identifiers. It is used for the response process to match the strategy through the starting node, so as to determine whether the response strategy requested by the interactive voice matches the response process. The conditional judgment node is not limited to configuring the judgment conditions and the conditions, identifiers, subsequent nodes, etc. of the branches corresponding to each judgment condition. The interactive node is not limited to configuring the voice identifier as the response voice, so that when running to the interactive node, it is determined to automatically perform a voice interactive response with the indicated response voice. The execution node is not limited to configuring the operation parameters of the corresponding execution operation, such as the parameter position of the call parameter, the waiting time, etc.

[0082] As an optional implementation, after playing the target answer voice, the method further includes:

[0083] S1, using the target answering voice playback completion status to update the answering process status;

[0084] S2, determining the current execution node of the response process according to the updated response process state;

[0085] S3, execute the execution operation indicated by the current execution node.

[0086] In a target response process, it is not limited to including two or more interactive nodes. After using the target response voice for voice interaction, it is not limited to using the target response voice playback completion status to update the response process status, so as to determine the current execution node of the response process according to the updated response process status. If the current execution node is the termination node of the response process, it is determined that the response process execution is completed. If the current execution node is a non-termination node, it is determined that the response process flows to the current execution node, and the response process continues to be executed according to the current execution node until the response process ends.

[0087] Taking the general IVR process file using the intelligent voice navigation MRCP protocol as an example, the voice interaction response interaction process is not limited to the following: Figure 6 The general IVR process file is represented as MRCP, the access module is used to answer the request and call of the process, and the execution module is used to parse and execute the response process.

[0088] 1) The user initiates a call, such as "transfer to operator";

[0089] 2) MRCP recognizes the user's speech, obtains the semantic recognition result, and sends the recognition result to the access module for access to the response process;

[0090] 3) The access module identification result is sent to the execution module;

[0091] 4) The execution module determines the matching response code according to the recognition result, and loads the configuration data of the corresponding response process from the database. After receiving the process data returned by the database, the execution module executes the process nodes step by step according to the instructions of the response process;

[0092] 5) When the execution module executes to the interaction node, if a prompt tone "transferring" is played, the current execution state of the answering process is saved in the cache, and an instruction to play the prompt tone is returned to the access module;

[0093] 6) After receiving the playback instruction, the access module searches for the audio file of the prompt tone to be played, and calls the corresponding component to play the prompt tone "transferring" in the user's accessed call;

[0094] 7) After the audio is played, the access module obtains the audio playback result, such as whether the audio is played correctly, and sends the audio playback result to the execution module;

[0095] 8) The execution module receives the audio playback result, obtains the current execution status of the process from the cache, and continues to execute the response process;

[0096] 9) When the execution module executes to the interaction node again, such as "call transfer", the execution status of the current answering process is saved in the cache again, and the call transfer information is returned to the access module according to the instruction of the interaction node;

[0097] 10) After receiving the call transfer information, the access module calls the corresponding component to initiate a call transfer request, transfers the user's call to the requested system, and completes the voice interaction and response interaction.

[0098] Correspondingly, Figure 4 Taking the test scenario 6 shown as an example, the response execution process of the voice interaction is not limited to the following:

[0099] 1) When the incoming traffic hits "Test Scenario 6", the process flows to "Determine whether it is nighttime";

[0100] 2) The "Determine whether it is nighttime" node determines whether the current time is nighttime according to the configured time conditions, thereby determining whether to enter the daytime (no) branch or the nighttime (yes) branch;

[0101] 3) Taking the process flow to the night (yes) branch as an example, the process flows to the "night prompt" node. The "night prompt" node indicates to perform voice response interaction and play the prompt sound corresponding to the "night prompt". At this time, the process saves the current execution state to the cache and returns the instruction to play the voice file xxx.wav of the "night prompt" to the general process;

[0102] 4) The general process receives the instruction to play the "night prompt", calls the media server of the call center, and plays the prompt tone to the incoming traffic. At this time, the user can hear the prompt tone in the handset;

[0103] 5) After the prompt tone is played, the media server of the call center returns a "playing completed" signal to the general process file, and the general process file forwards this result and requests the next response strategy;

[0104] 6) The process execution is awakened, the playback result is fed back through the general process file, the execution status is obtained from the cache, the process is located at the "night prompt node", and the process flow continues;

[0105] 8) The process flows to the "Welcome" node;

[0106] 9) The "Welcome" node instructs to conduct voice response interaction again and play the prompt sound corresponding to the "Welcome". At this time, the process continues to save the execution status to the cache and returns the instruction to play the voice text xx.wav of the "Welcome" to the general process file.

[0107] 10) The general process receives the instruction to play the "welcome message", calls the media server of the call center, and plays the prompt tone to the incoming call. At this time, the user can hear the prompt tone in the handset.

[0108] 11) After the prompt tone is played, the media server of the call center returns a "playing completed" signal to the general process file, the general process file forwards this result, and the process determines that the current process is terminated.

[0109] When the current answering process ends, it is not limited to instructing the general process file to continue recognizing the voice in the access call, so as to perform a voice interactive response according to the answering process of the corresponding answering strategy called by the recognized interactive voice.

[0110] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0111] According to another aspect of the embodiments of the present invention, a voice interaction response device for implementing the above-mentioned voice interaction response method is also provided. Figure 7 As shown, the device comprises:

[0112] The acquisition unit 702 is used to acquire a target response strategy matching the target interaction voice when the target interaction voice is identified from the access traffic, wherein the target response strategy is used to indicate a target response process matching the target interaction voice;

[0113] A determination unit 704, configured to determine a target response voice for responding to a target interactive voice according to a target response process;

[0114] The playing unit 706 is used to play the target response voice.

[0115] Optionally, the above-mentioned voice interaction response device also includes a general unit, which is used to receive access traffic using a general process file before obtaining a target response strategy that matches the target interactive voice, wherein the general process file is used to call voice recognition to perform semantic recognition on the interactive voice; when the semantic recognition result of the interactive voice hits a preset response code, it is determined that the target interactive voice is identified from the access traffic.

[0116] Optionally, the acquisition unit 702 is also used to acquire a target answer strategy that matches a target answer code corresponding to a target interactive voice, wherein the preset answer code includes a target answer code, and the target answer strategy is used to indicate a target answer process for answering the target answer code.

[0117] Optionally, the above-mentioned voice interaction response device also includes a parsing unit, which is used to receive description data of the target response process configured for the target response code before obtaining the target response strategy matching the target interactive voice; parse the description data to obtain the various process nodes included in the target response process and the connection relationship between each process node; verify the correctness of the target response process, wherein the correctness of the target response process includes the node correctness of each process node and the connection correctness of the connection relationship between each process node; when the correctness of the target response process is verified, the target response process is determined as the target response strategy matching the target response code.

[0118] Optionally, the above-mentioned voice interactive response device also includes a configuration unit, which is used to display a node control template in a process configuration interface before receiving the description data of the target response process configured for the target response code; construct the target response process using the node control template; and generate description data of the target response process when the target response process is constructed.

[0119] Optionally, the above-mentioned configuration unit is also used to add a target node control to the initial response process displayed on the process configuration interface in response to a selection operation on the target node control template, wherein the initial response process includes at least a starting node control, and the starting node control is used to indicate the response code corresponding to the initial response process; establish a connection relationship between the target node control and the candidate node control in the initial response process; and when the initial response process includes at least one response node control, use the initial response process as the target response process.

[0120] Optionally, the above-mentioned voice interactive response device also includes an updating unit, which is used to update the response process status using the playback completion status of the target response voice after playing the target response voice; determine the current execution node of the response process according to the updated response process status; and execute the execution operation indicated by the current execution node.

[0121] In an embodiment of the present application, when a target interactive voice is identified from access traffic, a target answering strategy that matches the target interactive voice and is used to indicate a target answering process is obtained, and a target answering voice for answering the target interactive voice is determined according to the target answering process, thereby playing the target answering voice. By calling the target answering strategy when the target interactive voice is identified from the access traffic, the purpose of automatic voice answering according to the target answering voice that matches the target interactive voice as indicated by the target answering strategy is achieved, thereby achieving the technical effect of voice navigation through the answering voice determined by the target answering process indicated by the target answering strategy, and further solving the technical problem of cumbersome voice answering interaction operations caused by the high difficulty in developing the voice navigation function.

[0122] According to another aspect of the embodiment of the present invention, an electronic device for implementing the above-mentioned voice interaction answering method is also provided. The electronic device may be Figure 1 The terminal device or server shown in the figure. This embodiment is described by taking the electronic device as a server as an example. Figure 8 As shown, the electronic device includes a memory 802 and a processor 804. The memory 802 stores a computer program, and the processor 804 is configured to execute the steps in any of the above method embodiments through the computer program.

[0123] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0124] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0125] S1, when a target interactive voice is identified from the access traffic, obtaining an answering strategy matching the target interactive voice, wherein the answering strategy is used to indicate a target answering process matching the target interactive voice;

[0126] S2, determining a target response voice for responding to the target interactive voice according to the target response process;

[0127] S3, play the target answering voice.

[0128] Alternatively, a person skilled in the art may understand that: Figure 8 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an IOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, etc.) as shown in, or with Figure 8 Different configurations are shown.

[0129] Among them, the memory 802 can be used to store software programs and modules, such as the program instructions / modules corresponding to the voice interaction response method and device in the embodiment of the present invention. The processor 804 executes various functional applications and data processing by running the software programs and modules stored in the memory 802, that is, to realize the above-mentioned voice interaction response method. The memory 802 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 802 may further include a memory remotely arranged relative to the processor 804, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 802 can be specifically, but not limited to, used to store information such as target interactive voice, target response strategy, target response process, target response voice, etc. As an example, such as Figure 8 As shown, the memory 802 may include but is not limited to the acquisition unit 702, the determination unit 704, and the playback unit 706 in the voice interactive response device. In addition, other module units in the voice interactive response device may also be included but are not limited to, which will not be repeated in this example.

[0130] Optionally, the transmission device 806 is used to receive or send data via a network. Specific examples of the network may include wired networks and wireless networks. In one example, the transmission device 806 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 806 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0131] In addition, the electronic device further comprises: a display 808 for displaying the target response process; and a connection bus 810 for connecting various module components in the electronic device.

[0132] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P, Peer To Peer) network, and any form of computing device, such as a server, terminal and other electronic devices, may become a node in the blockchain system by joining the peer-to-peer network.

[0133] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional implementations of the above-mentioned voice interaction response. The computer program is configured to execute the steps of any of the above-mentioned method embodiments when it is run.

[0134] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0135] S1, when a target interactive voice is identified from the access traffic, obtaining an answering strategy matching the target interactive voice, wherein the answering strategy is used to indicate a target answering process matching the target interactive voice;

[0136] S2, determining a target response voice for responding to the target interactive voice according to the target response process;

[0137] S3, play the target answering voice.

[0138] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0139] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0140] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.

[0141] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0144] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0145] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A voice interaction answering method, characterized in that: include: In the case where a target interactive voice is identified from the access traffic, a target answering strategy matching the target interactive voice is acquired, wherein the target answering strategy is used to indicate a target answering process matching the target interactive voice; According to the target response process, determining a target response voice for responding to the target interactive voice; Playing the target answering voice; Before acquiring the target answering strategy matching the target interactive voice, the method further includes: receiving the access traffic by using a general process file, wherein the general process file is used to call voice recognition to perform semantic recognition on the interactive voice; and determining to recognize the target interactive voice from the access traffic when the semantic recognition result of the interactive voice hits a preset answering code; Wherein, the acquiring of the target response strategy matching the target interactive voice comprises: acquiring the target response strategy matching the target response code corresponding to the target interactive voice, wherein the preset response code comprises the target response code, and the target response strategy is used to indicate the target response process for responding to the target response code; Wherein, before obtaining the target response strategy that matches the target interactive voice, it also includes: receiving the description data of the target response process configured for the target response code; parsing the description data to obtain the various process nodes included in the target response process and the connection relationship between the various process nodes; verifying the correctness of the target response process, wherein the correctness of the target response process includes the node correctness of the various process nodes and the connection correctness of the connection relationship between the various process nodes; when the correctness of the target response process passes the verification, the target response process is determined as the target response strategy that matches the target response code; Among them, before receiving the description data of the target response process configured for the target response code, it also includes: displaying a node control template in a process configuration interface; constructing the target response process using the node control template; and generating the description data of the target response process when the construction of the target response process is completed.

2. The method according to claim 1, characterized in that The process of constructing the target response by using the node control template includes: In response to the selection operation of the target node control template, a target node control is added to the initial response process displayed on the process configuration interface, wherein the initial response process at least includes a start node control, and the start node control is used to indicate a response code corresponding to the initial response process; Establishing a connection relationship between the target node control and the candidate node control in the initial response process; In the case where the initial response process includes at least one response node control, the initial response process is used as the target response process.

3. The method according to any one of claims 1 to 2, characterized in that: After playing the target answer voice, the method further includes: Using the completion status of the target answering voice to update the answering process status; Determining the current execution node of the response process according to the updated response process state; Execute the execution operation indicated by the current execution node.

4. A voice interactive answering device, characterized in that: include: An acquisition unit, configured to acquire a target response strategy matching the target interaction voice when a target interaction voice is identified from the access traffic, wherein the target response strategy is used to indicate a target response process matching the target interaction voice; A determination unit, configured to determine a target response voice for responding to the target interactive voice according to the target response process; A playing unit, used for playing the target answering voice; Before acquiring the target answering strategy matching the target interactive voice, the method further includes: receiving the access traffic by using a general process file, wherein the general process file is used to call voice recognition to perform semantic recognition on the interactive voice; and determining to recognize the target interactive voice from the access traffic when the semantic recognition result of the interactive voice hits a preset answering code; Wherein, the acquiring of the target response strategy matching the target interactive voice comprises: acquiring the target response strategy matching the target response code corresponding to the target interactive voice, wherein the preset response code comprises the target response code, and the target response strategy is used to indicate the target response process for responding to the target response code; Wherein, before obtaining the target response strategy that matches the target interactive voice, it also includes: receiving the description data of the target response process configured for the target response code; parsing the description data to obtain the various process nodes included in the target response process and the connection relationship between the various process nodes; verifying the correctness of the target response process, wherein the correctness of the target response process includes the node correctness of the various process nodes and the connection correctness of the connection relationship between the various process nodes; when the correctness of the target response process passes the verification, the target response process is determined as the target response strategy that matches the target response code; Among them, before receiving the description data of the target response process configured for the target response code, it also includes: displaying a node control template in a process configuration interface; constructing the target response process using the node control template; and generating the description data of the target response process when the construction of the target response process is completed.

5. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, and the program executes the method described in any one of claims 1 to 3 when executed.

6. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 3 through the computer program.

Images