Ivr process orchestration method, device and equipment, and storage medium

Abstract

The application provides an IVR flow arrangement method, device and equipment and a storage medium. The method pre-establishes a node database, and a user can generate a node path from a first node to an end node of a flow by using the node database. The coordinates of each node on the node path are calculated by using a coordinate algorithm, the nodes containing the coordinate information are encapsulated, an interactive voice response (IVR) flowchart is generated and displayed, a complete set of IVR flows related to the first node is automatically generated based on the node database and the IVR flowchart, and the efficiency of IVR flow configuration is effectively improved. A visual flow customization environment is provided for the user, operations of the user on the IVR flowchart in the visual flow customization environment are received and processed, IVR flow arrangement data is obtained, and the efficiency and data accuracy of flow arrangement can be greatly improved.

Description

Technical Field

[0001] This application relates to voice communication technology, and more particularly to an IVR workflow orchestration method, apparatus, device, and storage medium. Background Technology

[0002] Interactive Voice Response (IVR) is an important component of intelligent call center systems, responsible for providing voice prompts to users, collecting user information, and guiding users to accept services. Essentially, an IVR is an automated process interpreter and executor, responsible for parsing and executing the process files loaded into the IVR. The tasks performed by the IVR are entirely determined by the process.

[0003] Traditional IVR systems are typically designed for a specific business and configure different processes for each user's specific needs. This requires first understanding the user's detailed requirements through communication and checking the voice files before the call center system maintainer manually configures the specific processes for them.

[0004] Traditional IVR process structures and workflows are fixed, and once a business process is set up, it cannot be modified according to changes in actual business needs. However, as call center businesses continue to expand and business types become more diversified and complex, existing IVR business process orchestration is inflexible, inefficient, and has low accuracy in process configuration. Summary of the Invention

[0005] This application provides an IVR workflow orchestration method, apparatus, device, and storage medium. By pre-establishing a node database, it automatically generates a complete set of IVR workflows related to the first node based on the node database and provides users with a visual and customizable editing environment, thus solving the problems of low efficiency and poor flexibility in traditional IVR workflows.

[0006] Firstly, this application provides an interactive voice response flow arrangement method, including:

[0007] The first node is identified based on the business process flow. Based on the pre-set node database, the process node data in the node database is recursively processed layer by layer from the first node until the process end node is reached, generating a node path from the first node to the process end node. The node database includes various types of nodes, node attribute tags, and relationships between nodes.

[0008] The coordinate information of each node on the node path is calculated using a coordinate algorithm. The nodes containing coordinate information are encapsulated to obtain data in a visual format. Based on the visual format data, a graphical model is created to generate and display an interactive voice response (IVR) flowchart.

[0009] Based on the node database and the IVR flowchart, a visual process customization environment is provided for users. The user's operation on the IVR flowchart in the visual process customization environment is received and processed to obtain IVR process orchestration data.

[0010] The IVR process orchestration data is transmitted to a computer telephone platform for dial-up testing and verification, and the verification result returned by the computer telephone platform is received.

[0011] In one possible implementation, the step of recursively traversing the process node data in the pre-set node database, starting from the first node and continuing until the process end node, includes:

[0012] Based on the node database, obtain at least one neighboring node that is associated with the first node;

[0013] Determine whether the neighboring node is a process end node based on the attribute labels of the neighboring node;

[0014] If not, take the neighboring node as the first node, obtain at least one neighboring node that is related to the first node, and continue traversing until all neighboring nodes are the end nodes of the process.

[0015] In one possible implementation, the attribute tags include non-functional tags and functional tags, the functional tags including transfer to human agent tags and conversation end tags, and the step of recursively traversing the process node data in the pre-set node database, starting from the first node, until the process end node is reached, includes:

[0016] Based on the node database, obtain at least one first neighbor node that is associated with the first node;

[0017] If the attribute label of the first neighboring node is a function label, the first neighboring node is the end node of the node path from the first node to the first neighboring node.

[0018] Iterate through the first neighboring nodes whose attribute tags are not functional tags, and obtain the second neighboring nodes that are related to the first neighboring nodes;

[0019] If the attribute label of the second neighboring node is a function label, the second neighboring node is the end node of the node path from the first node to the second neighboring node;

[0020] Iterate through the second neighboring node whose attribute label is not a function label, obtain the third neighboring node that is related to the second neighboring node, and so on, until all node paths include the process end node.

[0021] In one possible implementation, providing users with a visual process customization environment based on the node database and the IVR flowchart includes:

[0022] A visual canvas area is generated, which includes the IVR flowchart. The visual canvas area is used to respond to user operations such as selecting, dragging, creating, and deleting nodes and the connections between nodes.

[0023] A tool area is generated, which is used to display the nodes in the node database that are associated with the target node in response to the user's selection operation on the target node in the IVR flowchart.

[0024] In one possible implementation, before calling the coordinate algorithm to calculate the coordinate information of each node data on the node path, the method further includes:

[0025] Perform type correctness verification on the node data;

[0026] Perform content integrity verification on node data of the correct type.

[0027] In one possible implementation, the type correctness check of the node data includes:

[0028] The fields in the node data are identified to obtain the feature fields of the node data, and it is determined whether the feature fields are consistent with the type of the node data.

[0029] If so, confirm that the node data type is correct;

[0030] If not, confirm that the node data type is incorrect and send an alarm notification.

[0031] In one possible implementation, the content integrity verification of node data of the correct type includes:

[0032] Determine whether the attribute label of the node data is a speech end label;

[0033] If so, check whether the fields in the node data exceed a preset threshold, where the preset threshold is the field value corresponding to the end-of-speech tag;

[0034] If the number of fields in the node data exceeds a preset threshold, the node data is confirmed to be complete.

[0035] If the fields in the node data do not exceed the preset threshold, the node data is confirmed to be incomplete, and an alarm notification is sent.

[0036] Secondly, this application provides an interactive voice response flow orchestration device, comprising:

[0037] The node path generation module is used to determine the first node according to the business process flow. Based on the pre-set node database, which includes various types of nodes, node attribute tags, and relationships between nodes, the module recursively traverses the process node data in the node database layer by layer from the first node until the process end node is reached, generating a node path from the first node to the process end node.

[0038] The flowchart generation module is used to calculate the coordinate information of each node on the node path using a coordinate algorithm, encapsulate the nodes containing coordinate information to obtain data in a visual format, perform graphical modeling based on the visual format data, and generate and display the interactive voice response (IVR) flowchart.

[0039] The process modification module is used to provide users with a visual process customization environment based on the node database and the IVR flowchart, receive and process user operations on the IVR flowchart in the visual process customization environment, and obtain IVR process orchestration data.

[0040] The verification module is used to transmit the IVR process orchestration data to the computer telephone platform for dial-up verification and to receive the verification results returned by the computer telephone platform.

[0041] Thirdly, this application provides an electronic device, including a memory, a processor, and computer-executable instructions stored in the memory and executable on the processor, wherein the processor executes the computer-executable instructions to implement the interactive voice response flow arrangement method described in any one of the first aspects above.

[0042] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the interactive voice response flow arrangement method described in any one of the first aspects above.

[0043] The IVR flow orchestration method, apparatus, device, and storage medium provided in this application identify the first node based on the business processing flow. According to a pre-set node database, the flow node data in the node database are recursively processed layer by layer from the first node until the flow end node is reached, generating a node path from the first node to the flow end node. The node database includes various types of nodes, node attribute labels, and relationships between nodes. Coordinate algorithms are used to calculate the coordinate information of each node on the node path. Nodes containing coordinate information are encapsulated to obtain visualized data. Graphical modeling is performed based on the visualized data to generate and display an interactive voice response (IVR) stream. The process diagram, by pre-establishing a node database, automatically generates a complete set of IVR processes related to the first node. Users do not need to rebuild node data according to business needs every time, effectively improving the efficiency of IVR process configuration. Based on the node database and the IVR process diagram, it provides users with a visual process customization environment, receives and processes user operations on the IVR process diagram in the visual process customization environment, obtains IVR process orchestration data, transmits the IVR process orchestration data to a computer telephony platform for dialing test verification, and receives the verification results returned by the computer telephony platform. Based on the node database, it provides users with a visual customization editing environment, which can greatly improve the efficiency of process orchestration and data accuracy. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0045] Figure 1 This is a schematic diagram illustrating an application scenario of the IVR workflow orchestration method provided in this application embodiment.

[0046] Figure 2 A flowchart of the IVR process orchestration method provided in the embodiments of this application.

[0047] Figure 3 This is a flowchart illustrating the method for recursively processing process node data in the node database layer by layer, as provided in this embodiment.

[0048] Figure 4 A schematic diagram of the interface for the customized environment of the visualization process provided in the embodiments of this application.

[0049] Figure 5 This is a schematic diagram of an IVR workflow orchestration apparatus provided in an embodiment of this application.

[0050] Figure 6 This is a schematic diagram of the structure of an electronic device based on an IVR workflow orchestration device provided in an embodiment of this application.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0053] In related technologies, IVR workflow orchestration is generally tailored to a specific business. Each client has its own voice broadcast workflow requirements. For example, for the telecommunications industry, this mainly includes account inquiry workflows, information modification workflows, and human customer service workflows; for the banking industry, it mainly includes information authentication workflows, information inquiry workflows, and transaction workflows. After determining the workflow requirements based on the business, developers can use drawing tools such as Visio to create intuitive workflow requirement documents. During this process, the IVR is rationally planned, defining the workflow branches, nodes, and relationships between nodes. Then, based on this workflow requirement document, the workflow is configured, prepared voice resources are added, and the orchestrated workflow is debugged.

[0054] However, in the process orchestration process described above, for each customer’s needs, the developers need to start writing the process requirement document from scratch. The process document reuse rate is low and the orchestration efficiency is low. Especially when the process requirements are complex, it is easy to get confused or missing when writing the process requirement document, resulting in a high error rate and long debugging time.

[0055] To address the aforementioned technical problems, this application aims to propose an IVR workflow orchestration method, apparatus, device, and storage medium. The core concept of this method is to pre-establish a node database, which includes node types, node attributes, and relationships between nodes. Based on the node database, a complete set of IVR workflows related to the first node is automatically generated, and a visual custom editing environment is provided to developers. This improves workflow orchestration efficiency and enhances data accuracy.

[0056] To better understand the solutions of the embodiments of this application, an application scenario involved in the embodiments of this application will be introduced below.

[0057] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of the IVR workflow orchestration method provided in the embodiments of this application, such as... Figure 1 As shown, it includes a client 100 and a server 200. Users can select the first node of the IVR process in their business requirements through the client 100. The client 100 can also be used to send process editing operation instructions to the server 200. The client 100 may include a personal computer, tablet computer, smart panel, etc., and this embodiment is not limited thereto.

[0058] The server 200 includes a node data storage module and a process orchestration module. The server 200 can establish a communication connection with the client 100 and respond to instructions sent by the client 100 to execute related operations. The node data storage module stores various IVR process nodes, node attribute tags, and the relationships between nodes. The process orchestration module can retrieve process nodes from the node data storage module based on the mobile phone store selected by the client 100, and automatically generate a complete set of IVR processes related to the first node based on the relationships between nodes. The process orchestration module can also perform process orchestration operations according to the process editing operation instructions from the client 100.

[0059] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0060] Figure 2 A flowchart illustrating the IVR workflow orchestration method provided in this application embodiment. For example... Figure 2 As shown, the method in this embodiment includes:

[0061] S201: Based on the business processing flow, the first node is identified. According to the pre-set node database, the process node data in the node database is recursively processed layer by layer from the first node until the process end node is reached, generating a node path from the first node to the process end node. The node database includes various types of nodes, node attribute tags, and relationships between nodes.

[0062] The execution entity in this application embodiment can be a server or an IVR workflow orchestration system within the server, wherein the IVR workflow orchestration system can be implemented in software.

[0063] Understandably, although the specific workflow arrangement differs for each IVR process, the redundancy rate of workflow nodes is high, and there are relatively fixed pairing relationships between workflow nodes, especially between parent and child nodes. Therefore, once the first node is determined, other nodes related to the first node can be found from the node database based on the type and attribute tags of the first node. By recursively processing the data layer by layer, a complete set of IVR processes related to the first node can be automatically generated.

[0064] Understandably, the entire IVR process related to the first node includes two arrays: NodeList and EdgeList. NodeList is an array-like object used to store a set of ordered nodes, while EdgeList is used to store the process connections, that is, the connection relationships between nodes.

[0065] S202: Calculate the coordinate information of each node on the node path using a coordinate algorithm, encapsulate the nodes containing coordinate information to obtain data in a visual format, perform graphical modeling based on the visual format data, and generate and display the IVR flowchart.

[0066] In this step, the IVR process related to the first node obtained from the node database was originally just code data. By calculating the coordinate information of each node and encapsulating the data information of each node into a visual format, the IVR process can be visualized, making it easier for developers to see the existing IVR process intuitively and make modifications based on it.

[0067] In this step, the coordinate algorithm can be...

[0068] It should be noted that the visualization format data in this application can be in JavaScript Object Notation (JSON) format, or other data formats that can be used by front-end graphics software. This application does not limit this.

[0069] S203: Based on the node database and the IVR flowchart, provide users with a visual process customization environment, receive and process user operations on the IVR flowchart in the visual process customization environment, and obtain IVR process orchestration data.

[0070] In this step, the visualization process customization environment mainly includes a visualization canvas area and a tool area. The visualization canvas area displays an IVR flowchart automatically generated based on the first node. In the visualization process customization environment, developers can select specific process nodes in the visualization canvas area, retrieve nodes related to the selected nodes from the tool area, and also drag, delete, and add nodes in the IVR flowchart to modify the IVR flowchart to the desired shape and generate corresponding IVR process orchestration data.

[0071] S204: Transmit the IVR process orchestration data to the computer telephone platform for dialing test verification, and receive the verification result returned by the computer telephone platform.

[0072] In this step, the computer telephony platform can be a platform with Computer Telephony Integration (CTI) capabilities. It integrates telephone communication and computer information through hardware and software interfaces and control devices, achieving the fusion of voice and data to enhance communication capabilities. The computer telephony platform can be used to verify whether the IVR workflow orchestration data can function correctly. Verification results can include the specific node where the error occurred and the type of error. Developers can then return to the visual workflow customization environment based on the verification results to debug the IVR workflow until the IVR workflow orchestration data passes verification.

[0073] In this embodiment, a node database is pre-established, including various types of nodes, node attribute tags, and relationships between nodes. Users can directly select the desired first node from the node database to generate a node path from the first node to the end node of the process, without having to rebuild the node data each time according to business needs. The coordinate information of each node on the node path is calculated using a coordinate algorithm, and the nodes containing coordinate information are encapsulated to obtain visualized format data. Graphical modeling is performed based on the visualized format data to generate and display an interactive voice response (IVR) flowchart. Through the node database, a complete set of IVR processes related to the first node is automatically generated, effectively improving the efficiency of IVR process configuration. Based on the node database and the IVR flowchart, a visualized process customization environment is provided for users. The user's operations on the IVR flowchart in the visualized process customization environment are received and processed to obtain IVR process orchestration data. The IVR process orchestration data is transmitted to a computer telephony platform for dialing test verification, and the verification results returned by the computer telephony platform are received, which can greatly improve the efficiency and accuracy of process orchestration.

[0074] The technical solution for the above IVR workflow orchestration method will be described in detail below.

[0075] In one possible implementation, the IVR process orchestration method provided in this embodiment obtains the complete process node path by recursively traversing the first node layer by layer. Figure 3 This is a flowchart of the method for recursively processing process node data in the node database layer by layer, as provided in this embodiment. Figure 3 As shown, based on a pre-set node database, the process node data in the node database is recursively traversed layer by layer from the first node until the process end node is reached, including:

[0076] S301: Based on the node database, obtain at least one neighboring node that is associated with the first node.

[0077] In this embodiment, at least one neighboring node associated with the first node can have the same attributes or different attributes. Based on the construction information of the first node, such as "Press 1 to wait, press 2 to leave a message", there can be one or more neighboring nodes associated with the first node in the node database.

[0078] It is understood that the first node in this embodiment is selected by the developers based on business requirements. This first node can be the first node in the entire business requirements, or it can be the first node of a certain process line among multiple process branches sorted out by the developers based on business requirements.

[0079] S302: Determine whether the neighboring node is a process end node based on the attribute label of the neighboring node.

[0080] In this step, the attribute labels of nodes with different attributes can be different. For example, an IVR process may include nodes of the dialogue type, nodes of the SMS type, nodes of the function execution type, nodes of the transfer to human agent type, etc. For the dialogue type node, its attribute labels include node ID, dialogue name, dialogue description, dialogue resource, and playback type. Among them, the node whose dialogue name is "end dialogue" can be used as the end node of the process.

[0081] S303: If not, take the neighboring node as the first node, obtain at least one neighboring node that is related to the first node, and continue traversing until all neighboring nodes are the end nodes of the process.

[0082] In this step, for neighboring nodes that are not the end node of the process, they are usually connected to the next step. Therefore, the neighboring node is taken as the first node, and according to the traversal recursive algorithm, neighboring nodes that are related to the first node are obtained from the node database until all neighboring nodes are the end nodes of the process.

[0083] In this embodiment, the user can directly select the required first node and generate a node path from the first node to the process end node based on the pre-set node database. This is highly efficient and facilitates further adjustments by developers. Furthermore, the use of a layer-by-layer recursive approach not only ensures the comprehensiveness of the node path but also guarantees the correctness of the relationships between nodes.

[0084] In one possible implementation, the attribute tags include non-functional tags and functional tags. The functional tags include transfer to human operator tags and script end tags. The IVR process orchestration method provided in this embodiment determines whether a process node is an end process node by judging whether the attribute tags of the process node are functional tags.

[0085] Specifically, based on a pre-set node database, the process node data in the node database is recursively processed layer by layer from the first node until the process end node is reached. This includes: obtaining at least one first neighboring node related to the first node based on the node database; if the attribute label of the first neighboring node is a function label, the first neighboring node is the process end node of the node path from the first node to the first neighboring node; traversing the first neighboring nodes with attribute labels other than function labels, obtaining a second neighboring node related to the first neighboring node; if the attribute label of the second neighboring node is a function label, the second neighboring node is the process end node of the node path from the first node to the second neighboring node; traversing the second neighboring nodes with attribute labels other than function labels, obtaining a third neighboring node related to the second neighboring node, and so on, until all node paths include the process end node.

[0086] In this embodiment, when the attribute label of the first neighboring node is the "transfer to human agent" label, it means that the next step for the first neighboring node, such as a node whose content is "transfer to human agent service", should be to transfer to a human agent, and this node path ends; when the attribute label of the first neighboring node is the "end of conversation" label, it means that the first neighboring node, such as a node whose content is "thank you for your call, wish you a pleasant life", will not have a next step, and this node path ends.

[0087] It is understood that the functional labels described in this embodiment are not limited to the "transfer to human" label and the "end of conversation" label; any attribute label that can represent a leaf node can be used as a functional label.

[0088] In this step, for the first neighbor node whose attribute label is not a functional label, it is usually connected to the next step. Therefore, the first neighbor node is traversed, and the second neighbor node that is related to each first neighbor node is obtained from the node database.

[0089] In this embodiment, the layer-by-layer recursion is also known as layer-by-layer traversal recursion. Based on the confirmed first node, the first neighbor node of the first layer that is related to the first node can be obtained from the preset node database. Furthermore, the second neighbor node of the second layer that is related to the first neighbor node can be obtained from the node database. The neighbor nodes of each layer are traversed in this way until all neighbor nodes are process end nodes.

[0090] In this embodiment, nodes are distinguished by functional labels and non-functional labels, which can easily and quickly determine whether a node is a process end node, thus improving the efficiency of IVR process generation.

[0091] In one possible implementation, such as Figure 4 As shown, Figure 4 This is a schematic diagram of the interface of the visual process customization environment provided in the embodiment of this application. The visual process customization environment mainly includes a visual canvas area 401 and a tool area 402.

[0092] The provision of a user-defined visual process environment based on the node database and the IVR flowchart includes: generating a visual canvas area 401, which includes the IVR flowchart and is used to respond to user operations such as selecting, dragging, creating, and deleting nodes and connections between nodes; and generating a tool area 402, which is used to respond to user selection of a target node in the IVR flowchart and display nodes in the node database that are associated with the target node.

[0093] In this embodiment, in the visualization canvas area 401, developers can drag and drop to move process nodes and draw connections to target nodes. Developers can select nodes in the IVR flowchart, at which point selectable operation steps will appear in the tool area 402, such as deleting, adding, and modifying information. In addition, the tool area 402 also displays a list of nodes that are related to the selected node. Developers can select the required nodes from the list and add them to the visualization canvas area 401 for editing by dragging and dropping.

[0094] In this embodiment, by providing users with a visual process customization environment and automatically displaying a list of nodes related to the selected node when the developer selects a node in the IVR flowchart based on a preset node database, the efficiency of process orchestration and data accuracy can be greatly improved.

[0095] In one possible implementation, in order to ensure the smooth implementation of subsequent process simulation and process execution, before calling the coordinate algorithm to calculate the coordinate information of each node data on the node path, the method further includes: performing type correctness verification on the node data; and performing content integrity verification on the node data with correct type.

[0096] It is understandable that even within the same process path, the types of nodes may differ. The type can be validated based on the fields in the node data. Specifically, the fields in the node data can be identified to obtain the characteristic fields of the node data, and it can be determined whether the characteristic fields match the type of the node data. If yes, the node data type is confirmed to be correct; if not, the node data type is confirmed to be incorrect, and an alarm notification is sent.

[0097] It should be noted that the methods for identifying fields in node data include regular expression recognition, dictionary recognition, etc., and this embodiment does not limit this method.

[0098] For example, if a node's node data includes "Send you a text message later", its characteristic field is "text message" because the type of the node data should be text message. If the type of the node data is function execution type, it indicates that the node data type is incorrect. In this case, an alarm notification is sent to the developers for confirmation or modification.

[0099] In this embodiment, content integrity verification is performed on node data of the correct type, including: determining whether the attribute tag of the node data is a speech end tag; if so, checking whether the fields in the node data exceed a preset threshold, the preset threshold being the field value corresponding to the speech end tag; if the fields in the node data exceed the preset threshold, confirming that the node data is complete; if the fields in the node data do not exceed the preset threshold, confirming that the node data is incomplete, and sending an alarm notification.

[0100] Understandably, nodes with the attribute tag "end of conversation" are generally the ones requiring content integrity checks. These nodes typically contain formal, pre-set content such as "Call timeout, please hang up" or "Thank you for your call." Therefore, for these nodes with end of conversation tags, the fields in their node data are checked. If they do not exceed a preset threshold, the node data is considered to be missing content, and the developers should modify it accordingly.

[0101] In this embodiment, by performing type correctness verification and content integrity verification on the node data of process nodes, the accuracy of IVR process orchestration data can be ensured, which facilitates the debugging of the process orchestration process by developers and improves the efficiency of IVR process configuration.

[0102] Figure 5 This is a schematic diagram of an IVR workflow orchestration apparatus provided in an embodiment of this application. Figure 5 As shown, the IVR workflow orchestration device includes:

[0103] The node path generation module 51 is used to confirm the first node according to the business processing flow. According to the pre-set node database, which includes various types of nodes, node attribute tags and relationships between nodes, the module recursively traverses the process node data in the node database layer by layer from the first node until the process end node is reached, and generates a node path from the first node to the process end node.

[0104] The flowchart generation module 52 is used to calculate the coordinate information of each node on the node path using a coordinate algorithm, encapsulate the nodes containing coordinate information to obtain data in a visual format, perform graphical modeling based on the visual format data, and generate and display the interactive voice response (IVR) flowchart.

[0105] The process modification module 53 is used to provide a visual process customization environment for users based on the node database and the IVR flowchart, receive and process the user's operations on the IVR flowchart in the visual process customization environment, and obtain IVR process orchestration data.

[0106] The verification module 55 is used to transmit the IVR process orchestration data to the computer telephone platform for dial-up testing and verification, and to receive the verification results returned by the computer telephone platform.

[0107] In one possible design, the node path generation module 51 is specifically used for:

[0108] Based on the node database, obtain at least one neighboring node that is associated with the first node;

[0109] Determine whether the neighboring node is a process end node based on the attribute labels of the neighboring node;

[0110] If not, take the neighboring node as the first node, obtain at least one neighboring node that is related to the first node, and continue traversing until all neighboring nodes are the end nodes of the process.

[0111] In one possible design, the attribute tags include non-functional tags and functional tags, the functional tags including "transfer to human agent" tags and "end of dialogue" tags, and the node path generation module 51 is specifically used for:

[0112] Based on the node database, obtain at least one first neighbor node that is associated with the first node;

[0113] If the attribute label of the first neighboring node is a function label, the first neighboring node is the end node of the node path from the first node to the first neighboring node.

[0114] Iterate through the first neighboring nodes whose attribute tags are not functional tags, and obtain the second neighboring nodes that are related to the first neighboring nodes;

[0115] If the attribute label of the second neighboring node is a function label, the second neighboring node is the end node of the node path from the first node to the second neighboring node;

[0116] Iterate through the second neighboring node whose attribute label is not a function label, obtain the third neighboring node that is related to the second neighboring node, and so on, until all node paths include the process end node.

[0117] In one possible design, the process modification module 53 is specifically used for:

[0118] A visual canvas area is generated, which includes the IVR flowchart. The visual canvas area is used to respond to user operations such as selecting, dragging, creating, and deleting nodes and the connections between nodes.

[0119] A tool area is generated, which is used to display the nodes in the node database that are associated with the target node in response to the user's selection operation on the target node in the IVR flowchart.

[0120] In one possible design, the node path generation module 51 is also specifically used for:

[0121] Perform type correctness verification on the node data;

[0122] Perform content integrity verification on node data of the correct type.

[0123] In one possible design, the node path generation module 51 is also specifically used for:

[0124] The fields in the node data are identified to obtain the feature fields of the node data, and it is determined whether the feature fields are consistent with the type of the node data.

[0125] If so, confirm that the node data type is correct;

[0126] If not, confirm that the node data type is incorrect and send an alarm notification.

[0127] In one possible design, the node path generation module 51 is also specifically used for:

[0128] Determine whether the attribute label of the node data is a speech end label;

[0129] If so, check whether the fields in the node data exceed a preset threshold, where the preset threshold is the field value corresponding to the end-of-speech tag;

[0130] If the number of fields in the node data exceeds a preset threshold, the node data is confirmed to be complete.

[0131] If the fields in the node data do not exceed the preset threshold, the node data is confirmed to be incomplete, and an alarm notification is sent.

[0132] Figure 6 This is a schematic diagram of the structure of an electronic device based on an IVR workflow orchestration apparatus provided in an embodiment of this application. Figure 6 As shown, the electronic device of this embodiment includes: at least one processor 60 ( Figure 6 (Only one is shown) a processor, a memory 61, and a computer program stored in the memory 61 and executable on at least one processor 60, which executes the computer program to implement the steps in any of the above method embodiments.

[0133] The electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 6 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown in the figure, or combinations of certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0134] The processor 60 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0135] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0136] In some embodiments, memory 61 may be an internal storage unit of an electronic device, such as the memory of the electronic device. In other embodiments, memory 61 may be an external storage device of the electronic device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, memory 61 may include both internal and external storage units of the electronic device. Memory 61 is used to store operating systems, applications, bootloaders, data, and other programs, such as program code for computer programs. Memory 61 can also be used to temporarily store data that has been output or will be output.

[0137] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps described in the various method embodiments above.

[0138] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0139] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the aforementioned electronic device.

[0140] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0141] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0142] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0143] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs. Other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0144] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An interactive voice response flow orchestration method, characterized by, The application relates to an interactive voice response (IVR) flowchart generation method and device. The application comprises the following steps: confirming a first node according to a business process flow, recursively traversing process node data in a node database from the first node according to a pre-set node database, until a process end node is reached, generating a node path from the first node to the process end node, the node database comprising a plurality of different types of nodes, attribute labels of the nodes and association relationships between the nodes; calculating coordinate information of each node on the node path by using a coordinate algorithm, encapsulating the nodes with the coordinate information, obtaining visual format data, and generating and displaying an interactive voice response (IVR) flowchart according to the visual format data; providing a visual process customization environment for a user based on the node database and the IVR flowchart, receiving and processing operations of the user on the IVR flowchart in the visual process customization environment, and obtaining IVR process arrangement data; transmitting the IVR process arrangement data to a computer telephone platform for dialing test verification, and receiving verification results returned by the computer telephone platform; the attribute labels comprise non-functional labels and functional labels, the functional labels comprise a transfer to an artificial label and a speech end label, and the recursive traversal of the process node data in the node database from the first node according to the pre-set node database comprises the following steps: acquiring at least one first adjacent node associated with the first node based on the node database; if the attribute label of the first adjacent node is a functional label, the first adjacent node is taken as a process end node of a node path from the first node to the first adjacent node; traversing the first adjacent node with a non-functional label, acquiring a second adjacent node associated with the first adjacent node; if the attribute label of the second adjacent node is a functional label, the second adjacent node is taken as a process end node of a node path from the first node to the second adjacent node; 2. The method of claim 1, wherein, traversing the second adjacent node with a non-functional label, acquiring a third adjacent node associated with the second adjacent node, and so on, until all the node paths comprise process end nodes. the recursive traversal of the process node data in the node database from the first node according to the pre-set node database comprises the following steps: acquiring at least one adjacent node associated with the first node based on the node database; determining whether the adjacent node is a process end node according to the attribute label of the adjacent node; 3. The method of claim 1, wherein, if not, the adjacent node is taken as a first node, at least one adjacent node associated with the first node is acquired, and the traversal is continued until all the adjacent nodes are process end nodes. the provision of the visual process customization environment for the user based on the node database and the IVR flowchart comprises the following steps: generating a visual canvas area, the visual canvas area comprising the IVR flowchart, and the visual canvas area being used for responding to selection, dragging, creation and deletion operations of nodes and connections between the nodes by the user. A tool area is generated for displaying nodes associated with a target node in the IVR flowchart in response to a user selecting the target node.

4. The method of claim 1, wherein, Before invoking a coordinate algorithm to calculate coordinate information of each node data on the node path, the method further comprises: checking the type correctness of the node data; checking the content integrity of the type-correct node data.

5. The method of claim 4, wherein, The checking of the type correctness of the node data comprises: identifying fields in the node data to obtain characteristic fields of the node data, and determining whether the characteristic fields are consistent with the type of the node data; if yes, confirming that the node data is type-correct; if no, confirming that the node data is type-incorrect, and sending an alarm notification.

6. The method of claim 4, wherein, The checking of the content integrity of the type-correct node data comprises: determining whether the attribute label of the node data is an end-of-speech label; if yes, checking whether the number of fields in the node data exceeds a preset threshold, the preset threshold being a field value corresponding to the end-of-speech label; if the number of fields in the node data exceeds the preset threshold, confirming that the node data is complete; if the number of fields in the node data does not exceed the preset threshold, confirming that the node data is incomplete, and sending an alarm notification.

7. An interactive voice response flow arrangement device, comprising: a node path generation module configured to determine a first node according to a business process, and recursively traverse flow node data in a node database from the first node until an end-of-process node is reached, to generate a node path from the first node to the end-of-process node, wherein the node database comprises a plurality of different types of nodes, attribute labels of the nodes, and association relationships between the nodes; a flowchart generation module configured to calculate coordinate information of each node on the node path using a coordinate algorithm, encapsulate nodes containing the coordinate information to obtain visual format data, and generate and display an interactive voice response (IVR) flowchart based on the visual format data; a flow modification module configured to provide a visual flow customization environment for a user based on the node database and the IVR flowchart, receive and process operations of the user on the IVR flowchart in the visual flow customization environment, and obtain IVR flow arrangement data; a verification module configured to transmit the IVR flow arrangement data to a computer telephone platform for stress testing verification, and receive a verification result returned by the computer telephone platform; the attribute labels comprise non-functional labels and functional labels, the functional labels comprise a transfer-to-human label and an end-of-speech label, and the node path generation module is specifically configured to: obtain at least one first neighboring node associated with the first node based on the node database; if an attribute label of the first neighboring node is a functional label, the first neighboring node is the end-of-process node of the node path from the first node to the first neighboring node; traverse the first neighboring node with a non-functional attribute label, and obtain a second neighboring node associated with the first neighboring node. If the attribute label of the second adjacent node is a function label, the second adjacent node is taken as a first node of a node path of the second adjacent node, and a flow process ends at the node path; Second adjacent nodes with attribute labels being non-function labels are traversed, third adjacent nodes associated with the second adjacent nodes are obtained, and the process is repeated until the node path includes a flow process end node.

8. An electronic device comprising: A processor, and a memory connected to the processor in communication; The memory stores computer execution instructions; The processor executes the computer execution instructions stored in the memory to implement the method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1-6.

Images