Voice drawing method, device and equipment

Abstract

The invention provides a voice drawing method, device and equipment, relates to the technical field of computer application, and is used for improving the drawing efficiency. The method comprises the following steps: acquiring voice stream data input by a user, and converting the voice stream data into text data; according to the grammar rule and the text data, node data used for drawing nodes and connection line data used for describing the connection relation between the nodes are determined, and a target image is drawn according to the node data and the connection line data.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a voice drawing method, device and equipment. Background Art

[0002] Graphic data such as images or pictures can clearly convey technical ideas or business processes to staff, and can help professionals in different fields to communicate and cooperate effectively, such as flowcharts, program structure design diagrams, etc. Drawing efficiency is closely related to work efficiency, so improving drawing efficiency is particularly important for improving work efficiency.

[0003] With the development of Internet technology, the efficiency of drawing on paper can no longer meet the current demand for fast and convenient drawing. Therefore, in response to the drawing needs in various technical fields, various types of drawing software have appeared on the market, so that draftsmen can manually operate the drawing software on computer equipment to complete digital drawing. However, when the drawing is more complex, the draftsmen need to spend more time and the drawing efficiency is also lower. Summary of the invention

[0004] The present application provides a voice drawing method, device and equipment for improving drawing efficiency.

[0005] In a first aspect, an embodiment of the present application provides a voice drawing method, the method comprising: converting voice data into text data; determining node data and line data for drawing a graph based on grammatical rules and the text data, the line data being used to describe the connection relationship between nodes; and drawing a target graph based on the node data and the line data.

[0006] In the embodiment of the present application, the graphics are described by voice input, and after the voice data is converted into text data, the text data is split into node data and line data according to the grammatical rules, and then the nodes in the graphics can be generated according to the node data, and the lines between the nodes can be generated according to the line data, so that the target graphics can be obtained. It can be seen that in the drawing method provided in the embodiment of the present application, there is no need for the draftsman to perform drawing operations in the drawing software, and only voice description of the graphics is required, which reduces the workload of the draftsman and improves the drawing efficiency.

[0007] In a second aspect, an embodiment of the present application provides a voice drawing device, which includes: a conversion module, used to convert voice data input by a user into text data; a parsing module, used to determine node data and line data for drawing a graph based on grammatical rules and the text data, wherein the line data is used to describe the connection relationship between nodes; and a generation module, used to draw a target graph based on the node data and the line data.

[0008] In a third aspect, an embodiment of the present application provides a voice drawing device, comprising: at least one processor, and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the method described in the first aspect and any possible implementation manner by executing the instructions stored in the memory.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed on a computer, the computer executes the method described in the first aspect and any possible implementation manner.

[0010] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer instructions, which, when executed on a computer, enables the method described in the first aspect and any possible implementation method to be implemented.

[0011] Regarding the beneficial effects of the second to fifth aspects, reference can be made to the contents described in the first aspect above, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic diagram of an application scenario of a voice drawing method provided in an embodiment of the present application;

[0013] Figure 2 A flowchart of a voice drawing method provided in an embodiment of the present application;

[0014] Figure 3 A schematic diagram of a node connection provided in an embodiment of the present application;

[0015] Figure 4 A schematic diagram of an IVR flow chart provided in an embodiment of the present application;

[0016] Figure 5 A schematic diagram of the structure of a voice drawing device provided in an embodiment of the present application;

[0017] Figure 6 A schematic diagram of the structure of a voice drawing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0019] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their common and usual meanings.

[0020] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0021] The terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover but not exclude inclusion, for example, a product or device comprising a list of components is not necessarily limited to all the components expressly listed but may include other components not expressly listed or inherent to such product or device.

[0022] The term "module" refers to any known or later developed hardware, software, firmware, artificial intelligence, fuzzy logic, or combination of hardware and / or software code that is capable of performing the functions associated with that element.

[0023] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0024] For the convenience of explanation, the above description has been made in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The selection and description of the above embodiments are to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

[0025] In order to facilitate understanding of the technical solutions provided by the embodiments of the present application, the background technology related to the embodiments of the present application is first introduced here.

[0026] In response to the drawing needs in various technical fields, drawing software that meets the requirements of each technical field has been designed for each technical field. When using these drawing software, the draftsman is required to have a technical foundation in the relevant technical field. However, in actual work scenarios, the staff who propose solutions or requirements are usually business personnel. Business personnel do not have professional knowledge reserves in the relevant technical fields, and thus cannot use these drawing software for drawing. Therefore, business personnel need to sort out the solutions or requirements and send them to the draftsman, who will use the drawing software to draw.

[0027] For example, taking the interactive voice response (IVR) scenario as an example, an interactive voice response is an automated telephone system that can interact with users through voice recognition and speech synthesis technology. The IVR system is able to receive telephone calls and interact with users based on pre-recorded voice instructions or voice synthesized by text to speech (TTS) technology. Before applying the IVR system, it is necessary to draw an IVR flowchart according to the predefined business process so that the IVR system can perform corresponding tasks or operations based on the IVR flowchart. The business process is specified by the business personnel. Therefore, the IVR flowchart needs to be drawn by the business personnel based on the business process. The ordinary business flowchart, and then the drawing personnel use the drawing software to draw it in the drawing software according to the business flowchart.

[0028] It can be seen that the current drawing process is relatively cumbersome, and when the complexity of the drawing to be drawn is high, business personnel and draftsmen need to spend longer time to complete the drawing, that is, the drawing efficiency is low.

[0029] In view of this, the embodiment of the present application provides a voice drawing method, which uses the user's voice input to describe the graph, converts the voice data describing the graph into text data, and then determines the node data and line data used for drawing from the text data according to the grammatical rules, and then generates the nodes in the graph according to the node data, and generates the lines between the nodes according to the line data, thereby generating the target graph. In this way, there is no need for the draftsman to draw manually, and the information exchange process between the business personnel and the draftsman is reduced, the drawing process is simplified, and automatic voice drawing is realized, which improves the drawing efficiency.

[0030] In order to better understand the embodiments of the present application, the application scenarios applicable to the embodiments of the present application are described below.

[0031] Please refer to Figure 1 , is a schematic diagram of an application scenario of a voice drawing method provided by an embodiment of the present application. Figure 1As shown, the scene diagram includes a voice collection device 110 and a voice drawing device 120. The voice collection device 110 and the voice drawing device 120 can communicate with each other by wire or wirelessly.

[0032] The voice collection device 110 refers to a module or device with a sound collection function, such as a microphone or a device with a built-in microphone, and the device with a built-in microphone can be, for example, a mobile phone, a personal computer (PC), a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), etc. The voice drawing device 120 refers to a module or device with data processing capabilities, and the device can be, for example, a terminal device or a server. When the voice drawing device 120 is a module, it can be a functional module in the device.

[0033] like Figure 1 As shown, the user can describe the graph to be drawn in the form of speaking, the voice collection device 110 collects the user's speaking voice, and converts it into voice data, and sends it to the voice drawing device 120. The voice drawing device 120 converts the voice data into text data, and determines the node data and the line data from the text data according to the grammatical rules, and draws the target graph according to the node data and the line data. The specific implementation method of the voice drawing device 120 drawing the target graph according to the voice data will be described in detail below.

[0034] It should be noted that Figure 1 The voice collection device 110 and the voice mapping device 120 shown in the figure may be modules in the same device, or modules on two different devices, or two different devices, which is not limited in the embodiment of the present application.

[0035] The voice drawing method provided in the embodiment of the present application can be applied to application scenarios with drawing requirements, such as drawing of knowledge graphs, drawing of flowcharts of intelligent voice dialogue scenarios, etc. Among them, the intelligent voice dialogue scenario can be, for example, an intelligent outbound call scenario, an interactive voice response IVR scenario, etc.

[0036] Please refer to Figure 2 , is a flow chart of a voice drawing method provided in an embodiment of the present application. The following is a flow chart of a voice drawing device executing Figure 2 The steps shown are explained. Figure 2 The embodiment shown is applicable to Figure 1 The application scenario shown in the figure. Figure 2 The voice mapping device involved is, for example, Figure 1 The voice mapping device 110 is shown.

[0037] S201, converting voice data into text data.

[0038] The voice data may be sent to the voice mapping device by other devices, such as Figure 1 The voice collection device 110 shown may be a device that pre-stores voice data, which is not limited in this embodiment of the present application.

[0039] Exemplarily, taking the case where the voice drawing device and the voice collection device 110 are in the same device, the user can turn on the microphone through the browser interface in the device, and the user describes the target graphic in the form of speaking. The browser collects the user's speaking voice through the microphone to obtain voice data, and sends the voice data to the voice drawing device through a preconfigured network communication protocol, wherein the preconfigured network communication protocol is, for example, a full-duplex communication protocol, specifically, a Websocket communication protocol.

[0040] The voice data is obtained by collecting the user's voice describing the graphics to be drawn. When describing the graphics to be drawn, the user can describe the nodes in the graphics and the lines between the nodes. In order to better understand the way in which the user describes the graphics described in the embodiment of the present application, the following example is taken as an example of an IVR flow chart.

[0041] In the first case, the user describes the nodes in the IVR flow chart.

[0042] Example 1: The business process instructs to broadcast "Welcome to call XXXX customer hotline" to customers. The user can describe the voice as "Play the announcement welcome to call XXXX customer hotline".

[0043] Example 2: The business process instructs to call the interface "query customer tags", and the user can describe it in voice as "interface call to query customer tags".

[0044] Example 3: The business process indicates the associated sub-process "member sub-process", and the user can describe it in voice as "sub-process node member sub-process".

[0045] Example 4: The business process instructs to hang up the phone, and the user can describe it as "hang up" in voice.

[0046] In the second case, the user describes the connections between nodes in the IVR flowchart.

[0047] Example 5: The business process indicates connecting the "Start" and "Welcome" nodes, and the user can describe it in voice as "connect start node start end node welcome".

[0048] Example 6: The business process indicates the connection between the "Member User" condition of the "Query Customer Tags" node and the "Member Sub-Process" node. The user can describe it in voice as "Connect the starting node to query customer tags, the starting condition to member user, and the ending node to member sub-process".

[0049] After the voice drawing device obtains the voice data, the voice data can be converted into text data. Specifically, the voice drawing device can convert the voice data into text data using voice recognition technology. The voice recognition technology can be integrated into a voice recognition module or a voice recognition model. The voice recognition module can be, for example, an automatic speech recognition (ASR) module, which is not limited in the present embodiment of the application.

[0050] In practical applications, a speech recognition module with high speech recognition capability can be used to process speech data to ensure the accuracy of the converted text data, thereby improving the accuracy of drawing the target graphics.

[0051] S202, determining node data and line data for drawing a graph according to grammatical rules and text data, wherein the line data is used to describe the connection relationship between nodes.

[0052] Among them, the grammatical rules include first-category grammatical rules and second-category grammatical rules. The first-category grammatical rules are used to indicate the grammatical structure of node-type sub-text data, and the second-category grammatical rules are used to indicate the grammatical structure of line-type sub-text data. Node-type sub-text data refers to text data describing nodes, and line-type sub-text data refers to text data used to describe the connection relationship between nodes.

[0053] Specifically, the grammatical structure indicated by the first type of grammatical rules may be [node type] + [node description information]; the grammatical structure indicated by the second type of grammatical rules may be [starting node] + [connection relationship] + [ending node].

[0054] After obtaining the text data, the speech drawing device may split the text data according to the splitting rule to obtain M sub-text data, where M is a positive integer greater than 2. The splitting rule may indicate the grammatical structure of the node-type sub-text data and the grammatical structure of the link-type sub-text data. Alternatively, the splitting rule may indicate a section mark, which may be, for example, a punctuation mark, a specific keyword, etc.

[0055] The voice drawing device can determine the keywords in each sub-text data according to the pre-stored keyword library, wherein the keywords are used to indicate that the drawing tasks corresponding to the sub-text data are drawing nodes and drawing lines.

[0056] The keywords may specifically include keywords for drawing nodes and keywords for drawing lines. The keywords for drawing nodes may include node names and node types of target graphics, which may be set according to actual scenarios, and the embodiments of the present application do not limit this. The keywords for drawing lines may include verbs indicating drawing lines, such as line, connection, etc.

[0057] For example, when the graph is an IVR flowchart, the keywords for drawing nodes may be the node names or types of the nodes in the IVR flowchart, such as start, play, interface call, sub-process node, hang up, etc. When the graph is a knowledge graph, the keywords for drawing nodes may include the names of the entities.

[0058] Therefore, the voice drawing device can classify the M sub-text data according to the keywords in each sub-text data to obtain node-type sub-text data and line-type sub-text data. Specifically, taking one sub-text data as an example, if the voice drawing device determines that the sub-text data includes the keywords for drawing lines, the sub-text data is determined as line-type sub-text data. If it is determined that the sub-text data includes the keywords for drawing nodes but does not include the keywords for drawing lines, the sub-text data is determined as node-type sub-text data.

[0059] Furthermore, the speech drawing device can obtain node data according to grammatical rules and node-type subtext data, and obtain line data according to grammatical rules and line-type subtext data. The following describes a specific implementation of the speech drawing device obtaining node data and line data.

[0060] 1. The speech drawing device obtains node data according to grammatical rules and node class subtext data.

[0061] The speech drawing device can split the node-type subtext data according to the first type of grammatical rules to obtain the node type and node description information. The node description information is used to describe the task execution information and / or attributes of the node. For example, when the graph is an IVR flow chart, the node description information is used to describe the task execution information and attributes of the node. When the graph is a knowledge graph, the node description information is used to describe the attributes of the node.

[0062] Specifically, the grammatical structure indicated by the first type of grammatical rule is [node type] + [node description information]. Therefore, the speech drawing device can determine the text data indicating the node type in the node class sub-text data based on the grammatical structure and the pre-stored node type set, and determine the text data other than the node type indicated in the node class sub-text data as the node description information.

[0063] The node type set is related to the type of the drawn graph. For example, when the graph is an IVR flowchart, the node type set includes all node types related to the IVR flowchart, and the node type set may specifically include start, play, interface call, sub-process, hang up, etc. When the graph is a knowledge graph, the node type set may include the type or name of each entity.

[0064] Exemplarily, taking the graph as an IVR flow chart, and continuing to refer to Example 1 above, a node class sub-text data is "Playback Welcome to Call XXXX Customer Hotline". Based on the node type set and the grammatical structure indicated by the first type of grammatical rules, the voice drawing device can determine "playback" as the node type and determine "Welcome to Call XXXX Customer Hotline" as the node description information.

[0065] Furthermore, the speech drawing device can generate node data according to the node type and node description information. Specifically, the speech drawing device can generate a node name corresponding to the node class subtext data according to the node description information, and determine the node data according to the node name, node type and node description information.

[0066] The voice drawing device can directly use the node description information as the node name. Alternatively, if the node description information is long, a preset number of characters in the node description information can be intercepted as the node name, wherein the preset number can be pre-stored in the voice drawing device, and the preset number can be set based on actual needs, such as 20 characters, which is not limited in the embodiment of the present application.

[0067] In a possible implementation, the node description information is used to describe the task execution information of the node. In this implementation, the voice drawing device can also obtain the task execution information corresponding to the node type from the pre-stored task execution information library according to the node type and the node description information, and store the node name, node type and task execution information as node data.

[0068] Due to the different node types, the tasks / operations to be performed corresponding to the node types are different. For example, taking the graph as an IVR flowchart, the playback node needs to perform the task of broadcasting the words to the customer, the interface call node performs the task of calling the interface to obtain data, the hang-up node performs the task of hanging up the phone, the sub-process node performs the task of associating / flowing between sub-processes, and so on. Therefore, the voice drawing device can query whether the task execution information corresponding to the node type is stored in the pre-stored task execution information library based on the node type. If the task execution information corresponding to the node type is stored, the task execution information corresponding to the node type is obtained from the task execution information library. If the task execution information corresponding to the node type is not stored in the task execution information library, the node description information is used as the task execution information, and the node description information is associated with the node type and stored in the task execution information library.

[0069] In a possible implementation, the speech drawing device may also generate a unique node identifier for the node type, and associate the node identifier with the node name, node type, and node description information as node data. For example, the speech drawing device may use a timestamp as the node identifier, and the timestamp may refer to the time when the node-like subtext data is generated in the speech drawing device, or the time when the speech drawing device processes the node-like subtext data, which is not limited in the present embodiment of the application.

[0070] 2. The speech drawing device obtains connection data according to the grammatical rules and the connection-type subtext data.

[0071] The speech drawing device can split the connection-type subtext data according to the second type of grammatical rules, obtain the starting node, the connection relationship and the ending node, and associate and store the starting node, the connection relationship and the ending node as connection data.

[0072] Specifically, the grammatical structure indicated by the second type of grammatical rule is [starting node] + [connection relationship] + [end node]. Therefore, the speech drawing device can obtain the starting node and the ending node from the connection type subtext data according to the above grammatical structure and the pre-stored node type set. Among them, the starting node is the starting node in the grammatical structure, and the ending node is the end node in the grammatical structure. The node type set can correspond to the content described above, and will not be repeated here.

[0073] The speech mapping device can determine the text data between the start node and the end node as a connection relationship. In particular, when there is no text data between the start node and the end node, the start node and the end node are determined to be a direct connection relationship without a connection condition.

[0074] For example, taking Example 5 in the previous text as an example, the text data corresponds to "connection start node start end node welcome", and the voice drawing device can be divided into "start + welcome" according to the second type of grammatical rules. In this case, there is no other text data between "start" and "welcome", so "start" and "welcome" can be directly connected, and this connection method can also be called unconditional connection. For another example, taking Example 6 in the previous text as an example, the text data corresponds to "connection start node query customer label start condition member user end node member sub-process", which can be divided into "query customer label + member user + member sub-process" according to the second type of grammatical rules. The voice drawing device can determine the "member user" between the "query customer label" and "member sub-process" nodes as a connection relationship, and this connection method can also be called conditional connection. The situation in Example 6 above can be understood as when the customer is a member user, the query customer label node can be connected to the member sub-process node.

[0075] In a possible implementation, the link-type subtext data may include a start node, multiple connection relationships, and an end node corresponding to each of the multiple connection relationships.

[0076] For example, taking the connection sub-text data as "connection start node query customer label start condition member user end node member sub-process start condition non-member user end node non-member sub-process", the voice drawing device can know according to the second type of grammar rules that the start node is the query customer label, the connection relationship 1 is the member user, and the end node 1 corresponding to the connection relationship 1 is the member sub-process; the connection relationship 2 is the non-member user, and the end node 2 corresponding to the connection relationship 2 is the non-member sub-process. In this case, the voice drawing device can store the query customer label + member user + member sub-process as one connection data, and store the query customer label + non-member user + non-member sub-process as another connection data.

[0077] For example, please refer to Figure 3 , is a schematic diagram of a node connection provided in an embodiment of the present application. Figure 3 As shown, the connection between the start node and the welcome node is an unconditional connection, and the connection between the query customer tag and the member sub-process and the non-member sub-process is a conditional connection.

[0078] In a possible implementation, the connection data may further include a connection name. The connection name may be determined according to the connection relationship or the end node. Specifically, when the connection mode is a conditional connection, the voice drawing device may use the connection relationship as the connection name; when the connection mode is an unconditional connection, the voice drawing device may use the end node as the connection name.

[0079] In a possible implementation, the connection data may further include a connection identifier, which is used to uniquely identify the connection data. The connection identifier may be generated based on a timestamp, and the timestamp may be the time when the connection sub-text data is generated in the voice drawing device, or the time when the voice drawing device splits the connection sub-text data, which is not limited in the embodiment of the present application.

[0080] S203, drawing a target graph according to the node data and the line data.

[0081] Specifically, the voice drawing device can determine the node icon and the size of the node icon according to the node data, and render the node icon in the canvas according to the size of the node icon. According to the connection data, a connection line is established between the node icon of the starting node and the node icon of the ending node, and the connection relationship indicated in the connection data is configured on the connection line to obtain the target graph.

[0082] The node icon may be called from a pre-stored node component library. The preset canvas may be generated by a pre-configured drawing software in the voice drawing device. The drawing software may be determined according to the actual application scenario. For example, when the target graphic is an IVR flow chart, the drawing software may be AntV-X6, Draw.io, etc.

[0083] The voice drawing device may determine a node icon corresponding to the node type from a node component library according to the node type, and determine the size of the node icon according to the length of the node name, wherein the length of the node name may refer to the number of characters included in the node name. Specifically, the voice drawing device may determine the size of the node icon according to a preconfigured mapping relationship between the name length and the icon size and the length of the node name.

[0084] In a possible implementation, the node data further includes a node identifier, which can also be used as a unique identifier of the node component. Therefore, the voice mapping device can configure the node identifier into the node component.

[0085] In a possible implementation, the connection data further includes a connection name and / or a connection identifier, and the voice drawing device may configure the connection name and / or the connection identifier in the connection between the start node and the end node.

[0086] For example, if the connection data is [start] + [welcome], the voice drawing device can determine the start node in the canvas as the starting node and the welcome node as the ending node, and construct a connection between the start node and the welcome node. If the connection data also indicates that the connection name is welcome and the connection identifier is 20231204145843, the voice drawing device can also configure the welcome and 20231204145843 to the connection between the start node and the welcome node.

[0087] In a possible implementation, when the target graphic is an IVR flowchart, after obtaining the target graphic, the voice drawing device may also convert the target graphic into flowchart data in JSON format, and generate a script text executable by the IVR process engine based on the flowchart data.

[0088] The above is an example of a voice drawing device drawing a node type in a canvas. In actual applications, the voice drawing device needs to draw multiple node types. When the voice drawing device draws each node type, the position of the current node type to be drawn in the canvas can be calculated based on the node position of the previous node type rendered in the canvas and the preset spacing. Among them, the preset spacing can be pre-configured in the voice drawing device, and the preset spacing can refer to the horizontal spacing, vertical spacing, spacing between each connection relationship when there are multiple connection relationships, and other spacings in multiple dimensions. It can be set according to actual needs, and the embodiment of the present application does not limit this.

[0089] Among them, if the node types are different, the graphics displayed in the canvas of the node icons corresponding to the node types may be the same or different, which can be specifically determined according to the actual drawing software, and the embodiments of the present application are not limited to this.

[0090] Combine the following Figure 4 The target graphics drawn by the voice drawing device are shown in FIG. Figure 4 The target graph is used as an IVR flow chart. Figure 4 As shown, in the order from left to right, the first icon represents the start node of the IVR flowchart, the next icon connected to the start node icon represents the welcome node, the next icon connected to the welcome node icon represents the query customer tag node, when the connection relationship indicates a member user, the node icon of the query customer tag node is connected to the node icon of the member sub-process node, when the connection relationship indicates a non-member user, the node icon of the query customer tag node is connected to the node icon of the non-member sub-process. Among them, the task execution information configured in each node in the IVR flowchart is not displayed. Figure 4 However, in actual applications, the information configured for each node or line in the IVR flowchart can be displayed in the configuration panel.

[0091] It should be noted that in order to facilitate the voice drawing device to parse node data and connection data from text data, the user can describe the business process according to grammatical rules when inputting voice, so that the voice drawing device can parse node data and connection data from text data more accurately and quickly.

[0092] Based on the same inventive concept, the embodiment of the present application provides a voice drawing device, which is used to implement any of the above-mentioned voice drawing methods, for example, Figure 2 The voice drawing method shown, and the device can also realize the function of the voice drawing device mentioned above.

[0093] Please refer to Figure 5 , is a schematic diagram of the structure of a voice drawing device provided in an embodiment of the present application. Figure 5 As shown, the speech graphics device 500 includes a conversion module 501 , a parsing module 502 and a generation module 503 .

[0094] Exemplarily, the conversion module 501 is used to convert the voice data input by the user into text data; the parsing module 502 is used to determine the node data and line data used to draw the graph based on the grammatical rules and text data, and the line data is used to describe the connection relationship between nodes; the generation module 503 is used to draw the target graph based on the node data and line data.

[0095] In one possible implementation, the parsing module 502 is specifically used to: split the text data according to the splitting rules to obtain M sub-text data, where M is a positive integer greater than 2; determine the keywords in each sub-text data according to the keyword library, and the keywords are used to indicate that the drawing task corresponding to the sub-text data is drawing nodes or drawing lines; classify the M sub-text data according to the keywords in each sub-text data to obtain node-type sub-text data and line-type sub-text data; determine the node data according to the grammatical rules and the node-type sub-text data, and determine the line data according to the grammatical rules and the line-type sub-text data.

[0096] In a possible implementation, the grammatical rules include a first type of grammatical rules and a second type of grammatical rules, the first type of grammatical rules are used to indicate the grammatical structure of node-type sub-text data, and the second type of grammatical rules are used to indicate the grammatical structure of line-type sub-text data; wherein the grammatical structure indicated by the first type of grammatical rules is the node type and the node description information; and the grammatical structure indicated by the second type of grammatical rules is the starting node, the connection relationship, and the ending node.

[0097] In one possible implementation, the parsing module 502 is specifically used to: split the node class sub-text data according to the first type of grammatical rules to obtain the node type and node description information, the node description information is used to describe the node's attributes and / or task execution information; generate a node name corresponding to the node class sub-text data according to the node description information; determine the node data according to the node name, node type and node description information.

[0098] In one possible implementation, the node description information is used to describe the task execution information of the node; the parsing module 502 is specifically used to: obtain the task execution information corresponding to the node type from a pre-stored task execution information library according to the node type and the node description information; and associate the node name, node type and task execution information and store them as node data.

[0099] In one possible implementation, the parsing module 502 is specifically used to: split the connection-type sub-text data according to the second type of grammatical rules to obtain a starting node, a connection relationship, and an ending node; wherein a connection relationship corresponds to a starting node and an ending node; and the starting node, the connection relationship, and the ending node are associated and stored as connection data.

[0100] In one possible implementation, the generation module 503 is specifically used to: determine the node icon and the size of the node icon based on the node data, and render the node icon in the canvas according to the size of the node icon; establish a connection between the node icon of the starting node and the node icon of the ending node based on the connection data, and configure the connection relationship indicated by the connection data on the connection to obtain the target graph.

[0101] In a possible implementation, the node data includes a node type and a node name; the generation module 503 is specifically used to: determine a node icon corresponding to the node type according to the node type; and determine a size of the node icon according to the length of the node name.

[0102] Based on the same inventive concept, the embodiment of the present application provides a voice drawing device, which is used to implement any of the above-mentioned voice drawing methods, for example, Figure 2 The voice drawing method shown, and the device can also realize the function of the voice drawing device mentioned above.

[0103] Please refer to Figure 6 , is a schematic diagram of the structure of a voice drawing device provided in an embodiment of the present application. Figure 6 As shown, the voice mapping device 600 includes: at least one processor 601 , and a memory 602 communicatively connected to the at least one processor 601 .

[0104] The processor 601 may be a general-purpose processor or a dedicated processor. The processor 601 may include, for example, a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data. The central processing unit may be used to control the voice and graphics device 600, execute software programs and / or process data. Different processors may be independent devices or may be arranged in one or more processing circuits, for example, integrated in one or more dedicated integrated circuits.

[0105] In one embodiment, the memory 602 stores instructions executable by at least one processor 601. The at least one processor 601 implements the functions of the aforementioned voice drawing device by executing the instructions stored in the memory 602, and accordingly, can also implement the steps performed by the aforementioned voice drawing device.

[0106] In this embodiment, the speech mapping device 600 can also implement the functions of the preceding speech mapping apparatus 500 , and at least one processor 601 in the speech mapping device 600 can also implement the functions of the preceding conversion module 501 , the parsing module 502 and the generating module 503 .

[0107] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions. When the computer instructions are executed on a computer, the computer executes any of the above-mentioned voice drawing methods, for example, Figure 2 The voice mapping method shown.

[0108] Based on the same inventive concept, the embodiment of the present application provides a computer program product, which includes computer instructions. When the computer program product is executed on a computer, the above-mentioned voice drawing method as described above is performed, for example, Figure 2 The voice mapping method shown is implemented.

[0109] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0110] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A voice mapping method, characterized in that: include: Convert voice data into text data; Determine node data and line data for drawing a graph according to grammatical rules and the text data, wherein the line data is used to describe the connection relationship between nodes; Draw a target graph according to the node data and the line data.

2. The method according to claim 1, characterized in that The step of determining the node data and the line data for drawing the graph according to the grammatical rules and the text data includes: Splitting the text data according to the splitting rule to obtain M sub-text data, where M is a positive integer greater than 2; Determine a keyword in each sub-text data according to the keyword library, wherein the keyword is used to indicate that the drawing task corresponding to the sub-text data is drawing a node or drawing a line; Classify the M sub-text data according to the keywords in each sub-text data to obtain node-type sub-text data and link-type sub-text data; The node data is determined according to the grammatical rules and the node-type subtext data, and the link data is determined according to the grammatical rules and the link-type subtext data.

3. The method according to claim 2, characterized in that The grammatical rules include a first type of grammatical rules and a second type of grammatical rules, wherein the first type of grammatical rules are used to indicate the grammatical structure of the node-type sub-text data, and the second type of grammatical rules are used to indicate the grammatical structure of the link-type sub-text data; The grammatical structure indicated by the first type of grammatical rules is the node type and the node description information; the grammatical structure indicated by the second type of grammatical rules is the starting node, the connection relationship and the ending node.

4. The method according to claim 3, characterized in that The determining of the node data according to the grammatical rules and the node class subtext data includes: According to the first type of grammatical rules, split the node class subtext data to obtain node type and node description information, where the node description information is used to describe node attributes and / or task execution information; Generate a node name corresponding to the node class subtext data according to the node description information; Node data is determined according to the node name, the node type and the node description information.

5. The method according to claim 4, characterized in that The node description information is used to describe the task execution information of the node; The determining node data by using the node name, the node type and the node description information includes: According to the node type and the node description information, acquiring task execution information corresponding to the node type from a pre-stored task execution information library; The node name, the node type and the task execution information are associated and stored as the node data.

6. The method according to claim 3, characterized in that The determining of the connection data according to the grammatical rule and the connection-type subtext data comprises: According to the second type of grammatical rules, the connection-type subtext data is split to obtain a starting node, a connection relationship, and an ending node; wherein a connection relationship corresponds to a starting node and an ending node; The starting node, the connection relationship and the ending node are associated and stored as link data.

7. The method according to any one of claims 1 to 6, characterized in that: Drawing a target graph according to the node data and the line data includes: Determine a node icon and a size of the node icon according to the node data, and render the node icon in a canvas according to the size of the node icon; According to the line data, a line is established between the node icon of the starting node and the node icon of the ending node, and the connection relationship indicated by the line data is configured on the line to obtain a target graph.

8. The method according to claim 7, characterized in that The node data includes a node type and a node name; and determining a node icon and a size of the node icon according to the node data includes: According to the node type, determining a node icon corresponding to the node type; The size of the node icon is determined according to the length of the node name.

9. A voice drawing device, characterized in that: include: A conversion module, used for converting the voice data input by the user into text data; A parsing module, used to determine node data and line data for drawing a graph according to grammatical rules and the text data, wherein the line data is used to describe the connection relationship between nodes; A generation module is used to draw a target graph according to the node data and the line data.

10. A voice drawing device, characterized in that: include: at least one processor, and a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the method according to any one of claims 1 to 8 by executing the instructions stored in the memory.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 8.

12. A computer program product, characterized in that The invention comprises computer instructions, which, when executed on a computer, enable the method according to any one of claims 1 to 8 to be implemented.

Images