CN111897511A

CN111897511A - Voice drawing method, device, equipment and storage medium

Info

Publication number: CN111897511A
Application number: CN202010758970.3A
Authority: CN
Inventors: 苗同亚
Original assignee: iFlytek Co Ltd
Current assignee: iFlytek Co Ltd
Priority date: 2020-07-31
Filing date: 2020-07-31
Publication date: 2020-11-06

Abstract

The application provides a voice drawing method, a device, equipment and a storage medium, wherein the method comprises the following steps: extracting drawing keywords from the voice drawing instruction, wherein the drawing keywords are words for describing drawing operation; determining a drawing operation instruction corresponding to the drawing keyword based on the text feature of the drawing keyword; and executing the drawing operation instruction to draw the graph. Above-mentioned processing procedure has realized automatic matching and the mapping between the drawing keyword in the pronunciation drawing instruction and the drawing operation instruction, through carrying out above-mentioned processing procedure, can draw according to the pronunciation drawing instruction that the plotter sent is automatic to can promote plotter drawing efficiency, and promote the drawing and experience.

Description

Voice drawing method, device, equipment and storage medium

Technical Field

The present application relates to the field of intelligent control technologies, and in particular, to a voice drawing method, apparatus, device, and storage medium.

Background

Most of the existing drawing methods are manual drawing methods, a lot of drawing operations are required to be performed by a drawer, the drawing process is complicated, and much inconvenience is brought to the drawer.

With the continuous development of voice control technology, various products based on voice control continuously improve the living and working efficiency of people. If can make the plotter draw through pronunciation, will promote drawing efficiency greatly, promote the plotter and draw experience.

Disclosure of Invention

Based on the technical current situation, the application provides a voice drawing method, device, equipment and storage medium, and aims to enable a user to draw through voice, so that drawing efficiency is improved, and drawing experience of the user is improved.

In order to achieve the above purpose, the present application specifically proposes the following technical solutions:

a voice mapping method, comprising:

extracting drawing keywords from the voice drawing instruction, wherein the drawing keywords are words for describing drawing operation;

determining a drawing operation instruction corresponding to the drawing keyword based on the text feature of the drawing keyword; the drawing operation instruction is an instruction used for drawing a graph which is matched with the drawing keyword in a preset graph template library;

and executing the drawing operation instruction to draw the graph.

Optionally, the extracting a drawing keyword from the voice drawing instruction includes:

carrying out voice recognition processing on the voice drawing instruction to obtain a drawing instruction text;

and extracting drawing keywords from the drawing instruction text.

Optionally, the extracting of the drawing keywords from the drawing instruction text includes:

extracting a drawing grammar structure from the drawing instruction text by performing syntactic component analysis processing on the drawing instruction text, wherein the drawing grammar structure is a grammar structure representing drawing operation;

and respectively extracting keywords of the text content corresponding to each grammar component of the drawing grammar structure as drawing keywords.

Optionally, the extracting a drawing grammar structure from the drawing instruction text by performing syntactic component analysis processing on the drawing instruction text includes:

according to the generation scene of the voice drawing instruction, carrying out syntactic component analysis processing on the drawing instruction text to obtain syntactic components of the drawing instruction text;

and extracting a drawing grammar structure matched with the generation scene of the voice drawing instruction from the drawing instruction text according to the grammar components of the drawing instruction text and the generation scene of the voice drawing instruction.

Optionally, after extracting the drawing keyword from the voice drawing instruction, the method further includes:

judging whether the extracted drawing keywords contain complete drawing operation information or not; the complete drawing operation information at least comprises minimum information capable of representing one complete drawing operation;

and if the voice drawing command does not contain the complete drawing operation information, interacting with the object sending the voice drawing command, and extracting the drawing keywords from the interaction data of the object until the extracted drawing keywords contain the complete drawing operation information.

Optionally, the determining whether the extracted drawing keyword includes complete drawing operation information includes:

determining drawing contents corresponding to the voice drawing instruction according to the extracted drawing keywords;

and judging whether the extracted drawing keywords contain complete drawing operation information for drawing the drawing content or not according to the extracted drawing keywords and the drawing content corresponding to the voice drawing instruction.

Optionally, the determining, based on the text feature of the drawing keyword, a drawing operation instruction corresponding to the drawing keyword includes:

inputting the drawing keywords into a pre-trained drawing instruction mapping model, and determining drawing operation instructions corresponding to the drawing keywords;

the drawing instruction mapping model can determine the drawing operation instruction corresponding to the input drawing keyword based on the corresponding relation between the drawing keyword and the drawing operation instruction.

Optionally, the method further includes:

predicting and prompting the drawing content of the current drawing operation according to the historical drawing operation before drawing keywords from the voice drawing instruction;

when a preset drawing operation confirmation condition is met, drawing the prompted drawing content; and the preset drawing operation confirmation condition comprises that no voice drawing instruction is received within a set time length after the drawing content of the current drawing operation is prompted.

Optionally, the predicting and prompting the drawing content of the current drawing operation according to the historical drawing operation includes:

determining drawing habit information of a user according to historical drawing operation;

and predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user and the drawing content of the previous drawing operation.

Optionally, the predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user and the drawing content of the previous drawing operation includes:

and predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user, the category and/or the name of the drawing content of the previous drawing operation and the organizational structure model to which the drawing content of the previous drawing operation belongs.

Optionally, before acquiring the voice drawing instruction, the method further includes:

outputting a preset legend template and/or outputting drawing guide information.

Optionally, before extracting the drawing keyword from the voice drawing instruction, the method further includes:

and recognizing a voice drawing instruction sent by the target user from the collected voice data.

A voice mapping device, comprising:

the keyword extraction unit is used for extracting and obtaining drawing keywords from the voice drawing instruction, wherein the drawing keywords are words for describing drawing operation;

the instruction determining unit is used for determining a drawing operation instruction corresponding to the drawing keyword based on the text characteristic of the drawing keyword; the drawing operation instruction is an instruction used for drawing a graph which is matched with the drawing keyword in a preset graph template library;

and the instruction execution unit is used for executing the drawing operation instruction so as to draw the graph.

A voice mapping device comprising:

a memory and a processor;

wherein the memory is connected with the processor and used for storing programs;

the processor is used for realizing the voice drawing method by running the program in the memory.

A storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described voice mapping method.

By adopting the voice drawing method provided by the application, when the voice drawing instruction sent by a drawer is collected, drawing keywords are extracted from the voice drawing instruction, then the drawing operation instruction corresponding to the drawing keywords is determined based on the text features of the extracted drawing keywords, and finally the purpose of drawing a graph is realized by executing the drawing operation instruction. Above-mentioned processing procedure has realized automatic matching and the mapping between the drawing keyword in the pronunciation drawing instruction and the drawing operation instruction, through carrying out above-mentioned processing procedure, can draw according to the pronunciation drawing instruction that the plotter sent is automatic to can promote plotter drawing efficiency, and promote the drawing and experience.

Furthermore, the voice drawing method can determine a drawing operation instruction for drawing a figure matched with the drawing keyword in a preset figure template library according to the drawing keyword in the voice drawing instruction, execute the drawing operation instruction, and quickly draw the figure required to be drawn by the user, for example, a figure frame, a figure main body structure and the like can be further drawn based on one voice drawing instruction of the user, so that the drawing efficiency of the user can be greatly improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a schematic flow chart of a voice drawing method according to an embodiment of the present application;

FIG. 2 is a flow chart of another speech drawing method provided by the present application;

FIG. 3 is a flow chart of another speech drawing method according to an embodiment of the present application;

FIG. 4 is a schematic diagram of an architecture diagram for voice rendering provided by an embodiment of the present application;

fig. 5 is a schematic structural diagram of a voice drawing apparatus according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a voice drawing device according to an embodiment of the present application.

Detailed Description

The technical scheme of the embodiment of the application is suitable for drawing scenes, especially drawing scenes on electronic equipment, such as computer drawing and flat drawing. By adopting the technical scheme of the embodiment of the application, a plotter only needs to send out the voice drawing instruction, and can realize automatic drawing based on the voice drawing instruction of the plotter, so that the drawing efficiency can be improved, and the drawing experience of the plotter can be improved.

The technical scheme of the embodiment of the application can be applied to intelligent equipment with a voice acquisition function, such as a computer, a smart phone, a tablet personal computer, professional drawing equipment and the like, can also be applied to hardware processing equipment such as a processor and the like, or can also be written into an application program to be run. When a hardware device executes the technical scheme of the embodiment of the application or a software program written based on the voice drawing method provided by the embodiment of the application is run, automatic drawing processing based on a voice drawing instruction of a plotter can be realized. In the following description, the processing procedure of the voice mapping method provided by the present application is exemplarily described by taking an intelligent device as an execution subject, but it should be understood that the embodiment of the present application is not limited to the implementation of the voice mapping method provided by the present application, and besides the implementation described in the embodiment of the present application, any implementation that can implement the processing procedure of the voice mapping method provided by the present application is within the scope of the embodiment of the present application.

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a voice drawing method which can be applied to intelligent equipment with a voice acquisition function, such as a computer, a smart phone, a tablet computer, professional drawing equipment and the like. Referring to fig. 1, the method includes:

s101, extracting drawing keywords from the voice drawing instruction.

The drawing keywords are words for describing drawing operation.

Specifically, the voice drawing instruction refers to a drawing instruction voice uttered by spoken language when the plotter uses the intelligent device to perform electronic drawing. For example, voice commands such as "draw a circle", "create a table with four rows and three columns" and the like can be used as voice drawing commands.

When the intelligent equipment with the voice acquisition function works in a drawing mode, a voice drawing instruction sent by a drawer can be acquired in real time. When the voice drawing instruction is obtained, the semantic drawing instruction is analyzed, and drawing keywords are extracted from the semantic drawing instruction.

For example, for a voice drawing instruction of "newly creating a table with four rows and three columns" issued by a plotter, the intelligent device analyzes the voice drawing instruction, and extracts three drawing keywords of "newly creating", "four rows and three columns", and "table". It can be understood that, based on the three drawing keywords, a complete drawing operation can be represented, which is an operation for creating a new form.

As an exemplary implementation manner, after the voice drawing instruction is obtained, the smart device detects word components such as verbs and nouns related to drawing operation from the voice drawing instruction, so as to realize extraction of drawing keywords.

For example, when the smart device acquires a voice drawing instruction of "newly building a table with four rows and three columns", verbs, nouns and noun fixed words related to drawing operation are detected from the instruction, and finally three drawing keywords of "newly building", "table" and "four rows and three columns" are detected.

S102, determining a drawing operation instruction corresponding to the drawing keyword based on the text feature of the drawing keyword.

Specifically, the text feature of the drawing keyword refers to feature information that can be used to represent the drawing keyword, and may be, for example, a feature vector of the drawing keyword, a combined feature of each drawing keyword, or the text content of the drawing keyword itself.

The drawing operation instruction refers to a computer operation instruction recognizable by the intelligent device, and may specifically be in the form of an instruction code, a drawing function, or a drawing operator. The drawing operation instruction can be recognized and executed by the intelligent device. It is understood that the drawing operation instruction, when executed by the smart device, may implement a drawing operation corresponding to the drawing operation instruction.

All drawing operation instructions are stored in a storage device inside or outside the intelligent equipment, and any scene and any type of drawing operation can be realized based on the stored drawing operation instructions. The method and the device for the voice drawing operation command search determine the corresponding relation between the text features of the drawing keywords and the drawing operation command in advance, and when the drawing keywords are extracted from the voice drawing command, the drawing operation command corresponding to the text features of the drawing keywords is obtained through searching from all stored drawing operation commands according to the text features of the extracted drawing keywords.

The drawing operation instruction determined based on the text feature of the drawing keyword may be a single instruction or a plurality of instructions, and in the case of the plurality of instructions, the plurality of instructions form a drawing instruction set.

As a preferred implementation manner, in this embodiment of the application, the drawing operation instruction corresponding to the drawing keyword, which is determined based on the text feature of the drawing keyword, is an instruction for drawing a graphic matching the drawing keyword in a preset graphic template library.

The embodiment of the application presets a graph template library, and preset graph templates, such as an organization architecture diagram, a flow chart, a data flow chart and the like, are stored in the graph template library.

Meanwhile, the embodiment of the application predetermines the drawing operation instruction corresponding to each graph in the graph template library, and stores the drawing operation instruction in the storage device for storing the drawing operation instruction.

It is understood that the operation instruction corresponding to the graphics can be one or more according to the complexity of the graphics in the graphics template library. The instructions for drawing the graphics in the preset graphics template library in the embodiments of the present application refer to all instructions for drawing an image.

After extracting the drawing key words from the voice drawing instruction sent by the user. According to the embodiment of the application, firstly, the graph matched with the extracted drawing keyword is determined from the preset graph template library, and then, all drawing operation instructions corresponding to the graph are read from the drawing operation instruction storage device to serve as the drawing operation instructions corresponding to the extracted drawing keyword.

And S103, executing the drawing operation instruction to draw the graph.

Specifically, the intelligent device can realize the drawing operation corresponding to the drawing operation instruction by executing the determined drawing operation instruction, and draw a corresponding graph.

For example, the smart device executes drawing operation instructions corresponding to three drawing keywords, i.e., a "newly created" drawing keyword, a "four-row three-column" drawing keyword, and a "table" drawing operation instruction, i.e., a table with four rows and three columns can be drawn.

For example, after the smart device generates a macro command according to the determined drawing operation instruction, the smart device executes the drawing operation instruction, and the drawing operation is implemented.

As can be seen from the above description, with the voice drawing method provided in the embodiment of the present application, when a voice drawing instruction sent by a plotter is acquired, a drawing keyword is extracted from the voice drawing instruction, then a drawing operation instruction corresponding to the drawing keyword is determined based on a text feature of the extracted drawing keyword, and finally, the purpose of drawing a graph is achieved by executing the drawing operation instruction. Above-mentioned processing procedure has realized automatic matching and the mapping between the drawing keyword in the pronunciation drawing instruction and the drawing operation instruction, through carrying out above-mentioned processing procedure, can draw according to the pronunciation drawing instruction that the plotter sent is automatic to can promote plotter drawing efficiency, and promote the drawing and experience.

As an optional implementation manner, the extracting of the drawing keyword from the voice drawing instruction includes:

firstly, voice recognition processing is carried out on a voice drawing command to obtain a drawing command text.

For example, before performing the speech recognition processing on the voice drawing command, the embodiment of the present application further performs preprocessing on the voice drawing command, including noise reduction processing, silence removal processing, and the like.

After the preprocessing, voice recognition processing is carried out on the voice drawing command, and text content corresponding to the voice drawing command is recognized to obtain a drawing command text.

Then, drawing keywords are extracted from the drawing instruction text.

Specifically, the keyword extraction processing related to the drawing operation is performed on the drawing instruction text, so that the drawing keyword can be extracted.

For example, the above-mentioned extracting of the drawing keyword from the drawing instruction text may be specifically realized by executing steps SS10 to SS 11:

and SS10, extracting drawing grammar structure from the drawing instruction text by analyzing grammar components of the drawing instruction text.

Wherein the drawing grammar structure is a grammar structure representing drawing operations.

Specifically, by performing the syntax element analysis processing on the drawing instruction text, each syntax element included in the drawing instruction text can be specified, and for example, syntax elements such as a subject, a predicate, an object, a fixed term, a subject, and a complement included in the drawing instruction text, and text contents corresponding to each syntax element can be specified.

For example, by performing the syntactic analysis processing on "a table having four rows and three columns is newly created", it is possible to determine that the predicate "new", the object "table", and the determinants "one", "four rows and three columns" are included therein.

And extracting a syntactic structure representing drawing operation from the drawing instruction text based on the syntactic component analysis result of the drawing instruction text to obtain the drawing syntactic structure.

The drawing syntax structure is a syntax structure formed by drawing-related syntax components. For example, after performing syntax element analysis processing on "a table with four rows and three columns is newly created" and a predicate "new", an object "table" and a fixed phrase "one", "four rows and three columns" included therein are determined, syntax elements related to drawing operation, such as "new", "four rows and three columns" and "table", are extracted from the syntax elements, and a drawing syntax structure "new/four rows and three columns/table" can be obtained.

In general, the drawing syntax structure is composed of a subject, a predicate, and an object, and in some cases, the drawing syntax structure may have no subject, a predicate, and the like.

As a preferred implementation manner, since the generation scenes of the voice drawing commands are different, and the meanings indicated by the voice drawing commands are different, the embodiment of the present application is executed in combination with the generation scenes of the voice drawing commands when performing the syntactic component analysis processing on the voice drawing commands.

For example, "i want to add a third phone" in the address book operation scene indicates that the user wants to store a third phone number in the address book; however, in the drawing operation scenario, "i want to add zhang san phone" may indicate that the user wants to create a phone graphic, which indicates zhang san phone; or, in the text input scenario, "i want to add three phones" may indicate that the user wants to add several text characters of "three phones".

It can be seen that when the scenes in which the drawing voice instructions are generated are different, the actual meaning of the representation of the drawing voice instructions is different. Therefore, the scene for generating the voice drawing instruction is referred to when the drawing instruction text corresponding to the voice drawing instruction is subjected to syntactic component analysis, so that the semantics of the drawing instruction text can be more accurately determined, and more accurate syntactic component analysis can be further realized.

On the other hand, when the scene in which the voice drawing instruction is generated is different, the type of drawing operation represented by the drawing instruction text corresponding to the voice drawing instruction may also be different.

Therefore, when the drawing grammar structure is extracted from each grammar component of the drawing instruction text, the embodiment of the application takes the grammar component of the drawing instruction text and the generation scene of the voice drawing instruction as the basis, and extracts the drawing grammar structure matched with the generation scene of the voice drawing instruction from the drawing instruction text.

The drawing grammar structure matched with the generation scene of the voice drawing instruction is a drawing grammar structure capable of representing drawing operation matched with the generation scene of the voice drawing instruction.

The drawing grammar structure extracted in the above way can be matched with a scene for generating the voice drawing instruction, and conforms to the drawing operation of a plotter in the scene.

SS11 extracts keywords of text contents corresponding to each grammar component of the drawing grammar structure as drawing keywords.

Specifically, for a drawing grammar structure extracted from a drawing instruction text, keywords of text contents corresponding to each grammar component of the drawing grammar structure are respectively extracted as drawing keywords.

The keywords of the text content corresponding to each grammar component may be the text content itself corresponding to the grammar component.

For example, assuming that the drawing grammar structure extracted from the drawing instruction text is "red line/drawing/red triangle", the keywords of each grammar component are extracted, and the drawing keywords "red line", "drawing", "triangle" can be obtained.

As an exemplary processing manner, referring to fig. 2, in an embodiment of the present application, after extracting a drawing keyword from a voice drawing instruction, step S202 is further executed to determine whether the extracted drawing keyword includes complete drawing operation information.

The complete drawing operation information at least comprises minimum information capable of representing a complete drawing operation.

Specifically, in the drawing operation, it is generally necessary to specify various parameter information such as a drawing position, a drawing line width, a line color, a line type, and a drawing size. However, in a user's single-sentence voice drawing instruction, all parameter information may not be completely contained. At this time, the drawing operation cannot be performed based on the user single-sentence voice drawing instruction.

Therefore, after extracting the drawing keyword from the obtained voice drawing instruction, the embodiment of the present application first determines whether the extracted drawing keyword includes complete drawing operation information, where the complete drawing operation information specifically includes the minimum information capable of representing a complete drawing operation.

The minimum information that can represent a complete drawing operation at a time is the most indispensable information that can represent a drawing operation at a time, and examples thereof include a drawing position, a size, and a shape.

If the drawing keyword extracted from the voice drawing instruction contains complete drawing operation information, step S204 may be directly performed to determine the drawing operation instruction corresponding to the drawing keyword based on the text feature of the drawing keyword.

If the drawing keyword extracted from the voice drawing instruction does not contain complete drawing operation information, step S203 is executed, the object sending the voice drawing instruction is interacted with, and the drawing keyword is extracted from the interaction data with the object until the extracted drawing keyword contains complete drawing operation information.

Specifically, when the drawing keyword extracted from the drawing voice instruction does not include complete drawing operation information, the object sends more voice drawing instructions by interacting with the object sending the voice drawing instruction, continuously extracts the drawing keyword from each voice drawing instruction sent by the object, and returns to step S202 to determine whether the extracted drawing keyword includes complete drawing operation information; if not, step S203 is executed again until a drawing keyword containing complete drawing operation information is extracted from the voice drawing commands issued by the object.

For example, if the plotter first issues a voice drawing instruction "draw a circle", the drawing keywords "draw" and "circle" may be extracted. However, it is not known where a circle with a large radius is drawn, and thus the drawing keyword in the voice drawing instruction does not contain complete drawing operation information.

At this time, the interactive information "please determine at what position to draw a circle" with the plotter is output.

Based on the interactive information, the plotter issues a voice plotting instruction 'the circle center is at the (1,1) position' for the second time.

At this time, according to the voice drawing instruction, the drawing keyword "the center of the circle is (1, 1)", that is, the position of the drawing circle is determined. But the size of the drawn circle cannot be determined.

At this time, the interactive information "how large the radius of the circle to be drawn is requested" with the plotter is output again.

The plotter sends out a voice plotting instruction 'radius is 3 cm' for the third time based on the interactive information.

At this time, according to the voice drawing instruction, the drawing keyword "radius 3 cm" may be determined.

At this time, the total of 4 drawing keywords "drawing", "circle center (1, 1)", "radius 3 cm" are extracted, and based on the 4 drawing keywords, the position and size of the circle can be made clear, that is, the complete drawing operation information for drawing one circle is made clear, and at this time, the step S204 may be continuously executed, that is, the subsequent drawing processing is performed.

The above-mentioned interactive process with the object sending the voice drawing instruction may be a text interactive process, a voice interactive process, or an interactive process combining text and voice.

Steps S201, S204, and S205 in the method embodiment shown in fig. 2 are respectively the same as steps S101, S102, and S103 in the method embodiment shown in fig. 1, and for details, please refer to the contents of the method embodiment shown in fig. 1, which is not repeated herein.

As an exemplary implementation manner, the above-mentioned determining whether the extracted drawing keyword includes complete drawing operation information may specifically be processed as follows:

firstly, according to the extracted drawing keywords, determining drawing contents corresponding to the voice drawing instruction.

Specifically, according to the extracted drawing keyword, at least the drawing content corresponding to the voice drawing instruction should be determined.

For example, assuming that the voice drawing instruction is "draw a circle", the drawing content corresponding to the voice drawing instruction may be determined to be "circle" based on the drawing keywords "draw" and "circle" extracted therefrom.

And then, judging whether the extracted drawing keywords contain complete drawing operation information for drawing the drawing content or not according to the extracted drawing keywords and the drawing content corresponding to the voice drawing instruction.

Specifically, according to the determined drawing content, drawing operation information required for drawing the drawing content can be determined, for example, when a circle needs to be drawn, the position of the center of the circle and the radius of the circle need to be known.

Therefore, based on the drawing content corresponding to the voice drawing instruction and the drawing keyword extracted from the voice drawing instruction, it can be determined whether the extracted drawing keyword includes complete drawing operation information for drawing the drawing content.

For example, it is assumed that the acquired voice drawing instruction is "draw a circle", and the drawing keywords extracted therefrom are "draw" and "circle", but drawing "circle" requires explicit drawing of the center position and the radius of the circle, but in the extracted drawing keywords, keywords representing the center position and the radius of the circle are obviously not included, and thus it can be determined that the extracted drawing keywords do not include complete drawing operation information for drawing the circle.

As an optional implementation manner, the determining, based on the text feature of the drawing keyword, a drawing operation instruction corresponding to the drawing keyword specifically includes:

Specifically, the embodiment of the present application trains a drawing instruction mapping model in advance, and is configured to determine, based on a correspondence between a drawing keyword and a drawing operation instruction, a drawing operation instruction corresponding to the drawing keyword.

The training process of the drawing instruction mapping model comprises the following steps:

a large amount of speech data is acquired, including the voice data of the plotter, as well as speech data within other scenes. And performing voice recognition and semantic analysis processing on the acquired voice data, extracting a drawing grammar structure and key words in the drawing grammar structure, inputting the key words in the grammar structure and drawing operation instructions corresponding to the key words into the constructed drawing instruction mapping model, and realizing repeated training of the model until the model can automatically output the drawing operation instructions corresponding to the input key words.

Specifically, in the training process, if the input keyword hits a known keyword, the drawing operation instruction corresponding to the known keyword is directly used as the drawing operation instruction corresponding to the input keyword. And increasing the matching weight between the keyword and the drawing operation instruction.

On the contrary, if the input keyword is an unknown keyword, the model cannot determine the drawing operation instruction corresponding to the keyword, at this time, the user needs to manually draw by other auxiliary tools, and correspondingly, the model records the drawing action of the user, especially records each drawing operation instruction triggered in the drawing process of the user, so as to determine the drawing operation instruction corresponding to the keyword.

It should be noted that, in the training process, when the drawing keyword included in the voice drawing instruction issued by the user does not include complete drawing operation information, the user interacts with the voice drawing instruction, and extracts the drawing keyword from the interactive content until the extracted drawing keyword includes complete drawing operation information. Then training and identifying the corresponding relation between the drawing keywords containing the complete drawing operation information and the drawing operation instruction.

Further, as a preferred implementation manner, referring to fig. 3, in the embodiment of the present application, before extracting the drawing keyword from the voice drawing instruction, step S301 is first executed to predict and present the drawing content of the current drawing operation according to the historical drawing operation.

Specifically, the history drawing operation refers to a drawing operation performed by a current drawer before the current drawing operation.

It is understood that for a plotter, there may be interrelationships between the various drawing operations during a certain drawing process, or during a past drawing process.

For example, if a user is drawing a flowchart, after the user finishes drawing a flow box last time, the user is likely to draw another flow box in the drawing, and therefore, it is expected that the flow box is the drawing content of the drawing operation this time.

In the user drawing process, if the drawing content of the drawing operation can be automatically predicted and prompted according to the historical drawing operation of the user, the drawing operation of the user can be further simplified, and the user experience is improved.

For the above purpose, the embodiment of the present application sets that feature information of a user is recorded, and a historical drawing operation of the user is recorded, so as to predict a current drawing operation of the user.

Before extracting the drawing keywords from the voice drawing instruction, particularly before the user sends the voice drawing instruction at this time, identifying the identity information of the user, predicting the drawing content of the user at this time of drawing operation according to the historical drawing operation of the user, and prompting the predicted drawing content to the user. For example, the predicted drawing content may be prompted by a pop-up box or by voice broadcast.

After the drawing content of the current drawing operation is predicted and prompted, step S302 is executed to determine whether a preset drawing operation confirmation condition is met, where the condition may be exemplarily set that a voice drawing instruction is not received within a set time period after the drawing content of the current drawing operation is prompted, that is, the user does not correct the drawing content within the set time period after the drawing content of the current drawing operation is prompted, and then step S303 is executed to draw the prompted drawing content.

In contrast, if the preset drawing operation confirmation condition is not satisfied, for example, a voice drawing instruction is received within a set time length after the drawing content of the current drawing operation is prompted, step S304 is performed, a drawing keyword is extracted from the voice drawing instruction, and the processing of the subsequent steps S305 and S306 is performed.

It can be understood that the above-described processing implements automatic prediction of drawing contents, and a mechanism for drawing the predicted drawing contents is provided. In the user drawing process, the next drawing content of the user can be predicted in advance according to the drawing operation of the user, so that the drawing operation of the user is assisted, and the drawing efficiency is further improved.

The above steps S304 to S306 correspond to steps S101 to S103 in the method embodiment shown in fig. 1, and for details, please refer to the contents of the method embodiment shown in fig. 1, which is not described herein again.

For example, the predicting and prompting the drawing content of the current drawing operation according to the historical drawing operation includes:

first, according to the historical drawing operation, the user drawing habit information is determined.

Specifically, by summarizing the historical drawing operations of the user, the drawing habit information of the user, such as the drawing sequence of the habit of the user, the commonly used legend of the user, the biased font size and font style of the user, can be determined.

And then, predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user and the drawing content of the previous drawing operation.

Specifically, according to the drawing content of the previous drawing operation of the user, the drawing content of the current drawing operation of the user can be predicted, meanwhile, the specific form of the current drawing content of the user, such as the drawing position, the drawing color, the drawing font size, the drawing font and the like, can be determined by combining the information, and the drawing content of the current drawing operation can be determined.

As an optional implementation manner, the predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user and the drawing content of the previous drawing operation includes:

Specifically, in the embodiment of the present application, the user drawing habit information, the similarity between the category and/or name of the drawing content of the current drawing operation and the category and/or name of the drawing content of the previous drawing operation, and the relationship between the drawing content of the current drawing operation and the drawing content of the previous drawing operation are used together to predict the drawing content of the current drawing operation.

The relationship between the drawing content of the current drawing operation and the drawing content of the previous drawing operation may be a mutual relationship between the two drawing contents in the same organizational structure model.

The user drawing habit information comprises information such as drawing direction habit, legend selection habit, character size selection habit, drawing frequency and deviation and the like of user drawing. According to the drawing habit information of the user, the drawing content of the current drawing operation of the user can be predicted.

When the category and/or name of the drawing content of the previous drawing operation is known, the contents drawn by the current drawing operation may also have the same or similar category and/or name. For example, a member one under a company-level development group drawn according to the previous drawing operation may predict that the user may create a member two in the current drawing and the attribute of the member two is similar to that of the member one. Alternatively, the prediction may be performed according to which domain the drawing model selected by the user belongs to, which elements may be included, which elements already exist, which elements may be needed later, and the like. For example, in the internal job level relationship model of the company, when the board is drawn by the previous drawing operation, it is determined that the graph drawn by the user belongs to the field of the organization architecture of the company, and when the board is drawn by the previous drawing operation, the drawing may be performed by a manager belonging to the board.

The relationship between the drawing content of the current drawing operation and the drawing content of the previous drawing operation is generally a mutual relationship when the two drawing contents are in the same organizational structure model. According to the previous drawing content, the organizational structure model to which the graph drawn by the user belongs can be determined, in a certain determined organizational structure model, each drawing content is respectively used as each element in the organizational structure model, and the interrelation among the elements is determined by the organizational structure model. Therefore, based on the organizational structure model, the drawing content having a direct correlation with the previous drawing content can be determined, and the drawing content can be used as the prediction of the current drawing content.

In the embodiment of the present application, the three prediction directions are combined with each other and used together for predicting the drawing content of the current drawing operation.

As an exemplary implementation manner, the prediction process of each prediction direction may be implemented by a corresponding prediction model. The three prediction models with different prediction directions can be fused with each other to form a prediction model.

Optionally, the embodiment of the present application further provides that, before the voice drawing instruction is obtained, a preset legend template is output and/or drawing guidance information is output.

The preset legend template refers to a legend template matched with a plotter, such as a common legend template for the plotter, a legend template used by the plotter for the last drawing, and the like.

The drawing guidance information includes information for guiding the plotter to perform voice drawing, and the information may be output in a text form or a voice broadcast form.

In the embodiment of the application, when the plotter starts the drawing, the identity of the plotter is firstly identified, for example, when the plotter starts the drawing software, the identity of the plotter is determined by using a plotter login account number, plotter identification information and the like; or when the plotter talks for the first time, acquiring the voiceprint information of the plotter, and determining the identity of the plotter based on the voiceprint information.

The embodiment of the application corresponds to each plotter, records the historical plotting operation process of each plotter, and accordingly determines the type of the graph frequently drawn by the plotter. Based on the data accumulation, when the plotter performs the plotting, at the beginning of the plotting, the identity information of the plotter is firstly identified, and then the legend template which is often drawn by the plotter is output according to the identity information of the plotter, so that the plotter can quickly select the legend template.

For example, assuming that the user is recognized as a corporate administrator who often needs to draw a corporate personnel organization architecture diagram for corporate personnel management before the user formally speaks a voice drawing instruction, an organization architecture legend template may be output at this time to facilitate the user in drawing the corporate personnel organization architecture diagram.

On the other hand, when the plotter starts drawing, the plotter may output drawing guidance information, such as: you can say "create/create (one) organizational structure diagram/basic flow diagram/dataflow diagram … …" this way to guide the plotter through voice plotting.

For the plotter who performs voice plotting for the first time, the output of the guide information can enable the plotter to adapt to the voice plotting scene quickly, so that the voice plotting efficiency is improved.

Further, the embodiment of the application further provides that in a voice drawing scene, the intelligent device collects voice drawing instructions of a drawer in real time, then, drawing keywords are extracted from the collected voice drawing instructions, and a user determines drawing operation instructions.

In some cases, the sound source of a voice mapping scene is more, for example, in a conference scene, a speaker may need to map while explaining. Under normal conditions, the intelligent device for assisting the speaker to explain should collect the voice drawing instruction sent by the speaker, and execute drawing operation based on the collected voice drawing instruction.

However, sometimes there are more speakers in the meeting place, for example, in a conference scene, there is a speaker, and other people can participate in the discussion. At this moment, the intelligent device can gather the pronunciation of a plurality of users, if the intelligent device all carries out corresponding drawing operation to all voices of gathering, then can lead to drawing content confusion.

In order to make the drawing more orderly, the embodiment of the application sets that when the intelligent device collects voice data, a voice drawing instruction sent by a target user is identified from the collected voice data, and then drawing operation is executed based on the voice instruction.

For example, assuming that the user a is a user operating the smart device, that is, the user a is a speaker, when the voice data collected by the smart device is received, a voice drawing instruction issued by the user a is identified from the received voice data for a subsequent voice drawing operation.

To more vividly describe the processing procedure of the voice drawing method proposed in the embodiment of the present application, the following describes the user voice drawing processing procedure by taking the user voice drawing as an example of the organization architecture diagram shown in fig. 4.

In the initialization stage, no user voice operation instruction is received, and at this time, a common graphic sample template is output, such as: an organizational architecture diagram, a basic flow diagram, a dataflow diagram, etc. And prompts the user to draw using voice operations. For example, the output prompt: you can say, "create a graph" and "create a graph".

The user: i want to create an organizational architecture diagram for the company.

The creation in the statement is a specific operation, and a new file operation is triggered; the "organization architecture diagram" is a definition of a file to be created, and also provides a graphic template for a flow chart in a subsequent perfecting file, for example, the job description adopts a circular representation in fig. 4, connecting lines adopt directional arrows, the architecture diagram is drawn from top to bottom, the whole graph is in the middle, and the like.

The user: a board of directors is added.

The "add" in this statement is an action that triggers an operation to create a legend (the choice of this legend is determined to be the set of legends in the organizational architecture diagram, based on the above reference being "organizational architecture diagram"), with the keyword "board" centered as the name default location for the legend.

The user: one general manager is added.

The 'adding' in the statement is an action, the operation of creating a legend is triggered, the graph is in a hierarchical relationship according to the selected organizational structure model, the director is newly added above, the condition can predict that the adding can be the master manager, and the keyword contains the 'master manager', so the master manager position under the director is confirmed as the name of the legend, the legend is placed under the director, the legend is connected by a directed arrow, and finally the overall graph format is adjusted to be in central alignment. The automatic prediction is prompted to wait for the confirmation of the user, the user can confirm by default after time out, and the user can carry out auxiliary selection and confirmation operations through other external equipment such as a mouse and the like in the period.

The user: a financial department, a personnel administration department, a market sales department and a technical department are added under a general manager

In this statement, "general manager" is the above, under which is added an execution condition, which means that the following legend is added under the general manager and adds an operation for the same level. The number of legends newly created at this time is not specified in the sentence, so the "finance department", "personnel administration department", "marketing department" and "technical department" are all listed as sub-examples to be added here. The financial department, the personnel administration department, the marketing department and the technical department are uniformly and dispersedly added under a general manager and connected by directional arrows, so that the organization architecture diagram shown in fig. 4 can be obtained.

Further, when the user continues to speak the voice drawing command, the legend content may be further added to the drawn tissue architecture diagram by referring to the above processing procedure.

Corresponding to the above-mentioned voice drawing method, an embodiment of the present application further provides a voice drawing device, as shown in fig. 5, the device includes:

a keyword extraction unit 100, configured to extract a drawing keyword from the voice drawing instruction, where the drawing keyword is a word describing a drawing operation;

an instruction determining unit 110, configured to determine, based on a text feature of the drawing keyword, a drawing operation instruction corresponding to the drawing keyword;

the instruction execution unit 120 is configured to execute the drawing operation instruction to draw a graphic.

By adopting the voice drawing device provided by the embodiment of the application, when the voice drawing instruction sent by a plotter is collected, the drawing key words are extracted from the voice drawing instruction, then the drawing operation instruction corresponding to the drawing key words is determined based on the text features of the extracted drawing key words, and finally the purpose of drawing the graph is realized by executing the drawing operation instruction. Above-mentioned processing procedure has realized automatic matching and the mapping between the drawing keyword in the pronunciation drawing instruction and the drawing operation instruction, through carrying out above-mentioned processing procedure, can draw according to the pronunciation drawing instruction that the plotter sent is automatic to can promote plotter drawing efficiency, and promote the drawing and experience.

Furthermore, the voice drawing device can determine a drawing operation instruction used for drawing a preset graph template library and a graph matched with the drawing keyword according to the drawing keyword in the voice drawing instruction, execute the drawing operation instruction, and rapidly draw the graph required to be drawn by the user, for example, a graph frame, a graph main body structure and the like can be further drawn based on one voice drawing instruction of the user, so that the drawing efficiency of the user can be greatly improved.

As an optional implementation manner, the extracting a drawing keyword from the voice drawing instruction includes:

and extracting drawing keywords from the drawing instruction text.

As an optional implementation manner, the extracting a drawing keyword from the drawing instruction text includes:

As an optional implementation manner, the extracting, by performing syntactic component analysis processing on the drawing instruction text, a drawing syntactic structure from the drawing instruction text includes:

As an optional implementation manner, the apparatus further includes:

the interactive processing unit is used for judging whether the extracted drawing keywords contain complete drawing operation information or not; the complete drawing operation information at least comprises minimum information capable of representing one complete drawing operation;

As an optional implementation manner, the determining whether the extracted drawing keyword includes complete drawing operation information includes:

As an optional implementation manner, the determining, based on the text feature of the drawing keyword, a drawing operation instruction corresponding to the drawing keyword includes:

As an optional implementation manner, the apparatus further includes:

the prediction drawing unit is used for predicting and prompting the drawing content of the current drawing operation according to the historical drawing operation before the drawing key words are extracted from the voice drawing instruction;

As an optional implementation manner, the predicting and prompting the drawing content of the current drawing operation according to the historical drawing operation includes:

As an optional implementation manner, the apparatus further includes:

and the information output unit is used for outputting a preset legend template and/or outputting drawing guide information.

As an optional implementation manner, the apparatus further includes:

and the instruction identification unit is used for identifying a voice drawing instruction sent by the target user from the collected voice data.

Specifically, please refer to the contents of the above method embodiments for the specific working contents of each unit of the voice drawing apparatus, which are not described herein again.

Another embodiment of the present application further provides a voice drawing device, as shown in fig. 6, the device including:

a memory 200 and a processor 210;

wherein, the memory 200 is connected to the processor 210 for storing programs;

the processor 210 is configured to implement the voice mapping method disclosed in any of the above embodiments by running the program stored in the memory 200.

Specifically, the evaluation device for the target detection result may further include: a bus, a communication interface 220, an input device 230, and an output device 240.

The processor 210, the memory 200, the communication interface 220, the input device 230, and the output device 240 are connected to each other through a bus. Wherein:

a bus may include a path that transfers information between components of a computer system.

The processor 210 may be a general-purpose processor, such as a general-purpose Central Processing Unit (CPU), microprocessor, etc., an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs in accordance with the present invention. But may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

The processor 210 may include a main processor and may also include a baseband chip, modem, and the like.

The memory 200 stores programs for executing the technical solution of the present invention, and may also store an operating system and other key services. In particular, the program may include program code including computer operating instructions. More specifically, memory 200 may include a read-only memory (ROM), other types of static storage devices that may store static information and instructions, a Random Access Memory (RAM), other types of dynamic storage devices that may store information and instructions, a disk storage, a flash, and so forth.

The input device 230 may include a means for receiving data and information input by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor, among others.

Output device 240 may include equipment that allows output of information to a user, such as a display screen, a printer, speakers, and the like.

Communication interface 220 may include any device that uses any transceiver or the like to communicate with other devices or communication networks, such as an ethernet network, a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), etc.

The processor 2102 executes programs stored in the memory 200 and invokes other devices that may be used to implement the steps of the voice mapping method provided by the embodiments of the present application.

Another embodiment of the present application further provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is executed by a processor, the computer program implements the steps of the voice mapping method provided in any of the above embodiments.

The detailed operation contents of the above parts of the voice drawing device and the detailed processing contents of the computer program in the above storage medium when being executed by the processor can be referred to the contents of the above method embodiments of the present application, and are not repeated here.

While, for purposes of simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present application is not limited by the order of acts or acts described, as some steps may occur in other orders or concurrently with other steps in accordance with the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The steps in the method of each embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and technical features described in each embodiment may be replaced or combined.

The modules and sub-modules in the device and the terminal in the embodiments of the application can be combined, divided and deleted according to actual needs.

In the several embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described terminal embodiments are merely illustrative, and for example, the division of a module or a sub-module is only one logical division, and there may be other divisions when the terminal is actually implemented, for example, a plurality of sub-modules or modules may be combined or integrated into another module, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

The modules or sub-modules described as separate parts may or may not be physically separate, and parts that are modules or sub-modules may or may not be physical modules or sub-modules, may be located in one place, or may be distributed over a plurality of network modules or sub-modules. Some or all of the modules or sub-modules can be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, each functional module or sub-module in the embodiments of the present application may be integrated into one processing module, or each module or sub-module may exist alone physically, or two or more modules or sub-modules may be integrated into one module. The integrated modules or sub-modules may be implemented in the form of hardware, or may be implemented in the form of software functional modules or sub-modules.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software cells may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A voice mapping method, comprising:

and executing the drawing operation instruction to draw the graph.

2. The method of claim 1, wherein extracting the drawing keyword from the voice drawing instruction comprises:

3. The method according to claim 2, wherein the extracting a drawing grammar structure from the drawing instruction text by performing syntactic component analysis processing on the drawing instruction text comprises:

4. The method of claim 1, wherein after extracting the drawing keywords from the voice drawing instruction, the method further comprises:

5. The method according to claim 4, wherein the determining whether the extracted drawing keyword includes complete drawing operation information comprises:

6. The method according to claim 1, wherein the determining, based on the text feature of the drawing keyword, a drawing operation instruction corresponding to the drawing keyword comprises:

7. The method of claim 1, further comprising:

before drawing keywords are extracted from the voice drawing instruction, determining drawing habit information of a user according to historical drawing operation;

predicting and prompting the drawing content of the current drawing operation according to the drawing habit information of the user and the drawing content of the previous drawing operation;

8. The method according to claim 7, wherein predicting and prompting the drawing content of the current drawing operation according to the user drawing habit information and the drawing content of the previous drawing operation comprises:

9. The method of claim 1, wherein prior to obtaining the voice mapping instruction, the method further comprises:

10. A voice drawing device, comprising:

11. A voice mapping device, comprising:

a memory and a processor;

the processor is configured to implement the voice drawing method according to any one of claims 1 to 9 by executing the program in the memory.

12. A storage medium having stored thereon a computer program which, when executed by a processor, implements a voice mapping method as claimed in any one of claims 1 to 9.