Handwriting input method and system of electronic whiteboard, readable storage medium and computer

Abstract

The invention provides a handwriting input method and system of an electronic whiteboard, a readable storage medium and a computer, the method comprises the following steps: when the electronic whiteboard is in a writing mode, carrying out region identification on a handwriting region at preset time intervals to obtain corresponding to-be-identified data; constructing a feature extraction model, performing text recognition on the to-be-recognized data, and inputting a text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; performing data type judgment on the feature data, calling a corresponding identification strategy according to a judgment result, and performing data identification on the feature data by using the identification strategy to obtain a corresponding identification result; and performing binary conversion on the recognition result, and performing data storage on the binary conversion result. According to the invention, rapid data identification is realized by using different data types, so that the overall identification precision is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic whiteboards, and particularly relates to a handwriting input method, system, readable storage medium and computer for an electronic whiteboard. Background Art

[0002] With the rapid development of technology and the accelerating update of artificial intelligence, the level of the education industry is also constantly improving. As an emerging product in the education industry, the electronic whiteboard is a digital teaching demonstration device that replaces traditional blackboards and chalks. The electronic whiteboard can be completely separated from the mouse and keyboard, and use fingers or a specific pen to perform operations such as editing, annotating and saving computer files on the electronic whiteboard, thus bringing great convenience to users.

[0003] When teachers use the electronic whiteboard for teaching, they will display teaching-related content on the whiteboard, including function expressions, chemical equations, texts, charts and other relevant information. The current handwriting input method usually identifies symbols, functions and equations based on single characters and probability distribution strategies. However, this method is based on the general mode of machine learning, and there are certain differences in the processing of some specific characters and semantics, thus affecting the recognition efficiency and working efficiency of the electronic whiteboard for users' handwriting input. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a handwriting input method, system, readable storage medium and computer for an electronic whiteboard to at least solve the above-mentioned technical deficiencies.

[0005] The present invention provides a handwriting input method for an electronic whiteboard, including: When the electronic whiteboard is in the writing mode, perform area recognition on the handwriting area at preset time intervals to obtain corresponding data to be recognized; Construct a feature extraction model, perform text recognition on the data to be recognized, and input the text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; Judge the data type of the feature data, then call the corresponding recognition strategy according to the judgment result, and use the recognition strategy to perform data recognition on the feature data to obtain corresponding recognition results; Perform binary conversion on the recognition result and store the binary conversion result.

[0006] Further, the step of performing area recognition on the handwriting area at preset time intervals to obtain corresponding data to be recognized when the electronic whiteboard is in the writing mode includes: Perform two-dimensional coordinate transformation on the handwritten area to obtain two-dimensional coordinate information of the handwritten area; Set a scale ratio based on the two-dimensional coordinate information and area size of the handwritten area, and sample in the handwritten area in pixels to obtain corresponding data to be recognized.

[0007] Furthermore, the steps of constructing a feature extraction model include: Obtain the historical database of the electronic whiteboard and determine the data types of all input data in the historical database; Construct corresponding feature extraction strategies according to the data types of all input data in the historical database, and construct a feature extraction model according to the feature extraction strategies and each input data.

[0008] Furthermore, the steps of judging the data type of the feature data, then calling the corresponding recognition strategy according to the judgment result, and using the recognition strategy to perform data recognition on the feature data to obtain the corresponding recognition result include: If the data type of the feature data is a function equation type, obtain the corresponding first recognition strategy from a preset recognition strategy library based on the function equation; If the data type is a chemical equation type, obtain the corresponding second recognition strategy from a preset recognition strategy library based on the chemical equation type; Perform data recognition on the feature data according to the first recognition strategy and / or the second recognition strategy to obtain the corresponding recognition result.

[0009] The present invention also proposes a handwritten input system for an electronic whiteboard, including: An area recognition module, configured to perform area recognition on the handwritten area at preset intervals when the electronic whiteboard is in the writing mode to obtain corresponding data to be recognized; A model construction module, configured to construct a feature extraction model, perform text recognition on the data to be recognized, and input the text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; A data recognition module, configured to judge the data type of the feature data, then call the corresponding recognition strategy according to the judgment result, and use the recognition strategy to perform data recognition on the feature data to obtain the corresponding recognition result; A data storage module, configured to perform binary conversion on the recognition result and store the binary conversion result.

[0010] Furthermore, the area recognition module includes: A coordinate conversion unit for performing two-dimensional coordinate conversion on the handwriting area to obtain two-dimensional coordinate information of the handwriting area; A data sampling unit for setting a scale ratio based on the two-dimensional coordinate information and the area size of the handwriting area, and sampling in the handwriting area in pixels to obtain corresponding data to be recognized.

[0011] Furthermore, the model construction module includes: A type judgment unit for obtaining the historical database of the electronic whiteboard and judging the data types of all input data in the historical database; A model construction unit for constructing a corresponding feature extraction strategy according to the data types of all input data in the historical database, and constructing a feature extraction model according to the feature extraction strategy and each input data.

[0012] Furthermore, the data recognition module includes: A first strategy acquisition unit for, if the data type of the feature data is a function equation type, acquiring a corresponding first recognition strategy from a preset recognition strategy library based on the function equation; A second strategy acquisition unit for, if the data type is a chemical equation type, acquiring a corresponding second recognition strategy from a preset recognition strategy library based on the chemical equation type; A data recognition unit for performing data recognition on the feature data according to the first recognition strategy and / or the second recognition strategy to obtain a corresponding recognition result.

[0013] The present invention also proposes a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the handwriting input method of the above-mentioned electronic whiteboard is realized.

[0014] The present invention also proposes a computer, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the handwriting input method of the above-mentioned electronic whiteboard is realized.

[0015] The handwriting input method, system, readable storage medium and computer of the electronic whiteboard in the present invention obtain data to be recognized by real-time recognition of the area of the electronic whiteboard, extract features from the text recognition result of the data to be recognized by using the constructed feature extraction model, make a judgment based on the type of the extracted feature data, call the corresponding recognition strategy by using the type of the feature data, and then perform data recognition on the feature data through the recognition strategy. The writing content is segmented by the method of detecting and then recognizing line features, the writing content is quickly recognized by using a small amount of recognition information, and the data is quickly recognized by using different data types, thereby improving the overall recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the handwriting input method of the electronic whiteboard in the first embodiment of the present invention; Figure 2 is Figure 1 a detailed flowchart of step S101 in Figure 3 is Figure 1 a detailed flowchart of step S102 in Figure 4 is Figure 1 a detailed flowchart of step S103 in Figure 5 It is a schematic diagram of the geometric description of the line in the first embodiment of the present invention; Figure 6 It is a schematic diagram of the sub-segment feature of the line and the position feature relative to the stroke in the first embodiment of the present invention; Figure 7 It is a recognition result diagram of the chemical equation in the first embodiment of the present invention; Figure 8 It is a schematic diagram of the display of the associative search information of the chemical equation in the first embodiment of the present invention; Figure 9 It is a schematic diagram of the function visualization expression in the first embodiment of the present invention; Figure 10 It is a structural block diagram of the handwriting input system of the electronic whiteboard in the second embodiment of the present invention; Figure 11 It is a structural block diagram of the computer in the third embodiment of the present invention.

[0017] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0018] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0020] Embodiment 1 Please refer to Figure 1 , which shows the handwriting input method of the electronic whiteboard in the first embodiment of the present invention. The method specifically includes steps S101 to S104: S101, when the electronic whiteboard is in the writing mode, the handwriting area is recognized at preset intervals to obtain corresponding data to be recognized; Further, please refer to Figure 2 , the step S101 specifically includes steps S1011~S1012: S1011, perform two-dimensional coordinate conversion on the handwriting area to obtain two-dimensional coordinate information of the handwriting area; S1012, set a scale ratio based on the two-dimensional coordinate information and the area size of the handwriting area, and sample in the handwriting area in pixels to obtain corresponding data to be recognized.

[0021] In specific implementation, the user activates the writing mode in the electronic whiteboard. Among them, the writing model includes but is not limited to subject tools, and the subject tools include functions such as chemical equations and function equations. In the writing mode, the user writes corresponding content on the panel of the electronic whiteboard. The panel area is recognized every 500 ms. When the content written by the user is a function equation, the display and editing module set in the electronic whiteboard is divided into two parts: function expression display input and real-time function equation drawing display. Among them, the function equation expression display input area is the first part, which provides three input methods: handwriting, keyboard, and soft keyboard direct input, and can display and edit the function equation expression. The function drawing display control area is the second part, which is the real-time display of the function, and operations such as zooming and panning of the screen can be performed, as well as dynamic rendering and intersection display of multiple function curves. The two-dimensional Cartesian coordinate transformation is performed on this area, and the scale ratio is set according to the screen size, and sampling is performed in pixels within the display screen size range. The connection of the sample points is the required real function visualization sample line, which improves the rendering speed of the function curve. At the same time, for periodic functions and composite periodic functions, inflection points and extreme points are sampled; for functions with special discontinuous points and infinite discontinuity points, two-way sampling is performed within the pixel scale range to prevent the loss of feature points within the visible range due to the reduction of the function bitmap. The intersection point is displayed when the user clicks on a certain function and intersects with other function equations. First, it is judged whether the two line segments intersect. If they intersect, the numerical bisection method is used to solve and obtain it.

[0022] When the content written by the user is a chemical equation, the display and editing module in the electronic whiteboard is for the user interface visualization display and interaction with the keyboard and soft keyboard, including the following three parts: a) The handwriting area / direct input area is used for the interface, keyboard, and soft keyboard interaction of the user's writing; b) The color switching area is used for the user to display the color of the chemical equation according to their own preferences; this module provides an HSI color model and can perform disk color selection; c) The recognition and direct input result display area refers to the formatted display of the chemical equation, such as the relationship between superscripts and subscripts and the specified color.

[0023] Abstract character feature preparation, special character detection (numbers, letters, chemical symbols), handwriting data segmentation, Chinese character recognition, and special character scenario mode matching are performed on the handwriting area to achieve semantic division and semantic recognition of the handwriting area.

[0024] S102, construct a feature extraction model, perform text recognition on the data to be recognized, and input the text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; Further, please refer to Figure 3, the step S102 specifically includes steps S1021 to S1022: S1021, obtain the historical database of the electronic whiteboard, and judge the data types of all input data in the historical database; S1022, construct corresponding feature extraction strategies according to the data types of all input data in the historical database, and construct a feature extraction model according to the feature extraction strategies and each input data.

[0025] In specific implementation, obtain the historical data of the electronic whiteboard, and judge the data types of all input data in the historical database. Among them, the data types of the input data include chemical equation type, function equation type, and text type, etc. Construct corresponding feature extraction strategies for different data types, and use the constructed feature extraction strategies to process the above-mentioned input data to construct a corresponding feature extraction model.

[0026] Furthermore, use the feature extraction model to extract features from the text recognition result of the above-mentioned data to be recognized to obtain the feature data corresponding to the data to be recognized. Among them, different feature data correspond to different data types.

[0027] S103, judge the data type of the feature data, then call the corresponding recognition strategy according to the judgment result, and use the recognition strategy to perform data recognition on the feature data to obtain the corresponding recognition result; Furthermore, please refer to Figure 4 , the step S103 specifically includes steps S1031 to S1033: S1031, if the data type of the feature data is function equation type, obtain the corresponding first recognition strategy from the preset recognition strategy library based on the function equation; S1032, if the data type is chemical equation type, obtain the corresponding second recognition strategy from the preset recognition strategy library based on the chemical equation type; S1033, perform data recognition on the feature data according to the first recognition strategy and / or the second recognition strategy to obtain the corresponding recognition result.

[0028] In specific implementation, the data type of the feature data is judged, and the corresponding recognition strategy is called according to the judgment result. Among them, if the data type of the feature data is the function equation type, the corresponding first recognition strategy is obtained from the preset recognition strategy library based on the function equation. Specifically, since the characters involved in the function equation are very few and very simple, all the characters related to the function equation are first classified: characters that can obtain the recognition result with one stroke; characters that can obtain the recognition result with two or three strokes; similar characters. Thus, the following five steps are generated in this module: a) The one-stroke-one-recognition means that whenever the system collects a writing stroke of the user, the recognition module is called to perform initial recognition and feature extraction. Among them, characters such as "2, 3, 6, 7, 8, 9" are clear results. To improve the recognition accuracy, the initial recognition feature extraction of the pen can be combined with the Microsoft engine System.Windows.Ink, and the line sub-segment features are directly extracted according to the collected writing point positions, and the line features and the rectangular area formed by the lines are formed. This area is used to distinguish the upper and lower subscripts and recognize the nested functions such as exponents and logarithms to form complex functions. This feature is used for the decision-making and secondary recognition of multiple lines. In this way, the overall recognition efficiency of the function is improved, and the real-time performance of the recognition is increased.

[0029] b) The two-stroke and three-stroke verification and detection is a strategy that is only executed when the system calls the overall recognition. The purpose is to perform the initial feature integration decision on the lines with unclear character features. For example, some mathematical symbols such as Π, square root, x, i, ÷, +, etc. may require multiple strokes to form, and the initial features of consecutive strokes need to be integrated and decided. For example, when a stroke with the feature of "." is detected, the stroke features within the range of two adjacent strokes need to be detected to judge "i" and "÷". The same principle can be used for the initial feature joint judgment of Π, and the initial feature joint judgment can be performed for "+", square root, "4", "5", "t", etc. adjacent to one stroke, so as to achieve the effect of secondary recognition. This way of combining feature judgment and recognition also increases the recognition efficiency and prepares for the overall segmentation at the character level.

[0030] c) The operation symbol and function combination symbol check is to perform semantic block decision recognition on multi-character basic sub-functions (sin, cos, log, ln, tan, ctan, etc.). The main purpose of this strategy is to distinguish similar characters, such as {"l", "|", "1"}, {"0", "o", "O"}, {"(", "C"}, {"9", "g"}, etc. At the same time, it is also a secondary fuzzy matching. As long as multiple of these characters are clear, the type of mathematical symbol can be determined, which improves the recognition accuracy. Integrating these pen data forms a function recognition block unit.

[0031] d) The nested recombination of the said characters and combinatorial mathematical symbols is to perform a tree-like arrangement of the recognition result data of basic sub-functions such as square roots, absolute values, paired parentheses, triangles, fractions, exponents, logarithms, etc. by using positional relationships and nested relationships. It mainly has three steps: First, sort the rectangular intervals occupied by the recognition results (characters, combined stroke characters, and function character blocks) in the order from left to right and from top to bottom to obtain the initial recognition result blocks; Second, check special characters in sequence, including √ (square root), semicolons, exponents, and perform nested collection in the inside-out, up-down, and upper-left directions respectively; Third, further determine the situation of log symbols with subscripts and superscripts; Fourth, perform parentheses pairing for all basic sub-functions (sin, cos, log, ln, tan, ctan).

[0032] e) The decision of similar characters mentioned above refers to making a judgment in a scenario for those characters with similar writings such as 1, l, |, x, ✖ that are difficult to distinguish, so as to obtain the final recognition result. The steps for distinguishing "1, l, |" are as follows: First, perform parentheses pairing; Second, perform absolute value pairing; Third, confirm the number "1"; The distinction between "x" and "✖" is made by judging whether the adjacent recognized characters are arithmetic operation symbols, and then the final recognition result is obtained.

[0033] If the data type is a chemical equation type, then obtain the corresponding second recognition strategy from the preset recognition strategy library based on the chemical equation type. Specifically, first detect single-stroke characters, then detect multi-stroke characters within the character height range, and finally form character data from the associated writing stroke data to complete the segmentation. The more characters are detected, the more the segmentation conforms to the real result; Chemical equations are composed of numbers, letters, chemical symbols, and a small number of Chinese characters. The first three items can all be detected, and the remaining Chinese characters are processed separately: a) The abstract character features mentioned above refer to that each character has multiple conventional writings and can be considered as composed of one or more lines (strokes). Each line can be described geometrically in an abstract way. Referring to Figure 5 as shown, the sub-segment features of the line and the positional features relative to the stroke can be obtained (the 9-grid description of the upper-middle-lower and left-middle-right is as Figure 6 shown), and the overall features of the line are abstracted, such as vertical, horizontal, clockwise bending, counterclockwise bending, circle, closure, and the positions of the starting point, ending point, and key inflection points, etc. These features are also the basic elements of the geometric graphic description of chemical equation characters. Summarize and generalize them to obtain standard and abstract character feature data for detection and recognition. For example, for "9", there is a circle on it, and the end (ending) of the circle is a vertical stroke, a left-falling stroke, or a clockwise bend. As long as these geometric feature descriptions are detected and the character can be determined, among which 1, 2, 3, z, etc. may be the strokes of running script Chinese characters and need to be further confirmed according to the positional relationship of the strokes.

[0034] b) The detection of numbers, letters, and symbols is carried out in two steps: single-stroke detection and associated multi-stroke detection. The system will collect the data written by the user in real time, extract sub-segment features for each stroke, organize, filter, and process them to form line data, generating composite features and positional relationships, and conduct a single-stroke detection once to mark the recognition results. When receiving the instruction for segmented recognition, this module will conduct a second multi-stroke detection within the character height range of adjacent strokes. In this process, characters written with multiple strokes such as 4, 5, H, A, =, +, etc. can be detected.

[0035] c) The segmentation and Chinese character recognition refer to the Chinese character recognition after segmentation. The specific steps are as follows: First, combine all the stroke detection results, and based on the characteristics of the line relationships such as intersection, left and right adjacency, separation, and up and down correlation between their lines, conduct block division, grouping, and segmentation in terms of time sequence within the character height range to form the final character segmentation data. The initial character height is determined according to the maximum height of the strokes and the combined strokes of intersections. When the distance between lines is greater than the character height / 3, it is considered separated, and the same applies to block division and segmentation. Second, after segmentation, judge the subscripts and superscripts of non-Chinese characters. The judgment basis is to determine whether the next character is a subscript or superscript by referring to the nearest normal character in a line of text. Third, after segmentation, for multi-stroke Chinese characters, first extract the combined features, the position of each stroke in the segmented character, form the positional relationship of a 9-grid (upper-middle-lower, left-middle-right), and form the combined data of radicals. For Chinese characters with an upper-lower structure, their segmented features can be obtained, and for fonts with a left-middle-right structure, the features of their radicals and basic simple Chinese characters (such as people, field, sun, ten, soil, mouth, etc.) can be obtained. All Chinese characters can be made into a Chinese character feature library according to these basic features for matching. For the unrecognized data, use Microsoft's Chinese character recognition engine System.Windows.Ink to recognize a small number of Chinese characters and make decisions in combination with these features.

[0036] d) The special character scenario pattern matching means further processing the character recognition results obtained in c). All the stroke data within the character forms intervals (rectangular regions), and these intervals are used to judge line breaks and subscripts and superscripts. Then, in combination with chemical elements and chemical molecular formulas, etc., make semantic distinctions for similar characters to obtain the final recognition results with subscripts, superscripts, and positions.

[0037] e) For the processing of special scenarios, for some multi-character molecular formula symbols with connected strokes, the characteristic of this kind of connected characters is that the aspect ratio of the character interval is large, generally greater than 2. Currently, two processing methods are adopted: First, the sub-segment can be Right_Oblique_Top (see Figure 5As shown in the figure below, it is located at the bottom, performs single-stroke character segmentation, and then performs sub-segment character detection to achieve the effect of segmentation and recognition; second, adopt the method of Chinese character recognition to form the composite features of single strokes. Having these composite features means it is a cursive character, and the recognition result is as Figure 7 shown.

[0038] Perform data recognition on the feature data according to the above first recognition strategy and / or second recognition strategy to obtain the corresponding recognition result.

[0039] S104, perform binary conversion on the recognition result and store the binary conversion result.

[0040] In specific implementation, for chemical equations, they are processed through the associative memory module in the electronic whiteboard. Specifically: 1. Memory storage; 2. Memory association of key information. The so-called memory storage is to use the extended MathML (an XML-based mathematical markup language) to form the basic memory storage unit of the tree-shaped formatted chemical equation (including all chemical equations and ionic equations in junior and senior high school stages). Each storage unit combines the query string of each chemical equation to construct an associative dictionary data, forming memory fragments; the so-called memory association of key information is that according to the recognition result obtained in step 3, after visual display, a user query string is formed. The program will perform an associative search of the memory for the query string and display the associated storage unit information on the interface for the user to quickly select. The result case is as Figure 8 shown.

[0041] For function equations, use the function parsing and processing module in the electronic whiteboard for parsing and processing. Specifically: 1. Function parsing and solution, visually express the displayed function to form a y = f(x) equation expression, such as y = sin2x + 3, to form a compilable language code block, as Figure 9 shown, and these code blocks are compiled in real time to form a dynamic library and loaded into memory to form a context (function method) that can be called and executed by the CPU. By calling these function methods, the sample point values required by the display and editing module are solved, and the sample points are connected in sequence to form a visual curve of the function equation; on the basis of the bisection method, by calling these function methods, the intersection points (numerical results) required for two different curves can be solved and directly displayed to the user; 2. Function formatting conversion, format the recognized tree-shaped result to form the equation display on the interface, and can perform direct and nested conversions respectively according to numbers, constant symbols, operators, parentheses, and basic sub-functions.

[0042] In this embodiment, a data storage and sharing module is provided in the electronic whiteboard to store and share data of chemical equations. Users can select to edit the recognized chemical equations or function set cards, convert them into storable files through binary data conversion, and upload or share them to the cloud; they can also download and open files in this format on the whiteboard, reload them, and display editable chemical equations or function cards for the second time.

[0043] In summary, the handwriting input method of the electronic whiteboard in the above embodiments of the present invention obtains the data to be recognized by real-time recognition of the area of the electronic whiteboard, extracts features from the text recognition result of the data to be recognized by using the constructed feature extraction model, makes a judgment based on the type of the extracted feature data, and uses the type of the feature data to call the corresponding recognition strategy. Then, the feature data is recognized through the recognition strategy, the writing content is segmented by detecting and then recognizing the line features first, the writing content is quickly recognized by using a small amount of recognition information, and different data types are used to quickly recognize the data, thereby improving the overall recognition accuracy.

[0044] Embodiment 2 On the other hand, the present invention also proposes a handwriting input system for an electronic whiteboard. Please refer to Figure 10 , which shows the handwriting input system of the electronic whiteboard in the second embodiment of the present invention. The system includes: An area recognition module 11, configured to perform area recognition on the handwriting area at preset intervals when the electronic whiteboard is in the writing mode, so as to obtain corresponding data to be recognized; Further, the area recognition module 11 includes: A coordinate conversion unit, configured to perform two-dimensional coordinate conversion on the handwriting area to obtain two-dimensional coordinate information of the handwriting area; A data sampling unit, configured to set a scale ratio based on the two-dimensional coordinate information and area size of the handwriting area, and perform sampling in the handwriting area in units of pixels to obtain corresponding data to be recognized.

[0045] A model construction module 12, configured to construct a feature extraction model, perform text recognition on the data to be recognized, and input the text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; Further, the model construction module 12 includes: A type judgment unit, configured to obtain the historical database of the electronic whiteboard and judge the data types of all input data in the historical database; A model construction unit, configured to construct a corresponding feature extraction strategy according to the data types of all input data in the historical database, and construct a feature extraction model according to the feature extraction strategy and each of the input data.

[0046] A data recognition module 13, configured to determine the data type of the feature data, then call a corresponding recognition strategy according to the determination result, and use the recognition strategy to perform data recognition on the feature data to obtain a corresponding recognition result; Further, the data recognition module 13 includes: A first strategy acquisition unit, configured to, if the data type of the feature data is a function equation type, acquire a corresponding first recognition strategy from a preset recognition strategy library based on the function equation; A second strategy acquisition unit, configured to, if the data type is a chemical equation type, acquire a corresponding second recognition strategy from a preset recognition strategy library based on the chemical equation type; A data recognition unit, configured to perform data recognition on the feature data according to the first recognition strategy and / or the second recognition strategy to obtain a corresponding recognition result.

[0047] A data storage module 14, configured to perform binary conversion on the recognition result and store the binary conversion result.

[0048] The functions or operation steps implemented when the above-mentioned modules and units are executed are substantially the same as those in the above method embodiment, and will not be described in detail here.

[0049] The handwriting input system of the electronic whiteboard provided by the embodiment of the present invention has the same implementation principle and the same technical effects as those in the foregoing method embodiment. For the sake of brief description, for the parts not mentioned in the system embodiment, reference may be made to the corresponding content in the foregoing method embodiment.

[0050] Embodiment III The present invention also provides a computer. Please refer to Figure 11 , which shows the computer in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned handwriting input method of the electronic whiteboard is implemented.

[0051] Among them, the memory 10 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 10 can be an internal storage unit of a computer in some embodiments, such as the hard disk of the computer. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both an internal storage unit of a computer and an external storage device. The memory 10 can be used not only to store application software installed in the computer and various types of data, but also to temporarily store data that has been output or will be output.

[0052] Among them, the processor 20 can be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0053] It should be noted that Figure 11 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine some components, or have a different component arrangement.

[0054] An embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the handwritten input method of the electronic whiteboard as described above.

[0055] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0056] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connections (electronic devices) having one or more wirings, portable computer diskettes (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0057] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0058] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0059] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A handwriting input method for an electronic whiteboard, characterized in that: include: When the electronic whiteboard is in writing mode, performing area recognition on the handwritten area at preset intervals to obtain corresponding data to be recognized; Constructing a feature extraction model, and performing text recognition on the data to be recognized, and inputting the text recognition result into the feature extraction model for feature extraction to obtain corresponding feature data; Performing data type judgment on the characteristic data, calling a corresponding recognition strategy according to the judgment result, and performing data recognition on the characteristic data using the recognition strategy to obtain a corresponding recognition result; The recognition result is binary-converted, and the binary-converted result is stored in data.

2. The handwriting input method for an electronic whiteboard according to claim 1, characterized in that: When the electronic whiteboard is in writing mode, the steps of performing area recognition on the handwritten area at preset intervals to obtain corresponding data to be recognized include: Performing two-dimensional coordinate conversion on the handwritten area to obtain two-dimensional coordinate information of the handwritten area; The scale ratio is set based on the two-dimensional coordinate information and the area size of the handwriting area, and sampling is performed in the handwriting area in units of pixels to obtain corresponding data to be recognized.

3. The handwriting input method for an electronic whiteboard according to claim 1, characterized in that: The steps to build a feature extraction model include: Acquire the history database of the electronic whiteboard, and determine the data type of all input data in the history database; A corresponding feature extraction strategy is constructed according to the data types of all input data in the historical database, and a feature extraction model is constructed according to the feature extraction strategy and each input data.

4. The handwriting input method for an electronic whiteboard according to claim 1, characterized in that: The steps of performing data type judgment on the feature data, calling a corresponding recognition strategy according to the judgment result, and performing data recognition on the feature data using the recognition strategy to obtain a corresponding recognition result include: If the data type of the characteristic data is a function equation type, acquiring a corresponding first recognition strategy from a preset recognition strategy library based on the function equation; If the data type is a chemical equation type, obtaining a corresponding second recognition strategy from a preset recognition strategy library based on the chemical equation type; The feature data is identified according to the first identification strategy and / or the second identification strategy to obtain a corresponding identification result.

5. A handwriting input system for an electronic whiteboard, characterized in that: include: A region recognition module, used for performing region recognition on a handwritten region at preset intervals when the electronic whiteboard is in a writing mode, so as to obtain corresponding data to be recognized; A model building module is used to build a feature extraction model, and perform text recognition on the data to be recognized, and input the text recognition result into the feature extraction model to perform feature extraction to obtain corresponding feature data; A data identification module is used to determine the data type of the feature data, call a corresponding identification strategy according to the determination result, and use the identification strategy to perform data identification on the feature data to obtain a corresponding identification result; The data storage module is used to perform binary conversion on the recognition result and store the binary conversion result in data.

6. The handwriting input system for an electronic whiteboard according to claim 5, characterized in that: The region identification module comprises: A coordinate conversion unit, used for performing two-dimensional coordinate conversion on the handwriting area to obtain two-dimensional coordinate information of the handwriting area; The data sampling unit is used to set the scale ratio based on the two-dimensional coordinate information and the area size of the handwriting area, and to perform sampling in the handwriting area in units of pixels to obtain corresponding data to be recognized.

7. The handwriting input system for an electronic whiteboard according to claim 5, characterized in that: The model building module includes: A type determination unit, used for acquiring a history database of the electronic whiteboard and determining the data types of all input data in the history database; The model building unit is used to build a corresponding feature extraction strategy according to the data type of all input data in the historical database, and to build a feature extraction model according to the feature extraction strategy and each input data.

8. The handwriting input system for an electronic whiteboard according to claim 5, characterized in that: The data identification module comprises: A first strategy acquisition unit, configured to acquire a corresponding first recognition strategy from a preset recognition strategy library based on the function equation if the data type of the feature data is a function equation type; A second strategy acquisition unit, configured to acquire a corresponding second recognition strategy from a preset recognition strategy library based on the chemical equation type if the data type is a chemical equation type; A data identification unit is used to perform data identification on the feature data according to the first identification strategy and / or the second identification strategy to obtain a corresponding identification result.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the handwriting input method for an electronic whiteboard as claimed in any one of claims 1 to 5 is implemented.

10. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the handwriting input method for the electronic whiteboard as claimed in any one of claims 1 to 5 is implemented.

Images