Oracle bone word cloud generation method and system

Through image threshold segmentation method and vectorized description technology, feature extraction and glyph description library are constructed for oracle bone inscriptions, which solves the problem of automatic recognition and analysis in the generation of oracle word cloud, and improves the correlation understanding between oracle bone inscriptions and Chinese characters and word cloud generation. accuracy.

CN119445590APending Publication Date: 2025-02-14ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411516990.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-29
Publication Date
2025-02-14

AI Technical Summary

Technical Problem

The existing text processing methods based on modern Chinese are difficult to correctly process oracle bone inscriptions, resulting in difficulty in automatic identification and analysis when generating oracle word clouds, affecting the accuracy of word segmentation and word frequency statistics.

Method used

The image threshold segmentation method is used to extract the original shape of oracle bone rubbings to obtain the font skeleton, and a font description library is constructed through vectorized description to associate the corresponding Chinese characters, thereby improving the correlation understanding effect between oracle bone script and Chinese characters.

Benefits of technology

It improves the correlation understanding effect of oracle bone script corresponding to Chinese characters, enhances the analytical ability of oracle bone script characters and the accuracy of word cloud generation, and facilitates quick retrieval and understanding of oracle bone script content.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119445590A_ABST
    Figure CN119445590A_ABST
Patent Text Reader

Abstract

The invention provides an oracle word cloud generation method and system, and the method comprises the steps: obtaining oracle rubbing image information, intercepting an original oracle image from the oracle rubbing image information, and carrying out the oracle font skeleton extraction of the original oracle image; performing vectorization operation on the extracted oracle font skeleton to generate an oracle font description library comprising oracle font writing elements and stagnation points; according to the oracle font description library, constructing search indexes of oracle fonts and modern Chinese characters, and according to the search indexes, establishing an oracle font library; and constructing an oracle and modern Chinese character comparison table according to the search index and the oracle character library, and generating word cloud information of the oracle text of the oracle rubbing according to the oracle and modern Chinese character comparison table.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a word cloud generation technology, and in particular to an oracle word cloud generation method and system. Background Art

[0002] Word cloud generation technology is a visualization technology based on text data. It sorts and presents the words in the text data according to their frequency and importance to form a visually presented "word cloud". The word cloud generation technology based on text processing mainly performs preprocessing, word segmentation, and stop word removal on the input text data, then counts the frequency of each word and sorts the words according to the frequency. Finally, the sorted words are presented in a visual form. Due to the great differences in grammar, vocabulary, and expression between oracle bone inscriptions and modern Chinese, the existing text processing methods based on modern Chinese may not be able to correctly process oracle bone inscriptions, resulting in some problems when generating word clouds for oracle bone inscriptions. First, due to the complex shape and long history of oracle bone inscriptions, it is difficult to automatically recognize and parse oracle bone inscriptions, which will affect the accuracy of word segmentation and word frequency statistics. Secondly, understanding and interpreting the content of oracle bone inscriptions requires a deep cultural background and historical knowledge, which is difficult to fully achieve in automated text processing. Summary of the invention

[0003] One of the inventive purposes of the present invention is to provide a method and system for generating an oracle bone script word cloud. The method and system use an image threshold segmentation method to perform feature extraction on the original glyphs of oracle bone script rubbings to obtain the glyph skeleton of the original oracle bone script glyphs, and perform vectorized description on the glyph skeleton of the oracle bone script. The glyph description library of the oracle bone script can be obtained through the vectorized description, and the corresponding Chinese characters can be associated according to the glyph description library, thereby improving the association and understanding effect of the oracle bone script corresponding to the Chinese characters, which is conducive to the research and expansion of the oracle bone script glyphs.

[0004] Another object of the present invention is to provide a method and system for generating an oracle bone script word cloud, wherein the method and system utilize character decomposition of oracle bone script glyphs, and identification and editing of stroke elements and stationary points of the oracle bone script glyphs, indexing and storing the decomposed characters, identified and edited stroke elements and stationary points, and constructing an oracle bone script glyph library, thereby improving the parsing capability of the oracle bone script glyphs and facilitating rapid retrieval of oracle bone scripts corresponding to the character elements.

[0005] Another inventive object of the present invention is to provide an oracle bone script word cloud generation method and system, the method and system establish an oracle bone script library of the oracle bone script glyphs, after obtaining the oracle bone script glyphs corresponding to the oracle bone script rubbings, compare the oracle bone script glyphs with the corresponding oracle bone script glyph library to obtain standard oracle bone script glyphs, and find the corresponding oracle bone script according to the standard oracle bone script glyphs, and calculate the word frequency of each oracle bone script in the oracle bone script rubbings to generate an oracle bone script word cloud, the oracle bone script word cloud can effectively improve the overall understanding of the content of the oracle bone script rubbings.

[0006] In order to achieve at least one of the above-mentioned invention objects, the present invention further provides a method for generating an oracle word cloud, the method comprising: Acquire oracle bone inscription rubbings image information, intercept original oracle bone inscription images from the oracle bone inscription rubbings image information, and perform oracle bone inscription glyph skeleton extraction on the original oracle bone inscription images; Performing vectorization operation on the extracted oracle bone script glyph skeleton to generate an oracle bone script glyph description library including the oracle bone script glyph stroke elements and station points; Constructing a search index of oracle bone script glyphs and modern Chinese characters based on the oracle bone script glyph description library, and establishing the oracle bone script character library based on the search index; An oracle bone script and modern Chinese character comparison table is constructed based on the search index and the oracle bone script library, and word cloud information of the oracle bone script text of the oracle bone script rubbing is generated based on the oracle bone script and modern Chinese character comparison table.

[0007] According to one of the preferred embodiments of the present invention, the method for extracting the skeleton of oracle bone script includes: using a target detection model to locate the text area of ​​the oracle bone script rubbing, and intercepting the image of a single text area of ​​the oracle bone script rubbing, and setting a pixel threshold for the image within the single text area of ​​the oracle bone script, and performing feature extraction on the image of the part of pixels in the image within the single text area of ​​the oracle bone script that meets the pixel threshold, to obtain each oracle bone script skeleton image.

[0008] According to another preferred embodiment of the present invention, the method for constructing a glyph description library of the vectorized oracle bone script glyph skeleton includes: disassembling and editing the oracle bone script glyph skeleton image, wherein the oracle bone script glyph skeleton is disassembled to obtain pen element information including the strokes of the oracle bone script, and the stationary point information of the oracle bone script glyph skeleton on each pen element information is analyzed, and the pen element information and stationary point information of each oracle bone script glyph skeleton are converted into vector features, thereby obtaining a glyph description library of each oracle bone script glyph skeleton, and the glyph description library of the oracle bone script glyph skeleton is used to construct a meaning mapping relationship with modern Chinese characters.

[0009] According to another preferred embodiment of the present invention, the method for constructing a glyph description library for vectorization of the oracle bone script skeleton also includes: determining the contours of the corresponding stroke elements and stationary points based on the stroke element information and stationary point information after the oracle bone script skeleton is disassembled, and constructing control points of Bezier curves based on the contours of the stroke elements and stationary points, respectively, wherein the control points of the Bezier curves include a starting point and an ending point, wherein the starting point and the ending point of the Bezier curves with the same stroke element and stationary point contours are connected, the Bezier curves corresponding to the stroke element information and stationary point information of each oracle bone script are saved, and combined with the corresponding stroke elements and stationary points as the glyph description library for vectorization of the oracle bone script skeleton.

[0010] According to another preferred embodiment of the present invention, the oracle bone script skeleton is pre-edited, wherein the oracle bone script skeleton pre-editing method comprises: decomposing characters including strokes, radicals and components according to the oracle bone script structure, and defining modern Chinese characters for each stroke, radical and component according to the oracle bone script, and decomposing each defined character into stroke components and stationary points according to its own stroke features, and using the Serre curve to describe the glyph features of the characters and the glyph features of the stroke components corresponding to the characters in a hierarchical manner.

[0011] According to another preferred embodiment of the present invention, the method for constructing a glyph description library for vectorization of the oracle bone script glyph skeleton also includes: constructing a Cartesian coordinate system on the image displayed by each oracle bone script glyph skeleton, judging the coordinate value of each pixel in the Cartesian coordinate system that satisfies the pixel threshold according to a set pixel threshold, and respectively obtaining corresponding pixel point coordinate values ​​according to the characters, stroke elements and stationary points decomposed from the oracle bone script glyph skeleton, and respectively describing the glyph outline composed of the corresponding pixel point coordinate values ​​of the decomposed characters, stroke elements and stationary points according to the Saier curve.

[0012] According to another preferred embodiment of the present invention, a search index of the glyph description library is constructed according to the strokes or pinyin of modern Chinese characters based on the characters, strokes and stationary points stored in the glyph description library, wherein each character, stroke and stationary point in the glyph description library corresponds to a Chinese character description, and a corresponding mapping relationship between the character, stroke and stationary point and the Chinese character is constructed, and at the same time, an oracle bone script and Chinese character mapping relationship table is constructed for the complete oracle bone script glyph skeleton, and the meaning of the oracle bone script and the decomposed characters, strokes and stationary points can be found through the search index.

[0013] According to another preferred embodiment of the present invention, the oracle bone script word cloud generation method includes: obtaining all oracle bone script glyph skeleton information of the corresponding oracle bone script rubbings, and finding the character, stroke and station description information of each oracle bone script glyph skeleton according to the search index of the glyph description library, and finding the Chinese character information mapped by each oracle bone script glyph skeleton of the corresponding oracle bone script rubbings, calculating the frequency of occurrence of each Chinese character information in the corresponding oracle bone script rubbings, and sorting them in order according to the frequency for visual display of the text size.

[0014] In order to achieve at least one of the above-mentioned invention purposes, the present invention further provides an oracle word cloud generation system, which executes the above-mentioned oracle word cloud generation method.

[0015] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned oracle word cloud generation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 Shown is a schematic diagram of the process of an oracle word cloud generation method of the present invention.

[0017] Figure 2 Shown is a schematic diagram of the oracle word cloud generation effect in the present invention. DETAILED DESCRIPTION

[0018] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0019] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0020] Please combine Figure 1 and Figure 2The present invention discloses a method and system for generating an oracle bone script word cloud. The method mainly includes the following steps: first, it is necessary to perform high-definition photography on an oracle bone script rubbing to obtain the image information of the oracle bone script rubbing. Since the image information of the oracle bone script rubbing may contain multiple oracle bone script characters, the present invention needs to separate each oracle bone script character from each other to obtain a single complete oracle bone script character. After obtaining the single oracle bone script character, the present invention needs to further perform image processing operations on each oracle bone script character to obtain a clean oracle bone script glyph diagram, further decompose the oracle bone script glyph diagram into character elements of a single character, and decompose and edit the character elements and stationary points of each character according to the writing and structural characteristics. The present invention performs vectorization editing on the decomposed character elements, pen elements and stationary points according to the cuneiform characteristics of the oracle bone script itself, obtains a glyph description library of each oracle bone script, adds Chinese character interpretation to each oracle bone script character element, pen element and stationary point during the editing process, and establishes a search index for each oracle bone script character element, pen element and stationary point, thereby improving the parsing effect of the oracle bone script. The present invention also calculates the types and quantities of oracle bone inscriptions in each oracle bone inscription rubbing based on the search index, and visualizes the oracle bone inscription word cloud by calculating the word frequency. Therefore, the technical solution of the present invention has the advantage of being easy to study and research oracle bone inscriptions and their expressions, and provides an efficient tool for ancient character research and analysis.

[0021] Specifically, the method of the present invention has the following steps: first, the image of the oracle bone script rubbing needs to be normalized to obtain an oracle bone script image of a relatively standard form, and the features in the oracle bone script image are extracted to obtain an oracle bone script skeleton diagram. After obtaining the oracle bone script image, a screenshot is taken according to the position of the oracle bone script image, wherein the screenshot method may include but is not limited to standardized grid screenshots, or the text in the oracle bone script image is identified by a target detection model to obtain the corresponding text area. It should be noted that the target detection model in the present invention is not a text recognition model, but an image area recognition model; it represents that there is a complete single text image in this part. The above model can refer to existing mature target detection models such as the YOLO model. The present invention does not specifically limit the use type of specific target detection models.

[0022] The method for extracting the skeleton of oracle bone characters includes: using a target detection model to locate the text area of ​​an oracle bone script rubbing, intercepting an image in a single text area of ​​the oracle bone script rubbing, setting a pixel threshold for the image in the single text area of ​​the oracle bone script, extracting features from the image of the part of pixels in the image in the single text area of ​​the oracle bone script that meets the pixel threshold, and obtaining each oracle bone character skeleton image. Since oracle bone script is a wedge-engraved script, an optical image with a depth different from that of the surrounding area will exist on the image. The oracle bone script is affected by the wedge-engraved material or environment, such as part of the oracle bone script is wedge-engraved on a tortoise shell, and part of the oracle bone script may be wedge-engraved on an animal bone, and the tortoise shell and the animal bone are also affected by environmental factors, and the pixels in the text area are darker or shallower than the surrounding area. Therefore, the pixel threshold set by the present invention is dynamically changing, not a fixed threshold. When the image in the single text area of ​​the oracle bone script meets the pixel threshold for some pixels, it is necessary to extract each pixel area that meets the pixel threshold condition to obtain the oracle bone character skeleton image.

[0023] Furthermore, after obtaining the oracle bone script skeleton image, the oracle bone script skeleton needs to be disassembled and edited, wherein the present invention needs to disassemble the oracle bone script skeleton into different characters, and the characters in the present invention refer to the parts including strokes, radicals and radicals. Since oracle bone script does not have a very regular character structure like modern Chinese, the disassembly of the characters needs to be based on the corresponding text structure and meaning after the oracle bone script researchers have professional and in-depth research on the cuneiform characters of the oracle bone script itself. As a result, a certain amount of manual intervention is required in this part of the character disassembly operation. After the oracle bone script researchers disassemble the characters of each oracle bone script, they define the Chinese meaning of each character and edit it to obtain the corresponding oracle bone script skeleton character description library. After the oracle bone script skeleton is disassembled, the pen element information of the strokes of the oracle bone script is obtained, and the stationary point information of the oracle bone script skeleton on each pen element information is analyzed, and the pen element information and stationary point information of each oracle bone script skeleton are converted into vector features, so as to obtain the glyph description library of each oracle bone script skeleton, and the glyph description library of the oracle bone script skeleton is used to construct the meaning mapping relationship with modern Chinese characters. The meaning of the pen element described in the present invention is: including basic stroke forms such as dot, horizontal, vertical, left-falling, and right-falling. The meaning of the stationary point described in the present invention is: including "stopping the pen" or "stopping the tip" when writing, and the force is on the paper.

[0024] The vector conversion method of the character, stroke unit and station point includes: determining the outlines of the corresponding stroke units and station points according to the stroke unit information and station point information after the oracle bone script skeleton is disassembled, and constructing the control points of Bezier curves according to the outlines of the stroke units and station points respectively, wherein the control points of the Bezier curve include a starting point and an ending point, wherein the starting point and the ending point of the Bezier curve with the same stroke unit and station point outline are connected, and the Bezier curves corresponding to the stroke unit information and station point information of each oracle bone script are saved, and the corresponding stroke units and station points are combined as the character description library of the oracle bone script skeleton vectorization.

[0025] The method for constructing a glyph description library for vectorization of the oracle bone script glyph skeleton also includes: constructing a Cartesian coordinate system on the image displayed by each oracle bone script glyph skeleton, judging the coordinate value of each pixel in the Cartesian coordinate system that satisfies the pixel threshold according to the set pixel threshold, and respectively obtaining the corresponding pixel point coordinate values ​​according to the characters, stroke elements and stationary points decomposed from the oracle bone script glyph skeleton, and respectively describing the glyph outline composed of the corresponding pixel point coordinate values ​​of the decomposed characters, stroke elements and stationary points according to the Saier curve.

[0026] Furthermore, a search index of the glyph description library is constructed according to the strokes or pinyin of modern Chinese characters based on the characters, stroke elements and stationary points stored in the glyph description library, wherein each character, stroke element and stationary point in the glyph description library corresponds to a Chinese character description, and a corresponding mapping relationship between the character, stroke element and stationary point and the Chinese character is constructed. At the same time, a mapping relationship table between oracle bone script and Chinese character is constructed for the complete oracle bone script glyph skeleton. The search index can be used to find the characters, stroke elements and stationary points including the meaning and decomposition of the oracle bone script words.

[0027] In one of the preferred embodiments of the present invention, the oracle bone script word cloud generation method includes: obtaining all oracle bone script glyph skeleton information corresponding to the oracle bone script rubbing, and finding the character, stroke and station description information of each oracle bone script glyph skeleton according to the search index of the glyph description library, and finding the Chinese character information mapped to each oracle bone script glyph skeleton of the corresponding oracle bone script rubbing, calculating the frequency of each Chinese character information appearing in the corresponding oracle bone script rubbing, and sorting them in order according to the frequency to perform a visual display of the text size. Figure 2 As shown, when the frequency of the corresponding oracle bone script is larger, the area of ​​the oracle bone script in the visual display is also larger; that is to say, the character size of the oracle bone script word cloud described in the present invention will be positively correlated with the frequency of each oracle bone script appearing in the oracle bone script rubbings.

[0028] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0029] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0030] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for generating an oracle word cloud, characterized in that: The method comprises: Acquire oracle bone inscription rubbings image information, intercept original oracle bone inscription images from the oracle bone inscription rubbings image information, and perform oracle bone inscription glyph skeleton extraction on the original oracle bone inscription images; Performing vectorization operation on the extracted oracle bone script glyph skeleton to generate an oracle bone script glyph description library including the oracle bone script glyph stroke elements and station points; Constructing a search index of oracle bone script glyphs and modern Chinese characters based on the oracle bone script glyph description library, and establishing the oracle bone script character library based on the search index; An oracle bone script and modern Chinese character comparison table is constructed based on the search index and the oracle bone script library, and word cloud information of the oracle bone script text of the oracle bone script rubbing is generated based on the oracle bone script and modern Chinese character comparison table.

2. The method for generating an oracle word cloud according to claim 1, characterized in that: The method for extracting the skeleton of oracle bone script includes: using a target detection model to locate the text area of ​​the oracle bone script rubbing, and intercepting the image of a single text area of ​​the oracle bone script rubbing, and setting a pixel threshold for the image in the single text area of ​​the oracle bone script, and performing feature extraction on the image of the part of pixels that meet the pixel threshold in the image in the single text area of ​​the oracle bone script to obtain each oracle bone script skeleton image.

3. The method for generating an oracle word cloud according to claim 1, characterized in that: The method for constructing a glyph description library of the vectorized oracle bone script glyph skeleton comprises: disassembling and editing the oracle bone script glyph skeleton image, wherein the oracle bone script glyph skeleton is disassembled to obtain pen element information including the strokes of the oracle bone script, and the stationary point information of the oracle bone script glyph skeleton on each pen element information is analyzed, and the pen element information and stationary point information of each oracle bone script glyph skeleton are converted into vector features, thereby obtaining a glyph description library of each oracle bone script glyph skeleton, and the glyph description library of the oracle bone script glyph skeleton is used to construct a meaning mapping relationship with modern Chinese characters.

4. The method for generating an oracle word cloud according to claim 3, characterized in that: The method for constructing a glyph description library for vectorization of the oracle bone script skeleton also includes: determining the contours of the corresponding stroke elements and stationary points based on the stroke element information and stationary point information after the oracle bone script skeleton is disassembled, and constructing control points of Bezier curves based on the contours of the stroke elements and stationary points, respectively, wherein the control points of the Bezier curves include a starting point and an ending point, wherein the starting point and the ending point of the Bezier curves with the same stroke element and stationary point contours are connected, and the Bezier curves with the stroke element information and stationary point information corresponding to each oracle bone script are saved, and combined with the corresponding stroke elements and stationary points as the glyph description library for the oracle bone script skeleton vectorization.

5. The method for generating an oracle word cloud according to claim 4, characterized in that: The oracle bone script skeleton is pre-edited, wherein the oracle bone script skeleton pre-editing method includes: decomposing characters including strokes, radicals and components according to the oracle bone script structure, and defining modern Chinese characters for each stroke, radical and component according to the oracle bone script, and decomposing each defined character into stroke components and stationary points according to its own stroke features, and using the Saier curve to describe the glyph features of the character and the glyph features of the stroke components corresponding to the character in a hierarchical manner.

6. The method for generating an oracle word cloud according to claim 4, characterized in that: The method for constructing a glyph description library for vectorization of the oracle bone script glyph skeleton also includes: constructing a Cartesian coordinate system on the image displayed by each oracle bone script glyph skeleton, judging the coordinate value of each pixel in the Cartesian coordinate system that satisfies the pixel threshold according to a set pixel threshold, and respectively obtaining corresponding pixel point coordinate values ​​according to the characters, stroke elements and stationary points decomposed from the oracle bone script glyph skeleton, and respectively describing the glyph outline composed of the corresponding pixel point coordinate values ​​of the decomposed characters, stroke elements and stationary points according to the Saier curve.

7. The method for generating an oracle word cloud according to claim 6, characterized in that: A search index of the glyph description library is constructed according to the strokes or pinyin of modern Chinese characters based on the characters, strokes and stationary points stored in the glyph description library, wherein each character, stroke and stationary point in the glyph description library corresponds to a Chinese character description, and a mapping relationship between the corresponding characters, strokes and stationary points and Chinese characters is constructed. At the same time, an oracle bone script and Chinese character mapping relationship table is constructed for the complete oracle bone script glyph skeleton. The search index can be used to find the meaning of the oracle bone script word and the decomposed characters, strokes and stationary points.

8. The method for generating an oracle word cloud according to claim 7, characterized in that: The oracle bone script word cloud generation method comprises: obtaining all oracle bone script glyph skeleton information of the corresponding oracle bone script rubbings, and finding the character, stroke and station description information of each oracle bone script glyph skeleton according to the search index of the glyph description library, and finding the Chinese character information mapped to each oracle bone script glyph skeleton of the corresponding oracle bone script rubbings, calculating the frequency of occurrence of each Chinese character information in the corresponding oracle bone script rubbings, and sorting them in order according to the frequency to perform a visual display of the text size.

9. An oracle word cloud generation system, characterized in that: The system executes an oracle word cloud generation method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for generating an oracle word cloud as described in any one of claims 1 to 8.