CN111353047A - Method for generating artificial intelligence knowledge map based on Chinese character making method - Google Patents
Method for generating artificial intelligence knowledge map based on Chinese character making method Download PDFInfo
- Publication number
- CN111353047A CN111353047A CN201911391218.3A CN201911391218A CN111353047A CN 111353047 A CN111353047 A CN 111353047A CN 201911391218 A CN201911391218 A CN 201911391218A CN 111353047 A CN111353047 A CN 111353047A
- Authority
- CN
- China
- Prior art keywords
- chinese character
- chinese
- characters
- character
- section coding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 135
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 33
- 240000004282 Grewia occidentalis Species 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 10
- 238000013135 deep learning Methods 0.000 abstract description 7
- 238000003058 natural language processing Methods 0.000 abstract description 6
- 238000007418 data mining Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000012800 visualization Methods 0.000 description 5
- 240000000220 Panda oleosa Species 0.000 description 4
- 235000016496 Panda oleosa Nutrition 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 238000010225 co-occurrence analysis Methods 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 229910052695 Americium Inorganic materials 0.000 description 1
- 241000271566 Aves Species 0.000 description 1
- 241001137251 Corvidae Species 0.000 description 1
- 229910052685 Curium Inorganic materials 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 229910052766 Lawrencium Inorganic materials 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052729 chemical element Inorganic materials 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- CNQCVBJFEGMYDW-UHFFFAOYSA-N lawrencium atom Chemical compound [Lr] CNQCVBJFEGMYDW-UHFFFAOYSA-N 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention discloses a method for generating artificial intelligence knowledge map based on Chinese character making method, which comprises establishing stroke number of Chinese character, phonetic part of Chinese character, phonetic and polyphonic character of Chinese character, part of speech of Chinese character, variant character of Chinese character, false word of Chinese character, four corner number of Chinese character, and segment code of Chinese character making method by defining Chinese character range and set, and finally establishing basic dimension using stroke number of Chinese character, phonetic part of Chinese character, part of speech of Chinese character, variant character of Chinese character, false word of Chinese character, four corner number of Chinese character, the artificial intelligent knowledge map based on the Chinese character forming method is generated by taking the Chinese character forming method forming mode as the core dimension, through the mode, the method improves the accuracy and efficiency of natural language processing of the artificial intelligent deep learning engine for Chinese semantic and the comprehension capability of computer semantic, and can be used as a Chinese character learning auxiliary tool to more intuitively display the venation and connection of Chinese character development.
Description
Technical Field
The invention relates to a knowledge map method, in particular to a method for generating an artificial intelligence knowledge map based on a Chinese character making method.
Background
1. Knowledge graph:
knowledge map (Knowledge Graph) is a series of different graphs displaying Knowledge development process and structure relationship in the book intelligence field, describing Knowledge resources and carriers thereof by using visualization technology, mining, analyzing, constructing, drawing and displaying Knowledge and mutual relation between Knowledge resources and Knowledge carriers.
The knowledge graph is a modern theory which achieves the aim of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing a visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects. It can provide practical and valuable reference for subject research.
Specifically, the knowledge graph is a modern theory which achieves the purpose of multi-discipline fusion by combining theories and methods of applying subjects such as mathematics, graphics, information visualization technology, information science and the like with methods such as metrology introduction analysis, co-occurrence analysis and the like and utilizing a visualized graph to vividly display the core structure, development history, frontier field and overall knowledge framework of the subjects. The method displays the complex knowledge field through data mining, information processing, knowledge measurement and graph drawing, reveals the dynamic development rule of the knowledge field, and provides a practical and valuable reference for subject research.
2. Deep learning:
deep Learning (DL) is a new research direction in the field of Machine Learning (ML), and is an intrinsic rule and expression level of Learning sample data, and information obtained in the Learning process is very helpful for interpretation of data such as characters, images and sounds. The final aim of the method is to enable the machine to have the analysis and learning capability like a human, and to recognize data such as characters, images and sounds.
3. Data mining:
data mining refers to a nontrivial process of revealing implicit, previously unknown and potentially valuable information from a large amount of data in a database, and is a decision support process which is mainly based on artificial intelligence, machine learning, pattern recognition, statistics, databases, visualization technologies and the like, analyzes data of enterprises in a highly automated manner, makes inductive reasoning, excavates potential patterns from the data, helps decision makers to adjust market strategies, reduces risks and makes correct decisions.
Data mining is a technology for searching a rule from a large amount of data by analyzing each piece of data, and mainly comprises three steps of data preparation, rule searching and rule representation. The data preparation is to select required data from related data sources and integrate the data into a data set for data mining; the rule searching is to find out the rule contained in the data set by a certain method; the law representation is to represent the found laws as much as possible in a manner understandable to the user (e.g., visualization). The data mining task comprises association analysis, cluster analysis, classification analysis, anomaly analysis, specific group analysis, evolution analysis and the like.
4. And (3) natural language processing:
natural language processing, i.e., implementing man-machine natural language communication, or implementing natural language understanding and natural language generation, is very difficult. The root cause of the difficulty is the wide variety of ambiguities or ambiguities that exist widely across the various levels of natural language text and dialog. To resolve ambiguities, an extremely large amount of knowledge and reasoning is required. How to collect and sort out the knowledge more completely; how to find the proper forms and store them in the computer system; and how to effectively use them to disambiguate are very labor intensive and difficult tasks.
5. Chinese character making method
The Chinese character forming method includes pictograph, fingering, meeting meaning and pictophonetic sound. The ancient Chinese has a six-book method for word-making, and in addition to the four methods, the method also includes transfer and dummy borrowing.
Pictograph method
Some pictographs are not used to represent concrete objects directly, but are used to represent concepts related to the objects. For example: the big character originally has the shape of a person with a right front side, and the spread of hands and feet means the big character. This word-making method, which is generalized from nouns to adjectives, was developed later. Pictograms are the earliest in origin, but the least in number. Because there are many things in the universe, it is impossible to make a pictograph according to the characteristics of each thing, many abstract concepts cannot be drawn at all, and even if drawn, the method of drawing a cucurbit according to the drawing is too unwieldy. Later, in order to overcome the limitation of pictographs and meet the requirement of social development, another word-making method, namely a finger affair method, is invented.
Finger exercise
It is a word-making method that uses symbolic symbols or adds indicative symbols on the graph to express meaning. Such word-building methods can be broadly divided into two categories: one type is a simple symbol, i.e., a non-graphical symbol (graphical, i.e., pictographic). Another type is a symbol attached to a graphic.
The first step of Chinese character development from pictograph to ideograph is to make characters by finger affairs. However, this method cannot be applied to many things generally, and the dots, horizontal lines, etc. as symbols are mixed with other strokes and are not easy to distinguish, so that our ancestors have thought of a method in which several pictures are combined to represent a meaning, i.e., a method of meeting the meaning.
Method of meeting
That is, a new meaning of a new word-making method is represented by combining two or more words according to their meanings.
The Chinese characters are developed to this step, and the requirement of representation cannot be met. Because some do not solve the problem by drawing three or four pictures. The problem can be solved only by drawing five, six or seven, eight pictures, and unlike a character, the reverse image is drawn in a year. If the fact is true, writing a short article is more troublesome today, and writing a thick comic book is equivalent to compiling a thick comic book. Our ancestors have endless wisdom, and they think that the words are recorded and speeches are related to the voices, and then can the words be recorded or not recorded with the voices? Therefore, the pictophonetic characters are invented.
Shape and sound method
It is a word-making method by combining the side of the figure and the side of the sound. Because the pictophonetic characters are generated on the basis of pictographs, fingering and meeting. Although it belongs to ideographic characters, the Chinese character form constraint is broken through, and the relation between Chinese characters in squares and voice is communicated, which is a great development of Chinese characters from ideographic step to phonetic step and becomes the mainstream of Chinese character development. More than 80% of Chinese characters used today are pictophonetic characters. The method is very convenient for making words by using an iconophonetic method, and the words related to the golden wood, the water and fire, the birds, the beasts, the insects and the fishes, the sigh words and the pseudonymphs are almost all the pictophonetic words. The word-making method can continuously make new words today. For example, the recently discovered chemical elements "americium, curium, lawrencium" are named by the new-made pictophonetic characters. For simplifying traditional Chinese characters, the sound and shape methods such as "you", "bang", etc. are also preferred.
Transfer method
The past has many descriptions, and the more popular description is a word making method adopted to adapt to the development of the partials and the voice. If the original 'old' is used for representing an older meaning, and the 'k a o' sound is used for representing the old meaning due to different time and regions, then a 'exam' word which is the same as the 'old' word and has similar pronunciation and the same meaning is created. But the side of the "exam" word is "? ", the consonant side is"? "therefore, the" kao "word is also an pictophonetic word in terms of its word-making method.
Dummy borrowing method
It is a method of using homophone to express new meaning (the meaning of "false" is also used), for example, "Ru" is the name of water, and is used as pronouncing for second person. This kind of false borrowing phenomenon is mainly because there is no word and temporarily borrows a homophone word to replace at first, but later use all the time, borrow for a long time, magpie dove occupies. There is a meaning of the word itself, and it is only after another way is found that the word falls. For example, "then" means that the fire is already in the four points below, but after being borrowed by "then", the user only needs to add another fire beside the fire to turn into the word "fire" (form and sound).
6. Existing research tools and methods:
at present, in the industry, a method for generating an artificial intelligence knowledge graph based on a Chinese character making method is blank. The existing research tools and methods mainly take forms and card type arrangement as main points. The Chinese characters are used as basic units, efficient logic matrixes are not formed yet, the Chinese characters are still in a mutually split and isolated state, natural language processing, deep learning and data mining are carried out, and accuracy and efficiency are not high.
Meanwhile, a large number of Chinese character learners lack tools and methods capable of visually displaying the internal connection and venation of the Chinese characters, can only learn by relying on a large number of exercises, mainly take a large amount of time and energy by reading, transcribing, reciting and mersible writing, and have poor effects.
The invention builds segment codes for different character codes of Chinese characters based on a Chinese character making method, and the method comprises the following steps: chinese characters-stroke number-phonetic part-phonetic alphabet and polyphone-part of speech-variant character-common false character-four corner number-Chinese character making method-unique digital ID number of multi-section code. The method is characterized in that the number of strokes of a Chinese character, the phonetic parts of the Chinese phonetic alphabet, the part of speech of the Chinese character, variant characters of the Chinese character, common kana characters of the Chinese character and four corner numbers of the Chinese character are taken as basic dimensions, and the composition mode of a Chinese character making method is taken as a core dimension to be induced, analyzed and associated. Finally, an artificial intelligence knowledge map based on the Chinese character making method is generated.
The method comprises the steps of coding Chinese character characteristic sections, uniquely digitizing ID, and generating an artificial intelligence knowledge map based on a Chinese character word-making method, and establishing a logic array and the knowledge map at Chinese character information granularity. The natural language processing engine can generate a knowledge graph based on the method, so that Chinese can be understood more accurately and efficiently, and data mining and machine deep learning are performed. The logical chain of the dimension of the Chinese character making method is opened, and the comprehension capability of computer semantic calculation is improved.
And the Chinese character learner can intuitively and efficiently obtain the Chinese character data rule and vein by the method. Fast mastering Chinese characters, a great deal of Chinese characters, and becoming a high-level language learner. Meanwhile, the system can be spread and popularized at low cost through the network Internet, and promotes social equity and high-quality education guarantee of the people.
Disclosure of Invention
The invention mainly solves the technical problem of providing a method for generating an artificial intelligence knowledge map based on a Chinese character forming method, which establishes section codes for different feature codes of Chinese characters by taking the Chinese character forming method as a basis to form the following steps: chinese characters-stroke number-phonetic part-phonetic alphabet and polyphone-part of speech-variant character-common false character-four corner number-Chinese character making method-unique digital ID number of multi-section code. The method is characterized in that the number of strokes of a Chinese character, the phonetic parts of the Chinese phonetic alphabet, the part of speech of the Chinese character, variant characters of the Chinese character, common kana characters of the Chinese character and four corner numbers of the Chinese character are taken as basic dimensions, and the composition mode of a Chinese character making method is taken as a core dimension to be induced, analyzed and associated. Finally, an artificial intelligence knowledge map based on the Chinese character making method is generated.
The invention is realized by the following technical scheme.
The invention provides a method for generating an artificial intelligence knowledge map based on a Chinese character making method, which is characterized by comprising the following steps: the specific working steps comprise:
1) defining the range and set of Chinese characters;
2) carrying out section coding processing on the stroke number of the Chinese character, and determining the unique digital ID number of the stroke number section coding;
3) carrying out section coding processing on the Chinese pinyin part, and determining a unique digital ID number of the section coding of the Chinese pinyin part;
4) carrying out section coding processing on Chinese pinyin and polyphone of the Chinese characters, and determining the unique digital ID number of the section coding of the Chinese pinyin and the polyphone of the Chinese characters;
5) carrying out section coding processing on part of speech of the Chinese character, and determining a unique digital ID number of the section coding of the part of speech of the Chinese character;
6) carrying out section coding processing on the Chinese character variant characters, and determining the unique digital ID number of the section coding of the Chinese character variant characters;
7) carrying out section coding processing on the Chinese character Tong-Han, and determining the unique digital ID number of the section coding of the Chinese character Tong-Han;
8) carrying out section coding processing on the four-corner number of the Chinese character, and determining the unique digital ID number of the section coding of the four-corner number of the Chinese character;
9) carrying out section coding processing on the Chinese character word-making method, and determining the unique digital ID number of the section coding of the Chinese character word-making method;
10) establishing an artificial intelligence knowledge graph based on the ID number of the Chinese character word-building method by taking the ID number of the Chinese character stroke number, the ID number of the Chinese pinyin sound part, the part-of-speech ID number of the Chinese character, the ID number of the foreign-type character of the Chinese character, the ID number of the common-type character of the Chinese character and the ID number of the four-corner number of the Chinese character as basic dimensions and taking the ID number of the Chinese character word-building method as a core dimension;
11) and establishing the transverse connection of the knowledge graph through a knowledge graph editing tool.
Further, the Chinese character range and the set in the step 1) comprise all Chinese characters such as oracle, traditional Chinese characters, simplified Chinese characters and the like.
Further, the Chinese character stroke number segment codes in the step 2) are arranged in sequence according to the size of the Chinese character stroke number Arabic numerals.
Further, the part of speech of the Chinese characters in the step 5) is classified into: nouns, verbs, adjectives, adverbs, pronouns, prepositions, quantifiers, conjunctions, auxiliary words, numerators, sigers, and pseudonyms, and section coding is performed according to the part-of-speech classification of the modern Chinese.
Further, the Chinese characters of step 7) are arranged according to the sound parts and are subjected to segment coding.
Further, the Chinese character making method of the step 9) carries out section coding according to pictographs, fingering, meeting meanings, pictophonetics, commentary and pretending.
Further, the step 10) generates an artificial intelligence knowledge map based on the Chinese character making method, and can display a core structure and an integral knowledge framework and establish a logic network.
The invention has the beneficial effects that: the invention creates a logic array and a knowledge map by coding the Chinese character characteristic sections, uniquely digitizing ID and generating an artificial intelligence knowledge map based on a Chinese character word-making method. The natural language processing engine can generate a knowledge graph based on the method, so that Chinese can be understood more accurately and efficiently, and data mining and machine deep learning are performed. The logical chain of the dimension of the Chinese character making method is opened, and the comprehension capability of the computer semantic calculation can be improved. And the Chinese character learner can intuitively and efficiently obtain the Chinese character data rule and venation through the method, quickly master a large number of Chinese characters and become a high-level language learner. Meanwhile, the system can be spread and popularized at low cost through the network Internet, and promotes social equity and high-quality education guarantee of the people.
Drawings
FIG. 1 is a sequence table of the Chinese character stroke section coding of the present invention.
FIG. 2 is an example of "line" word stroke segment encoding of the present invention.
FIG. 3 is the sequence table of the Chinese character Pinyin part segment codes of the present invention.
FIG. 4 is an example of the "line" phonetic part knowledge map of the present invention.
FIG. 5 is an example of a knowledge graph of polyphone in the phonetic part of the "line" character of the present invention
FIG. 6 is a sequence table of part-of-speech section codes of Chinese characters in accordance with the present invention.
FIG. 7 is an example of a knowledge map of the multiple parts of speech of polyphone in the "line" character pronunciation part of the present invention.
FIG. 8 is an example of the knowledge map of the multiple-word variant characters of the polyphone part of the "line" character pronunciation part of the present invention.
FIG. 9 is an example of a knowledge map of the multi-pronouncing variant kanji of the "line" character pronunciation portion of the present invention.
FIG. 10 is a knowledge graph of four corner numbers of pronouncing characters and pronouncing characters of the line part of the Chinese character.
FIG. 11 is a block code table of the present invention.
FIG. 12 is a knowledge graph example of the four corner number word-making method for the polyphone characters of the phonetic part of the "line" character
FIG. 13 is a knowledge map of the unique digitized ID numbers of the "line" word multi-segment codes of the present invention.
FIG. 14 is the artificial intelligence knowledge map generated by the Chinese character line-making method of the present invention.
FIG. 15 is a pictographic method of creating an artificial intelligence knowledge map and building a connection in accordance with the present invention.
FIG. 16 is a diagram of the artificial word method of the present invention for generating an artificial intelligence knowledge graph and establishing connections.
FIG. 17 is an artificial intelligence knowledge graph generated and associated by the idea word-building method of the present invention.
FIG. 18 is a diagram of the method for forming words by shape and sound of the present invention to generate artificial intelligence knowledge map and establish relationship.
FIG. 19 is a method for transferring words to create an artificial intelligence knowledge map and establish relationships in accordance with the present invention.
FIG. 20 is a diagram of artificial intelligence knowledge graph generation and association establishment by the fake borrowing method of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention is provided to enable those skilled in the art to more readily understand the advantages and features of the present invention, and to clearly and unequivocally define the scope of the present invention.
A method for generating artificial intelligence knowledge map based on Chinese character making method includes the following steps:
1) defining the range and set of Chinese characters;
the character set comprises all Chinese characters such as oracle-bone inscription, traditional Chinese characters, simplified Chinese characters and the like,
oracle is based on the book "Oracle dictionary" by Wangbing Benxing, published by Beijing Art Press;
the traditional Chinese characters are based on the book Wen Jie word and the book Kangxi dictionary;
simplified Chinese characters are based on the simplified Chinese character scheme published by State administration of the people's republic of China in 1956, and finally the simplified character general table is formulated. 2) Referring to fig. 1 and 2, the segment coding process is performed according to the stroke number of the Chinese character, and a unique digital ID number containing the stroke number segment coding is established;
in the process of establishing Chinese character coding, firstly, the established coding section adopts stroke number as the unique digital ID number and adopts stroke number sequencing. Meanwhile, since the Chinese character font changes greatly in ancient times and nowadays, especially, many of the constituent elements adopted by oracle and seal characters are annihilated in the evolution history and are inconsistent with the modern Chinese characters, the classification mode of the radicals is not adopted,
stroke number segment codes are arranged in sequence according to the stroke number Arabic numerals of the Chinese characters;
divide into one, two, three, up to thirty-three;
and uniformly classifying the Chinese characters with More strokes into More parts of More than one.
3) Referring to fig. 3 and 4, the section encoding process is performed according to the chinese pinyin part, and a unique digitized ID number containing the section encoding of the chinese pinyin part is established. The Chinese Pinyin is sorted according to 26 letters, wherein the Chinese has no initial parts of i, v and u, and the total number of the initial parts is 23.
4) Referring to fig. 5, segment coding processing is performed according to the chinese pinyin and polyphone of the chinese character, and a unique digital ID number including the segment coding of the chinese pinyin and polyphone of the chinese character is determined;
polyphone is a word with two or more pronunciations, different pronunciations have different meanings, different usage and different parts of speech. The pronunciation distinguishes the functions of part of speech and word meaning; according to different use conditions and different pronunciations, the pronunciations have different usage functions,
the Chinese phonetic alphabet and the multi-phonetic character section coding are that the Chinese character is distinguished to have a plurality of phonetic parts, each phonetic part has a plurality of pronunciations, then the section coding is analogized, and the number of the pronunciations is marked as several.
If there are multiple pronunciations in a certain part of a Chinese character, for simplicity, the mode is labeled "number/total number".
Example (c):
xing is an
① go around three people, and have the question of my teacher (statement & description)
Line h ng
② Yuanyang Shiqi-twelve Royal.
5) Referring to fig. 6 and 7, the segment coding process is performed according to the part of speech of the chinese character, and a unique digital ID number including the segment coding of the part of speech of the chinese character is established; according to the classification of parts of speech of modern Chinese, the classification is as follows: 1 noun 2 verb 3 adjective 4 adverb 5 pronoun 6 preposition 7 adverb 8 conjunctions 9 helpwords 10 pronouns 11 sigh words 12 analogies.
6) Referring to fig. 8, the section coding process is performed according to the variant Chinese characters, and a unique digital ID number including the section coding of the variant Chinese characters is determined; variant characters: the Chinese characters are a group of characters with the same pronunciation and meaning but different font style, because the Chinese characters are composed of ideograms, notes and marks, the angle of selection of the ideograms is different from people to people, the notes are different from the letters in the alphabetic writing, therefore, the phenomenon of one character with multiple shapes is all the same in the history of the Chinese characters,
the number of the character is 1, if no variant character exists, the mark is 1;
if there is variant word, arrange in order behind the number 1;
● if a Chinese character has multiple variant characters, it is labeled as "serial/total" mode for simplicity.
7) Referring to fig. 9, the section coding process is performed according to the kanji character, and a unique digital ID number including the section coding of the kanji character is determined;
if there is no kana, labeled 0;
if the number is a logical character, the numbers 1 are arranged in sequence;
if a Chinese character has multiple common false, for simplicity, it is labeled as "sequence/total" mode.
The examples of the pass-false characters arranged according to the sound parts are as follows:
universal kana example table
8) Referring to fig. 10, the sector coding process is performed according to the four-corner number of the chinese character, and a unique digital ID number including the sector coding of the four-corner number of the chinese character is determined;
the four-corner number character searching method is a common character searching method as the pinyin character searching method and the radical character searching method, the four-corner number can be used for inputting Chinese characters like strokes, the efficiency is higher than that of strokes, and code fetching is visual and convenient.
In the four-corner number character-looking up method, basic strokes of horizontal stroke, vertical stroke, left falling stroke and right falling stroke are reserved and are called single strokes, and meanwhile, some character-forming units called compound strokes are added, and are combinations of a plurality of basic strokes, such as , ten and the like which are intersected with each other, and the compound strokes are called fork; the 'eight' and 'person' formed by left falling and right falling are called 'eight', and the complex strokes are also common in Chinese characters. Ten numbers are defined in the four corner numbers by a single pen and a complex pen, and are respectively represented by ten numbers from 0 to 9. The four-corner number character-searching method is characterized by that according to the single stroke or complex stroke contained in Chinese character the Chinese character can be numbered, it does not depend on writing stroke order, but adopts the single stroke or complex stroke form of four corners of left upper corner, right upper corner, left lower corner and right lower corner of Chinese character, so that it has four codes, and one Chinese character can be represented by four numerals. The coding method can be directly used for small keyboard input or can be used for large keyboard input. And performing section coding processing according to the four-corner number of the Chinese character, and determining a unique digital ID number containing the section coding of the four-corner number of the Chinese character.
9) Referring to fig. 11 and 12, the section coding process is performed according to the chinese character construction method, and a unique digital ID number including the section coding of the chinese character construction method is established;
the Chinese character forming method includes pictograph, fingering, meeting, pictophonetic, commentary and deception;
building a section code: 01 pictograph-02 means-03 meeting-04 pictophonetic-05 notes-06 pretends.
10) Referring to fig. 13, an artificial intelligence knowledge graph based on the Chinese character word-making method is generated by taking the Chinese character stroke number ID number, the Chinese pinyin part ID number, the Chinese character part of speech ID number, the Chinese character variant character ID number, the Chinese character false-word ID number and the Chinese character four-corner number ID number as basic dimensions and taking the Chinese character word-making method ID number as a core dimension.
11) Referring to fig. 14, 15, 16, 17, 18, 19 and 20, an artificial intelligence knowledge graph based on the Chinese character forming method is generated, a core structure and an overall knowledge framework can be displayed, and a logic network is established.
Those skilled in the art will appreciate that, in addition to implementing the system and its various modules, devices, units provided by the present invention in pure computer readable program code, the system and its various devices provided by the present invention can be implemented with the same functionality in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like by entirely logically programming method steps. Therefore, the system and various devices thereof provided by the present invention can be regarded as a hardware component, and the devices included in the system and various devices thereof for realizing various functions can also be regarded as structures in the hardware component; means for performing the functions may also be regarded as structures within both software modules and hardware components for performing the methods.
What has been described above is merely a specific embodiment of the present invention. It will be apparent to those skilled in the art that various changes and modifications can be made without departing from the inventive concept thereof, and these changes and modifications can be made without departing from the spirit and scope of the invention.
Claims (7)
1. A method for generating artificial intelligence knowledge map based on Chinese character making method is characterized in that: the specific working steps comprise:
1) defining the range and set of Chinese characters;
2) carrying out section coding processing on the stroke number of the Chinese character, and determining the unique digital ID number of the stroke number section coding;
3) carrying out section coding processing on the Chinese pinyin part, and determining a unique digital ID number of the section coding of the Chinese pinyin part;
4) carrying out section coding processing on Chinese pinyin and polyphone of the Chinese characters, and determining the unique digital ID number of the section coding of the Chinese pinyin and the polyphone of the Chinese characters;
5) carrying out section coding processing on part of speech of the Chinese character, and determining a unique digital ID number of the section coding of the part of speech of the Chinese character;
6) carrying out section coding processing on the Chinese character variant characters, and determining the unique digital ID number of the section coding of the Chinese character variant characters;
7) carrying out section coding processing on the Chinese character Tong-Han, and determining the unique digital ID number of the section coding of the Chinese character Tong-Han;
8) carrying out section coding processing on the four-corner number of the Chinese character, and determining the unique digital ID number of the section coding of the four-corner number of the Chinese character;
9) carrying out section coding processing on the Chinese character word-making method, and determining the unique digital ID number of the section coding of the Chinese character word-making method;
10) finally, establishing an artificial intelligence knowledge graph based on the Chinese character word-making method by taking the number ID number of strokes of the Chinese character, the number ID of the phonetic part of the Chinese character, the part-of-speech ID number of the Chinese character, the number ID of variant characters of the Chinese character, the number ID of common-case characters of the Chinese character and the number ID of four corners of the Chinese character as basic dimensions and taking the number ID of the Chinese character word-making method as a core dimension;
11) and establishing the transverse connection of the knowledge graph through a knowledge graph editing tool.
2. The method for generating artificial intelligence knowledge graph based on Chinese character construction method according to claim 1, wherein the Chinese character range and set of step 1) includes all Chinese characters such as oracle, traditional Chinese characters and simplified Chinese characters.
3. The method for generating artificial intelligence knowledge map based on Chinese character making method according to claim 1, wherein the stroke number segment codes of the Chinese characters of step 2) are arranged in sequence according to the Arabic numeral size of the stroke number of the Chinese characters.
4. The method for generating artificial intelligence knowledge map based on Chinese character making method according to claim 1, wherein the part of speech of Chinese characters in step 5) is classified according to the part of speech of modern Chinese characters as follows: nouns, verbs, adjectives, adverbs, pronouns, prepositions, quantifiers, conjunctions, auxiliary words, numerators, sigers, and pseudonyms, and section coding is performed according to the part-of-speech classification of the modern Chinese.
5. The method for generating artificial intelligence knowledge graph based on Chinese character making method according to claim 1, wherein said Chinese characters of step 7) are segmented and coded according to the arrangement of sound parts.
6. The method for generating artificial intelligence knowledge graph based on Chinese character modeling method according to claim 1, wherein the Chinese character modeling method of step 9) performs section coding according to pictographs, fingering, meeting, pictophonetics, commentary, and fiction.
7. The method for generating an artificial intelligence knowledge graph based on the Chinese character forming method according to claim 1, wherein the artificial intelligence knowledge graph based on the Chinese character forming method generated in the step 10) can show a core structure and an overall knowledge framework and establish a logic network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911391218.3A CN111353047A (en) | 2019-12-30 | 2019-12-30 | Method for generating artificial intelligence knowledge map based on Chinese character making method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911391218.3A CN111353047A (en) | 2019-12-30 | 2019-12-30 | Method for generating artificial intelligence knowledge map based on Chinese character making method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111353047A true CN111353047A (en) | 2020-06-30 |
Family
ID=71195734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911391218.3A Pending CN111353047A (en) | 2019-12-30 | 2019-12-30 | Method for generating artificial intelligence knowledge map based on Chinese character making method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111353047A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286176A (en) * | 1999-12-01 | 2001-03-07 | 罗宇翔 | Method for editing index-type Chinese dictionary and manner for expressing pronunciation, shape and meaning of word |
| CN1409240A (en) * | 2001-09-05 | 2003-04-09 | 王金根 | New audio-video information system of attributing all things and words |
| CN101493999A (en) * | 2009-02-18 | 2009-07-29 | 贾守治 | Hanzi direct search tri-code word detection method |
| CN104462512A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Chinese information search method and device based on knowledge graph |
| CN109656385A (en) * | 2018-12-28 | 2019-04-19 | 北京金山安全软件有限公司 | Input prediction method and device based on knowledge graph and electronic equipment |
-
2019
- 2019-12-30 CN CN201911391218.3A patent/CN111353047A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1286176A (en) * | 1999-12-01 | 2001-03-07 | 罗宇翔 | Method for editing index-type Chinese dictionary and manner for expressing pronunciation, shape and meaning of word |
| CN1409240A (en) * | 2001-09-05 | 2003-04-09 | 王金根 | New audio-video information system of attributing all things and words |
| CN101493999A (en) * | 2009-02-18 | 2009-07-29 | 贾守治 | Hanzi direct search tri-code word detection method |
| CN104462512A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Chinese information search method and device based on knowledge graph |
| CN109656385A (en) * | 2018-12-28 | 2019-04-19 | 北京金山安全软件有限公司 | Input prediction method and device based on knowledge graph and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 陈涛: "《康熙字典》的古汉语知识图谱构建方法研究" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Coulmas | Writing systems: An introduction to their linguistic analysis | |
| CN110489760A (en) | Based on deep neural network text auto-collation and device | |
| US5119296A (en) | Method and apparatus for inputting radical-encoded chinese characters | |
| CN105677822A (en) | Enrollment automatic question-answering method and system based on conversation robot | |
| Secord | Science in Print: Essays on the History of Science and the Culture of Print | |
| Cavalli-Sforza et al. | Arabic readability research: current state and future directions | |
| CN1027558C (en) | Five-stroke and two-dimension encoding method and keyboard | |
| CN105045410A (en) | Method for correspondingly identifying formalized phonetic alphabets and Chinese characters | |
| Youguang | Modernization of the Chinese language | |
| CN115859962B (en) | Text readability evaluation method and system | |
| CN111353047A (en) | Method for generating artificial intelligence knowledge map based on Chinese character making method | |
| CN103838393A (en) | Chinese character structure digital literacy input method | |
| Hsieh | Hanzi, Concept and Computation: A preliminary survey of Chinese Characters as a Knowledge Resource in NLP | |
| Gupta et al. | Implementation of rule based algorithm for Sandhi-Vicheda of compound hindi words | |
| Vachkova et al. | School in Digital Age: How Big Data Help to Transform the Curriculum. Information 2021, 12, 33 | |
| CN110502128B (en) | Chinese character multi-element input method and system | |
| Arafah et al. | Typos’ Effects on Web-Based Programming Code Output: A Computational Linguistics Study | |
| Zhao | Chinese character components, radicals and phonetics | |
| Li et al. | CLGC: A corpus for Chinese literary grace evaluation | |
| KR20000072146A (en) | The high speed interpretative method program of the English sentences with the color pens | |
| He et al. | The Establishment of Chinese Character Reference Framework for the English Monophthong | |
| Fakhriniso | METHODS OF TEACHING JAPANESE HIEROGLYPHS USING COMPUTER SIMULATION MODELS BASED ON THE TYPE OF READING | |
| Li | Constant Evaluation of L2 Students' English Witing Ability. | |
| CN114115886A (en) | Method for realizing pure Chinese programming and establishing pure Chinese operating system by using Chinese character positive and negative numerical code method | |
| Lyu et al. | Multimodal Discourse Analysis of English Teaching Materials in Colleges and Universities from the Perspective of Ecological Philosophical Perspective |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200630 |
|
| RJ01 | Rejection of invention patent application after publication |