Method for analyzing language structure by using linguistic expression

Abstract

The present invention relates to a method for analyzing the structure of more than 7,000 languages existing on the earth, by using linguistic expressions, the method comprising the steps of: analyzing a morpheme and a syntax of a target sentence by a morpheme and syntax analysis unit; and calculating, by a linguistic expression calculation unit, on the basis of a pre-learned linguistic expression learning algorithm provided from a linguistic expression learning algorithm, a linguistic expression for the morpheme and the syntax of the sentence analyzed by the morpheme and syntax analysis unit, wherein the linguistic expression calculation unit divides the sentence into four parts including an upper left part, a lower left part, an upper right part, and a lower right part, around a sentence center symbol, assigns a subject symbol to the upper left part, assigns a core verb symbol to the lower left part, assigns a verb type symbol (or a predicate symbol) to the lower right part, assigns a non-predicate symbol for the remaining phrase, except for the subject and the verb, in the upper right part, and then inputs symbolized specific information such as a character count symbol (.) indicating the character count of a noun, an adjective, and the like with a number, along with person symbols (1 to 4) indicating a first person, a second person, a third person, and a non-person to at least one of four subscripts including an upper left script, a lower left subscript, an upper right subscript, and a lower right subscript of each assigned symbol. Accordingly, a specific sentence of a specific language is precisely analyzed into an accurate sentence structure, thereby improving the efficiency of linguistic usages such as sentence recognition, interpretation, translation, search, and the like.

Description

Language structure analysis method using linguistic formulas

[0001] The present invention relates to a method for analyzing language structure using a linguistic formula, and more specifically, to a method for analyzing language structure using a linguistic formula that analyzes language structure syntactically, targeting the principle by which words compose sentences, by using a linguistic formula that hierarchically subdivides both functional and morphological components of sentences of a specific language.

[0002] With the development of artificial intelligence (AI) and machine learning, major technological challenges are emerging, including the analysis of natural language (including Esperanto) that humans use to communicate in daily life, the understanding of natural language that enables electronic devices to operate according to input given in natural language, and the generation of natural language that converts the contents of videos or tables into natural language that humans can understand.

[0003] Linguistics is an academic discipline that studies the principles by which language arises, changes, and is used. It is used in various fields such as anthropology, psychology, semiotics, and cryptography, and has had a great influence on foreign language learning, but recently, its development and application are becoming more active in order to conveniently use electronic devices such as question / answer, information retrieval, voice information input, information analysis, foreign language translation, voice recognition, and character notation through artificial intelligence using natural language processing.

[0004] To process the more than 7,000 natural languages ​​that exist on Earth, it is necessary to accurately analyze the structure of sentences, and the more detailed the sentence structure is, the higher the accuracy can be.

[0005] As one method of representing the structure of a sentence, a method of classifying the structure of a sentence hierarchically and representing it as a tree diagram is being utilized, as shown in Figure 1.

[0006] However, in these tree diagrams, there was a problem that the structure of the tree diagram became more complex as the sentences became more complex.

[0007] Moreover, despite the complex structure, there were limitations in analyzing the sentence structure because information that could be consistently seen, such as person, nominative case, possessive case, gender, singular, and plural, was not displayed.

[0008] Meanwhile, with regard to language analysis, Patent Publication No. 10-2018-0057922, cited as a prior art document in this application, discloses an invention for correcting errors occurring in speech recognition through post-processing by a speech recognition error correction device based on post-processing using language analysis, including: a speech recognition unit that recognizes input speech and outputs the recognition result in the form of text, as illustrated in FIG. 2; a speech recognition unit that performs morphological analysis on the output text sentence, performs syntax analysis using the morphological analysis result, and performs semantic analysis on the syntax analysis result as a unit of dependent structure; an error candidate search unit that searches for error candidates using preset air information based on the analysis results analyzed through the morphological analysis, syntax analysis, and semantic analysis; a correct answer candidate search unit that identifies possible correct answer candidates for the searched error candidates and ultimately generates one correct answer result; and a text generation unit that generates a final text with the error corrected for the input speech using the generated correct answer candidates.

[0009] However, as shown in Fig. 3, the result of the parsing in the speech recognition error correction device based on post-processing using language analysis according to the prior literature only lists the sentence syntax, and does not display detailed classification information on the functional composition and morphological composition of each syntax.

[0010] For example, there is a problem in that, in the past, only the syntax of a sentence was broken down and depicted, and specific information about each syntax and detailed information about the structure of the entire sentence were not provided.

[0011] That is, since various information about the sentence, such as information indicating whether each phrase is a subject, predicate, or modifier; information about the person, gender, nominative case, possessive case, etc. of the subject; information about the type of verb that constitutes the predicate that determines the structure of the sentence if it is a predicate; and information about whether it is a word, a derived phrase, a derived clause, a negative sentence, or an interrogative sentence if it is a non-predicate, were not systematically classified, there were limitations in analyzing the language structure.

[0012] The present invention has been devised to solve the above-described problem, and its purpose is to provide a language structure analysis method using a language formula, which can precisely and precisely analyze the exact sentence structure of sentences in each language by expressing the sentence structure of a specific language among the more than 7,000 languages ​​existing on Earth in a three-dimensional and hierarchical manner down to the minimum level of the language, that is, the most complex content, in a language formula.

[0013] Although the purpose of the present invention has been specifically described above, not only the purpose described above, but also additional purposes derived in the process of achieving the purpose described above are included in the scope of the problem to be solved by the present invention.

[0014] In a preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing the structure of a language using a language formula is provided, comprising: a step of analyzing morphemes and phrases of a target sentence by a morphological and syntactic analysis unit; and a step of calculating a language formula for the morphemes and phrases of the sentence analyzed by the morphological and syntactic analysis unit based on a pre-learned language formula learning algorithm provided from a language formula learning algorithm by a language formula calculation unit, wherein the language formula calculation unit divides a sentence into four parts, namely, upper left, lower left, upper right, and lower right, centered on a sentence center symbol, and assigns a subject symbol to the upper left, a core verb symbol to the lower left, a verb type symbol to the lower right, and a non-predicate symbol for the remaining phrases excluding the subject and the verb to the upper right.

[0015] In another preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing the structure of a language is provided using a language formula including, in the above-described embodiment, upper left superscript, lower left superscript, upper right superscript, and lower right superscript symbols for each of the sentence-centered symbol, the subject symbol, the core verb symbol, the verb type symbol, and the non-predicate symbol for the remaining phrase.

[0016] In another preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing the structure of a language is provided using a language formula, in which the verb type symbol in the above-described embodiment includes a first verb (V1) indicating symbol for all intransitive verbs other than the be verb, a second verb (V2) indicating symbol for the be verb, a third verb (V3) indicating symbol for all transitive verbs except the fourth verb (V4) which is a transitive verb carrying an object and an objective complement, and a fourth verb (V4) indicating symbol for a transitive verb carrying an object and an objective complement.

[0017] In another preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing the structure of a language is provided using a language formula, in which, in the above-described embodiment, the upper left superscript, lower left superscript, upper right superscript, and lower right superscript of the verb type symbol are assigned one of a person symbol indicating a person, a quantity symbol indicating singular and plural, and a tense symbol of a base form, present tense, past tense, present perfect tense, and past perfect tense, for each of the first verb (V1) to fourth verb (V4) indicator symbols.

[0018] In another preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing the structure of a language is provided using a language formula in which the subject symbol and the non-predicate symbol in the above-described embodiment include any one of a noun symbol indicating a noun, an adjective symbol indicating an adjective, an adverbial symbol indicating an adverb and a prepositional phrase, an infinitive symbol indicating a to-infinitive or to-less infinitive, a gerund or participle symbol indicating a verb in the ing form, an ed form symbol indicating a verb in the ed form, a being participle symbol indicating a verb form in the being pp form, and a derivative clause symbol indicating a derivative clause.

[0019] In another preferred embodiment of the present invention, in order to solve the above-described problem, in the above-described embodiment, the subject symbol and the non-predicate symbol are provided in one of four digits located at the upper left, lower left, upper right, and lower right of the subject symbol and the non-predicate symbol, a person symbol (1 to 4) indicating the first person, the second person, the third person, and the impersonal, a character symbol (.) indicating the number of characters of the corresponding noun together with a number, a number symbol (1, 2, 4) indicating the number of the noun as singular, plural, and dual, a property symbol (a, b, c, d) indicating the physical properties of the noun such as living thing, other thing, mental thing, and vulgar thing, a case symbol (1 to 9) indicating the nominative, possessive, objective, dative, vocative, nominative, ablative, and self, a gender symbol (1, 2, 3) indicating masculine, feminine, and neutral, a living thing symbol (1, 2) indicating living and inanimate things, and the above A method for analyzing language structure using a linguistic expression is provided, which indicates at least one of the following symbols: this, that, that, there, and a movement symbol (., -, ∼, →) at the top of the subject symbol and the non-predicate symbol.

[0020] In another preferred embodiment of the present invention, in order to solve the above-described problem, in the above-described embodiment, the subject symbol and the non-predicate symbol are provided with parentheses to the right of the subject symbol and the non-predicate symbol, and for the remaining phrases excluding the subject and the predicate within the parentheses, at least one of a noun symbol indicating a noun, an adjective symbol indicating an adjective, an adverbial symbol indicating an adverb and a prepositional phrase, an infinitive symbol indicating a to-infinitive or to-less infinitive, a gerund or participle symbol indicating a verb in the ing form, an ed form symbol indicating a verb in the ed form, a being participle symbol indicating a verb in the being pp form, and a derivative clause symbol indicating a derivative clause is provided, thereby expressing a linguistic formula for a phrase modifying the subject symbol and the non-predicate symbol in front of the parentheses.

[0021] In another preferred embodiment of the present invention, in order to solve the above-described problem, a method for analyzing language structure using a language formula is provided, wherein in the above-described embodiment, the upper left superscript of the sentence-centered symbol includes any one of a symbol (0) indicating that the text is spoken over time, a symbol (1) indicating that the text is written from left to right, a symbol (2) indicating that the text is written from right to left, a symbol (3) indicating that the text is written from top to bottom, a symbol (4) indicating that the text is written from bottom to top, a symbol (5) indicating a drum sound language, and a symbol (6) indicating other things.

[0022] In another preferred embodiment of the present invention, in order to solve the above-described problem, a language structure analysis method using a language formula is provided, in which, in the above-described embodiment, the upper right superscript of the sentence-centered symbol includes a symbol (a) representing what is in the sentence as it is and a symbol (e) representing what the sentence means.

[0023] In another preferred embodiment of the present invention, in order to solve the above-described problem, a language structure analysis method using a language formula is provided, in which, in the above-described embodiment, the lower part of the sentence-centered symbol includes a symbol indicating, in numbers or letters, what language the sentence-centered symbol is dealing with.

[0024] In another preferred embodiment of the present invention, in order to solve the above-described problem, in the above-described embodiment, the symbols further include a connection symbol representing a conjunction used in a sentence of a natural language, so that the symbols can be added in parallel, and further include a punctuation mark used in a sentence of a natural language, so that the type of sentence can be expressed, and a language structure analysis method using a language formula is provided.

[0025] According to a method for analyzing language structure using a language formula according to a preferred embodiment of the present invention, by expressing the sentence structure of a specific language in detail and using a language formula, a specific sentence of a specific language can be precisely analyzed as an accurate sentence structure, thereby improving the efficiency of linguistic utilization such as sentence recognition, interpretation, translation, and search.

[0026] According to a method for analyzing language structure using a language formula according to a preferred embodiment of the present invention, by expressing the sentence structure of a specific language in detail using a language formula, there is an effect of being able to systematically understand the structure of a specific language.

[0027] According to a method for analyzing language structure using a language formula according to a preferred embodiment of the present invention, there is an effect in that the level of development of a language can be judged by using the level of expression of a language formula that expresses the sentence structure of a specific language in detail as an indicator.

[0028] According to a method for analyzing language structure using a language formula according to a preferred embodiment of the present invention, it is possible to help in linguistic research by determining the similarity between a specific language and another language through comparison of language formulas that express the sentence structure of a specific language in detail.

[0029] Although the effects of the present invention have been specifically described above, the present invention includes not only the above-described effects but also additional effects derived in the process of obtaining the above-described effects as effects of the present invention.

[0030] Figure 1 is an example diagram showing the hierarchical classification of sentence structures in conventional linguistics and displaying them as a tree diagram.

[0031] Figure 2 is a flowchart illustrating the operation flow of a speech recognition error correction method based on post-processing using language analysis according to prior literature.

[0032] Figure 3 is an example diagram showing the results of syntactic analysis in a speech recognition error correction device based on post-processing using language analysis according to prior literature.

[0033] Figure 4 is a system configuration diagram for implementing a language structure analysis method using a language formula according to a preferred embodiment of the present invention.

[0034] FIG. 5 is a structural diagram showing a language formula structure in a language structure analysis method using a language formula according to a preferred embodiment of the present invention.

[0035] FIG. 6 is an exemplary diagram showing the arrangement of the subscript information (or satellite information) of the subject symbol, verb symbol, and non-predicate symbol in a language structure analysis method using a language formula according to a preferred embodiment of the present invention.

[0036]

[0037] Throughout the specification, including the drawings and detailed description, elements that are identical and have the same function and / or the same technical or physical effect are given the same reference numerals or are given the same designations, and the descriptions of elements and their functions shown or described in different embodiments are interchangeable or applicable to each other in different embodiments.

[0038] In addition, for the purpose of simplifying the identification of the drawings, reference numbers described in one drawing may be omitted in other drawings, and parts that are not related to the present invention or the description of a specific part may be omitted in the drawings, but this does not mean that they are absent.

[0039] In addition, it should be noted that the reference symbols used in the drawings of the prior art and the drawings of the present invention are unrelated to each other, and even if they are the same reference symbols, they are different and separate components.

[0040] Hereinafter, with reference to the attached drawings, embodiments of the present invention will be described in detail so that a person having ordinary skill in the art to which the present invention pertains can easily practice the invention.

[0041] It should be noted that the following embodiments are not intended to limit the present invention, and that it may be implemented in many different forms, including various modifications, equivalents, or alternatives.

[0042] The features and effects of the present invention will become clearer with reference to the embodiments described in detail below together with the attached drawings.

[0043] In describing embodiments of the present invention, specific descriptions of known functions or configurations will be omitted unless actually necessary. Furthermore, the terms described below are defined based on their functions in the embodiments of the present invention and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the overall content of this specification.

[0044] Throughout the specification, when a part is said to be "connected" to another part, this includes not only the cases where it is "directly connected" but also the cases where it is "electrically connected" with another element in between.

[0045] Additionally, when a part is said to "include" a component, this should be understood to mean that it may include other components, but not to the exclusion of other components, unless otherwise specifically stated, and does not preclude the presence or possibility of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0046]

[0047] Hereinafter, with reference to FIGS. 4 to 6, a method for analyzing language structure using a language expression according to a preferred embodiment of the present invention will be described in more detail with detailed examples.

[0048] First, a system for implementing a language structure analysis method using a language expression according to a preferred embodiment of the present invention includes a morphological and syntactic analysis unit (100), a language expression production unit (200), a language expression database (300), and a language expression learning algorithm unit (400).

[0049] The morphological and syntactic analysis unit (100) performs morphological analysis on sentences input as text, analyzes them into words divided into morpheme units and the parts of speech of each word, and uses the morphological analysis results to identify syntactic relationships between each word.

[0050] The language expression production unit (200) produces a language expression based on the parts of speech and syntactic relationships of words divided into morpheme units analyzed by the morphological and syntactic analysis unit (100) and the language expression learning algorithm provided by the language expression learning algorithm unit (400). The language expression production process will be described in more detail below.

[0051] The language expression produced by the language expression production unit (200) is stored in the language expression database (300) together with the sentence, the sentence morphological analysis result, and the syntax analysis result.

[0052] The language learning algorithm unit (400) updates the language expression production algorithm by learning from the previously produced language expressions and sentences, sentence morphological analysis results, and syntax analysis results accumulated in the language expression database (300) based on a pre-programmed algorithm that implements a language structure analysis method using language expressions according to a preferred embodiment of the present invention. The learned language expression production algorithm updated in this way is provided to the language expression production unit (200).

[0053]

[0054] Hereinafter, a specific example will be given of a process for producing a language expression based on the part of speech and syntactic relationship of words divided into morpheme units analyzed by the morpheme and syntax analysis unit (100) in the language expression production unit (200) and the language expression learning algorithm provided by the language expression learning algorithm unit (400).

[0055]

[0056] First, as illustrated in FIG. 5, a language expression according to a preferred embodiment of the present invention is divided into four parts centered on a sentence center symbol (S, referred to as 'integral S'), and divided into upper left (SLU: Sentence Left Up), lower left (SLD: Sentence Left Down), upper right (SRU: Sentence Right Up), and lower right (SRD: Sentence Right Down). In this embodiment, the objects assigned to each quadrant divided into upper, lower, left, and right parts centered on the center symbol (S) are, for example, and their positions can be changed and assigned.

[0057] In a language structure analysis method using a language formula according to a preferred embodiment of the present invention, the lower left (SLD) and lower right (SRD) of the lower part centered on the center symbol (S) are assigned analysis symbols for the predicate part of the sentence as predicate parts, and the upper left (SLU) and upper right (SRU) of the upper part are assigned the remainder excluding the predicate part, for example, the subject part and the modifier part.

[0058] The upper left (SLU) of the sentence center symbol (S) is assigned a symbol for the first non-predicate word in the sentence. The symbol for the non-predicate word in the upper left (SLU) of this center symbol (S) becomes the symbol for the subject.

[0059] For example, any one of the non-predicate indicator symbols including the subject symbol represented by a number in the table below may be assigned.

[0060]

[0061] M1M2M314825367

[0062] In Table 1 above, it can be divided into M1 group, M2 group, and M3 group.

[0063] For example, 1 is a noun symbol representing a noun. A noun is a word that reveals existence or a part of existence. Depending on the method of revealing, it can be called a noun if it is revealed by name, a demonstrative noun if it is revealed by pointing to it, a personal noun if it is revealed by a person, etc. The specific details of 1 can be indicated in detail by adding parentheses to the right of 1 and within those parentheses.

[0064] 2 is an adjective symbol indicating an adjective. It corresponds to the word "what" used when answering the question "How is an adjective?"

[0065] Adjectives specifically define the meaning of a noun by appearing before or after it. They can be placed in front or behind it. These 2 can include a, an, the, this, that, etc., and can be distinguished from other adjectives by adding a period (·), bar (―), tilde (∼), etc. above the adjective symbol "2."

[0066] 3 is an adverbial symbol that indicates an adverb and a prepositional phrase. An adverb is a word that modifies something other than a noun and limits its meaning. It can modify verbs, adjectives, adverbs, and sentences, and a one-word adverb is "3 .1 " or you can just say "3" by omitting ".1". And when there are multiple adverbs, you can use the number of characters (.) as many as the number (n) to say "3". .n " can be displayed.

[0067] Meanwhile, when 3 represents a preposition or a prepositional phrase, a circle is placed above "3" to distinguish it from "3" which represents an adverb. " is displayed as ", and when there are two or more words, use the number of characters symbol (.) equal to the number (n) " " can be displayed as " "You can put parentheses on the right side of the expression and provide detailed information within the parentheses.

[0068] 4 is an infinitive symbol representing the to-infinitive in the form of 'to + verb infinitive' or the infinitive without to.

[0069] 5 is a gerund or participle symbol indicating doing (verb+ing).

[0070] 6 is the ed form symbol representing done (verb + ed).

[0071] 7 is the be-ing participle symbol, which indicates the verb form in the be-ing participle (being pp) form.

[0072] Numbers 4 to 7 belonging to this M2 group are derivatives of verbs.

[0073] 8 belongs to the M3 group and is a derived clause symbol meaning a derived clause (subordinate clause).

[0074] The above-mentioned non-predicate indicator symbols, as shown in Figure 6, are again indicated by the upper left superscript, lower left superscript, upper right superscript, and lower right superscript, and the person symbols (1-4) indicating the first person, second person, third person, and impersonal in one of the four superscripts centered around the subject symbol and non-predicate symbol, the character symbol (.) indicating the number of characters of the corresponding noun along with the number, the number symbol (1, 2, 4) indicating the number of the noun as singular, plural, and dual, the property symbols (a, b, c, d) indicating the physical properties of nouns such as living things, other things, mental things, and vulgar things, the case symbols (1-9) indicating the nominative, possessive, objective, dative, vocative, nominative, ablative, locative, and self, the gender symbols (1, 2, 3) indicating masculine, feminine, and neuter, and the living symbol (1, 2) And, among the subject symbols and predicate symbols, at least one of the indicator symbols indicating this, that, that, there, and movement (., -, ~, →) can be indicated by adding it to the upper part of the symbol.

[0075] The non-predicate indicator symbol described above can be applied not only to the subject part in the upper left (SLU) of the central symbol (S), but can also be applied equally to the modifier part in the upper right (SRU).

[0076] Additionally, if there are multiple predicates, the linguistic formula can be derived by listing them repeatedly as many times as there are numbers.

[0077] Meanwhile, the core verb (ε) is indicated at the bottom left (SLD) or bottom right (SRD) of the sentence center symbol (S). In the case of a group verb consisting of two or more words, the first word becomes the core verb (ε), and the rest of the group verbs except the core verb (ε) become residual verbs (ω). In the case of a single-word verb, it becomes the core verb (ε) itself.

[0078] The core verb (ε) displayed in the lower left (SLD) or lower right (SRD) has the following functions:

[0079] 1. The core verb (ε) determines the time of the sentence.

[0080] 2. The core verb (ε) requires a subject before it.

[0081] 3. If the core verb (ε) is placed in front of the subject on the upper left (SLU), it becomes a question.

[0082] 4. When not is placed after the core verb (ε), it becomes a negative sentence.

[0083] 5. When placed in front of the subject with not, it becomes a negative question.

[0084] 6. The derivation clause requires that there be a representative at the very beginning of the derivation theory.

[0085] 7. When the core verb (ε) in a derivative clause comes out of the sentence, the subject and the verb representative before the core verb (ε) are omitted.

[0086] For example, in the sentence "Do Fishes swim?", the subject "Fishes" is a noun, so "1" is placed in the subject part in the upper left (SLU). The core verb "Do", which comes first, comes before the subject "fishes", so the core verb symbol ε is placed in the lower left (SLD) of the sentence center symbol (S), but its position is placed before the "1" in the subject part. In addition, the remaining residual verb (ω) "swim" is an intransitive verb, not a be verb, so it is represented by the first verb (V1) symbol "1" in the lower right (SRD). As a result, ε 1 S1 ? A mathematical expression can be produced using linguistic expressions. At this time, sentence symbols (?) used in general sentences, such as "?", can be used together.

[0087] The lower right (SRD) of the sentence center symbol (S) indicates the verb type symbol (or predicate symbol) with a number or symbol. For example, based on English, all intransitive verbs other than be verbs (V1) are indicated with 1, all second-class verbs (V2) that indicate be verbs are indicated with 2, all third-class verbs (V3) that are transitive verbs except for the fourth-class verb (V4) that are transitive verbs that take an object and an objective complement are indicated with 3, and all fourth-class verbs (V4) that are transitive verbs that take an object and an objective complement are indicated with 4.

[0088] For example, the first verb can be expressed as follows:

[0089] Water flows.

[0090] In the above sentence, in the language structure analysis method using a language formula according to a preferred embodiment of the present invention, water is a noun and a subject, so it is marked as "1" in the upper left (SLU), and flows is an intransitive verb, not a be verb, so it is marked as "1", which is the first verb (V1) symbol, in the lower right (SRD). 1 S1 can produce mathematical expressions and language expressions.

[0091] Meanwhile, the above symbols can be added in parallel by further including a conjunction symbol representing a conjunction used in a natural language sentence, and can express a type of sentence by further including a punctuation mark used in a natural language sentence.

[0092] Additionally, in a language structure analysis method using a language formula according to a preferred embodiment of the present invention, all symbols (e.g., numbers) can be separated by spaces, and numbers within parentheses can also be separated by spaces. However, the space between symbols and parentheses is connected.

[0093] Meanwhile, in a language structure analysis method using a language formula according to a preferred embodiment of the present invention, it can be expressed as a simple formula, but it can also be expressed as a more specifically analyzed basic formula.

[0094] For example, if we look at She was a student, the simple expression expressed in simple language can be expressed as follows.

[0095]

[0096] On the other hand, in the basic formula, the subject She is a noun, so it is 1, and since it is a third person, we can further specify it as "13" by adding 3 to the subscript of noun 1. Furthermore, since She is a personal pronoun, we add a circle (o) to the upper part of 1 to make it " " can be expressed more specifically as:

[0097] Also, since She is singular, we add "1" to the superscript to indicate singularity, so " " can be expressed as, and since She is a female, we add 2 to the lower left subscript, " " can be expressed as " , and since it is the nominative case, 1 is added to the upper left subscript, " " can be expressed as. And since She is one letter, it is written as " in the subscript on the right. " can be expressed as, but the symbol (.1) that usually represents one letter can be omitted. In summary, the subject She is "1" in the simple expression, but in the basic expression or by omitting .1 It can be expressed specifically as follows.

[0098] Also, since the verb was is a be verb, which is a second verb (V2), "2" is used to indicate the second verb symbol at the lower right (SRD) centered on the sentence center symbol (S). " can be expressed as, and since was is past tense, "2" is added to the upper left subscript of 2, " " can be expressed as, and since it is singular, add 1 to the upper right subscript of 2 to get " " can be expressed as ", and since it is a single letter, ".1" can be omitted and said as "2". In summary, was is a past tense singular verb, and only this verb part can be expressed in a verbal form as follows.

[0099]

[0100] Also, since "a student" is a two-letter noun phrase, we use a dot (.) to indicate the number of letters. " can be expressed as, specifically, it is limited by the article a in front, so a dot (·) is added to the top of "2". " is expressed as ", and then "1" comes after it, which represents the noun "student". In other words, " means a noun phrase. " and then add parentheses to the right of it and write specific information inside it. " ( 1)" can be said, "student" is a student and a living thing, so "a" indicating a living thing is indicated as the right subscript of "1" indicating the noun "student". (2 )" can be made more specific.

[0101] Also, since it is a declarative sentence, you can add a period (.) after the parentheses.

[0102] As a result, the basic formula for She was a student can be expressed as follows.

[0103]

[0104] That is, in the language structure analysis method using a language expression according to a preferred embodiment of the present invention, the layers can be expressed with different depths as described above, as needed or according to design.

[0105] The method for analyzing language structure using a language formula according to a preferred embodiment of the present invention described above may also be implemented in the form of a recording medium including computer-executable instructions, such as an application or program module executed by a computer. The computer-readable medium may be any available medium that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include all computer storage media. The computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented by any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0106] The method for analyzing language structure using a language formula according to an embodiment of the present invention described above can be executed by an application that is installed by default on a terminal (which may include a program included in a platform or operating system installed by default on the terminal), and can also be executed by an application (i.e., a program) that a user directly installs on a master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method for analyzing language structure using a language formula according to an embodiment of the present invention described above can be implemented as an application (i.e., a program) that is installed by default on a terminal or directly installed by a user, and can be recorded on a computer-readable recording medium such as a terminal.

[0107] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.

[0108] The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.

Claims

1. In the method of analyzing the structure of language using language formula, A step of analyzing the morphemes and syntax of the target sentence by the morphological and syntax analysis unit, A step of generating a language expression for the morpheme and phrase of the sentence analyzed by the morpheme and phrase analysis unit based on a pre-learned language expression learning algorithm provided from a language expression learning algorithm by a language expression production unit, The above language expression production unit is, Divide the sentence into four parts: upper left, lower left, upper right, and lower right, centered on the central symbol. Assign the subject symbol to the upper left, Assign the key verb symbol to the lower left above, Assign the verb type symbol to the lower right above, Assigning non-predicate symbols to the above idols for the remaining phrases excluding the above subject and the above verb, A method of analyzing the structure of a language using linguistic formulas.

2. In paragraph 1, The above sentence center symbol and Each of the above subject symbol, core verb symbol, verb type symbol, and non-predicate symbol for the remaining phrases includes the upper left superscript, lower left superscript, upper right superscript, and lower right superscript symbols. A method of analyzing the structure of a language using linguistic formulas.

3. In paragraph 1, The above verb type symbols are, The first verb (V1) indicator symbol for all intransitive verbs other than the verb be, The second verb (V2) indicator symbol indicating the verb to be, The third verb (V3) indicator symbol, which is all transitive verbs except the fourth verb (V4), which is a transitive verb that carries an object and an objective complement, and Including the fourth verb (V4) indicator symbol, which is a transitive verb with an object and an objective complement. A method of analyzing the structure of a language using linguistic formulas.

4. In paragraph 3, A method for analyzing the structure of a language using a language formula, wherein the upper left superscript, lower left superscript, upper right superscript, and lower right superscript of the above verb type symbol are assigned one of a person symbol indicating a person, a quantity symbol indicating singular and plural, and a tense symbol of the infinitive, present tense, past tense, present perfect tense, and past perfect tense, for each of the first verb (V1) to fourth verb (V4) symbol.

5. In paragraph 1, The above subject and predicate symbols are, A noun symbol representing a noun, and Adjective symbols that indicate adjectives, and Adverbial symbols indicating adverbs and prepositional phrases, Infinitive symbol indicating to-infinitive or to-less infinitive, A gerund or participle symbol indicating a verb in the ing form, The ed form symbol representing a verb in the ed form, The beating participle symbol, which indicates the verb form in the beating participle (being pp) form, Containing any one of the derivative clause symbols that signify a derivative clause, A method of analyzing the structure of a language using linguistic formulas.

6. In paragraph 5, The above subject and predicate symbols are, With the subject and predicate symbols above as the center, one of the four consonants: upper left, lower left, upper right, and lower right. Person symbols (1-4) indicating the first person, second person, third person, and impersonal, A character count symbol (.) that indicates the number of characters in the noun along with a number, Number symbols (1, 2, 4) that indicate the number of the above nouns as singular, plural, or dual, Property symbols (a, b, c, d) that indicate the physical properties of nouns such as living things, other things, mental things, and vulgar things, Case symbols (1-9) indicating nominative, possessive, objective, dative, vocative, instrumental, ablative, and self, Gender symbols (1, 2, 3) representing masculine, feminine, and neuter, Biological symbols (1, 2) representing living and non-living things, At the top of the subject and predicate symbols, there are indicator symbols indicating this, that, that, there, and movement (., -, ∼, →). Indicate by indicating at least one of the following: A method for analyzing language structure using language formulas.

7. In paragraph 5, The above subject and predicate symbols are, A language structure analysis method using a language formula, which expresses a language formula for a phrase modifying the subject symbol and non-predicate symbol in front of the parentheses by adding parentheses to the right of the subject symbol and non-predicate symbol, and adding at least one of a noun symbol indicating a noun, an adjective symbol indicating an adjective, an adverbial symbol indicating an adverb and a prepositional phrase, an infinitive symbol indicating a to-infinitive or to-less infinitive, a gerund or participle symbol indicating a verb in the ing form, an ed form symbol indicating a verb in the ed form, a being participle symbol indicating a verb form in the being pp form, and a derivative clause symbol indicating a derivative clause, for the remaining phrases excluding the subject and predicate within the parentheses.

8. In paragraph 2, The upper left superscript of the above sentence center symbol is: A symbol (0) indicating what was said over time, A symbol (1) indicating that the text is written from left to right, A symbol (2) indicating that the text is written from right to left, A symbol (3) indicating that the text is written from top to bottom, A symbol (4) indicating that the text is written from the bottom up, Symbols representing the North Korean language (5), Symbols indicating other things (6) A method for analyzing language structure using a language formula, including any one of the following.

9. In paragraph 2, The upper right superscript of the above sentence center symbol is: A symbol (a) that represents the sentence as it is, A symbol (e) that indicates what the sentence means, A language structure analysis method using a language formula, which includes a numeric symbol (n) indicating the number of minimum units of sentence classification.

10. In paragraph 2, At the bottom of the above sentence center symbol, A language structure analysis method using a linguistic formula that includes symbols representing the language being addressed by the sentence-centered symbol in numbers or letters.

11. In any one of paragraphs 1 to 10, The above symbols are, By further including a conjunction symbol representing a conjunction used in a natural language sentence, the above symbols can be added in parallel, A language structure analysis method using linguistic formulas that can express the type of sentence, including punctuation marks used in natural language sentences.

Images