KR102716693B1 - System and method for supporting text conversion services using customized regular expressions for each user - Google Patents

Abstract

A system supporting a text conversion service using a user-specific customized regular expression according to one embodiment of the present invention includes: an input unit for receiving a user's spoken voice; a voice recognition model unit for converting the spoken voice into a primary text, and converting the primary text into a secondary text converted into a regular expression by applying a preset regular expression to be utilized by each user; and a regular expression setting unit for setting and providing a user-specific regular expression.

Description

System and method for supporting text conversion services using customized regular expressions for each user

The present invention relates to a system and method for receiving and processing natural language spoken by a person, and more specifically, to a system and method for supporting a text conversion service using regular expressions customized for each user.

In general, sentences spoken by a person can be converted into text through speech recognition. In automatic translation systems using speech recognition technology and conversation systems based on natural language understanding technology, sentences spoken by a user are input and preset language processing is performed.

Meanwhile, sentences input into language processing systems such as automatic translation systems and conversation systems often have their sentence order changed, such as nouns or adverbs being placed at the end of the sentence, due to the user's free speech or the use of inversion techniques to emphasize the meaning of the sentence.

When sentences composed in a different order from the general sentence structure are input, the quality of the language processing system may deteriorate.

These problems can arise in both rule-based language processing systems, which handle common sentence structures well (i.e., the majority of sentence structures), and statistical-based language processing systems.

Therefore, in conventional language processing systems, in order to process languages such as inverted sentences or vocative cases with missing punctuation marks, the partial or complete matching of character strings was checked and then modified into a pre-specified sentence form for processing. However, for such modification processing, not only was a large database required to cope with all input cases, but there was also the problem that language processing itself was impossible if the constructed database did not match the actual input sentence.

In this regard, Korean Patent Publication No. 1497411 (Title of the Invention: Style Conversion Device, Style Conversion Method, Storage Medium, Automatic Dialogue Service System and Method) discloses a style conversion device including a communication unit which receives a target sentence for conversion, a phrase conversion DB in which specific phrases and style-converted phrases corresponding to them are stored, a phrase comparison unit which separates the last phrase from the target sentence for conversion and selects the style-converted phrase by comparing it with the stored contents of the phrase conversion DB, and a sentence generation unit which forms a result sentence by replacing the phrase included in the target sentence for conversion with the phrase selected by the phrase comparison unit.

Publication of Patent Publication No. 10-2021-0047709

The purpose of the present invention is to provide a system and method that support a text conversion service using a user-specific customized regular expression that can solve conventional problems.

According to one embodiment of the present invention for solving the above problem, a system supporting a text conversion service using a user-specific customized regular expression comprises: an input unit for receiving a user's spoken voice; a voice recognition-conversion model unit for converting the spoken voice into a primary text and replacing the primary text with a secondary text which is a normalized sentence by applying a preset regular expression to be utilized by the user; and a regular expression setting unit for setting and providing a pre-defined regular expression, wherein the voice recognition-conversion model unit comprises: a voice-to-text conversion unit for converting the spoken voice into text through an STT program; a filtering unit for determining whether strings in the converted primary text include strings of a pre-defined regular expression; and a regular expression replacement unit for replacing strings, the strings of which are confirmed by the filtering unit to include strings of a pre-defined regular expression, based on a preset regular expression pattern.

delete

delete

delete

delete

delete

According to one embodiment of the present invention for solving the above problem, a method for converting text using a customized regular expression for each user includes the steps of: receiving a user's spoken voice from an input unit; and converting the spoken voice into a primary text in a voice recognition-conversion model unit, and applying a preset regular expression to be utilized for each user to the primary text to replace it with a secondary text which is a normalized sentence, wherein the voice recognition-conversion model unit includes: a voice-to-text conversion unit which converts the spoken voice into text through an STT program; a filtering unit which determines whether strings in the converted primary text include strings of a pre-defined regular expression; and a regular expression replacement unit which replaces strings confirmed by the filtering unit to include strings of a pre-defined regular expression based on a preset regular expression pattern.

delete

delete

delete

delete

The use of a text conversion system and method using a user-specific customized regular expression according to one embodiment of the present invention provides the advantage of preventing incorrect analysis during natural language processing by enabling correct sentence reconstruction for various sentence formats such as carelessly uttered by a user, inverted sentences, typos, additional exclamations, or meaningless inputs.

FIG. 1 is a device configuration diagram of a text conversion system using user-specific customized regular expressions according to one embodiment of the present invention.
Figure 2 is a detailed configuration diagram of the voice recognition-conversion model part illustrated in Figure 1.
Figures 3 and 4 are examples of regular expressions.
Figure 5 is an example of the algorithm for the regular expression substitution part.
FIG. 6 is a flowchart illustrating a method for supporting a text conversion service using a user-specific customized regular expression according to one embodiment of the present invention.
Figure 7 is a detailed flowchart of process S720 of Figure 6.

Hereinafter, embodiments of the present specification will be described with reference to the accompanying drawings. However, this does not limit the technology described in the present specification to specific embodiments, but should be understood to include various modifications, equivalents, and/or alternatives of the embodiments of the present specification. In connection with the description of the drawings, similar reference numerals may be used for similar components. In the present specification, expressions such as "has," "may have," "includes," or "may include" indicate the presence of a corresponding feature (e.g., a component such as a number, function, operation, or part), and do not exclude the presence of additional features.

As used herein, the phrases “A or B,” “at least one of A and/or B,” or “one or more of A or/and B” can include all possible combinations of the listed items. For example, “A or B,” “at least one of A and B,” or “at least one of A or B” can all refer to (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B.

As used herein, the expressions “first,” “second,” “first,” or “second,” etc. can describe various components, regardless of order and/or importance, and are only used to distinguish one component from another, but do not limit the components. For example, a first user device and a second user device can represent different user devices, regardless of order or importance. For example, without departing from the scope of the rights set forth in this specification, a first component can be referred to as a second component, and similarly, a second component can also be referred to as a first component.

When it is stated that a component (e.g., a first component) is "(operatively or communicatively) coupled with/to" or "connected to" another component (e.g., a second component), it should be understood that the component can be directly coupled to the other component, or can be connected via another component (e.g., a third component). On the other hand, when it is stated that a component (e.g., a first component) is "directly coupled to" or "directly connected" to another component (e.g., a second component), it should be understood that no other component (e.g., a third component) exists between the component and the other component.

The expression "configured to" as used herein can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of." The term "configured to" does not necessarily mean only that which is "specifically designed to" in terms of hardware. Instead, in some contexts, the expression "a device configured to" can mean that the device is "capable of" doing something together with other devices or components.

For example, the phrase "a processor configured (or set) to perform A, B, and C" can mean a dedicated processor (e.g., an embedded processor) to perform those operations, or a generic-purpose processor (e.g., a CPU or application processor) that can perform those operations by executing one or more software programs stored in a memory device.

The terms used in this specification are only used to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include the plural expression unless the context clearly indicates otherwise. The terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the art described in this specification. Among the terms used in this specification, terms defined in general dictionaries may be interpreted as having the same or similar meaning in the context of the related art, and shall not be interpreted in an ideal or excessively formal meaning unless explicitly defined in this specification. In some cases, even if a term is defined in this specification, it cannot be interpreted to exclude the embodiments of this specification.

First, before explaining the present invention, let us briefly explain the regular expression mentioned in the present invention.

The dictionary definition of regular expression is a formal language used to express a set of strings with specific rules. It is mainly used for searching and replacing strings in programming languages and text editors.

Also, regular expressions are a widely used method for expressing a set of strings with specific rules. Depending on their complexity, regular expressions can include a single string, multiple strings, and wildcard characters (meaning any number of characters) that connect them, as well as negation and range checks that indicate the status when not included. In the past, attack signatures could be expressed with just one string, but now signatures that use a combination of multiple strings are widely used. By using these regular expressions, you can find various strings with just a small number of expressions by finding strings with a specific pattern in packets that are being communicated at high speed.

Hereinafter, a system and method for supporting a text conversion service using a user-specific customized regular expression according to one embodiment of the present invention will be described in more detail based on the attached drawings.

FIG. 1 is a device configuration diagram of a text conversion system using a user-specific customized regular expression according to one embodiment of the present invention, FIG. 2 is a detailed configuration diagram of a voice recognition-conversion model section illustrated in FIG. 1, FIGS. 3 and 4 are diagrams showing examples of regular expressions, and FIG. 5 is an example diagram of an algorithm of a regular expression substitution section.

Referring to FIGS. 1 to 5, a text conversion system (100) using a user-specific customized regular expression according to one embodiment of the present invention includes an input unit (110) and a voice recognition-conversion model unit (120).

The above input unit (110) may be configured to receive a user's spoken voice, convert it into a voice file, and provide it.

The above-mentioned voice recognition-conversion model unit (120) may be configured to convert a voice file provided from the input unit (110) into a primary text using an STT (Speech to Text) program and output it, and then apply a preset regular expression to be used by each user to substitute it into a secondary text, which is a normalized sentence, and output it.

More specifically, the speech recognition model unit (120) includes a speech-to-text conversion unit (121), a filtering unit (122), and a sentence substitution unit (122).

The above-mentioned voice-to-text conversion unit (121) may be configured to convert a voice file into text through an STT (Speech to Text) program.

The above filtering unit (122) may be configured to determine (filter) whether the strings in the primary text converted by the voice-to-text conversion unit (121) include strings of a predefined regular expression.

The above regular expression substitution unit (123) may be configured to substitute a string that has been confirmed to contain a string of a regular expression defined in the above filtering unit (122) based on a preset regular expression pattern.

That is, the regular expression substitution part (123) may be configured to substitute an input sentence containing typical typos and words that are difficult to distinguish during morphological analysis into a regular sentence by applying a preset regular expression pattern.

For example, in the sentence “I like apples”, the word “전”, which is a contraction of “저+는”, is included as a word that is difficult to distinguish during morphological analysis. This word “전” can be analyzed as “전(煎)” meaning “before” or “전(全)” meaning “all” as an adjective, and thus is ambiguous. The sentence substitution unit (110) detects elements of sentences with this ambiguity and replaces them based on regular expressions.

FIG. 6 is a flowchart illustrating a method for supporting a text conversion service using a user-specific customized regular expression according to one embodiment of the present invention, and FIG. 7 is a detailed flowchart of process S720 of FIG. 6.

Referring to FIGS. 6 and 7, a method (S700) for supporting a text conversion service using a customized regular expression for each user according to one embodiment of the present invention includes the steps of first receiving a user's spoken voice from an input unit (110) (S710), converting the spoken voice into a primary text in a voice recognition-conversion model unit (120), and applying a preset regular expression to be utilized for each user to the primary text to replace it with a secondary text, which is a normalized sentence (S720).

Here, the S720 process may include a step of determining whether the strings in the primary text converted by the speech recognition-conversion model unit include strings of the defined regular expression.

In addition, it may include a step of replacing a string in the primary text with a string in the defined regular expression.

Therefore, by using a system and method that supports a text conversion service using a user-specific customized regular expression according to one embodiment of the present invention, a sentence converted from voice to text can be replaced with a normalized sentence according to a regular expression, so that typical typos or ambiguous words included in an input sentence can be corrected according to a regular expression, which has the advantage of allowing the correction of such words.

The system according to an embodiment disclosed in this document may be a device of various forms. The electronic device may include, for example, a portable communication device (e.g., a smart phone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a home appliance device. The electronic device according to an embodiment of this document is not limited to the above-described devices.

The embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first", "second", or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first) is referred to as "coupled" or "connected" to another (e.g., a second) component, with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

The term "module" as used in this document may include a unit implemented in hardware, software or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally configured component or a minimum unit of the component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

An embodiment of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., the electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

According to one embodiment, the method according to one embodiment disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer as a commodity. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read only memory (CDROM)), or may be distributed online (e.g., downloaded or uploaded) via an application store (e.g., Play Store TM) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a part of the computer program product may be at least temporarily stored or temporarily generated in a machine-readable storage medium, such as a memory of a manufacturer's server, a server of an application store, or an intermediary server.

According to one embodiment, each of the components (e.g., modules or programs) described above may include a single or multiple entities. According to one embodiment, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., modules or programs) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the components of the plurality of components identically or similarly to those performed by the corresponding component of the plurality of components prior to the integration. According to one embodiment, the operations performed by a module, program or other component may be executed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

100: A system that supports text conversion services using user-specific customized regular expressions.
110: Input section
120: Speech Recognition-Conversion Model Section
121: Speech-to-text conversion unit
122: Filtering section
123: Regular expression substitution
130: Regular expression provider

Claims (6)

An input section for receiving the user's spoken voice;
A speech recognition-conversion model unit that converts the above-mentioned spoken voice into a primary text and replaces the primary text with a secondary text, which is a normalized sentence, by applying a preset regular expression to be utilized by each user; and
Includes a regular expression setting section that sets and provides predefined regular expressions,
The above speech recognition-conversion model part
A voice-to-text conversion unit that converts the above spoken voice into text through an STT program;
A filtering unit that determines whether the strings in the converted primary text contain strings of a predefined regular expression; and
It is characterized by including a regular expression substitution unit that substitutes a string confirmed to contain a string of a regular expression defined in the above filtering unit based on a preset regular expression pattern.
A system that supports text conversion services using customized regular expressions for each user.
delete delete A step of receiving the user's spoken voice from the input unit; and
In the speech recognition-conversion model section, the spoken voice is converted into a primary text, and a step is included in replacing the primary text with a secondary text, which is a normalized sentence, by applying a preset regular expression to be utilized by each user.
The above speech recognition-conversion model part
A voice-to-text conversion unit that converts the above spoken voice into text through an STT program;
A filtering unit that determines whether the strings in the converted primary text contain strings of a predefined regular expression; and
It is characterized by including a regular expression substitution unit that substitutes a string confirmed to contain a string of a regular expression defined in the above filtering unit based on a preset regular expression pattern.
A method to support text conversion services using user-specific customized regular expressions.
delete delete