KR101935109B1 - Sensitivity Analyzing Method of Phrase Unit for Fassion Field and Storage Medium Having the Same - Google Patents

Abstract

A method for analyzing a word segment sentiment in a fashion field according to the present invention is a word segment sentiment analysis method in a fashion segment performed through a management server installed with a word segment sentiment analysis program of a fashion field stored in a storage medium, (B) extracting a plurality of emotional vocabularies included in the fashion field from the atypical text data; and (c) extracting a plurality of emotional vocabularies included in the fashion field from the atypical text data, (C) constituting a sentence constituting at least a part of a sentence, (d) assigning affirmative / negative polarity weights of the emotional vocabulary constituting the combined sentence in the step (c) (E) analyzing positive / negative polarity of a sentence combining at least a part of the emotional vocabulary with a negative irregular weight, and analyzing the result of (e) And (f) analyzing trends in the fashion field.

Description

BACKGROUND OF THE INVENTION Field of the Invention The present invention relates to a sensibility analysis method for a word phrase in a fashion field, and a storage medium including the sensibility analyzing method.

The present invention relates to a word sensibility analysis method in a fashion field and a storage medium including the same, and more particularly, to a word sensibility analysis method in a fashion field that enables analysis in units of word phrases, and a storage medium .

Recently, the Internet has been actively used, and various online services have been provided by the appearance of smart phones and the like. In addition, various related services are being researched and developed to provide users with such services.

In addition, service providers need to accurately determine the needs and demands of users according to the increasingly diverse needs of users. To do so, algorithms are being studied to determine the demand and demand of users more accurately.

However, in the case of the fashion / apparel field, it is very difficult to analyze the unstructured text existing on the online service because the majority of emotional and quantifiable data is formed.

For this reason, up to now, there has been little developed an analysis method capable of precisely predicting trends in the fashion / apparel field, and there is a problem that the accuracy of a few existing analysis systems is greatly reduced.

Therefore, a method for solving the above problems is required.

Japanese Laid-Open Patent Publication No. 2006-318426

Disclosure of Invention Technical Problem [8] The present invention has been devised in order to solve the problems of the prior art described above, and has an object to enable accurate analysis and prediction of trends in the fashion field through effective analysis of emotional vocabulary.

The problems of the present invention are not limited to the above-mentioned problems, and other problems not mentioned can be clearly understood by those skilled in the art from the following description.

In order to achieve the above-mentioned object, the present invention provides a method for analyzing sentence-by-word sensibility in a fashion field, the method comprising the steps of: (B) extracting a plurality of emotional vocabularies included in the fashion field from the atypical text data; and (b) extracting a plurality of emotional vocabularies included in the fashion field from the atypical text data (C) constituting a sentence combining at least some of the emotional vocabularies, and (d) assigning positive / negative polarity weights of the emotional vocabulary constituting the combined sentence in the step (c) (E) analyzing positive / negative polarity of sentences combining at least some of the emotional vocabulary through positive / negative polarity weights of the emotional vocabulary; and (e) Through the analysis of the system comprises (f) analyzing the trend of the sphere.

In the step (b), the emotional vocabulary may be at least one of a single vocabulary or a word phrase in which a plurality of vocabularies are combined.

The step (d) may further include the steps of: (d-1) calculating a first probability that each emotional vocabulary constituting the sentence occurs in the entire amorphous text data; and (D-2) calculating a second probability that occurs in the unstructured text data; calculating (d-3) calculating a third probability that occurs in the atypical text data in which each emotional vocabulary constituting the sentence has a negative tendency; (D-4) calculating a fourth probability at which the first probability and the second probability occur at the same time; and (d-5) calculating a fifth probability at which the first probability and the third probability occur at the same time, (D-6) determining an affirmative / negative polarity weight value of the emotional vocabulary according to whether the value obtained by subtracting the fifth probability from the fourth probability is positive or negative.

The step (e) may calculate positive / negative polarity of a sentence in which at least a part of the emotional vocabulary is combined by summing positive / negative polarity weights of the emotional vocabularies calculated in the step (d).

In order to solve the above-described problems, the method for analyzing sentence-by-word sensibility in a fashion field and the storage medium including the same have the following effects.

First, there is an advantage of being able to analyze and predict trends of fashion / apparel field accurately and reasonably.

Second, since the analysis can be performed by assigning affirmative / negative polarity weights to each word phrase, it is possible to analyze in terms of macroscopic aspects.

Third, there is an advantage that the emotional text can be analyzed quantitatively and it can be easily provided by the user.

Fourth, users have the advantage of being able to utilize them for active marketing through analysis results.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description of the claims.

1 is a flowchart illustrating an entire process of a sensitivity analysis method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a detailed process of a sensitivity analysis method according to an exemplary embodiment of the present invention; FIG. And
FIG. 3 is a table showing an example of an emotional vocabulary given an affirmative / negative polarity weight in the emotional analysis method according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. In describing the present embodiment, the same designations and the same reference numerals are used for the same components, and further description thereof will be omitted.

A method for analyzing a word segment emotion in a fashion field according to the present invention is performed through a management server installed with a word segment emotion analyzing program of a fashion field stored in a storage medium and is installed in the management server, Lt; / RTI >

In addition, a program for the emotion analysis of a word segment in the fashion field driven thereby can be outputted through a video output device such as a display module, and can provide visual information to a user through a visualized graphic user interface.

Particularly, the storage medium storing the word segment emotion analysis program of the fashion field can be installed in the management server using a mobile disk or a communication network, It can be operated by functional means. That is, in the present invention, information processing by software is realized through hardware.

Hereinafter, an algorithm of a word segment emotional analysis program in the fashion field of the present invention executed through the management server will be described.

1 is a flowchart illustrating an entire process of a sensitivity analysis method according to an embodiment of the present invention

As shown in FIG. 1, the emotional analysis method according to an exemplary embodiment of the present invention includes: (a) collecting atypical text data for an online service and storing the collected atypical text data in the management server; (B) extracting a plurality of emotional vocabularies included in the field; (c) composing a sentence combining at least some of the emotional vocabularies; and (c) (E) analyzing positive / negative polarity of sentences combining at least some of the emotional vocabulary through affirmative / negative polarity weights of the emotional vocabulary, (d) assigning affirmative / And analyzing trends of the fashion field through the analysis result of the step (e).

Each of these steps will be described in detail below.

In step (a), unregistered text data is extracted from various online services and collected.

Here, the online service may be various online service media using a communication network such as the web, SNS, etc., and is not limited to any online service. In the case of the above-mentioned unstructured text data, it refers to data of document type which is complicated in its structure and is not formatted.

That is, in this step, data of a document type is extracted for various online services, and then step (b) is performed.

In the step (b), a plurality of emotional vocabularies included in the fashion field are extracted from the atypical text data. In this step, a plurality of vocabularies related to the fashion field are extracted from the extracted atypical text data. At this time, representative vocabularies including representative vocabulary such as nouns and adverbs, Respectively.

In particular, in the case of the present embodiment, the step (b) may extract the emotional vocabulary of the semantic unit including at least one word. In other words, emotional vocabulary in the form of a word phrase, which represents a single meaning by combining plural word phrases, is included in the object as well as an emotional vocabulary of only one word.

For example, the fashion related noun 'color, texture, touch, charm; As well as a list of individual vocabulary units such as 'urban, sensual, modern, active, attractive', verb and adjective 'sophisticated, sexy, elegant, unique, elegant, feminine' I would like to buy an emotional vocabulary that has a combination of multiple words such as "I like to see, I want to buy, I like".

Next, a step (c) of constructing a sentence combining at least some of the emotional vocabularies is performed. In this step, a specific combination of sentences is formed through the emotional vocabulary extracted in the step (b).

In the following steps (d) to (e), affirmative / irregularity weights of each emotional vocabulary constituting the sentence constituted in the step (c) are given and the positive / negative polarity of the entire sentence is judged .

2 is a flowchart illustrating a detailed process of the emotion analysis method according to an embodiment of the present invention. As shown in FIG. 2, step (d) may include steps (d-1) to (d-6).

First, in step (d-1), the first probability that each emotional vocabulary included in the sentence constituted by the step (c) occurs in the entire unstructured text data is calculated.

That is, in this step, the probability of occurrence of the individual emotional vocabulary constituting the sentence can be calculated for all the unstructured text data extracted from various online services.

Next, in step (d-2), the second probability that each emotional vocabulary constituting the sentence will occur in the unstructured text data having positive tendency is calculated.

In this step, probabilities of occurrence of individual emotional vocabularies constituting the corresponding sentence can be calculated by targeting only the atypical text data having a positive affinity selected from all the unstructured text data extracted from various online services.

Next, in step (d-3), the third probability that each emotional vocabulary constituting the sentence occurs in the amorphous text data having a negative tendency is calculated.

In this step, probability of occurrence of individual emotional vocabulary constituting the corresponding sentence can be calculated by targeting only the unstructured text data having a negative tendency selected from all the unstructured text data extracted from various online services.

The affirmative / negative polarity weighting value of the emotional vocabulary can be determined through the steps (d-4) to (d-6) through the first probability to the third probability of each emotional vocabulary calculated as described above.

Wherein the first probability and the second probability are simultaneously calculated for each emotional vocabulary in the step (d-4), and in the step (d-5), the first probability and the third probability The fifth probability to be generated at the same time.

Then, in the step (d-6), whether or not the value obtained by subtracting the fifth probability calculated in the step (d-5) from the fourth probability calculated in the step (d-4) And judges the positive / negative polarity weighting value of the emotional vocabulary according to the result.

FIG. 3 is a table showing an example of an emotional vocabulary given an affirmative / negative polarity weight in the emotional analysis method according to an embodiment of the present invention.

As shown in FIG. 3, the predetermined emotional vocabulary may be composed of a single word, or may be a word phrase in which a plurality of words are combined. Through the steps (a) to (d), it is possible to calculate the polarity index for each emotion word.

As shown in the table of FIG. 3, the polarity index of the emotional vocabulary that gives a negative impression due to the characteristics of fashion / apparel products such as' price as low as price, high price, '' And it is positive feeling in the characteristics of fashion / apparel goods such as 'light', 'high value', 'worthy', 'concise', 'easy', 'impressed' And the polarity index of the emotional vocabulary that gives the emotional vocabulary has a positive value.

The polarity intensity of these emotional vocabularies can be judged as the absolute value of each polarity index.

Next, in the step (e), a sentence in which at least some of the emotional vocabulary is combined through the affirmative / negative polarity weighting value of the emotional vocabulary calculated in the step (d) Positive / negative polarity.

In this step, the affirmative / negative polarity of the sentence is calculated by summing up the positive / negative polarity weights calculated in the step (d) for each emotional vocabulary constituting the combined sentence.

For example, if a sentence contains three emotional vocabularies, the final affirmation / negativity of the sentence is calculated by determining whether the final positive / negative polarity weights of the three emotional vocabularies are positive or negative. It will be possible.

Thereafter, step (f) of analyzing trends in the fashion field is performed through the analysis result of step (e).

In this stage, the process of analyzing trends in the fashion field is carried out through the emotional vocabulary given positive / negative polarity weighting and the polarity of the sentence composed of the above results.

In this step, the selection of high-frequency emotional vocabulary in unstructured data, the selection of emotional vocabulary that is statistically significant for each channel / subject, the frequency and use field, and the selection of basic vocabulary for emotion in the field of fashion This allows precise analysis and prediction of fashion trends.

Then, the analysis result can be visualized and provided to the user from the management server, and the user can utilize the analysis result displayed through the user terminal for aggressive marketing.

As described above, the present invention is advantageous in that it quantitatively analyzes sensible text rationally and realistically, and accurately analyzes and predicts trends in the fashion / apparel field.

Then, such analysis result can be visualized and presented to the user, and the user can utilize the analysis result for active marketing.

It will be apparent to those skilled in the art that the present invention can be embodied in other specific forms without departing from the spirit or scope of the invention as defined in the appended claims. It is obvious to them. Therefore, the above-described embodiments are to be considered as illustrative rather than restrictive, and the present invention is not limited to the above description, but may be modified within the scope of the appended claims and equivalents thereof.

Claims (5)

A method for analyzing emotion in a word field in a fashion field, which is performed through a management server installed with a word segment emotion analysis program of a fashion field stored in a storage medium,
(A) collecting unstructured text data on an online service and storing the collected unstructured text data in the management server;
(B) extracting a plurality of emotional vocabularies included in the fashion field from the atypical text data;
(C) composing sentences combining at least some of the emotional vocabularies;
(D) assigning affirmative / negative polarity weights of the emotional vocabulary constituting the combined sentence in the step (c);
(E) analyzing positive / negative polarity of a sentence combining at least a part of the emotional vocabulary through positive / negative polarity weighting of the emotional vocabulary; And
Analyzing trends in the fashion field through the analysis result of step (e);
/ RTI >
The step (d)
(D-1) calculating a first probability that each emotional vocabulary constituting the sentence occurs in all irregular text data;
(D-2) calculating a second probability that each emotional vocabulary constituting the sentence occurs in atypical text data having an affirmative tendency among all the atypical text data;
(D-3) calculating a third probability that each emotional vocabulary constituting the sentence occurs in atypical text data having a negative tendency among all the atypical text data;
(D-4) calculating a fourth probability that the first probability and the second probability occur simultaneously;
(D-5) calculating a fifth probability that the first probability and the third probability occur simultaneously; And
Judging the affirmative / negative polarity weighting value of the emotional vocabulary according to whether the value obtained by subtracting the fifth probability from the fourth probability is positive or negative and judging the polarity intensity of the sensible vocabulary based on the absolute value of the polarity weighting value d-6);
Lt; / RTI >
The step (e)
Wherein the affirmative / negative polarity of each emotional vocabulary calculated in the step (d) is summed up to calculate a positive / negative polarity of a sentence combining at least some of the emotional vocabulary. The method according to claim 1,
In the step (b)
Wherein the emotional vocabulary is at least one of a single vocabulary or a word phrase in which a plurality of vocabularies are combined. delete delete A computer-readable storage medium having recorded thereon a program for causing a computer to execute the word segment emotion analysis method of claim 1 or 2.

Images