KR20160121132A - Analysis apparatus and method for product trends and sale based on social big data - Google Patents

Analysis apparatus and method for product trends and sale based on social big data Download PDF

Info

Publication number
KR20160121132A
KR20160121132A KR1020150050691A KR20150050691A KR20160121132A KR 20160121132 A KR20160121132 A KR 20160121132A KR 1020150050691 A KR1020150050691 A KR 1020150050691A KR 20150050691 A KR20150050691 A KR 20150050691A KR 20160121132 A KR20160121132 A KR 20160121132A
Authority
KR
South Korea
Prior art keywords
sns
product
topic
trend
sales
Prior art date
Application number
KR1020150050691A
Other languages
Korean (ko)
Inventor
오창헌
최대우
김주상
Original Assignee
주식회사 노스트
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 주식회사 노스트 filed Critical 주식회사 노스트
Priority to KR1020150050691A priority Critical patent/KR20160121132A/en
Publication of KR20160121132A publication Critical patent/KR20160121132A/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Tourism & Hospitality (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The present invention relates to an apparatus for analyzing product trend and sales on the basis of social big data and a method thereof, so as to acquire materials of customer viewpoint by using social big data and then to perform product sales relation analysis on the basis of the same. The apparatus for analyzing the product trend and sales on the basis of the social big data may include: an SNS document collection part collecting SNS documents corresponding to searching information by accessing a social network service (SNS), if the searching information including a product and a product related word are inputted; a topic modeling part generating a number of product topics by performing topic modeling as to the SNS documents; and a topic analysis part grasping, visualizing and providing topic trend, by performing statistical analysis as to the product topics.

Description

Technical Field [0001] The present invention relates to an apparatus and method for analyzing product trends and sales based on social big data,

The present invention relates to a merchandise trend and sales analysis apparatus based on a social big data, which can grasp trend trends of a specific merchandise through big data accumulated through a social network service such as a blog, a Twitter and the like, ≪ / RTI >

In general, companies regularly collect sales data, ie, sales data, and analyze the data of wholesalers (or dealers, etc.) and analyze sales data.

However, the conventional sales data collection procedure is performed only by automatically matching the sales data provided from a large number of suppliers to the data collection format of the manufacturer and collecting the sales data to provide the data. It is not reflected.

Social media, on the other hand, is transforming existing forms of communication by making it possible for users to produce and share contents in real time because they do not need professional knowledge or skills to use as a global communication tool. Especially, as a new medium of communication, it spreads social issues at home and abroad in real time, allowing users to communicate their opinions with their acquaintances and the public, thereby largely causing the possibility of social change. Due to the change of information subject through social media, the data became more massive and caused 'superflood' of information called 'big data'. This big data is a new opportunity to understand social reality and meaningful information As a new field of research for the discovery of. Various studies have been actively conducted to analyze big data efficiently.

Early research on social media has focused on the use of social media as microblogging and attempts to understand the structure of the community (Java et al., 2007; Huberman et al., 2008). Since then, there have been applied studies such as Jansen et al. (2009), which analyzes Twitter as part of viral marketing.

Recently, research on how microblogging with political features affect their actual political situation (Drezner and Farrell, 2007; Williams and Gulati, 2008) as well as social media as a tool to predict the outcome of actual elections (Tumasjan et al., 2010; Livne et al., 2011) have been actively used. In addition to the vast amount of text data generated in real-time, social media is used as an influential channel for opinion leadership, such as agenda setting and public opinion formation. .

Korean Patent Laid-Open No. 10-2013-0027680

In order to solve the above problems, according to the present invention, there is provided a social big data-based product trend and a sales method which allow companies to acquire data of a consumer's perspective using a social big data, Analyzing apparatus and method.

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

According to an embodiment of the present invention, when search information including goods and product related words is input, access to a social network service (SNS) is performed to search for SNS documents corresponding to the search information An SNS document collecting unit for collecting SNS documents; A topic modeling unit that performs topic modeling on the SNS documents to generate a plurality of product topics; And a topic analyzing unit for analyzing and providing statistical analysis on the plurality of product topics to identify and visualize topic trends, and to provide a merchandise trend and sales analysis apparatus based on the social big data.

The topic analyzer may further include at least one of a pre-stored salesperson activity DB, a marketing DB, and a performance DB to identify trends in merchandise sales trends related to topic trends.

The SNS document collecting unit generates a query using the search information as a parameter, and collects SNS documents corresponding to the search information through the query.

According to another aspect of the present invention, there is provided a search method comprising: inputting search information including goods and product related words; Generating a query having the search information as a search parameter, accessing a social network service (SNS) and collecting SNS documents through the query; Performing topic modeling on the SNS documents to generate a plurality of product topics; And a statistical analysis on at least one of a sales employee activity DB, a marketing DB, and an achievement DB acquired and stored in advance and a statistical analysis on the plurality of product topics, thereby visually identifying and visualizing a trend of a sales trend of a product related to a topic trend And a method for analyzing a product based on a social big data.

The present invention can acquire data from a consumer perspective through big data accumulated through a social network service such as a blog, a Twitter, etc., and statistically analyzes it with a sales employee activity DB, a marketing DB, Based on product sales association analysis. This allows pharmaceutical companies to more accurately analyze current product trends from a consumer perspective and to plan accurate and specific sales and promotion strategies that reflect these trends.

1 is a view for explaining a merchandise trend and sales analysis apparatus based on a social big data according to an embodiment of the present invention.
FIG. 2 is a diagram showing an operation diagram (Plate Notation) for the LDA. FIG.
3 is a diagram for explaining a product trend and a sales analysis method based on a social big data according to an embodiment of the present invention.
4 is an example of topic and topic trends generated in accordance with one embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS The above and other objects, features and advantages of the present invention will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, in which: FIG. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

The following terms are defined in consideration of the functions of the present invention, and these may be changed according to the intention of the user, the operator, or the like.

The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art to which the present invention pertains. Only. Therefore, the definition should be based on the contents throughout this specification.

1 is a view for explaining a merchandise trend and sales analysis apparatus based on a social big data according to an embodiment of the present invention.

1, the product trend and sales analysis apparatus of the present invention may include a data input / output unit 11, an SNS document collection unit 12, a topic modeling unit 13, a topic analysis unit 14, and the like .

The data input / output unit 11 is provided with a monitor, a keyboard, a speaker, a mouse, and the like. The data input / output unit 11 receives information related to a product to be analyzed from the user, that is, search information, To be guided visually and audibly.

The SNS document collecting unit 12 generates a query to be requested to a social network service (SNS) such as a blog or a tree and then transmits a query to a social network service via a blog collector and a Twitter API (for example, Twitter4j) Collect all product related documents uploaded to the SNS.

At this time, it is preferable that the SNS document collection object is a text-based SNS that provides a comment by utilizing the fact that the topic model should be used.

The SNS document can be collected in the form of the following equation.

Figure pat00001

In this case, the ID is an identifier of the user who created the SNS document, data is the date on which the SNS document was uploaded, lang is the language information to be used when the SNS is serving the world, reply is the name of the user The user information about the text, txt is included in the SNS document.

The topic modeling unit 13 performs topic modeling on the SNS documents to generate a plurality of product topics. That is, the SNS documents collected through the SNS document collecting unit 12 are searched and analyzed to extract words frequently appearing in the SNS document, and probability values are applied to the respective words, After discovering a continuous pattern, let it acquire a continuous pattern of found words as one topic.

However, if the amount of the SNS document is too large, a comment graph corresponding to the SNS documents is generated in order to minimize data throughput, and a cluster-specific document (i.e., a corpus) And performs the topic modeling operation based on the document.

The topic modeling unit 13 of the present invention can perform the topic modeling operation using a topic model such as LDA (Latent Dirichlet Allocation), PAM (Pachinko Allocation Model), Hierarchical LDA, . The LDA uses the Dirichlet distribution to calculate the probability that words in a text document will be included in a particular topic. Where each document is stochastically represented by several topics rather than a single topic, and each topic is represented by a specific distribution of words. Gibbs sampling, which is one of the Markov Chain Monte Carlo (MCMC) algorithms for LDA, classifies data by a given parameter and estimates the parameter again by the classification. Fig. 2 is a diagram representing an operation diagram for the LDA, in which α is a parameter for a dirikler prior probability in a distribution of a topic per document, β is a posterior probability of a word distribution per topic, . And θ is the topic distribution for the document, z is the topic for a particular word in a particular document, w is a specific word, N is the length of the document, LDA is the estimated θ and z from the parameters α, β, .

The topic analyzing unit 14 analyzes a plurality of product topics generated through the topic modeling unit 13 in combination with time to identify a topic trend and provide it as a graph or the like. In addition, information on other independent variables such as salesperson activity DB, marketing DB, and other performance DBs are additionally provided from a product manufacturing (sales) company, and statistical analysis is performed on these and topics through an R program It is possible to calculate the trend of the sales of the product related to the topic trend.

R program was developed by Robert Gentleman and Ross Ihaka of the University of Auckland, New Zealand, and is now constantly updated by the R core team. As well as taking the GNU GPL license policy, development packages for developers around the world are actively being developed. In addition, it supports various operating systems and is widely used as a tool for statistics calculation, matrix processing, etc. for many general users including statisticians and researchers.

R is a free open source, so many libraries are developed and shared so that not only statistical processing but also natural language processing, machine learning, and semantic technology can be easily integrated. As a result, the O2 Service Open API enables various statistical analysis and visualization of data provided by the O2 infrastructure such as social data, trends, and topics through linkage with R.

3 is a diagram for explaining a product trend and a sales analysis method based on a social big data according to an embodiment of the present invention.

First, a search information input window is provided to a user to allow the user to input information on goods and goods related words (S1).

Then, a query is generated using the product and product association information as retrieval parameters (S2).

Then, after accessing the SNS such as a blog or a tree through a blog collector and a Twitter API (e.g., Twitter4j), it is determined whether the query is related to the query generated through the step S2 (for example, (S3) in which all the SNS documents (in which the name of the medicines, the diseases and symptoms related to the medicines are posted) are collected.

Then, SNS documents are searched and analyzed to extract words frequently appearing in SNS documents, a probability value is applied to each word, a continuous pattern of words most related to the SNS document is found, and a series of found words (S4) as shown in Fig. 4 (a).

Further, information on other independent variables such as sales employee activity DB, marketing DB, other performance DB, etc. is further received from the product manufacturer and statistical analysis is performed on these and product topics, Know the trend and guide the user. That is, by analyzing the occurrence frequency of each topic according to the passage of time, it is possible to understand not only the trend trend, but also the correlation between the salesperson activity and the topic, the correlation between the marketing degree and the topic, And various kinds of statistical data related to trends of merchandise sales related to the topic trend are variously calculated and visualized as shown in FIG. 4 (b) (S5).

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

Claims (4)

An SNS document collecting unit for accessing the SNS (Social Network Service) and collecting SNS documents corresponding to the search information, when the search information including the goods and product related words is input;
A topic modeling unit that performs topic modeling on the SNS documents to generate a plurality of product topics; And
And a topic analyzer for identifying and visualizing topic trends by performing statistical analysis on the plurality of product topics. The apparatus of claim 1, wherein the topic analyzer
Wherein the trend of the sales of the product related to the topic trend is grasped by additionally using at least one of the pre-stored salesperson activity DB, the marketing DB, and the performance DB. The method of claim 1, wherein the SNS document collecting unit
Wherein a query is generated using the search information as a parameter, and the SNS documents corresponding to the search information are collected through the query. Receiving search information including goods and product related words;
Generating a query having the search information as a search parameter, accessing a social network service (SNS) and collecting SNS documents through the query;
Performing topic modeling on the SNS documents to generate a plurality of product topics; And
Visualizing and providing a trend of merchandise sales change related to a topic trend by performing a statistical analysis on at least one of a sales employee activity DB, a marketing DB, and a performance database acquired and stored in advance and the plurality of merchandise topics Including social Big data based product trends and revenue analysis methods.
KR1020150050691A 2015-04-10 2015-04-10 Analysis apparatus and method for product trends and sale based on social big data KR20160121132A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150050691A KR20160121132A (en) 2015-04-10 2015-04-10 Analysis apparatus and method for product trends and sale based on social big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150050691A KR20160121132A (en) 2015-04-10 2015-04-10 Analysis apparatus and method for product trends and sale based on social big data

Publications (1)

Publication Number Publication Date
KR20160121132A true KR20160121132A (en) 2016-10-19

Family

ID=57250474

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150050691A KR20160121132A (en) 2015-04-10 2015-04-10 Analysis apparatus and method for product trends and sale based on social big data

Country Status (1)

Country Link
KR (1) KR20160121132A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020116985A1 (en) * 2018-12-06 2020-06-11 주식회사 인스브룩크 E-commerce platform evaluation system and method
KR102190897B1 (en) * 2019-09-19 2020-12-15 (주)어반유니온 Method and Apparatus for analyzing fashion trend based on big data
KR102574865B1 (en) * 2023-03-29 2023-09-07 그린브릭스컴퍼니 주식회사 AI-powered Advertising Data Visualization System

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130027680A (en) 2011-09-08 2013-03-18 (주)신성아트컴 Sorting system for the medicine sales data and the method thereof

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130027680A (en) 2011-09-08 2013-03-18 (주)신성아트컴 Sorting system for the medicine sales data and the method thereof

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020116985A1 (en) * 2018-12-06 2020-06-11 주식회사 인스브룩크 E-commerce platform evaluation system and method
KR102190897B1 (en) * 2019-09-19 2020-12-15 (주)어반유니온 Method and Apparatus for analyzing fashion trend based on big data
KR102574865B1 (en) * 2023-03-29 2023-09-07 그린브릭스컴퍼니 주식회사 AI-powered Advertising Data Visualization System

Similar Documents

Publication Publication Date Title
Milovic et al. Prediction and decision making in health care using data mining
KR20180072167A (en) System for extracting similar patents and method thereof
CN108647249A (en) Public sentiment data prediction technique, device, terminal and storage medium
Malik et al. The Importance of Text Mining for Services Management
Asooja et al. Forecasting emerging trends from scientific literature
Stoica et al. Mining customer feedback documents
Sydow et al. Diversity of editors and teams versus quality of cooperative work: experiments on Wikipedia
Wolcott et al. Modeling time-dependent and-independent indicators to facilitate identification of breakthrough research papers
Ma et al. Tag-latent dirichlet allocation: Understanding hashtags and their relationships
KR101625124B1 (en) The Technology Valuation Model Using Quantitative Patent Analysis
JP4376887B2 (en) Method, apparatus, and program for extracting cause compensation for business efficiency degradation in business process
KR20160121132A (en) Analysis apparatus and method for product trends and sale based on social big data
CN112016769B (en) Method and device for managing relative person risk prediction and information recommendation
Bogdan et al. Is strategic management ready for big data? A review of the big data analytics literature in management research
RU2718978C1 (en) Automated legal advice system control method
Zheng et al. Putting humans back in the loop of machine learning in Canadian smart cities
Gutsche Automatic weak signal detection and forecasting
Chu et al. Knowledge flow of biomedical informatics domain: Position-based co-citation analysis approach
EP3493082A1 (en) A method of exploring databases of time-stamped data in order to discover dependencies between the data and predict future trends
Riesener et al. Concept for the identification of product innovation potentials by the application of text mining
Delgosha et al. Semantic structures of business analytics research: applying text mining methods
Hassan et al. ESG Fingerprint: How Big Data and Artificial Intelligence Can Support Investors, Companies, and Stakeholders?
Yalaoui et al. A survey on data quality: principles, taxonomies and comparison of approaches
JP2003248687A (en) Information processor and its method
Botzenhardt et al. A Text Mining Application for Exploring the Voice of the Customer