KR20180075852A - System and method for intelligent marketing analysis through processing non-fixed form bigdata - Google Patents

Abstract

Provided are an intelligent marketing analysis system through amorphous big data processing and a method thereof. The method collects a plurality of amorphous data related to any product or service offline and online, standardizes the collected amorphous data into structured data by analyzing the collected amorphous data according to predetermined standards, fuses the structured data according to predetermined standards, integrally analyzes the fused structured data on the basis of a predetermined marketing performance index, and processes and provides statistical information of individual structured data and a result of an integrated analysis into visualization information visually identifiable by a user.

Description

TECHNICAL FIELD [0001] The present invention relates to an intelligent marketing analysis system and method using atypical big data processing,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an intelligent marketing analysis system and method for collecting, processing, formatting, and analyzing atypical big data.

In order to analyze and utilize data, expertise in element technology such as data mining, statistical analysis, and mathematical optimization and a broad understanding of the field in which the data is generated are needed. For example, in the field of marketing research, there is a need for an expert capable of understanding the types of knowledge or information related to consumer behavior, needs,

On the other hand, the rapid growth of IoT application products and services has led to a significant increase in the generation of consumption related data, but there is a lack of experts who have the ability to analyze and analyze data effectively. As a result, the level of data analysis usually stays at the frequency of keyword frequency, resulting in poor accuracy of the analysis and most of the data is being billed.

However, according to the existing marketing research method, there is a limit in that it takes a lot of manpower and time to collect and analyze massive data on / off-line. In addition, there is a problem that a system of professional extraction standard and classification system is not systematically established in the big data analysis related to automatic fusion and emotion of heterogeneous data.

Therefore, there is a need to process a large amount of unstructured data collected through the formalization process and various analysis methods for use as marketing research data.

In this regard, in Korean Patent Laid-Open No. 10-2010-0032967 (entitled "VIRAL MARKET ANALYSIS METHOD AND SYSTEM"), when marketing information and environment variables, which are customer conditions, are inputted, similar marketing cases and comparative analysis A viral marketing analysis method and system capable of presenting optimal marketing methods and results are disclosed. The system includes an advertisement summary DB for accumulating advertisement data; An input device for inputting customer basic information and environment variables; And a computer for searching, from the advertisement summary DB, similar data corresponding to the customer basic information and environment variables when the customer basic information and the environment variable are input through the input device, and outputting the result.

One embodiment of the present invention supports systematic gathering / analysis / service of data for consumer marketing research, so that from the huge information (i.e., big data) generated on-line and off-line, ), And to establish a differentiated competitive strategy, and to provide a method of the intelligent marketing analysis system.

It should be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to an aspect of the present invention, there is provided an intelligent marketing analysis system for processing at least one of a purchase environment, a process, and a pattern of a consumer in an offline site, An offline site device for collecting unstructured data, formatting the collected unstructured data into first formatted data according to predetermined criteria, and transmitting the unstructured data to a marketing integrated analysis device; And online, crawling text data for any product and service as unstructured data, formatting the crawled unstructured data into second fixed data according to a predetermined criterion, and extracting first fixed data and second fixed data received from the offline site apparatus, Processing the integrated analysis on the merged set of formative data based on a predetermined marketing performance index, analyzing the statistical information of the individual set of formulated data and the result of the integrated analysis And a marketing integration analyzing device that processes the visualization information and provides the visualization information to the user. At this time, the marketing performance index defines the interaction rules between various types of formal data, and the interaction rules are set as marketing-meaningful rules.

According to another aspect of the present invention, there is provided an intelligent marketing analysis method using atypical big data processing, comprising: collecting a plurality of atypical data related to an arbitrary product or service on-line and on-line; Analyzing the collected plurality of irregular data according to a predetermined criterion and formatting the same into regular data; Integrating the form data according to a predetermined criterion, and analyzing the integrated form data based on the predetermined marketing performance index; And the statistical information of the individual fixed form data and the result of the integrated analysis into the visualization information which can be visually confirmed by the user. At this time, the marketing performance index defines the interaction rules between various types of formal data, and the interaction rules are set as marketing-meaningful rules.

According to any one of the above-mentioned tasks, when a subject for marketing analysis is determined, the associated on / off-line big data is automatically collected and stored, and each collected atypical data type (e.g., text, , Meaningful formal data is automatically extracted and stored in the DB through the formalization module and the marketing analysis / research function is automatically transferred to the customer (ie, the customer who has commissioned the marketing research) through the fusion of the heterogeneous data stored in the DB Service API.

In this way, it is possible to extract and analyze objective and effective marketing indicators by using various non-standard heterogeneous data collection / formatting / analysis techniques on / off-line related to consumer marketing. In addition, by processing various unstructured data, it can be utilized as an online-based marketing service solution through heterogeneous data convergence / analysis.

1 is a configuration diagram of an intelligent marketing analysis system according to an embodiment of the present invention.
2 is a conceptual diagram for explaining a marketing synthesis analysis process according to an embodiment of the present invention.
3 is a flowchart illustrating an intelligent marketing analysis method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description in the drawings are omitted, and like parts are denoted by similar reference numerals throughout the specification. In the following description with reference to the drawings, the same reference numerals will be used to designate the same names, and the reference numerals are merely for convenience of description, and the concepts, features, and functions Or the effect is not limited to interpretation.

Throughout the specification, when an element is referred to as "including" an element, it does not exclude other elements unless specifically stated to the contrary, But do not preclude the presence or addition of one or more of the other features, numbers, steps, operations, elements, parts, or combinations thereof.

In this specification, the term "unit" or "module" includes a unit implemented by hardware, a unit implemented by software, and a unit realized by using both. Further, one unit may be implemented using two or more hardware, or two or more units may be implemented by one hardware. On the other hand, 'to' or 'module' is not meant to be limited to software or hardware, but may be configured to be in an addressable storage medium and configured to play one or more processors. Thus, by way of example, 'a' or 'module' refers to components such as software components, object-oriented software components, class components and task components, and processes, Microcode, circuitry, data, databases, data structures, tables, arrays, and variables, as will be appreciated by those skilled in the art. It is to be understood that the functions provided in such components and portions (or modules) may be combined with a smaller number of components and / or components (or modules) (Or ' modules '). ≪ / RTI > In addition, the components and 'part' (or 'module') may be implemented to play one or more CPUs in a device or a secure multimedia card.

The " terminal " referred to below can be implemented as a computer or a portable terminal that can access a server or other terminal through a network. Here, the computer includes, for example, a notebook computer, a desktop computer, a laptop computer, and the like, each of which is equipped with a web browser (WEB Browser), and the portable terminal may be a wireless communication device , Communication-based terminals such as International Mobile Telecommunication (IMT), Code Division Multiple Access (CDMA), W-CDMA (W-CDMA) and Long Term Evolution (LTE), smart phones, And may include a handheld based wireless communication device. The term " network " may also be used in a wired network such as a local area network (LAN), a wide area network (WAN) or a value added network (VAN) And may be implemented in all kinds of wireless networks, such as communication networks.

The intelligent marketing analysis system according to an embodiment of the present invention to be described below can automatically collect, process, formulate, and analyze big data on / offline, rather than existing marketing analysis service based on manpower- Generate marketing analysis reports automatically through comparison / analysis of heterogeneous data, and serve customers online.

To this end, the intelligent marketing analysis system according to an embodiment of the present invention comprehensively analyzes offline information such as offline information on a consumer purchase process and a purchasing environment on the offline, and online information such as a product review and a product review date. At this time, the intelligent marketing analysis system according to an embodiment of the present invention automatically collects and processes atypical large data (e.g., image, bio-signal, text, and the like) generated on various channels on / And supports marketing analysis services through formalization and analysis.

Hereinafter, an intelligent marketing analysis system and a method thereof according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a configuration diagram of an intelligent marketing analysis system according to an embodiment of the present invention.

As shown in FIG. 1, the intelligent marketing analysis system 10 includes a plurality of offline site devices 100 and a marketing integration analysis device 200. In one embodiment of the present invention, the offline site apparatus 100 and the marketing integrated analysis apparatus 200 may be each a server apparatus, and hereinafter, the two apparatuses will be referred to as servers.

The intelligent marketing analysis system 10 comprises a single marketing integration analysis server 200 at the center and a plurality of offline site servers 100 installed at an offline site (i.e., a store). At this time, the offline site server 100 is connected to the marketing integration analysis server 200 through a network such as the Internet, and the marketing analysis use form data acquired from the offline site is transmitted to the central marketing integration analysis server 200 through a pre- (200). In addition, the offline site server 100 is installed in an offline store requiring marketing analysis services. The offline site server 100 includes cameras and sensors (entrance sensors, beacon sensors, bio-signals Sensors for collecting information). The offline site server 100 may be implemented on a terminal device.

Specifically, the offline site server 100 includes a site data collection unit 110, a formatting processing unit 120, a local database 130, and a data transfer unit 140.

The field data collecting unit 110 interlocks with at least one information collecting apparatus installed in the corresponding off-line site to acquire data from each information collecting apparatus. At this time, the information collecting apparatus may be a camera apparatus and various sensor apparatuses.

The formatting processor 120 processes the various data collected through the field data collecting unit 110 into a predetermined format so as to be analyzed and extracts the predetermined format data by analyzing the processed data.

Specifically, when the camera is installed as the information collecting device, the formatting processor 120 analyzes the inputted image data to determine the change of the customer distribution by each store session, the product of interest, the residence time in the store, And the like. At this time, depending on the service scenario desired by the customer, the camera used may be a fixed or mobile camera. The fixed camera is used for collecting information for an unspecified number of visitors, and the portable camera can be used for collecting information about a specific selected focus group.

When a sensor is installed as an information collecting device, sensing information inputted from a sensor fixed to a door is analyzed to extract form data such as the number of customers entering and exiting the store by time, and the number of customers in the store by time. In addition, by analyzing the customer's heartbeat sensing information and the customer's location information in the store during the residence time measured from the bio-signal sensor (smart band, etc.) that can be attached to the customer visiting the store, Is extracted. In addition, the beacon sensor can extract the location information of the visiting customer and the traveled route from the beacon sensor.

The data analyzed and formatted through the formatting processor 120 is stored in the local database 130 on the offline site server 100 and transferred to the marketing integration analysis server 200 through the data transfer unit 140. In this case, the data transfer unit 140 has an API defined in advance to be linked with the marketing integration analysis server 200 in order to transmit the formatted data.

The marketing integration analysis server 200 includes an online data collection unit 210, a formatting processing unit 220, an integration database 230, a heterogeneous data fusion unit 240, a marketing synthesis analysis unit 250, a visualization engine 260, And a user API providing unit 270.

The online data collection unit 210 collects (crawls) text data on-line (e.g., the Internet).

At this time, the online data collection unit 210 may collect text information existing on the online, such as consumer reviews, evaluation of professional media / experts, articles of press, and the like for specific products and services.

The formatting processor 220 processes the collected various online data into a predetermined format so as to be analyzed, and analyzes the processed data to extract predetermined formatted data.

At this time, the formatting processor 220 extracts format data such as consumer response (emotion), association word extraction, comparison / statistical data, and the like, and stores the extracted format data in the integration database 230.

The integrated database 230 integrates and stores the format data extracted by the marketing integration analysis server 200 on-line and the format data received from the offline site server 100.

Although not shown in FIG. 1, the marketing integration analysis server 200 may separately include a data reception unit for receiving offline formatted data by communicating with the data transmission unit 140 of the offline site server 100. At this time, an API matched with the data transfer unit 140 of the offline site server 100 may be defined on a data receiving unit (not shown) of the marketing integration analysis server 200.

The heterogeneous data fusion unit 240 fuses the related data stored in the integrated database 230 with a plurality of related data based on a predetermined reference (e.g., time).

The marketing synthesis analyzer 250 comprehensively analyzes the merged formal data based on predetermined marketing performance indicators for marketing analysis.

2 is a conceptual diagram for explaining a marketing synthesis analysis process according to an embodiment of the present invention.

The marketing performance index is a rule - based index for collectively analyzing heterogeneous formal data. It defines how various heterogeneous data interact and is used to derive meaningful marketing results.

The plurality of formatting data (# 1 to #n) shown in FIG. 2 includes data including a time stamp that proves the fact that data exists at any point in time, data including a time stamp .

At this time, as shown in FIG. 2, the marketing synthesis analyzer 250 applies a marketing performance index to a plurality of formatted data, and determines a relation between the formatted data according to an arbitrary criterion Analyze interactions interactively. In FIG. 2, a time interval in which the influence of each format data is generated is displayed according to the time, and valid time intervals for each of the format data are analyzed in an integrated manner, so that the relationship and interaction between the heterogeneous data can be understood.

The visualization engine 260 generates information (such as a table or a graph) in which the user can visually confirm information such as statistics, change trends, and degree of change of the individual fixed data.

In addition, the visualization engine 260 can visualize the information according to the result of the integrated analysis through the marketing performance index in a text form such as a sentence.

The user API provider 270 reports the final analysis report generated through the visualization engine 260 to the user online.

At this time, the user API provider 270 may provide the user API to the user terminal 300 connected through a network (e.g., the Internet). Also, a user (for example, a customer or a marketing-related user) who wishes to receive a marketing service through a user API can view the finalized visualization result through an authentication process.

This enables users to receive online marketing analysis data based on formal data such as consumer response (emotion), association word extraction, and comparison / statistical data.

Hereinafter, an intelligent marketing analysis method using atypical big data processing through the intelligent marketing analysis system 10 according to an embodiment of the present invention will be described with reference to FIG.

3 is a flowchart illustrating an intelligent marketing analysis method according to an embodiment of the present invention.

First, various kinds of unstructured data related to various kinds of goods (or services) are collected on-line and off-line (S310).

Such unstructured data includes data recorded or sensed by the purchasing environment, process, and pattern of the consumer in the offline site. In the online site, the specific products and services (i.e., products and services corresponding to the products provided by the offline sites, etc.) , A review of a specialized media / expert, an article of the press, and the like.

Next, the collected irregular data is subjected to data processing, analysis, and shaping processing to extract the regular data (S320).

Specifically, if the unstructured data collected from the offline site is image data taken from a camera installed offline, the image analysis can be performed by analyzing the customer distribution of each store session by time, the product of interest, the residence time in the store, And extracts stereotyped data such as emotion. In addition, the non-fixed data may be sensing data through various sensors installed offline. For example, the sensing information inputted from the sensor fixed to the door is analyzed, and the form data such as the number of customers entering and leaving the store by time and the number of customers in the store by time are extracted. In addition, by analyzing the customer's heartbeat sensing information and the customer's location information in the store during the residence time measured from the bio-signal sensor (smart band, etc.) that can be attached to the customer visiting the store, Is extracted. The beacon sensor installed in the store extracts the location information of the customer visiting the offline store and the traveled route.

When unstructured data collected on-line is text information existing on the online such as consumer's evaluation of a specific product and service, evaluation of professional media / experts, articles of press, consumer reaction (emotion), association word extraction, comparison / statistics And extracts form data such as data.

The process of extracting the unstructured data and the process of shaping the unstructured data are processed in parallel for each data, so that the processing sequence of steps S310 and S320 is not limited to the serial order.

Next, the marketing synthesis analysis is processed by fusing heterogeneous type data acquired on the offline sites and online (S330).

At this time, a plurality of related data are merged based on a preset reference (for example, time) based on different types of formatted data, and based on the rule-based marketing performance indexes previously set for the merged formatted data, And analyze whether they interact with each other.

Then, the analysis result based on the individual form data and the marketing performance index is generated as the visualization information, respectively (S340).

At this time, it is possible to generate information such as statistics, change trend, and degree of change of the individual fixed data as a form (for example, a table or a graph) that the user can visually confirm, Can be visualized in a text form such as a sentence.

Next, a final analysis report including the visualization information data is provided to an arbitrary user terminal connected via the Internet or the like (S350).

At this time, the user terminal may further include performing an authentication procedure for the user as a terminal of a user (for example, a customer or a marketing-related user) who wants to receive a marketing service through a user API.

The intelligent marketing analysis method using the intelligent marketing analysis system through the atypical big data processing according to an embodiment of the present invention described above can be implemented by a computer program stored in a medium executed by a computer or a record including a command executable by a computer But may also be implemented in the form of a medium. Such a recording medium is a computer-readable medium, which may be any available medium that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. The computer-readable medium may also include computer storage media, which may be volatile and / or non-volatile, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, Nonvolatile, removable and non-removable media.

While the methods and systems of the present invention have been described in connection with specific embodiments, some or all of those elements or operations may be implemented using a computer system having a general purpose hardware architecture.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

10: Intelligent Marketing Analysis System
100: Offline site device
200: Marketing integration analyzer

Claims (8)

In an intelligent marketing analysis system using atypical big data processing,
The offline site collects unstructured data that records or senses at least one of the purchasing environment, process, and pattern of the consumer, formats the collected unstructured data into first fixed data according to predetermined criteria, and transmits the unstructured data to the marketing integration analyzer Offline site devices; And
The method comprising the steps of: crawling text data for an arbitrary product and service as online data on-line; formatting the crawled unstructured data into second format data according to a predetermined criterion; Processing the integrated analysis of the merged form data based on a predetermined marketing performance index, and outputting the statistical information of the individual formed data and the result of the integration analysis to the user And a marketing integration analyzing device for processing and providing visualized information that can be visually confirmed,
Wherein the marketing performance indicator is defined as an interaction rule between various types of formal data, and the interaction rule is set as a marketing-meaningful rule. The method according to claim 1,
Wherein the offline site device comprises:
Analyzing image data photographed from a camera installed offline as atypical data and extracting at least one form data among a customer distribution change per each store session, an interested product, a residence time in a store, Intelligent marketing analysis system. The method according to claim 1,
Wherein the offline site device comprises:
Analyzing sensing information inputted from a sensor fixed at a door of a sensor installed offline as atypical data, extracting at least one of the number of customers entering the store by the time of day and the number of customers by the time of day,
As the atypical data, the heartbeat sensing information is analyzed together with the customer location information in the store during the residence time measured from the bio-signal sensor mounted on the off-line visiting customer, and the user's emotional response to the arbitrary merchandise is extracted as the regular data, or
Wherein at least one of the location information and the movement route of the visiting customer measured from the beacon sensor installed offline as the atypical data is extracted. The method according to claim 1,
Wherein the marketing integration analyzer comprises:
Extraction of at least one set of the consumer sensibility response, associative word, and comparison / statistical data from at least one textual data of at least one of a consumer review for an arbitrary product and service, an evaluation of a professional media / expert, and an article of the press as unstructured data , An intelligent marketing analysis system. An intelligent marketing analysis method using atypical big data processing through intelligent marketing analysis system,
Collecting a plurality of unstructured data related to any product or service on-line and on-line;
Analyzing the collected plurality of irregular data according to a predetermined criterion and formatting the same into regular data;
Integrating the form data according to a predetermined criterion, and analyzing the integrated form data based on the predetermined marketing performance index; And
Processing the statistical information of the individual fixed form data and the result of the integrated analysis into visualized information that can be visually confirmed by a user,
Wherein the marketing performance indicator is defined as an interaction rule between various types of formal data, and the interaction rule is set as a marketing-meaningful rule. 6. The method of claim 5,
Wherein the step of shaping comprises:
Analyzing image data photographed from a camera installed offline as atypical data and extracting at least one form data among a customer distribution change per each store session, an interested product, a residence time in a store, Intelligent marketing analysis method. 6. The method of claim 5,
Wherein the step of shaping comprises:
Analyzing sensing information inputted from a sensor fixed at a door of a sensor installed offline as atypical data, extracting at least one of the number of customers entering the store by the time of day and the number of customers by the time of day,
As the atypical data, the heartbeat sensing information is analyzed together with the customer location information in the store during the residence time measured from the bio-signal sensor mounted on the off-line visiting customer, and the user's emotional response to the arbitrary merchandise is extracted as the regular data, or
Wherein at least one of the location information and the movement route of the shop visit customer measured from the beacon sensor installed offline as the atypical data is extracted. 6. The method of claim 5,
Wherein the step of shaping comprises:
Extraction of at least one set of the consumer sensibility response, associative word, and comparison / statistical data from at least one textual data of at least one of a consumer review for an arbitrary product and service, an evaluation of a professional media / expert, and an article of the press as unstructured data , Intelligent marketing analysis method.

Images