KR20220104100A - Analysis method and system for customized search based on artificial intelligence - Google Patents

Abstract

The present invention relates to an analysis system and method for AI-based customized search. The analysis system and method for AI-based customized search may collect a plurality of types of unstructured data related to any marketing company offline and online, analyze the collected plurality of types of unstructured data according to predetermined criteria to standardize the data into structured data, converge the structured data according to the predetermined criteria, perform integrated analysis the converged structured data based on predetermined marketing performance indicators, and process and provide statistical information of individual structured data and results of integrated analysis into visualization information that users can visually check.

Description

Analysis system and method for AI-based customized search { ANALYSIS METHOD AND SYSTEM FOR CUSTOMIZED SEARCH BASED ON ARTIFICIAL INTELLIGENCE }

The present invention relates to an analysis system and method for AI-based customized search, which collects a plurality of unstructured data related to an arbitrary marketing company offline and online, and analyzes the collected plurality of unstructured data according to a preset standard. It is formalized into structured data, the structured data are fused according to a preset standard, the fused structured data is integrated and analyzed based on a preset marketing performance index, and the user can visually view statistical information and the results of the integrated analysis of individual structured data. It relates to an analysis system and method for AI-based customized search that can be processed and provided as visible information that can be checked.

In order to analyze and utilize data, expertise in elemental technologies such as data mining, statistical analysis, and mathematical optimization and a broad understanding of the field in which the data is generated are required. For example, in the field of marketing research, expert personnel with sufficient understanding of the types of knowledge or information related to consumer behavior, desire, and environment in each field are required.

On the other hand, although the generation of consumption-related data is greatly increasing due to the rapid spread of IoT application products and services, there is a shortage of experts with scientific/effective data analysis ability and experience. Accordingly, the level of data analysis is usually at the level of measuring keyword frequency, and the accuracy of the analysis is lowered, and most of the data is dead.

However, according to the existing marketing research method, there is a limitation in that it takes a lot of manpower and time to collect and analyze vast amounts of on/offline data. In addition, the automatic convergence of heterogeneous data and analysis of emotion-related big data has a problem in that professional extraction standards and classification systems are not systematically established.

Therefore, in order to utilize it as marketing research data, there is an urgent need for a realistic and applicable technology that can process a large amount of collected unstructured data through a formalization process and various analysis methods.

The present invention has been devised to solve the above problems, and the present invention collects a plurality of unstructured data related to an arbitrary marketing company offline and online, and analyzes the collected plurality of unstructured data according to a preset standard to form It is structured into data, the structured data are fused according to a preset standard, the fused structured data is integrated and analyzed based on a preset marketing performance index, and the user can visually check the statistical information of individual structured data and the results of the integrated analysis. The purpose is to provide an analysis system and method for AI-based customized search that can be processed and provided as visible information.

As a technical means for achieving the above-described technical problem, an intelligent marketing analysis system through atypical big data processing according to an aspect of the present invention records or senses at least one of a consumer's purchasing environment, process, and pattern in an offline site. an offline site device for collecting unstructured data, formalizing the collected unstructured data into first structured data according to a preset standard, and transmitting the collected unstructured data to an integrated marketing analysis device; and crawling text data for certain products and services online as unstructured data, formulating the crawled unstructured data into second structured data according to a preset criterion, and first structured data received from the offline site device and The second structured data is fused according to a preset criterion, an integrated analysis of the fused structured data is processed based on a preset marketing performance index, and statistical information of the individual structured data and the result of the integrated analysis are processed. It includes a marketing integrated analysis device that processes and provides visualization information that a user can visually check.

In addition, an intelligent marketing analysis method through unstructured big data processing according to another aspect of the present invention comprises: collecting a plurality of unstructured data related to any product or service offline and online; analyzing the plurality of collected unstructured data according to a preset criterion to form it into structured data; fusion of the structured data according to a preset standard, and an integrated analysis of the fused structured data based on a preset marketing performance index; and processing the statistical information of the individual structured data and the result of the integrated analysis into visualization information that a user can visually confirm.

According to any one of the above-described problem solving means of the present invention, when a subject for marketing analysis is determined, related on/offline big data is automatically collected and stored, and each collected atypical data type (eg, text, image, etc.) Accordingly, meaningful structured data can be automatically extracted through the standardization module and stored in the DB, and can be automatically provided through the service API through the fusion of heterogeneous structured data stored in the DB.

1 is a block diagram of an intelligent marketing analysis system according to an embodiment of the present invention.
2 is a conceptual diagram for explaining a marketing comprehensive 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.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention, parts irrelevant to the description in the drawings are omitted, and similar reference numerals are attached to similar parts throughout the specification. In addition, while describing with reference to the drawings, even if the configuration indicated by the same name, the drawing number may vary depending on the drawing, and the drawing number is only described for convenience of description, and the concept, feature, and function of each configuration by the corresponding drawing number Or the effect is not to be construed as limiting.

Throughout the specification, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless specifically stated to the contrary. It should be understood that the above does not preclude the possibility of the existence or addition of other features or numbers, steps, operations, components, parts, or combinations thereof.

As used herein, the term “part” or “module” includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware. Meanwhile, '~ unit' or '~ module' is not limited to software or hardware, and may be configured to be in an addressable storage medium or to reproduce one or more processors. Accordingly, as an example, '~part' or '~module' means components such as software components, object-oriented software components, class components and task components, processes, functions, and properties. includes fields, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within these components and '~units' (or '~modules') may be combined with a smaller number of components and '~units' (or '~modules') or with additional components. It can be further divided into '~parts' (or '~modules'). In addition, components and '~ unit' (or '~ module') may be implemented to play one or more CPUs in a device or secure multimedia card.

The “terminal” referred to below may be implemented as a computer or portable terminal that can access a server or other terminal through a network. Here, the computer includes, for example, a laptop, a desktop, and a laptop equipped with a web browser (WEB Browser), and the portable terminal is, for example, a wireless communication device that ensures portability and mobility. ,IMT (International Mobile Telecommunication), CDMA (Code Division Multiple Access), W-CDMA (W-Code Division Multiple Access), LTE (Long Term Evolution), etc. communication-based terminals, smartphones, tablet PCs, etc. All kinds of hands It may include a handheld-based wireless communication device. In addition, “network” refers to a wired network such as a local area network (LAN), a wide area network (WAN) or a value added network (VAN) or a mobile radio communication network or satellite It may be implemented as any kind of wireless network, such as a communication network.

The intelligent marketing analysis system according to an embodiment of the present invention, which will be described below, is not a marketing analysis service through the existing human resource-based questionnaire and data survey, but automatically collects, processes, standardizes and It automatically generates a marketing analysis report through comparison/analysis of heterogeneous structured data, and provides online service to customers.

To this end, the intelligent marketing analysis system according to an embodiment of the present invention comprehensively analyzes and processes offline information on the consumer purchasing process and purchase environment, and online information such as online product reviews and user reviews. At this time, the intelligent marketing analysis system according to an embodiment of the present invention automatically collects and processes atypical big data (eg, images, biosignals, texts, movement lines, etc.) Therefore, marketing analysis service is supported through standardization and analysis.

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

1 is a block 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 an integrated marketing analysis device 200 . In an embodiment of the present invention, the offline site device 100 and the marketing integrated analysis device 200 may each be a kind of server device, and the two devices will be referred to as a server hereinafter.

The intelligent marketing analysis system 10 is composed of one central marketing integrated analysis server 200 and a plurality of offline site servers 100 installed in offline sites (ie, stores). At this time, the offline site server 100 is connected to the marketing integrated analysis server 200 through a network such as the Internet, and the structured data for marketing analysis obtained from the offline site is transferred to the central marketing integrated analysis server through a predefined API. (200). In addition, the offline site server 100 is installed in an offline store that requires a marketing analysis service, and cameras and sensors (entry sensor, beacon sensor, biosignal) installed in a plurality of areas of the offline store to collect information for marketing analysis. It is interlocked with information collection devices such as sensors for collection, etc.). The offline site server 100 may be implemented on a kind of terminal device.

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

The field data collection unit 110 is interlocked with at least one information collection device installed in the corresponding offline field to acquire data from each information collection device. In this case, the information collection device may be a camera device and various sensor devices.

The formalization processing unit 120 processes various data collected through the field data collection unit 110 into a preset format to enable analysis, and then analyzes the processed data to extract preset formatted data.

Specifically, when a camera is installed as an information collecting device, the stereotype processing unit 120 analyzes the input image data, and through analysis of the input image data, the customer distribution changes by time and store session, products of interest, time spent in the store, movement lines, emotion through facial expression recognition Extract structured data such as In this case, according to a service scenario desired by the customer, the camera used may be a fixed or mobile camera. Such a fixed camera may be used to collect information from a large number of unspecified visitors, and a mobile camera may be used to collect information from a specific selected focus group.

In addition, when a sensor is installed as an information collecting device, the sensor information input from the sensor fixed to the door is analyzed, and structured data such as the number of customers entering the store by time period and the number of customers in the store by time period is extracted. In addition, by analyzing the customer's heart rate sensing information and customer location information in the store during the store stay time measured from the biosignal sensor (smart band, etc.) Extract the structured data of Also, it is possible to extract the location information and the moving route of the customer visiting the offline store from the beacon sensor.

The data analyzed and standardized through the standardization processing unit 120 is stored in the local database 130 on the offline site server 100 , and is also transmitted to the marketing integrated analysis server 200 through the data transmission unit 140 . In this case, the data transmission unit 140 has an API defined in advance to interwork with the marketing integration analysis server 200 in order to transmit the standardized data is implemented.

The integrated marketing analysis server 200 includes an online data collection unit 210 , a formalization processing unit 220 , an integrated database 230 , a heterogeneous data fusion unit 240 , a marketing comprehensive analysis unit 250 , a visualization engine 260 and and a user API providing unit 270 .

The online data collection unit 210 collects (crawls) text data online (eg, the Internet).

In this case, the online data collection unit 210 may collect text information existing online, such as consumer reviews on specific products and services, evaluations of specialized media/experts, and media articles.

The formalization processing unit 220 processes the collected various online data into a preset format to enable analysis, and then analyzes the processed data to extract preset formatted data.

In this case, the standardization processing unit 220 extracts structured data such as consumer reaction (sentiment), related word extraction, comparison/statistical data, and the like, and stores the extracted structured data in the integrated database 230 .

The integrated database 230 integrates and stores the structured data extracted from the online marketing integration analysis server 200 and the structured data received from the offline site server 100 .

For reference, although not shown in FIG. 1 , the integrated marketing analysis server 200 may separately include a data receiver that communicates with the data transmitter 140 of the offline site server 100 to receive the offline standardized data. In this case, an API matching the data transmitter 140 of the offline site server 100 may be defined on the data receiving unit (not shown) of the marketing integrated analysis server 200 .

The heterogeneous data fusion unit 240 fuses a plurality of related data based on a preset criterion (eg, time) with the structured data stored in the integrated database 230 .

The marketing comprehensive analysis unit 250 comprehensively analyzes the fused structured data based on a marketing performance index preset for marketing analysis.

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

Marketing performance index is a rule-based index for comprehensively analyzing heterogeneous structured data. It defines how various heterogeneous structured data interact and is used to derive marketingly meaningful analysis results.

The plurality of structured data (#1 to #n) shown in FIG. 2 includes data including a time stamp proving the fact that the data existed at a certain point in time, respectively, and data not including a time stamp. includes

At this time, the marketing comprehensive analysis unit 250 applies the marketing performance index to a plurality of structured data as shown in FIG. 2 , and the degree of relevance between the structured data according to an arbitrary criterion (eg, passage of time) and Analyze interactions in an integrated way. In FIG. 2 , a time interval that has an effect for each structured data is displayed as time passes, and the relationship and interaction between heterogeneous structured data can be understood by analyzing the effective time section for each structured data in an integrated manner.

The visualization engine 260 generates information such as statistics, change trend, and degree of change of individual structured data in a form (eg, a table or graph, etc.) that a user can visually check.

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

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

In this case, the user API providing unit 270 may provide the user API to the user terminal 300 accessed through a network (eg, the Internet). In addition, a user (eg, a customer or a marketing-related user) who wants to receive a marketing service through the user API can view the finally generated visualization result through the authentication process.

Through this, the user can receive online marketing analysis data based on structured data such as consumer reaction (emotion), related word extraction, and comparison/statistical data.

Hereinafter, an intelligent marketing analysis method through 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 .

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

First, various types of unstructured data related to various types of products (or services) are collected online and offline (S310).

These unstructured data include data that records or senses the consumer's purchasing environment, process, and pattern in the offline site, and specific products and services (ie, products and services corresponding to the products provided by the offline site, etc.) in the online site. It includes text data that exists online, such as consumer reviews, professional media/professional evaluations, and media articles.

Next, the collected unstructured data is processed and analyzed, respectively, and the structured data is extracted by standardized processing (S320).

Specifically, if the atypical data collected from an offline site is image data taken from a camera installed offline, through image analysis, changes in customer distribution by time and by store session, products of interest, time spent in the store, movement lines, and facial expression recognition Extracts structured data such as emotions. In addition, the unstructured data may be data sensed through various sensors installed offline. For example, by analyzing the sensing information input from a sensor fixed to the door, structured data such as the number of customers entering and leaving the store by time period and the number of customers in the store by time period is extracted. In addition, by analyzing the customer's heart rate sensing information and customer location information in the store during the store stay time measured from the biosignal sensor (smart band, etc.) Extract the structured data of In addition, the location information and the moving route of the customer visiting the offline store are extracted from the beacon sensor installed in the store.

If the unstructured data collected online is text information that exists online, such as consumer reviews on specific products and services, professional media/expert evaluations, and media articles, consumer reactions (emotions), related word extraction, comparison/statistics Extracts structured data such as data.

As described above, the process of extracting the unstructured data and the process of formulating the unstructured data are processed in parallel for each data, and accordingly, the processing order of the steps (S310) and (S320) is not limited to a serial order.

Next, a comprehensive marketing analysis is processed by fusion of heterogeneous structured data acquired on the offline site and online (S330).

At this time, the heterogeneous structured data is fused based on a preset criterion (eg, time), and a plurality of related data is fused, and the fused structured data is used in what way is the heterogeneous structured data based on a pre-set rule-based marketing performance index? It derives marketingly meaningful analysis results by performing an integrated analysis of interaction.

Then, the results analyzed based on the individual structured data and the marketing performance index are respectively generated as visualization information (S340).

At this time, information such as statistics, change trend and degree of change of individual structured data can be generated in a form that users can visually check (eg, table or graph, etc.) The corresponding information can be visualized in the form of text such as sentences.

Next, a final analysis report including visualization information data is provided to any user terminal connected through the Internet (S350).

In this case, the user terminal is a terminal of a user (eg, a customer or a marketing-related user) who wants to receive a marketing service through the user API, and may further include the step of performing an authentication procedure for the user.

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

Although the methods and systems of the present invention have been described with reference to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general purpose hardware architecture.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

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

10: Intelligent Marketing Analytics System
100: offline site device
200: marketing integrated analysis device

Claims (1)

In an intelligent marketing analysis system through processing of unstructured big data, unstructured data that records or senses at least one of a consumer's purchasing environment, process and pattern on an offline site is collected, and the collected unstructured data is generated according to a preset standard 1 Offline site device that formalizes structured data and transmits it to marketing integrated analysis device; and
Crawling text data for certain products and services online as unstructured data, formulating the crawled unstructured data into second structured data according to a preset criterion, and first structured data received from the offline site device and the The second structured data is fused according to a preset criterion, an integrated analysis of the fused structured data is processed based on a preset marketing performance index, and statistical information of the individual structured data and the result of the integrated analysis are displayed to the user. including a marketing integrated analysis device that is processed and provided into visualization information that can be visually confirmed,
The marketing performance indicator is an interaction rule between various heterogeneous structured data is defined, and the interaction rule is set as a marketingly meaningful rule, an intelligent marketing analysis system.

Images