KR20230072085A - AI-based store management platform service method - Google Patents

Abstract

The AI-based store management platform service method according to the present invention builds a database by matching store identification codes with store-related information, store-related images, and store-related content, and provides information about the registered store-related information and the registered store-related images. performing AI learning; Obtaining a store signboard picture through a user terminal and acquiring location information of the user terminal; obtaining an identification code of the store based on an image recognition result of the store signboard picture and location information of the user terminal; selecting content corresponding to the identification code of the store from the database and providing the content to the user terminal; and filtering out false user reviews by verifying whether the store user reviews received from the user terminal are authentic based on the AI learning result.

Description

AI-based store management platform service method

The present invention relates to a method for providing a store management platform service based on AI, and more particularly, based on an image recognition result for a store signboard and location information of a user terminal, various information and contents related to the store can be provided. It is about an AI-based store management platform service method that can verify the authenticity of store user reviews.

Store information provided through the Internet is inflated information due to online advertising agency, or is distributing advertising information of companies other than actual users, or hired personnel often write false reviews, so it is difficult to trust it. reality is difficult.

Even in this reality, the size of the online advertising market is steadily increasing, and this is true not only for large companies and small and medium-sized businesses, but also for small business owners. Among them, the size of the advertising market using Augmented Reality is experiencing remarkable growth.

In addition, due to the development of the Internet and SNS, users go beyond simply using the store, and actively engage in activities such as raising satisfaction or complaints after using the store through user reviews, or recommending it to others. However, it is a reality that there are not a few cases in which store user reviews falsely disparage stores with malice.

Therefore, the technical problem to be solved by the present invention is based on the recognition result of the store signboard and the location information of the user terminal, AI that can provide store-related information in various contents such as video, image, voice, text, animation, etc. It is to provide a service method based on the store management platform.

And another technical problem to be solved by the present invention is to provide a store management platform service method capable of determining the authenticity of store reviews using AI learning results and filtering out malicious false reviews.

The technical problems to be achieved by the present invention are not limited to the above-mentioned technical problems, and other technical problems not mentioned can be clearly understood by those skilled in the art from the description below. There will be.

In the AI-based store management platform service method according to the present invention for solving the above technical problem, a database is built by matching store identification codes with store-related information, store-related images, and store-related content, and the store-related information and performing AI learning on the store-related image. Obtaining a store signboard picture through a user terminal and acquiring location information of the user terminal; obtaining an identification code of the store based on an image recognition result of the store signboard picture and location information of the user terminal; selecting content corresponding to the identification code of the store from the database and providing the content to the user terminal; and filtering out false user reviews by verifying whether the store user reviews received from the user terminal are authentic based on the AI learning result.

The step of verifying the authenticity of the store use review may include analyzing a text portion of the store use review based on an AI learning result for the store-related information; and determining that the store review is a false review if the content analysis result indicates that the store review is not related to a product or service provided in the store.

The verifying the authenticity of the store use review may include analyzing a photo included in the store use review based on an AI learning result for the store related images; and if the photo does not relate to a product provided in the store or an item used in the store as a result of the analysis, determining the store review as a false review.

In the step of verifying the authenticity of the store review, if the photographing location information included in the tag information of the photo included in the store review does not match the location information of the store, the store review is regarded as a false review. It may further include a step of judging.

The AI-based store management platform service method may further include transmitting a warning message to the user terminal when the store review is determined to be a false review.

The AI-based store management platform service method may further include selecting the store review as a verification target when the evaluation grade of the store review is lower than a predetermined level.

In the AI-based store management platform service method, if the store review is determined to be a true review, the rating level of the store review is low based on the analysis result of the text part of the store review. The step of notifying the manager of the store of the reason may be further included.

The AI-based store management platform service method may further include automatically uploading the store review to a predetermined online medium when the store review is determined to be a true review.

The AI-based store management platform service method includes collecting and analyzing content related to the store from the predetermined online medium based on the AI learning result; and updating the database by reflecting the content analysis result.

The AI-based store management platform service method may include notifying a manager of the store of a result of analyzing the content and inquiring whether the database is updated; and updating the database when an approval command is received from the manager of the store.

According to the present invention, based on AI-based sign recognition and location information of a user terminal, various information related to the store can be provided as augmented reality content combining video, image, voice, text, and animation.

In addition, according to the present invention, it is possible to determine the authenticity of the store review using the AI learning result, and to filter malicious false review.

1 is a configuration diagram of a service system for implementing an AI-based store management platform service method according to the present invention.
2 is a flowchart illustrating an example of an AI-based store management platform service method according to the present invention.
3 is a conceptual diagram of building a store-related database according to the AI-based store management platform service method according to the present invention.
4 shows an example in which store-related content is provided according to the AI-based store management platform service method according to the present invention.
5 is a flowchart illustrating an example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention.
FIG. 6 illustrates an example of managing store use reviews received from the user terminal 100 according to the store use review management method shown in FIG. 5 .
7 is a flowchart illustrating another example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention.
8 illustrates an example of managing store use reviews received from the user terminal 100 according to the store use review management method shown in FIG. 7 .
9 is a flowchart illustrating another example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention.
10 is a conceptual diagram for explaining other functions of the AI-based store management platform service method according to the present invention.

In order to fully understand the present invention, its operational or functional advantages, and the objects achieved by the practice of the present invention, reference should be made to the accompanying drawings illustrating preferred embodiments of the present invention and the contents described in the accompanying drawings.

Hereinafter, with reference to the accompanying drawings, the present invention will be described in more detail. Since the present invention may have various changes and various forms, specific embodiments are illustrated in the drawings and described in detail in the text. However, it should be understood that this is not intended to limit the present invention to the specific disclosed form, and includes all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

Like reference numerals have been used for like elements throughout the description of each figure. In the accompanying drawings, the dimensions of the structures may be enlarged or reduced than the actual size for clarity of the present invention.

Terms such as first and second may be used to describe various components, but the components should not be limited by the terms. These terms are only used for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element, without departing from the scope of the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, the terms "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

In addition, unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in this application, it should not be interpreted in an ideal or excessively formal meaning. don't

1 is a configuration diagram of a service system for implementing an AI-based store management platform service method according to the present invention.

The service system 10 includes a user terminal 100 , a service server 200 , a database 300 and a store manager terminal 400 . Meanwhile, the user terminal 100 and the store manager terminal 400 are shown as smart phones, but the scope of the present invention is not limited thereto, and they may be PCs or notebook tablets.

The service server 200 may provide a platform for managing a store based on AI. Store management may include store information management, sales management, customer management, store advertisement, communication functions with customers, and the like.

In particular, the service system 10 provides store-related content such as video, image, voice, text, animation, etc. based on the image recognition result of the store signboard through the user terminal 100 and the location information of the user terminal 100. may be provided to the user terminal 100. Meanwhile, such store-related contents may be provided based on augmented reality combined with actual store photos taken through the user terminal 100 .

In addition, the service system 10 verifies the authenticity of store review posted by the user through the user terminal 100, filters out false reviews, and uploads only true reviews, thereby causing damage caused by malicious users. can prevent

In addition, the service server 200 extracts information necessary for store management by collecting and analyzing content or items related to registered stores on the Internet without the involvement of users and store managers, and then updates the database 300 based on this. It can also perform an active management function that informs the user.

2 is a flowchart illustrating an example of an AI-based store management platform service method according to the present invention. Hereinafter, the method will be described in detail with reference to the necessary drawings.

First, the service server 200 builds a database by matching store-related information, store-related images, and store-related contents provided by a store manager with corresponding store identification codes for a plurality of registered stores ( S100). Here, the content provided by the store manager is store-related information and may include video, image, voice, text, animation, and the like.

And the service server 200 performs AI learning on the store-related information and the store-related image (S110). Based on these AI learning results, the service server 200 can determine whether specific information is store-related information, and can determine whether a specific image or photo is a store-related picture.

3 is a conceptual diagram of building a store-related database according to the AI-based store management platform service method according to the present invention.

When the store manager accesses the service server 200 through the store manager terminal 400 and uploads various data corresponding to store-related information, the service server 200 selects a content scenario through auto-editing and Content is created by applying a predetermined template.

Then, the service server 200 performs customizing for this, converts it into a database, and stores it. At this time, customizing may be performed according to a request or command received from the store manager terminal 400 . And the stored content may be provided based on augmented reality through the user terminal 100 .

Referring back to FIG. 2 , when a user who wants to be provided with store-related content takes a picture of a store signboard through the user terminal 100, the location information of the user terminal 100 is obtained (S120), and these provide service It is provided to the server 200.

Then, the service server 200 acquires the identification code of the store based on the image recognition result of the signboard photo of the store and the location information of the user terminal 100 (S130), and identifies the acquired store. The content corresponding to the code is provided based on augmented reality using the image obtained from the user terminal 100 (S140).

In addition, the service server 200 verifies the authenticity of the store review received from the user terminal 100 by applying the AI learning result, and filters out the false review (S150). Therefore, the service server 200 can filter malicious and false user reviews.

Meanwhile, the service method of FIG. 2 may further include setting a content providing language. Then, the content corresponding to the identification code of the store may be provided in the set content providing language.

4 shows an example in which store-related content is provided according to the AI-based store management platform service method according to the present invention.

When a user photographs (signboard tagging) a signboard of 'Bandjeong Beauty Salon' with his/her terminal 100 linked to the service server 200, the user terminal 100 captures it along with the location information of the service server 200, operating system server). Then, the service server 200 provides store-related content based on augmented reality through the user terminal 100 .

5 is a flowchart illustrating an example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention. Hereinafter, the use review management method will be described with reference to necessary drawings.

First, store use reviews are received from the user terminal 100 to the service server 200 (S200). Then, the service server 200 analyzes the contents of the text part of the store use review based on the AI learning result for store information (S210).

In addition, the service server 200 determines whether the store use review is related to products or services provided in the store (S220). If the content of the store review is correct for a product or service provided in the store, the service server 200 determines the store review as a true store review and posts the store review on the service platform. Do (S230).

However, if the content of the store review is not related to a product or service provided in the store, the service server 200 determines the store review as a false review and filters it (S240), and posts it on the service platform. may not

Meanwhile, the service server 200 transmits a warning message about writing a false review to the user terminal 100 that has transmitted the false review (S250). By doing so, it is possible to remind users that 'I should not write a malicious store review.'

In this case, the service server 200 notifies the store manager terminal 400 of the contents of the store use review and inquires whether a warning message is transmitted, and only when a permission command is received from the store manager terminal 400. , a warning message can be transmitted to the user terminal 100 .

This is to receive confirmation from the store manager for authenticity determination, since the warning message may be a sensitive matter. It is preferable that this procedure is also applied to the example of FIG. 7 to be discussed later.

FIG. 6 illustrates an example of managing store use reviews received from the user terminal 100 according to the store use review management method shown in FIG. 5 .

6(a) is a review of a store called 'Chinese Castle', a Chinese restaurant, and a one-star store review saying "The pork cutlet at this house is really bad. The employees are unfriendly..." is sent to the user terminal (100 ) indicates that it was received from

Then, as shown in (b) of FIG. 6, the service server 200 analyzes the text part of the store use review by referring to the data of the database 300 based on the AI learning result, and as a result of the analysis, 'pork cutlet' is It is possible to recognize that the menu is not provided by 'Chinese Castle', and determine that the store review is a false review.

On the other hand, the service server 200 analyzes the pork cutlet photo included in the store review and recognizes that the picture is not a menu provided by 'Chineseity', and based on this, the store review is a false store review. may be judged to be

7 is a flowchart illustrating another example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention. Hereinafter, the use review management method will be described with reference to necessary drawings.

First, store usage reviews including photos are received from the user terminal 100 to the service server 200 (S300). Then, the service server 200 analyzes the photos based on the AI learning result for store photos (S310).

And the service server 200 determines whether the photo relates to a product provided in the store or a product used in the store (S320). If the photo corresponds to a product provided in the store or a product used in the store, the service server 200 determines the store review as a true store review and transmits the store review to the service platform. Post (S230).

However, if the photo does not relate to a product provided in the store or an item used in the store, the service server 200 determines the store review as a false review and filters it (S340), and sends it to the service platform. may not be published.

Meanwhile, the service server 200 transmits a warning message about writing a false review to the user terminal 100 that has transmitted the false review (S350). By doing so, it is possible to remind users that 'I should not write a malicious store review.'

The store review management method shown in FIG. 7 may have meaning in blocking malicious false store review reviews, but in order to accurately determine and take action on false store review reviews, the store review management method of FIG. It may also be performed on a complementary level.

Meanwhile, as another method of determining the authenticity of the store review by analyzing the photo included in the store review, there is a method of using tag information of the photo. For example, the service server 200 may determine the store review as a false review if the location information included in the tag information of the photo included in the store review does not match the store location information. there is. Of course, this method has a limitation in that the photo must include tag information as well as photographing location information.

The method for managing store user reviews described above is preferably performed by using the store user reviews as a verification target only when the evaluation grade of the store user reviews is lower than a predetermined level.

8 illustrates an example of managing store use reviews received from the user terminal 100 according to the store use review management method shown in FIG. 7 .

8(a) is a review of a store called 'Chinese Castle', a Chinese restaurant, and a 2-star store review saying "The store is really messy. The dishes are less washed..." is a user terminal (100) indicates that it has been received from

Then, the service server 200 refers to the data of the database 300 based on the AI learning result, as shown in (b) of FIG. and it may be determined that the store user reviews are false user reviews.

9 is a flowchart illustrating another example of a method for managing store use reviews in the AI-based store management platform service method according to the present invention. Hereinafter, the use review management method will be described with reference to necessary drawings.

In a situation where the platform service method is running, if the analysis result based on the AI learning result determines that the store review with a low evaluation grade is true (S400), the store review is posted on the service platform (S410).

Then, the service server 200 notifies the store manager terminal 400 of the reason for the low rating of the store review based on the analysis result of the text portion of the store review (S420). Then, the store manager who is notified of this can take action to resolve the reason for the low rating.

For example, if the store use review written by the first user includes the text "The cup is broken", the service server 200 may transmit such content to the store manager terminal 400 . The transmission method may be SNS, SMS, or the like. Then, the store manager can solve the reason for receiving the low rating by checking this and replacing the broken cup.

Of course, the service server 200 may notify the store manager terminal 400 of the reason even when the level of the store user review is higher than a predetermined level. Then the store manager can feel rewarded and feel the taste of work.

Referring back to FIG. 9 , the service server 200 automatically uploads the store use reviews to a predetermined online medium (S430). here. Online media may be various SNSs, blogs, cafes, and the like.

On the other hand, if the service server 200 also has a high evaluation grade and is true, it can be automatically uploaded to the predetermined online medium. According to such an automatic upload function, the store manager can save the trouble of individually uploading user reviews through an online medium.

10 is a conceptual diagram for explaining other functions of the AI-based store management platform service method according to the present invention.

The service server 200 may collect and analyze store-related content from the Internet based on AI learning results. Then, the service server 200 may update the database 300 in which store-related data is stored, if necessary as a result of content analysis.

At this time, the service server 200 may inquire whether the database 300 is updated while transmitting the analysis result to the store manager terminal 400 . In addition, the database 300 may be updated based on analysis of self-collected data only when an update approval command is received from the store manager terminal 400 .

For example, it is assumed that as a result of analyzing the content collected by the service server 200, there is content about a specific product other than a product sold in the store. Then, the service server 200 may add the specific product to a list of products sold in the store.

At this time, the service server 200 notifies the store manager terminal 400, and only when an approval command to update the specific product to a product sold in the store is received from the service server 200, the database 300 ) can be updated.

In this way, the service server 200 goes beyond providing various services based on the content uploaded by the store manager, and actively analyzes and applies its own collected data to perform store-related management functions so that the store manager needs to update necessary data. It can relieve you of the trouble of doing it.

As described above, although the present invention has been described by the limited embodiments and drawings, the present invention is not limited to the above embodiments, and those skilled in the art in the field to which the present invention belongs can make various modifications and variations from these descriptions. this is possible

Therefore, the scope of the present invention should not be limited to the described embodiments and should not be defined, and should be defined by not only the claims to be described later, but also those equivalent to these claims.

10: service system 100: user terminal
200: service server 300: database
400: Store manager terminal 500: Internet

Claims (10)

Building a database by matching store identification codes with store-related information, store-related images, and store-related content, and performing AI learning on the registered store-related information and the registered store-related images;
Obtaining a store signboard picture through a user terminal and acquiring location information of the user terminal;
obtaining an identification code of the store based on an image recognition result of the store signboard picture and location information of the user terminal;
selecting content corresponding to the identification code of the store from the database and providing the content to the user terminal; and
Based on the AI learning result, the AI-based store management platform service method comprising the step of filtering out false reviews by verifying the authenticity of the store review received from the user terminal.
According to claim 1,
The step of verifying the authenticity of the store use review,
Analyzing the contents of the text portion of the store use review based on the AI learning result of the store-related information; and
As a result of the content analysis, if the store review is not related to a product or service provided in the store, determining the store review as a false review, AI-based store management platform service. method.
According to claim 2,
The step of verifying the authenticity of the store use review,
Analyzing a photo included in the store use review based on an AI learning result of the store-related image; and
As a result of the analysis, if the photo does not relate to a product provided in the store or an item used in the store, determining the store review as a false review, characterized in that it further comprises an AI-based store Management platform service method.
According to claim 2,
The step of verifying the authenticity of the store use review,
Further comprising the step of determining that the store review is a false review if the photographing location information included in the tag information of the photo included in the store review is not consistent with the store location information. Based store management platform service method.
According to any one of claims 2 to 4,
When the evaluation grade of the store review is lower than the predetermined grade, further comprising the step of selecting the store review as a verification target, AI-based store management platform service method.
According to any one of claims 2 to 4,
If the store review is determined to be a false review, further comprising the step of sending a warning message to the user terminal, AI-based store management platform service method.
According to any one of claims 2 to 4,
If the store review is judged to be a true review,
Based on the analysis result of the text part of the store review, notifying the manager of the store of the reason why the store review is low, characterized in that it further comprises an AI-based store Management platform service method.
According to any one of claims 2 to 4,
If the store review is judged to be a true review,
Characterized in that it further comprises the step of automatically uploading the store use reviews to a predetermined online medium, AI-based store management platform service method.
According to any one of claims 2 to 4,
Based on the AI learning result, collecting and analyzing content related to the store from the predetermined online medium; and
Characterized in that it further comprises the step of updating the database by reflecting the content analysis result, AI-based store management platform service method.
According to claim 9,
notifying the manager of the store of the content analysis result and inquiring whether the database is updated; and
When an approval command is received from the manager of the store, characterized in that it further comprises the step of updating the database, AI-based store management platform service method.

Images