KR102587882B1 - System for providing price choosing serivce - Google Patents

Abstract

A method of providing a price selection service according to food taste is provided, including receiving patient medical record data transmitted from a medical advice request terminal to calculate medical expenses, parsing the received medical record data to extract a diagnosis, and A step of deriving and classifying a medical diagnosis, a medical diagnosis site, and an identifier of a detailed disease name from the diagnosis, a step of extracting at least one image identification information included in the received medical record data, and the classified identifier and the extracted image identification information. Based on this, extracting reference data with a preset similarity from previously constructed big data, outputting advisory data already mapped and stored to the extracted reference data, and generating advisory data for the patient's medical record data, and It includes the step of transmitting the generated advice data to the medical advice request terminal.

Description

System for providing price selection service based on food taste {SYSTEM FOR PROVIDING PRICE CHOOSING SERIVCE}

The present invention relates to a system for providing a price selection service according to the taste of food, and provides a platform to eradicate fake reviews by eliminating reviews or ratings and providing an option to allow customers to select a price according to the quality perceived by the customer according to the taste of the food. .

Looking for product reviews during the information search process before purchasing a new product has become a behavior pattern for most consumers. Therefore, the importance of reviews has increased, and marketing using reviews has increased. A review is essentially an objective review of a product based on the critic's experience. However, as viral marketing has increased, so-called ‘false reviews’ have emerged, where critics receive compensation from companies to review products. The damage caused by this has gradually increased, and open market companies and some countries are imposing sanctions on false reviews in various ways. Korea's Fair Trade Commission requires this to be stated when writing a review after receiving support for a product, but since detection is not easy and punishment is weak, there is a blind spot in that it is practically left to the individual's conscience. In a situation where false reviews and real reviews were mixed, the damage was passed on to small business owners.

At this time, a method for identifying false or fake reviews was researched and developed. In this regard, Korean Patent Publication No. 2019-0123397 (published on November 1, 2019) and Korean Patent Publication No. 2020-0000925 are prior art. (Released on January 6, 2020) collects review information, classifies review information into real review information and fake review information, verifies the linguistic differences between real review information and fake review information, and provides information on linguistic differences. Based on this, a classification model that can distinguish fake reviews is constructed, a structure that calculates the discrimination accuracy between real and fake review information by inputting review information into the classification model, and an optimal model for distinguishing fake reviews. By using the app and pointing the camera at it, you can see reviews about the store, and by providing a translated language according to the user's nationality, not only Koreans but also foreigners can receive services.

However, if a restaurant is known for being a so-called good restaurant, it is not uncommon for them to hire part-time workers from nearby competing restaurants to order food and then conduct so-called star rating terrorism to lower the rating and make their restaurant popular first. Even in cases where the restaurant is not known for being a good restaurant, there are cases where people give star ratings simply because they are in a bad mood or as a way to vent their anger. Violence tends to be directed at the weak, but by leaving malicious reviews, customers end up being abusive rather than abusive. Additionally, a new term called review beggar was coined, which refers to people who promise to leave a review but then receive a service and do not actually leave a review. As the number of delivery companies increases, the importance of reviews left by customers who order food has increased. If the rating is low, customers will not choose the product, so restaurant owners are forced to hire a marketing company to raise reviews and ratings, which is a double whammy. Accordingly, research and development of a platform that eliminates reviews and ratings and determines prices based on food taste or service is required.

In one embodiment of the present invention, at least one affiliated store sets different price options for each menu, and if the user likes the quantity and quality of the food and the affiliated store's service, the user selects and pays an appropriate price, so that the affiliated store It allows the menu to be modified or developed by understanding which price options are most often selected for each menu, and since customer users can also indicate the parts they are dissatisfied with as prices, and conversely, they can also indicate the parts they are satisfied with as prices, so compensation is provided. It is possible to provide a win-win method of providing a price selection service according to the taste of the food by receiving or conveying the meaning of encouragement. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes the steps of receiving patient medical record data transmitted from a terminal requesting medical advice for calculating medical expenses, and parsing the received medical record data. ), extracting the diagnosis, deriving and classifying the identifier of the medical diagnosis, medical diagnosis site, and detailed disease name from the diagnosis, extracting at least one image identification information included in the received medical record data, classified identifier And based on the extracted image identification information, extracting reference data with a preset similarity from previously constructed big data, outputting advisory data already mapped and stored to the extracted reference data to provide advice on the patient's medical record data. It includes a step of generating data, and a step of transmitting the generated advice data to a medical advice request terminal.

According to one of the above-described means for solving the problem of the present invention, at least one franchise sets different price options for each menu, and if the user likes the quantity and quality of the food and the franchise's service, he or she selects an appropriate price. By asking people to pay, merchants can modify or develop menus by understanding which price options are most often selected for each menu. Users, who are customers, can also indicate the parts they are dissatisfied with as prices, and conversely, the parts they are satisfied with can also be marked by price. Since it can be expressed as a win-win, it can be rewarded or convey the meaning of encouragement.

Figure 1 is a diagram for explaining a system for providing a price selection service according to food taste according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a selection service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a price selection service according to food taste is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart for explaining a method of providing a price selection service according to food taste according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as:

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram for explaining a system for providing a price selection service according to food taste according to an embodiment of the present invention. Referring to FIG. 1, the system 1 for providing a price selection service according to food taste may include at least one user terminal 100, a selection service providing server 300, and at least one affiliated store terminal 400. . However, since the system 1 for providing price selection service according to food taste shown in FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the selection service providing server 300 through the network 200. In addition, the selection service providing server 300 may be connected to at least one user terminal 100 and at least one affiliated store terminal 400 through the network 200. Additionally, at least one affiliated store terminal 400 may be connected to the selection service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 may be a user terminal that selects an affiliated store, menu, and price option using a web page, app page, program, or application related to a price selection service according to food taste. At this time, in the case of prepayment, the user of the user terminal 100 may be a user who selects the highest price option as the default and then receives a refund equal to the difference by selecting the lowest price or another price option if he does not like it or the taste is strange.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The selection service providing server 300 may be a server that provides a price selection service web page, app page, program, or application according to food taste. In addition, the selection service providing server 300 receives information such as price options and menus from at least one affiliated store terminal 400, and provides information regarding the selected affiliated store, price, and menu at the user terminal 100. It may be a server that transmits to the affiliated store terminal 400. In addition, when the user terminal 100 calculates in advance, the selection service providing server 300 allows the user to pay for the highest price option as default, and then, if the user does not like it, selects a different price option, equal to the difference. It may be a server that allows a refund to be made to the payment method of the user terminal 100. The server 300 that provides the selection service to at least one affiliated store terminal 400 may be a server that reports statistical data on which price options are most often selected for each menu, and the affiliated store owner of the affiliated store terminal 400 provides information on each menu. By understanding which price options are most frequently selected, you can provide an opportunity to modify or further develop the menu.

Here, the selection service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one affiliated store terminal 400 may be an affiliated store terminal that uses a web page, app page, program, or application related to a price selection service according to food taste. The affiliated store terminal 400 may be a terminal that transmits menu and price options to the selection service providing server 300. Additionally, the affiliated store terminal 400 may be a terminal that receives data on price option selection for each menu from the selection service providing server 300 as a report.

Here, at least one affiliated store terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one affiliated store terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one affiliated store terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the selection service providing server included in the system of Figure 1, and Figures 3 and 4 are an embodiment of a price selection service according to food taste according to an embodiment of the present invention. This is a drawing to explain.

Referring to FIG. 2, the selection service providing server 300 includes a storage unit 310, a payment unit 320, a transmission unit 330, a prepaid management unit 340, an information provision unit 350, and a tag management unit 360. ), a tag delivery unit 370, and a review removal unit 380.

The selection service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100 and at least one affiliated store terminal 400 provides prices according to food taste. When transmitting a selection service application, program, app page, web page, etc., at least one user terminal 100 and at least one affiliated store terminal 400 may select a price selection service application, program, app page according to food taste, You can install or open web pages, etc. Additionally, a service program may be run on at least one user terminal 100 and at least one affiliated store terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Before explaining Figure 2, the social background from which the service of the present invention was derived will be briefly explained.

Last year, a new word was coined: delivery beggar. They started calling delivery workers who secretly skipped food to be delivered to customers beggars. In fact, a scene of a customer eating the ordered food was filmed on a closed circuit, and a person who appeared to be a delivery person even posted a certified photo of the stolen food to an online community. There were also people who posted tips for skipping food without being noticed. However, recently the word delivery beggar has begun to be used with the opposite meaning. Not the delivery person, but some of the delivery recipients who have problems are criticized for being delivery beggars.

This is a word that refers to a black consumer, a customer who intentionally files malicious complaints. The tactics of black consumers are evolving day by day. It takes advantage of the fact that reviews left by customers are the lifeblood of food delivery companies. There are people who demand ridiculous service by holding hostage the reviews that many people check before ordering food. Review beggars are quiet people who promise to leave a review on a delivery app, but then receive the service and leave no review. As the number of delivery companies increases, the importance of reviews left by customers who order food also increases. There is a company that is holding an event where they will give you a service if you agree to leave a review when ordering. There are people who take advantage of this and only receive services.

Since users consider reviews and star ratings as the top priority when choosing a restaurant, it is no exaggeration to say that reviews and star ratings are directly related to the livelihood of business owners. Accordingly, self-employed people who have no choice but to be ranked B in the face of such evaluations have no choice but to bow to customers' unreasonable demands or abuse of power. The double whammy of dissatisfaction with delivery agency drivers pouring directly into restaurant companies is the responsibility of business owners. This is because complaints such as the shape of the food being distorted during the delivery process or the bell being pressed when asked not to be rang are also reflected in the restaurant evaluation.

Store owners who have suffered star rating attacks either hire professional reviewers who manage reviews or sign contracts with marketing companies for hundreds to tens of millions of won to manage reviews and ratings. Shopping malls have expanded in proportion to the size of the growing Internet market. In a competitive world where exposure to consumers is essential, top listing exposure and good reviews are essential requirements. The companies that are offering to solve the concerns of shopping mall owners are online advertising agencies. They approach CEOs saying they have a way to increase exposure rankings, but nothing is followed. There are many store owners requesting termination of the contract, but the agency says they have fulfilled the contract and notifies them that refunds are not possible. Complaints are constantly being filed with the Online Advertising Dispute Resolution Committee or the Korea Consumer Agency. Even this is only an adjustment matter and is not mandatory, so if the agency rejects the committee's decision, there is no way.

As it is pointed out that star ratings and malicious reviews are fatal to companies, delivery agencies and portal sites are putting forward measures to eradicate malicious reviews. On the 17th, Naver announced that it would eliminate star ratings for ‘Smart Place’, which provides business information such as restaurants and cafes to Naver. In July of last year, Baedal Minjok introduced a system that temporarily ‘blinds’ reviews at the request of self-employed people and modifies or deletes reviews after 30 days of adjustment. However, business owners explain that there is still a question mark as to whether such measures will be effective. Also, there must be a valid reason to delete a malicious review, but it is difficult and complicated to distinguish whether a malicious review is sincere or malicious. Accordingly, one embodiment of the present invention provides a price option so that if you are dissatisfied by removing reviews or ratings, you can compensate for the amount in money. Conversely, if you want to praise, give an additional price as a price option with the concept of a tip. By allowing you to choose, you can eradicate the practice of bullying by holding reviews or ratings hostage.

Referring to FIG. 2 , the storage unit 310 may collect at least one menu and at least one price from at least one affiliated store terminal 400, map them to at least one affiliated store terminal 400, and store them. At least one affiliated store terminal 400 may register and upload at least one menu and at least one price, and receive statistical data on the menu and price selected by the user terminal 100 as a report.

The payment unit 320 can proceed with payment using the menu and price selected by the user terminal 100. After selecting a menu, the user terminal 100 may select at least one price previously mapped and stored in the menu and proceed with payment.

The transmission unit 330 may transmit information about the menu and price selected by the user terminal 100 to at least one affiliated store terminal 400.

When paying in advance at the user terminal 100, the prepaid management unit 340 ensures that payment is made at the highest price among at least one price, and then reselects the price from the user terminal 100 and processes a refund or partial cancellation for the difference. can do.

The information provider 350 sorts the menus and prices selected from the plurality of user terminals 100 by menu and transmits them to at least one affiliated store terminal 400, and at least one price of the plurality of user terminals 100. The percentage paid at the highest price and the percentage paid at the lowest price can be sent together in a report. At this time, the user terminal 100 may be a plurality of user terminals 100 belonging to different entities. Here, you can analyze the information of people who chose each price. You can collect and organize the gender, age, occupation, income, etc. of the person who selects each price option. If excessive personal information cannot be collected, you can determine whether the user chooses the lowest price at all restaurants or not. In fact, it can be inferred and analyzed whether a person chooses a low price because the food is not tasty, or whether they choose the lowest price at all restaurants because they do not have money.

When the lowest price or the highest price among at least one price is selected in the user terminal 100, the tag management unit 360 may select and store at least one tag preset in the user terminal 100. . For example, if the price was low, tags were added by dividing them into various categories such as taste of food/quantity of food/degree of doneness of food/quality of ingredients/unfriendly staff/unfriendly delivery, etc. and delivered to the affiliated store terminal (400). It is done. If reviews disappear, you won't know how to get feedback until you're right before the business closes. Accordingly, since the taste of food, friendliness, delivery speed, etc. can vary, tags can be provided for each category and the user's tastes can also be known. At this time, the tag is not fixed, but may be a dynamic classifier that can be newly created, changed, or deleted depending on the registered text.

Analysis of information resources is required to purify and classify data, but as the terms used by various types of restaurants and customers are different, and the human and material resources they possess are different, each restaurant and customer has different There are many cases where you cannot express your information with the set tags. At this time, if there is no tag (option), most platforms create a miscellaneous box and allow information to express oneself in the miscellaneous. In order to tag the data described in this way, an embodiment of the present invention In , the words and sentences included in the other box are expressed in vector form, and then clustering of the words and sentences in the other box expressed in vector form is performed. At this time, clustering is a representative unsupervised learning method widely applied in research in the field of text mining and information retrieval theory, and depending on the clustering method, it is divided into Hierarchical Clustering, Partitional Clustering, and Spectral Clustering. Clustering).

The most commonly used clustering algorithms are the bottom-up hierarchical clustering algorithm and the K-means algorithm. Although the K-means algorithm has lower performance than bottom-up hierarchical clustering, it is evaluated as an efficient clustering algorithm. Accordingly, in one embodiment of the present invention, the K-means algorithm can be applied as a clustering algorithm, focusing more on efficiency than clustering performance. Of course, bottom-up hierarchical clustering algorithms are not excluded. At this time, the K-means algorithm is performed on the premise that K center points in the vector space can be expressed as K clusters, and clusters are generally formed by calculating the cosine similarity of each vector. The K-means algorithm can further use various extension algorithms such as Bisecting, Antipole, and Multipole, depending on how to create a cluster.

The above-mentioned process is described in detail as follows.

First, you can proceed with morpheme analysis and stop word removal for words and sentences listed in the Other box. In order to perform K-means with the words and sentences listed in the Other box, the data listed in the Other box must be converted into a form suitable for clustering. For this purpose, a numerical process is performed to convert words and sentences into vectors. For numerical work, morphological analysis is performed on words and sentences, and as a result, each morpheme forms the dimension of one vector. Depending on whether the corresponding morpheme is included, each vector element has a value of 1 or 0, and a morpheme analyzer can be used in this process.

The second is to create a tag pool. Measuring distances and comparing standards between words and other boxes containing sentences is achieved through vector multiplication. For this purpose, it is necessary to define a standard vector containing information about all morphemes, and the tag pool extracted from all other boxes can be used as this standard vector. The tag pool refers to a pool that contains all tags extracted from words and sentences included in all other boxes without duplication.

The third is the process of creating a tag hierarchy, which is created based on the tag pool created previously. The vector for creating a tag hierarchy can compare the elements of the tag pool and assign a vector value based on the number of times random tags are included in the same tag pool. For example, a vector value is given depending on the degree to which two random tags are entered simultaneously in words and sentences entered by multiple guests in one miscellaneous box. Each tag vector calculated according to this method is converted to a unit vector, clustered through K-means, and vectors with high similarity can be grouped into several tag groups through cluster analysis. Then, by repeatedly applying the above clustering operation to each group, a tag hierarchy for the entire tag set can be created.

Finally, the tag vector must be calculated. Finally, all preparations for performing the clustering algorithm are completed through the process of creating the tag vector. Through this process, a standard is established to infer how similar information each other box has to each other. In addition, in order to reflect the tag hierarchy in the tag vector, a value calculated based on the hierarchy can be used, and the vector value given at this time can use, for example, the Leacock-Chodorow Measure, but is not limited to this. . Because the Leacock-Chodorow Measure expresses lexical similarity with values from 0 to infinity, it can be applied to update the weight of the tag vector.

Once all preparations for clustering are completed, new tags can be derived by grouping each other box. At this time, when applying K-means clustering to determine the first clustering K value, the number of clustering result groups (K) has an important effect on clustering performance. In most cases, K is set as a static variable to derive clustering results according to the number. However, considering the characteristic of having tags in different directions due to the direction and specificity of different customers and restaurants, it is very difficult to set a constant K value. It's difficult.

Therefore, in the method according to an embodiment of the present invention, it is also possible to set different K values according to different tags according to words and sentences included in the miscellaneous box. K-means repeatedly regenerates clusters until the optimal cluster is created. In other words, once a cluster is created by K-means, the center value is recalculated for all clustered groups and vector multiplication is performed in order on the K clusters for all tag pools. Afterwards, the tag pool is assigned again to the group with the largest vector product, and the vector multiplication and assignment process is performed until the last tag pool. As a result, when a new clustering result is calculated, the process of finding the center value is repeated again to achieve the optimal clustering state. At this time, the end point is when no change occurs in the newly formed results compared to the previous clustering results.

When ordering by selecting the same menu from at least one affiliated store in the user terminal 100, the tag delivery unit 370 can generate an order form by transmitting the tag selected in the user terminal 100 to at least one affiliated store. there is. For example, assuming that a user ordered samgyetang, and the price of samgyetang ranges from 12,000 won to 14,000 won as shown in (b) of Figure 3, the customer gave the lowest price of 12,000 won and selected the tag "It smells bad." let's do it. In this case, while sending the order form to the affiliated store, since the customer is sensitive to unpleasant odors, if the customer can cook to eliminate odor, the customer's satisfaction level can increase and the price of the option selected can also increase. Of course, if tags such as “I have no money because I am a student” or “I am a job seeker, please give me a discount” are selected, it is not a problem with the quality of service provided by the restaurant, so the business owner has nothing to worry about.

The review removal unit 380 can set the user terminal 100 so that ratings or reviews cannot be written. In addition, even if the review removal unit 380 removes reviews within its own platform, it cannot also remove reviews or ratings on other platforms. At this time, in order to recognize and provide notification of “bad” reviews in real time, the following emotion analysis method can be used.

Sentiment analysis refers to a method of extracting emotions contained in an object, mainly from text. It is also a subfield of text mining and includes opinion mining. At this time, the process of emotional analysis begins with the process of collecting data (Data Acquisition). Here, data to be analyzed and training data are needed, and a text pre-processing process is performed to enable natural language processing (NLP). First of all, the collected raw data generally has a lot of noise, so it is often not appropriate to use it as is for learning.

Therefore, a preprocessing process is necessary to remove noise and retain only the words necessary for learning. In the preprocessing process, methods such as splitting the sentence into words (Tokenize), deleting words unrelated to emotions such as conjunctions, articles, and verbs (Remove Stopword), and modifying words to their original form (Lemmatize) can be used. To create an emotion analysis model, machine learning-based methods and dictionary-based methods can be used. At this time, machine learning-based methods can also reflect words that are not in the dictionary or words that are frequently used in a specific domain in the analysis, so they can also be used in the legal service field, which includes a lot of technical and legal terms. Lastly, to verify the performance of the emotion analysis model, cross-validation can be used based on machine learning, and evaluation measures include precision, accuracy, recall, and F1 score, which is the harmonic mean of precision and recall, may be used, but is not limited to this.

In addition, corrections can be made to the classification results of the sentiment analysis model. For example, even if text is classified as positive, a 90% positive review may contain a more favorable evaluation of the service than a 30% positive review. It is highly likely. Therefore, a method of assigning a higher correction value to the latter review can be used. In addition, in order to evaluate services using user feedback, define the type of user feedback, classify reviews, and perform sentiment analysis using the learning algorithm Support Vector Machine (SVM). This method can be used. In a support vector machine, classification can be performed using adjectives, document frequency information for the four parts of speech, TF-IDF, and the obtained chi-square statistic as input variables, respectively. Of course, it is not limited to the above-mentioned ones, and it is obvious that various methods can be used.

Hereinafter, the operation process according to the configuration of the selection service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

Referring to FIG. 3, (a) the selection service providing server 300 collects menus and price options from at least one affiliated store terminal 400 and stores them based on the unique identification code of the affiliated store. And (b) the selection service providing server 300 sets three price options for each menu, for example, and allows the user to select one and calculate it. At this time, (c) in the case of prepayment, since the product has not been tasted, payment is made at the highest price, and the difference is either deposited or partial cancellation depending on the price selected. In the case of postpay, (d) if the menu you ate was seolleongtang, but it contains too little meat and you feel it would be a waste to pay 9,000 won, you can select 8,000 won.

As shown in (a) of FIG. 4, the service providing server 300 can provide a percentage by accumulating the price selected by the consumer for each price range. For example, if a large number of people are concentrated on the too low price of 7,000 won, the business owner can provide a percentage. You need to think about the menu. Conversely, if a large number of people pay for the high amount of 9,000 won, it means that the majority are satisfied, which can also act as positive feedback. And as shown in (b), the user of the user terminal 100 can select a tag corresponding to an element with which the user is satisfied when satisfied with the food, and select a tag corresponding to an element with which the user is dissatisfied.

Matters that are not explained regarding the method of providing price selection service according to food taste in FIGS. 2 to 4 are the same as or are derived from the content described above regarding the method of providing price selection service according to food taste through FIG. 1. Since it can be easily inferred, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between components included in the system for providing a price selection service according to food taste of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 5, the selection service providing server collects at least one menu and at least one price from at least one affiliated store terminal, maps them to at least one affiliated store terminal, and stores them (S5100).

Then, the selection service providing server processes payment using the menu and price selected by the user terminal (S5200) and transmits information about the menu and price selected by the user terminal to at least one affiliated store terminal (S5300).

The sequence between the above-described steps (S5100 to S5300) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5300) may change, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained about the method of providing price selection service according to food taste in Figure 5 are the same as or from the content explained about the method of providing price selection service according to food taste through Figures 1 to 4. Since it can be easily inferred, the description below will be omitted.

The method of providing a price selection service according to food taste according to an embodiment described with reference to FIG. 5 may also be implemented in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. You can. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing a price selection service according to the taste of food according to an embodiment of the present invention described above is performed by an application basically installed on the terminal (this may include a program included in the platform or operating system, etc., which is basically installed on the terminal). It may be executed by an application (i.e., a program) installed by the user directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing a price selection service according to the taste of food according to an embodiment of the present invention described above is implemented as an application (i.e., a program) installed by default in the terminal or directly installed by the user, and is implemented by a computer such as the terminal. It may be recorded on a readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

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

Claims (6)

After selecting a menu, a plurality of user terminals belonging to different entities select at least one price pre-mapped and stored in the menu and proceed with payment;
At least one affiliated store terminal that registers and uploads at least one menu and at least one price, and receives statistical data on the menu and price selected by the user terminal as a report; and
A storage unit that collects at least one menu and at least one price from the at least one affiliated store terminal, maps them to the at least one affiliated store terminal, and stores them; a payment section that processes payment using the menu and price selected by the user terminal; A transmission unit that transmits information about the menu and price selected by the user terminal to the at least one affiliated store terminal, and when paying in advance at the user terminal, ensures that payment is made at the highest price among at least one price, and then, at the user terminal A prepaid management unit that reselects the price and processes a refund or partial cancellation for the difference, sorts the menus and prices selected by the plurality of user terminals by menu and transmits them to the at least one affiliated store terminal, and at least one of the plurality of user terminals An information provider that transmits the rate paid at the highest price among the prices and the rate paid at the lowest price together as a report, the price of the lowest or highest amount among at least one price from the user terminal. When selected, a selection service providing server including a tag management unit that receives and stores at least one tag preset in the user terminal;
A system for providing price selection services based on food taste, including.
delete delete delete delete According to claim 1,
The server providing the selected service is,
a review removal unit that disables the user terminal from writing ratings or reviews;
A system for providing price selection service according to food taste, further comprising:

Images