WO2024043365A1

WO2024043365A1 - Method for processing order and device therefor

Info

Publication number: WO2024043365A1
Application number: PCT/KR2022/012733
Authority: WO
Inventors: 이혜란
Original assignee: 쿠팡 주식회사
Priority date: 2022-08-24
Filing date: 2022-08-25
Publication date: 2024-02-29
Also published as: KR20240028020A

Abstract

A method for processing an order for a regular delivery and a device therefor are provided. An order processing method, performed by an electronic device, according to an embodiment of the present disclosure may comprise the steps of: determining, on the basis of user information, a user keyword set corresponding to the user information, wherein the user keyword set comprises one or more user keywords indicating at least some of the user information; calculating, on the basis of a corresponding relation between the user keyword set and each of multiple menu keyword sets determined to correspond to multiple pieces of menu information, respectively, the degree of relevance between the user information and each of the multiple pieces of menu information, wherein a first menu keyword set included in the multiple menu keyword sets comprises one or more menu keywords indicating at least some of first menu information included in the multiple pieces of menu information; and determining, on the basis of the order of sizes of multiple calculated degrees of relevance, a regular delivery menu set to correspond to a regular delivery request, the regular delivery menu set including two or more pieces of menu information among the multiple pieces of menu information.

Description

Method and device for processing orders

This disclosure relates to technology for processing orders.

As non-face-to-face services expand due to various environmental factors, the size of the delivery service market is growing rapidly. To keep pace with this growth, operators of platforms that provide delivery services are making various efforts to increase the number of users of their platforms. As part of its various efforts, operators are applying technologies to the platform to improve user convenience.

The technical problem to be solved through an embodiment of the present disclosure is to provide technology that can improve user convenience.

Another technical problem to be solved through an embodiment of the present disclosure is to provide a technology that can increase the number of users of a platform.

Another technical problem to be solved through an embodiment of the present disclosure is to provide technology that can provide recommendations optimized for the user's preferences by reflecting the user's various inputs within the platform.

Another technical problem to be solved through an embodiment of the present disclosure is to provide a technology that can automatically recommend menu information to match the user's preferences.

Another technical problem to be solved through an embodiment of the present disclosure is to provide a technology that can automatically recommend a plurality of menu information to suit the user's preferences as a regular delivery menu set.

Another technical problem to be solved through an embodiment of the present disclosure is to provide a technology that can automatically configure a diet for a specific period with only a simple input from the user.

Another technical problem to be solved through an embodiment of the present disclosure is to provide technology that can automatically configure menus without duplicating menu information.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by those skilled in the art from the description below.

An order processing method according to an embodiment of the present disclosure includes the steps of determining, based on user information, a user keyword set corresponding to the user information - the user keyword set is an order processing method performed by an electronic device; , Containing one or more user keywords representing at least part of the user information - , Based on a correspondence relationship between each of a plurality of menu keyword sets determined to correspond to each of the plurality of menu information and the user keyword set, the user information and the Calculating the degree of relevance of each of the plurality of menu information - the first menu keyword set included in the plurality of menu keyword sets includes one menu keyword representing at least a portion of the first menu information included in the plurality of menu information It may include the step of determining a regular delivery menu set including two or more menu information among the plurality of menu information to correspond to the regular delivery request, based on the size order of the calculated plurality of degrees of relevance. .

In one embodiment, the step of determining the plurality of menu keyword sets corresponding to each of the plurality of menu information may be further included.

In one embodiment, the first menu information includes store information selling the first menu, time information at which the first menu was ordered, age information of the user who ordered the first menu, name information of the first menu, At least some of the image of the first menu, price information of the first menu, category information of the first menu, nutritional ingredient information of the first menu, ingredient information of the first menu, and allergy information of the first menu may include.

In one embodiment, determining the plurality of menu keyword sets includes determining the first menu keyword set, and determining the first menu keyword set is included in the first menu information. Inputting the text into a first classification model - the first classification model is a supervised learning-based artificial neural network model - and based on the output value of the first classification model, a menu included in the first menu keyword set It may include the step of determining keywords.

In one embodiment, determining the plurality of menu keyword sets includes determining the first menu keyword set, and determining the first menu keyword set is included in the first menu information. Inputting the image into a second classification model - the second classification model is a supervised learning-based artificial neural network model - and based on the output value of the second classification model, a menu included in the first menu keyword set It may include the step of determining keywords.

In one embodiment, the user information includes menu information ordered by the user, allergy information of the user, information on the number of orders made by the user, information on reviews written by the user, information on the age of the user, information on the user's favorites, It may include at least part of the user's address information, information on the time the user ordered the menu, and price information of the menu ordered by the user.

In one embodiment, the step of calculating the degree of relevancy includes calculating the plurality of degrees of relevancy based on calculating a weight and a numerical value representing the correspondence relationship between a user keyword and a menu keyword, and the weight is: It may be varied based on action information included in the user information and indicating the user's activities.

In one embodiment, calculating the degree of relevance may include calculating the plurality of degrees of relationship in response to the user's regular delivery request.

In one embodiment, in response to the user's regular delivery request, calculating the plurality of degrees of relevance includes a combination of a setting value included in the regular delivery request and the user keyword set and the plurality of menu keyword sets. It may include calculating the plurality of degrees of relatedness based on the corresponding relationship with each other.

In one embodiment, among a plurality of weights applied to calculate relevance, a first weight corresponding to an item included in the setting value may be greater than a second weight corresponding to a user keyword.

In one embodiment, the step of calculating the plurality of degrees of relevance based on the correspondence relationship between the combination and each of the plurality of menu keyword sets is performed when the type of the item included in the setting value and the type of the user keyword are the same. If so, it may include deleting the user keyword from the combination.

In one embodiment, the set value may include at least some of monthly budget information, desired delivery time information, allergy information, preferred nutritional ingredient information, and upper price limit information per menu as items.

In one embodiment, the step of determining the regular delivery menu set includes determining a plurality of menu allocation areas to correspond to the regular delivery request, and in each of the plurality of menu allocation areas, a menu selected from the plurality of menu information. It may include the step of allocating information.

In one embodiment, the step of allocating menu information selected from the plurality of menu information includes, when the first menu information is allocated to a first menu allocation area included in the plurality of menu allocation areas, the first menu allocation area It may include the step of allocating menu information different from the first menu information to N menu allocation areas (N, where N is a natural number) following .

In one embodiment, the step of allocating menu information selected from the plurality of menu information includes, when the first menu information is assigned to a first menu allocation area included in the plurality of menu allocation areas, the first menu information is assigned to the first menu information. It may include a step of reducing the corresponding degree of relevance.

In one embodiment, the step of reducing the degree of relevance corresponding to the first menu information may include gradually increasing the degree of relevance to the first menu information when menu information in a menu allocation area following the first menu allocation area is sequentially allocated. It may include a step of increasing the corresponding degree of relevance.

In one embodiment, determining the regular delivery menu set may include modifying the menu information in response to a user's correction input for menu information included in the regular delivery menu set.

In one embodiment, modifying the menu information may include disabling modification of the menu information based on an average delivery time of the menu information.

In one embodiment, the step of transmitting a notification informing of regular delivery to the user terminal before the reference time from the desired delivery time corresponding to the regular delivery request may be further included.

An electronic device according to another embodiment of the present disclosure includes a processor, a communication interface, a memory, and a computer program loaded into the memory and executed by the processor, wherein the computer program is based on user information. Thus, instructions for determining a user keyword set corresponding to the user information - the user keyword set includes one or more user keywords representing at least part of the user information - to correspond to each of a plurality of menu information An instruction for calculating a degree of relevance between the user information and each of the plurality of menu information based on the correspondence relationship between each of the determined plurality of menu keyword sets and the user keyword set - a first menu keyword included in the plurality of menu keyword sets The set includes one or more menu keywords representing at least a portion of the first menu information included in the plurality of menu information - and based on the calculated order of magnitude of the plurality of degrees of relevance, two or more of the plurality of menu information It may include instructions for determining a regular delivery menu set including menu information to correspond to a regular delivery request.

According to the present disclosure, user convenience can be improved.

According to the present disclosure, the number of users of the platform can be increased.

According to the present disclosure, recommendations optimized for the user's preferences can be provided by reflecting the user's various inputs within the platform.

According to the present disclosure, menu information can be automatically recommended to match the user's preferences.

According to the present disclosure, a plurality of menu information can be automatically recommended as a set of regular delivery menus to suit the user's preferences.

According to the present disclosure, a diet for a specific period can be automatically configured with just a simple input from the user.

According to the present disclosure, a menu can be automatically configured so that menu information does not overlap.

The effects according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description of the specification.

Figure 1 shows an environment in which devices according to an embodiment of the present disclosure can be applied.

2 illustrates a computing device that can implement a device according to an embodiment of the present disclosure.

Figure 3 shows a screen to which the home UI (User Interface) of a platform that can be referenced in an embodiment of the present disclosure is applied.

Figure 4 is a flowchart showing an order processing method according to an embodiment of the present disclosure.

FIG. 5 is a flowchart showing detailed operations of the determination operation (S400) of the regular delivery menu set described with reference to FIG. 4.

Figure 6 shows a screen to which a regular reservation button that can be referred to in an embodiment of the present disclosure is applied.

Figure 7 shows a screen to which a platform setting UI that can be referenced in an embodiment of the present disclosure is applied.

Figure 8 shows a screen to which the diet UI of the platform that can be referenced in an embodiment of the present disclosure is applied.

FIG. 9 illustrates the menu allocation area of the menu UI described with reference to FIG. 8 .

Figure 10 shows a screen to which a modified UI of a platform that can be referenced in an embodiment of the present disclosure is applied.

The various embodiments described in the present disclosure are illustrative for the purpose of clearly explaining the technical idea of the present disclosure, and are not intended to limit them to specific embodiments. The technical idea of the present disclosure includes various modifications, equivalents, and alternatives of each embodiment described in the present disclosure, and embodiments selectively combined from all or part of each embodiment. In addition, the scope of rights of the technical idea of the present disclosure is not limited to the various embodiments or specific descriptions thereof presented below.

Terms used in this disclosure, including technical or scientific terms, unless otherwise defined, may have meanings commonly understood by those skilled in the art to which this disclosure pertains.

Expressions such as “comprises”, “may include”, “provided”, “may be provided”, “has”, “may have”, etc. used in the present disclosure refer to the target feature (e.g. For example, a function, operation or component, etc.) is present and does not exclude the presence of other additional features. In other words, such expressions should be understood as open-ended terms that imply the possibility of including other embodiments.

The singular expressions used in this disclosure may include plural meanings unless the context dictates otherwise, and this also applies to the singular expressions described in the claims.

Expressions such as "first", "second", or "first", "second", etc. used in the present disclosure distinguish one object from another when referring to a plurality of objects of the same type, unless otherwise indicated in the context. It is used to do so, and does not limit the order or importance between objects. For example, each user terminal included in the plurality of user terminals according to the present disclosure may be distinguished from each other by being expressed as “first user terminal” and “second user terminal”.

As used in this disclosure, expressions such as “A, B, and C,” “A, B, or C,” “at least one of A, B, and C,” or “at least one of A, B, or C” refer to each of the listed It can refer to an item or all possible combinations of listed items. For example, “at least one of A or B” may refer to both (1) at least one A, (2) at least one B, (3) at least one A and at least one B.

As used in this disclosure, the expression “based on” is used to describe one or more factors that influence the decision, act of judgment, or action described in the phrase or sentence containing this expression, and this expression does not exclude additional factors influencing the decision, act of judgment, or action.

As used in the present disclosure, the expression that a certain component (e.g., a first component) is “connected” or “connected” to another component (e.g., a second component) refers to any of the above. It may mean that a component is not only directly connected or connected to the other component, but is also connected or connected through another new component (for example, a third component).

The expression “configured to” used in the present disclosure means, depending on the context, “set to”, “having the ability to”, “changed to”, “made to”, “to do”. It can have meanings such as “possible.” This expression is not limited to the meaning of "specially designed in hardware," for example, a processor configured to perform a specific operation refers to a general purpose processor capable of performing that specific operation by executing software. It may mean, or it may mean a special purpose computer structured through programming to perform a specific operation.

The term "platform" used in this disclosure may refer to a tangible or intangible space that serves as the basis for users' use by integrating and managing services of the same or similar purpose, and although there are differences in detailed meaning, it is comprehensive. May be referred to interchangeably with “software,” “application,” or “solution.” In one embodiment, a platform may be a tangible or intangible space that integrates delivery services.

The term “User Interface (UI)” used in this disclosure refers to a physical or virtual medium created for the purpose of temporary or permanent access to enable communication between people and objects, systems, machines, or computer programs, etc. It can mean. In other words, a user interface can refer to a means through which people, objects, systems, machines, or computer programs interact.

The term “artificial intelligence (AI)” used in this disclosure may refer to technology that imitates human learning ability, reasoning ability, or perception ability and implements this on a computer, such as machine learning or symbolic logic. It may include the concept of Machine Learning (ML) can be an algorithmic technology that classifies or learns the characteristics of input data on its own. Specifically, artificial intelligence is a machine learning algorithm that can analyze input data, learn the results of the analysis, and make judgments or predictions based on the results of the learning. Additionally, technologies that mimic the cognitive or judgment functions of the human brain using machine learning algorithms can also be understood as the category of artificial intelligence. For example, technical fields such as verbal understanding, visual understanding, reasoning/prediction, knowledge representation, or motion control may be included in areas where artificial intelligence can be applied.

The term “machine learning” used in this disclosure may refer to the process of training a neural network model using experience processing data. Such machine learning can mean that computer software improves its own data processing capabilities. A “neural network model” is a model built by modeling the correlation between data, and the correlation can be expressed by a plurality of parameters. This neural network model extracts and analyzes features from given data to derive correlations between data. Repeating this process to optimize the parameters of the neural network model can be called machine learning. For example, a neural network model can learn (e.g., supervised learning) the mapping (correlation) between input and output for data given as input-output pairs. Alternatively, a neural network model may derive regularities between given data and learn the relationship (for example, unsupervised learning) even when only input data is given.

The terms “artificial intelligence learning model”, “machine learning model”, or “neural network model” used in this disclosure may be designed to implement the human brain structure on a computer, and may be designed to simulate the neurons of a human neural network and have weights. It may include a plurality of network nodes having . “Multiple network nodes” may have connections between neurons by simulating the synaptic activity of neurons sending and receiving signals through synapses. Specifically, in an artificial intelligence learning model, multiple network nodes are located in layers of different depths and can exchange data according to convolutional connection relationships. The artificial intelligence learning model may be, for example, an artificial neural network model or a convolution neural network model, but the scope of the present disclosure is not limited to the examples described above, and various known It should be noted that neural network models may be applied to the present disclosure.

Hereinafter, various embodiments described in the present disclosure will be described with reference to the attached drawings. In the accompanying drawings and descriptions of the drawings, identical or substantially equivalent components may be assigned the same reference numerals. Additionally, in the description of various embodiments below, duplicate descriptions of the same or corresponding components may be omitted, but this does not mean that the components are not included in the embodiments.

Figure 1 shows an environment in which the order processing device 100 according to an embodiment of the present disclosure can be applied. This environment may include an order processing device 100, a user terminal 200, or a store terminal 300. Figure 1 shows an example in which one user terminal 200 and one store terminal 300 are applied to the order processing device 100, but this is only for convenience of understanding, and the user terminal 200 The number and number of store terminals 300 may vary. In addition, Figure 1 only shows a preferred embodiment for achieving the purpose of the present disclosure, and some components may be added or deleted as needed.

Hereinafter, each component shown in FIG. 1 will be described in more detail.

The order processing device 100 may be a server device of a platform that provides delivery services to users (hereinafter referred to interchangeably with the term “user”). Delivery service may refer to a service that transports ordered products, and product may refer to goods or services. For example, the delivery service may be a food delivery service, a meal-kit delivery service, or a convenience goods delivery service.

The order processing device 100 may receive or transmit information from the user terminal 200 or the store terminal 300 through a network in order to implement platform operations related to the delivery service. For example, the order processing device 100 may receive information about a product sold in a store from the store terminal 300 and execute a series of operations to enable the information about the product to be posted on the platform. For another example, the order processing device 100 receives an order, that is, a request for delivery of a product, from the user terminal 200, and executes a series of operations to ensure that the product is delivered to the user using the user terminal 200. It may be possible. In addition, the order processing device 100 performs various known operations to mediate commercial transactions between suppliers (e.g., users of the store terminal 300) and consumers (e.g., users of the user terminal 200). can do.

The order processing device 100 is an example of a delivery service and can perform various operations related to a regular delivery service, that is, a service that transports a plurality of products at different times during a specific period of time. However, to avoid redundant description, various operations related to the regular delivery service will be described in detail later with reference to the drawings of FIG. 4 and below.

The order processing device 100 may perform various processing operations on information received from the user terminal 200 or the store terminal 300. For example, the order processing device 100 may process the information such as modifying, deleting, selecting, calculating, deciding, or extracting the information. For another example, the order processing device 100 may store the information or the processed information in internal storage or external storage of the order processing device 100. In addition, the order processing device 100 can perform various known operations to process information obtained according to the user's use of the platform into a required format.

Order processing device 100 may be implemented with one or more computing devices. For example, all functions of order processing device 100 may be implemented in a single computing device. For another example, a first function of the order processing device 100 may be implemented in a first computing device, and a second function that is distinct from the first function may be implemented in a second computing device that is distinct from the first computing device. . For example, a computing device may be, but is not limited to, a Desktop, Laptop, Application Server, Proxy Server, or Cloud Server, and has computing capabilities. This can include all types of equipped devices.

Each of the user terminal 200 and the store terminal 300 may be a user terminal that uses a platform related to a delivery service. In the present disclosure, for convenience of understanding, the user terminal 200 is referred to as the terminal of the demander of the delivery service, and the store terminal 300 is referred to as the terminal of the provider of the delivery service. In one embodiment, in order for users to use the platform, a web browser or application may be installed on each of the user terminal 200 and the store terminal 300. This user terminal 200 or store terminal 300 is, for example, a desktop, workstation, laptop, tablet computer, wearable device, or smartphone. It may be any one of devices such as a smart phone, but is not limited to these examples and may include all types of computing devices equipped with computing functions.

The order processing device 100, the user terminal 200, and the store terminal 300 may communicate through a network. A network is any type of wired or wireless network, for example, a Local Area Network (LAN), a Wide Area Network (WAN), a Mobile Radio Communication Network, or a Wireless Broadband Internet (Wibro). It can be implemented as:

2 illustrates a computing device 400 that can implement a device according to an embodiment of the present disclosure. In this disclosure, the computing device 400 may be represented as an electronic device, and the computing device 200 and the electronic device may be referred to interchangeably. Each of the above-described order processing device 100, user terminal 200, and store terminal 300 may be implemented by this computing device 400. Computing device 400 may include one or more processors 410, one or more memories 420, or a communication interface 430. In one embodiment, some components may be deleted from computing device 400 or other components (eg, display, etc.) may be added to computing device 400 . Additionally, some components may be integrated and implemented additionally or alternatively, or may be implemented as a single or plural entity. In this disclosure, one or more processors 410 may be referred to as processor 410. The expression processor 410 may mean a set of one or more processors, unless the context clearly expresses otherwise. Additionally, in this disclosure, one or more memories 420 may be referred to as memory 420 . The expression memory 420 may mean a set of one or more memories, unless clearly expressed differently in context.

At least some components within the computing device 400 are connected to each other through a bus, General Purpose Input/Output (GPIO), Serial Peripheral Interface (SPI), or Mobile Industry Processor Interface (MIPI), and transmit data or signals. can be given or received.

The processor 410 may perform operations or data processing related to control or communication of each component of the computing device 400. Specifically, the processor 410 runs software (e.g., commands, instructions, or programs) received from other components to execute at least one component of the computing device 400 connected to the processor 410. can be controlled. As an example, the processor 410 may load instructions or data into the memory 420, process the instructions or data stored in the memory 420, and store result data according to the processing in the memory 420. there is. Additionally, the processor 410 may be operatively connected to components of the computing device 400 to perform various operations related to the present disclosure, such as calculation, processing, data generation or processing.

Memory 420 can store various data. Data stored in memory 420 is data acquired, processed, or used by at least one component of computing device 400 and may include software (e.g., commands, instructions, or programs, etc.). You can. As an example, the memory 420 may store instructions for operating the processor 410 as a computer program. The computer program, when loaded into memory 420, may include one or more instructions that cause processor 410 to perform operations according to various embodiments of the present disclosure. That is, the processor 410 may perform operations according to various embodiments of the present disclosure by executing one or more instructions described above. Additionally, memory 420 may include volatile or non-volatile memory. In one embodiment, the program is software stored in the memory 420, and is an operating system, application, or application for controlling the resources of the computing device 400 and provides various functions to the application so that the application can utilize the resources of the computing device 400. It may include provided middleware, etc.

The communication interface 430 may also be called a network interface. The communication interface 430 can establish a wired or wireless communication channel with an external device and transmit and receive various data with the external device. In one embodiment, the communication interface 430 may include at least one port for connecting to an external device via a wired cable in order to communicate with the external device via a wired cable. In this case, the communication interface 430 can communicate with a wired external device through at least one port. In one embodiment, communication interface 430 may include a cellular communication module and be configured to connect to a cellular network (e.g., 3G, LTE, 5G, Wibro, or Wimax). In one embodiment, the communication interface 430 includes a short-range communication module and can transmit and receive data with an external device using short-range communication (e.g., Wi-Fi, Bluetooth, Bluetooth Low Energy (BLE), UWB). . In one embodiment, communication interface 430 may include a contactless communication module for contactless communication. Non-contact communication may include at least one non-contact proximity communication technology, such as, for example, Near Field Communication (NFC) communication, Radio Frequency Identification (RFID) communication, or Magnetic Secure Transmission (MST) communication. In addition to the various examples described above, the computing device 400 may be implemented in various known ways for communicating with external devices, and the scope of the present disclosure is not limited by the examples described above.

In one embodiment, computing device 400 may further include a display. The display can display various screens based on control of the processor 410. For example, the display may display a screen to which various UIs of a delivery service-related platform are applied based on control of the processor 410. At this time, in order to display a screen with various UIs applied on the display, for example, a web browser or a dedicated application may be installed on the computing device 400. Additionally, the display is a component capable of interacting with the user, and can display various screens based on control of the processor 410 and receive user input from the user. This display may be implemented in the form of a touch sensor panel (TSP) that can recognize the contact or proximity of various external objects (eg, fingers, stylus, etc.). Additionally, the touch sensor panel may have various structures and types, and the present disclosure can be applied regardless of the structure and type of the touch sensor panel.

In one embodiment, computing device 400 may further include an input device (eg, mouse or keyboard, etc.). The input device may receive information to be used in components of computing device 400 from outside of computing device 400 (eg, a user).

Various embodiments to be described with reference to the drawings below in FIG. 3 will be described based on a platform related to a delivery service for delivered food, but this is an example and the present disclosure also applies to a platform related to a service for delivering products different from delivered food. It should be noted that the technical ideas of can be applied.

Figure 3 shows a screen 10 to which the home UI of a platform that can be referenced in an embodiment of the present disclosure is applied. The screen 10 to which the home UI is applied may include a location identifier 11, a search bar 12, an advertisement area 13, a category area 14, or a recommendation area 15.

3 in detail, the location identifier 11 may be an identifier indicating current location information of the user terminal 200. The search bar 12 may be a tool for searching menu information or store information desired by the user. The advertising area 13 may be an area that displays advertising information related to the platform on the user terminal 200. The category area 14 may be an area that categorizes and displays menu information posted on the platform. Here, one or more category icons 14a representing classification criteria of menu information (for example, “packaging,” “new restaurant,” or “per serving”) may be displayed in the category area 14. The recommendation area 15 may be an area that recommends and displays menu information posted on the platform using various recommendation algorithms of the platform. In one embodiment, the recommendation algorithm may be an algorithm based on menu information and user information, but to avoid redundant description, a detailed description of this will be made later through the drawings of FIG. 4 and below. One or more recommendation icons 15a representing the target of recommendation may be displayed in the recommendation area 15. In one embodiment, the recommendation icon 15a may be an icon representing a specific store or an icon representing a specific food from a specific store.

The screen 10 to which the home UI described so far has been applied can be understood as a screen that can be basically applied to a platform related to delivery food delivery services. However, it should be noted that some components constituting the screen 10 may be deleted or other general-purpose components may be added to the screen 10 as needed. Additionally, the arrangement of the components constituting the screen 10 may vary.

Hereinafter, methods according to various embodiments of the present disclosure will be described in detail. In particular, embodiments related to regular delivery services among the various services that can be provided on the platform will be described in detail. Although operations are shown in a specific order in the drawings below, it should be noted that the operations do not necessarily have to be executed in the specific order or sequential order shown, or that all of the illustrated operations must be executed to obtain the desired results.

Additionally, each step of the methods to be described with reference to the drawings below may be performed by a computing device. In other words, each step of the methods may be implemented as one or more instructions executed by a processor of a computing device. All steps included in these methods may be performed by a single physical computing device; however, the first steps of the method may be performed by a first computing device and the second steps of the method may be performed by a second computing device. It could be. Hereinafter, the description will be continued assuming that each step of the above-described methods is performed by the order processing device 100 shown in FIG. 1. However, for convenience of explanation, the description of the operator of each step included in the methods may be omitted.

In step S100, a plurality of menu keyword sets corresponding to each of the plurality of menu information may be determined.

Menu information may refer to information about menus (e.g., delivery food) posted on the platform. Menu information includes, for example, store information selling the menu, information on the time the menu was ordered, age information of the user who ordered the menu, name information of the menu, image of the menu, price information of the menu, category information of the menu (e.g. For example, Japanese or Korean food, etc.), nutritional information of the menu, ingredient information of the menu, and allergy information of the menu may be included. Menu information can be obtained in various ways. For example, menu information about menus sold at the store may be obtained from the store terminal 300. As another example, menu information may be obtained from action information indicating the user's activities within the platform (eg, ordering a menu, giving a review score, etc.).

A menu keyword set may refer to a set including one or more menu keywords. Here, the menu keyword is a keyword representing at least part of the menu information, and may mean information in which part of the menu information has been processed. For example, by processing the information on the time when the menu was ordered, the time zone in which the menu was frequently ordered (for example, "17:00-18:00" or "12:00-13:00", etc.) is converted into a menu keyword. By processing the age information of the user who ordered the menu, the age group for which the menu is frequently ordered (for example, "20s" or "50s", etc.) can be determined as a menu keyword, and the nutritional information of the menu By processing, “diet menu” or “muscle strengthening diet” may be determined as menu keywords. In addition to the examples described above, all examples in which menu information can be processed and keyworded may be included in the present disclosure.

In one embodiment, an artificial neural network model may be used to determine menu keywords. Here, the artificial neural network model is a supervised learning-based classification model. The first classification model outputs keywords using input information as text (part of menu information) and the input information as images (part of menu information). It may include a second classification model that outputs keywords. Here, the classification model may be a model that finds out which class (eg, dog or cat) the input information (eg, image) belongs to. In learning this classification model, the label indicating the class and the input information can be used as a pair as learning data, and evaluation data for evaluating the model according to learning can be prepared separately from the learning data. there is. In one embodiment, preparation of training or evaluation data, i.e. labeling, can be automated by processing action information. For example, if the action of the user selecting “A Category Area” is included and the order of “A Menu” is included, then the category information corresponding to “A Category Area” is used as a label for the name information of “A Menu”. can be extracted. For another example, if the action of the user selecting the "B category area" is included and the order of the "B menu" is followed, category information corresponding to the "B category area" is used as the label of the image of the "B menu". can be extracted. In other words, when the selection of a specific category area leads to a user's order for a specific menu, the selection of the specific category area and the specific ordered menu have a meaningful relationship as a pair, so their properties can be used as learning data or evaluation data. It can be used as. According to this embodiment, the acquisition of learning data or evaluation data can be automated by using action information representing the user's activities within the platform. In addition, various known techniques for learning a classification model may be referred to in the present disclosure, and all techniques that can be used in the operation of determining menu keywords using menu information may be referred to in the present disclosure.

To describe the operation of the first classification model in detail, text included in menu information is input to the first classification model, and a menu keyword may be determined based on the output value of the first classification model according to the input. For example, by inputting the name information of the menu (eg, A Spicy Tteokbokki) into the first classification model, the category information (eg, snack food) of the menu may be determined as a menu keyword. For another example, by inputting the price information of the menu into the first classification model, the serving size information (for example, 1 serving or 2 servings) of the menu may be determined as a menu keyword.

To describe the operation of the second classification model in detail, an image included in menu information is input to the second classification model, and a menu keyword may be determined based on the output value of the second classification model according to the input. For example, by inputting the image of the menu into the second classification model, the category (eg, spicy food/non-spicy food) information of the menu may be determined as a menu keyword.

Based on the operations described so far, a menu keyword set may be determined to include one or more menu keywords corresponding to menu information. For example, “A menu information” can be determined by three menu keywords such as {“teenagers”, “12:00-13:00”, “diet menu”, “Korean food”, “1 serving”}. In this way, a plurality of menu keyword sets corresponding to each of the plurality of menu information posted on the platform can be determined.

In one embodiment, the operation (S100) of determining the menu keyword set may be performed when menu information is first posted or updated on the platform. In other words, the operation (S100) of determining the menu keyword set can be performed in advance regardless of the timing of the user's regular delivery request.

In step S200, based on the user information, a user keyword set corresponding to the user information may be determined.

User information may refer to information about users who use the platform. User information includes, for example, menu information ordered by the user, information on the number of orders made by the user, information on reviews written by the user (e.g., rating of the review, review text), information on the user's age, information on the user's favorites, and information on the user's favorites. It may include at least part of address information, information on the time the user ordered the menu, and price information on the menu ordered by the user. User information can be obtained in various ways. For example, the user's user information may be obtained as input from the user terminal 200. For another example, user information may be obtained from the user terminal 200 as action information indicating the user's activities within the platform.

A user keyword set may refer to a set including one or more user keywords. Here, the user keyword is a keyword representing at least part of the user information, and may mean information in which part of the user information has been processed. For example, by processing information on the time when a user ordered a menu, the time zone in which the user frequently ordered (for example, "17:00-18:00" or "12:00-13:00", etc.) is converted into a user keyword. By processing the user's age information, the user's age group (for example, "20s" or "50s", etc.) can be determined as a user keyword, and by processing the menu information ordered by the user, the user Preferred diet information (for example, “diet menu” or “muscle strengthening diet”) may be determined as a menu keyword. In addition to the examples described above, all examples in which user information can be processed and keyworded may be included in the present disclosure.

Based on the operations described so far, a user keyword set may be determined to include one or more user keywords corresponding to user information. For example, “A user information” may be determined by three user keywords such as {“teenagers”, “12:00-13:00”, “diet menu”, “Korean food”, “1 serving”}. In this way, a set of user keywords corresponding to user information of users using the platform can be determined.

In one embodiment, the operation of determining the user keyword set (S200) may be performed when the user first joins the platform or at a specific period. In other words, the determination operation (S200) of the user keyword set can be performed in advance regardless of the timing of the user's regular delivery request.

In step S300, the degree of relevance between user information and menu information may be calculated based on the correspondence relationship between the menu keyword set and the user keyword set.

Specifically, a numerical value representing the correspondence relationship between menu keywords included in the menu keyword set and user keywords included in the user keyword set can be calculated. Here, the correspondence relationship may mean a relationship that allows menu keywords and user keywords to correspond, and the numerical value may be determined in advance according to the corresponding combination of menu keywords and user keywords. For example, if the menu keyword is “teenagers” and the user keyword is “teenagers,” “1” can be calculated as a number, and if the user keyword is “twenties”, “0” can be calculated as a numeric value. That is, if the menu keyword and the user keyword are the same, “1” can be calculated as a number, and if the menu keyword and the user keyword are not the same, “0” can be calculated as a number. For another example, if the menu keyword is "12:00-13:00" and the user keyword is "18:00-19:00", "0" may be calculated as a number, and the user keyword is "15:00-19:00". If “16:00”, “0.5” can be calculated as a number, and if the user keyword is “12:00-13:00”, “1” can be calculated as a number. That is, if the menu keyword and the user keyword are the same, “1” can be calculated as a number, and in a similar order of the menu keyword and the user keyword, a high number close to “1” can be calculated. For another example, if the menu keyword is "egg ingredients" and the user keyword is "egg allergy," "0" may be calculated as a number, and if the user keyword is "N/A", "1" may be calculated as a number. You can. That is, if the menu keyword and the user keyword are the same, “0” can be calculated as a number, and if the menu keyword and the user keyword are not the same, “1” can be calculated as a number. The example described above is for convenience of understanding, and the number determined may vary depending on the corresponding combination of menu keywords and user keywords, and all relationships that map the relationship between multiple keywords as numbers are possible. Technology may be referenced.

In this way, by calculating the correspondence relationship between all menu keywords included in the menu keyword set and all user keywords included in the user keyword set as numbers and adding these numbers, the degree of relevance between user information and menu information can be calculated. there is.

[Formula 1]

In one embodiment, weights may be applied to the numbers when adding them up. When explained specifically with reference to Equation 1, a first value (x_1) based on the correspondence relationship between the first menu keyword and the first user keyword and a second value (x_2) based on the correspondence relationship between the second menu keyword and the second user keyword ), the degree of relevance (y) can be calculated by applying the first weight (w_1) to the first number and the second weight (w_2) to the second number. In other words, the degree of relevance can be calculated by a weighted sum of numbers and weights.

The weight may be predetermined according to the corresponding combination. For example, all corresponding combinations may be predetermined to be “1”. In one embodiment, the weights may vary based on action information. Specifically, the weight may become smaller or larger depending on the user's activities within the platform. For example, in the corresponding combination of the name information of the menu included in the menu information and the review information included in the user information, if the rating of the review among the review information is greater than the standard value, the weight of the corresponding combination may be increased and higher than the standard value. If it is small, the weight may be lowered. As a result, the degree of relevance with menu information to which the user has given a high rating may be calculated to be large, or the degree of relationship to menu information to which the user has given a low rating may be calculated to be small. According to this embodiment, a degree of relevance optimized for the user's preferences can be calculated by reflecting the user's various inputs within the platform. This degree of relevance serves as a standard for later allocation (i.e., recommendation) of menu information, so ultimately, menu information optimized for the user's preferences can be recommended.

Based on the operations described so far, the degree of relevance between each of the plurality of menu information posted on the platform and the user information can be calculated.

Regarding the timing of calculating the degree of relevance, the operation (S300) for calculating the degree of relevance may be performed according to a specific cycle. In one embodiment, calculating the degree of relevancy may include calculating a plurality of degrees of relevancy in response to a user's regular delivery request. According to the former, the relevance calculation operation (S300) is performed before the regular delivery request, so that the relevance can be immediately returned to the regular delivery request, and according to the latter, it is calculated at the time of the regular delivery request. A degree of relevance calculated in accordance with the user's preference can be calculated.

A regular delivery request may be a user request related to a service that delivers multiple products at different times during a specific period. In one embodiment, a subscription request may include settings. The setting value is a value accompanying a user's regular delivery request, and can collectively refer to information required for regular delivery. The set value may include, for example, at least some of monthly budget information, desired delivery time information, allergy information, preferred nutritional ingredient information, and upper price limit information per menu as items. The setting value may be obtained from the user terminal 200 according to the setting UI, which will be described later with reference to FIG. 7.

In one embodiment, calculating a plurality of degrees of relevance includes calculating a plurality of degrees of relevance based on a combination of a set of settings and user keywords included in a regular delivery request and a corresponding relationship between each of the plurality of menu keyword sets. may include. In other words, information can be additionally, supplementally, or alternatively included as a setting value in the user keyword set, and the degree of relevance can be calculated using this.

For the calculation of the degree of relevance based on the correspondence between the combination and the menu keyword set, reference may be made to the previously described description of calculation of the degree of relevance based on the correspondence between the user keyword set and the menu keyword set. In other words, the combination simply merges the user keyword set and the setting value, and the operation of calculating the relevance using the combination can be performed similarly to the operation of calculating the relevance using the user keyword set.

In one embodiment, if the type of item included in the setting value and the type of the user keyword are the same, the user keyword may be deleted from the combination. For example, if the user keyword includes "Month" as the time zone when the user frequently orders, but the desired delivery time information included in the setting value includes "Tuesday, Thursday, Friday", then the time zone when the user frequently orders User keywords related to may be deleted from the combination. In other words, setting values, which are user input values, can be included in the combination in priority over user keywords, which are analysis values, and analysis values that conflict with setting values that more directly reflect the user's intention can be excluded from the calculation of relevance. there is.

In one embodiment, among a plurality of weights applied to calculate relevance, the weight corresponding to the item included in the setting value may be greater than the weight corresponding to the user keyword. In other words, in calculating relevance, the weight of the setting value, which is the user's input value, is set larger than the weight of the user keyword, which is the analysis value, so that the setting value that more directly reflects the user's intention has a higher relevance than the user keyword. It can act as a more important factor in calculation.

In step S400, based on the calculated order of magnitude of relevance, a set of regular delivery menus may be determined to correspond to the regular delivery request. A regular delivery menu set may refer to a set of menu information scheduled to be delivered at a plurality of times corresponding to a regular delivery request. For example, if "August 20, 2022 to August 21, 2022" is the period corresponding to the regular delivery request and "lunch" is requested for regular delivery as the desired delivery time, {" as the regular delivery menu set. “chicken”, “fried rice”} can be determined. In other words, as a set of regular delivery menus, the menu information for “lunch on August 20, 22” may be determined as “chicken”, and the menu information for “lunch on August 21, 22” may be determined as “fried rice.” In this way, a plurality of menu information may be determined as a regular delivery menu set to correspond to a regular delivery request. According to step S400, a set of regular delivery menus is determined based on the degree of relevance calculated based on the correspondence relationship between the user and the menu, thereby automatically recommending a plurality of menu information to match the user's preferences.

In one embodiment, menu information may be modified in response to a user's correction input for menu information included in a regular delivery menu set. In other words, the automatically determined diet may be partially changed according to the user's preference, and the automatically configured diet may be modified to better match the user's preference. In one embodiment, a modification input for a meal plan may be used as a user keyword in user information, similar to review information.

Additionally, modification of menu information may be disabled based on the average delivery time of menu information. To implement deactivation of this modification, the average delivery time may be stored and managed per menu information published on the platform. According to this embodiment, by disabling the modification of menu information whose delivery time is approaching, it is possible to prevent damage to the store due to the user's modification.

For a more detailed explanation related to step S400, it will be described with reference to FIG. 5. FIG. 5 is a flowchart showing detailed operations of the determination operation (S400) of the regular delivery menu set described with reference to FIG. 4. Referring to FIG. 5, a plurality of menu allocation areas may be determined to correspond to a regular delivery request (S410), and menu information selected from a plurality of menu information may be assigned to each of the plurality of menu allocation areas (S420). The menu allocation area may refer to an area related to a plurality of time points (i.e., times when delivery is requested) corresponding to a regular delivery request. That is, the menu allocation area is an area visually displayed on the screen of the user terminal 200 (for example, a position displayed on a menu table) and may mean an area displayed corresponding to a plurality of viewpoints. In some cases, the menu allocation area may refer to an area of information (for example, a location in a data structure) that has a connection relationship with a plurality of viewpoints. According to this embodiment, menu information is allocated to a plurality of menu allocation areas corresponding to regular delivery requests based on the size order of relevance, so that the menu for a specific period is automatically adjusted to match the user's preferences with a simple input from the user. It can be configured.

Regarding step S420, in one embodiment, the step of allocating menu information selected from a plurality of menu information includes, when the first menu information is allocated to the first menu allocation area included in the plurality of menu allocation areas, the first menu information is allocated to the first menu allocation area included in the plurality of menu allocation areas. It may include the step of allocating menu information different from the first menu information to N menu allocation areas (N is a natural number) following the allocation area. If menu information is allocated based only on the order of magnitude of relevance, only menu information with maximum relevance can be included in the regular delivery menu set. According to this embodiment, by excluding menu information included in the menu allocation area N times from allocation to the menu allocation area, it is possible to automatically configure a menu, that is, a set of regular delivery menus, without duplicating menu information.

Regarding step S420, in another embodiment, the step of allocating menu information selected from a plurality of menu information includes, when the first menu information is allocated to the first menu allocation area included in the plurality of menu allocation areas, the first menu information is allocated to the first menu allocation area. It may include a step of reducing the degree of relevance corresponding to the menu information. Likewise, if menu information is allocated based only on the order of magnitude of relevance, only the menu information with the greatest relevance can be included in the regular delivery menu set. According to this embodiment, by reducing the relevance of the menu information included in the menu allocation area by a predetermined value, it is possible to prevent only menu information with the highest relevance from being allocated, and to prevent menu information from being duplicated. In other words, a set of regular delivery menus can be automatically configured.

Here, the step of reducing the relevance may include gradually increasing the relevance corresponding to the first menu information when the menu information of the menu allocation area following the first menu allocation area is sequentially allocated. . Since the relevance before reduction reflects the user's preference, it is necessary to gradually increase the reduced relevance and restore it to its original state as the menu information that makes up the menu diversifies. According to this embodiment, the decreased relevance is gradually increased so that menu information corresponding to the decreased relevance can be included again in the menu.

This will be described again with reference to FIG. 4 .

In step S500, a notification notifying regular delivery may be transmitted to the user terminal 200 before the standard time from the desired delivery time corresponding to the regular delivery request. The decision operation (S400) of the regular delivery menu set, that is, the menu composition operation, is an operation determined before each actual delivery time (e.g., desired delivery time) included in the regular delivery, so it is determined from each actual delivery time. By sending a notification to the user terminal 200 before the reference time, it is possible to check whether actual delivery is in progress. According to this embodiment, when delivery becomes unnecessary due to a change in the user's circumstances, the user's convenience can be further improved by reflecting this.

So far, various methods of the present disclosure have been described with reference to FIGS. 4 and 5 . According to the above-described methods, menu information optimized for the user's preferences can be recommended. Additionally, with a simple user input, multiple menu information can be configured and recommended as a menu during a specific period corresponding to a regular delivery request. Furthermore, user convenience can be further improved by automatically organizing menus so that menu information does not overlap.

Hereinafter, various UIs that can be displayed on the screen of the user terminal 200 will be described with reference to FIGS. 6 to 10.

Figure 6 shows a screen 20 to which a regular reservation button 21, which may be referred to in an embodiment of the present disclosure, is applied. One area 22 of the screen 20 may include at least a portion of the screen 10 shown in FIG. 3 . However, it should be noted that some components constituting the screen 20 may be deleted or other general-purpose components may be added to the screen 20 as needed. Additionally, the arrangement of the components constituting the screen 20 may vary.

The regular reservation button 21 shown in FIG. 6 may be a button that receives a user's selection input to initiate a regular reservation request. When the regular reservation button 21 is selected by the user, the screen 20 may be converted to the screen 30 to which the setting UI, which will be described later with reference to FIG. 7, is applied. As shown in FIG. 6, rather than a button, a UI for initiating a regular reservation request may be applied to the screen in any number of different ways, for example, a specific predetermined gesture (e.g., a swipe gesture, etc.) When input, the screen 20 may be converted to the screen 30 to which the settings UI is applied.

Figure 7 shows a screen 30 to which a platform setting UI that can be referenced in an embodiment of the present disclosure is applied. The settings UI may be a UI for receiving the setting value of a regular delivery request as input. The settings UI may include an area that selectively receives input from the user for the automatic button 31 or the manual button 32. For example, when the automatic button 31 is selected by the user, by subsequent input of the setting value and selection input of the schedule creation button 34, a screen to which the diet UI, which will be described later with reference to FIG. 8, is applied ( The screen 30 is switched to 40 and an automatically configured diet can be displayed on this screen 40. For another example, when the manual button 32 is selected by the user, by selecting the schedule creation button 34, the screen 30 is converted to the screen 40 to which the diet UI is applied, and the user selects this screen ( You can manually configure your diet using the diet UI applied in 40).

The settings UI may include a settings area 33 that receives input for setting values from the user. The setting area 33 may include one or

more input boxes

33a, 33b, and 33c, and the

input boxes

33a, 33b, and 33c may be boxes that receive input from a user who selects a setting value. In one embodiment, the upper or lower limit values of the

input boxes

33a, 33b, and 33c may be determined in advance depending on the attributes corresponding to the

input boxes

33a, 33b, and 33c. For example, the lower limit value of the first input box 33a may be set to “0”, and input of negative values may not be permitted. For another example, the third input box 33c may have the lower limit value set to "1" and the upper limit value set to "31", and inputs of values less than "1" or more than "31" are not permitted. It may not be possible. According to this embodiment, even if there is an error in the user's input, the input can be prevented from being received. In one embodiment, the

input boxes

33a, 33b, and 33c may be implemented in a variety of well-known ways. For example, the second input box 33b may be implemented as a drop-down list or combo box. In addition, the

input boxes

33a, 33b, and 33c can be implemented in various ways, such as a drop-down list, combo box, radio button, or check box.

7 shows the setting values, including "monthly budget", "desired delivery (delivery) time", "allergy information", "desired day of the week", "start date", and "end date", but the scope of the present disclosure is It is not limited to this, and setting values such as “whether or not to include delivery costs in the monthly budget” and “if first priority delivery is not possible, priority on delivery time or menu priority” may be further included in the setting area 33.

The schedule creation button 34 shown in FIG. 7 may be a button that transmits the settings input from the settings UI to the order processing device 100 and receives the user's selection input to display the diet determined according to the transmission. . As described above, when the schedule creation button 34 is selected and input, the screen 30 may be switched to the screen 40 to which the diet menu UI is applied.

Figure 8 shows a screen 40 to which the diet UI of the platform that can be referenced in an embodiment of the present disclosure is applied. The diet UI shown in FIG. 8 is displayed in calendar format, but it should be noted that the display format may vary. The menu UI may be a UI for displaying a regular delivery menu set corresponding to a regular delivery request, that is, a menu. The menu UI can display a bar (41) corresponding to a specific period according to a regular delivery request. The menu UI may include one or more menu allocation areas (41, 42) and one or more blank areas (43) corresponding to the specific period. Each of the allocated

areas

41 and 42 and the blank area 43 may be displayed to correspond to a specific date on the calendar. Here, the

menu allocation areas

41 and 42 may be an area included in a specific period and to which menu information is allocated according to the user's settings, and the blank area 43 may be an area included in a specific period but assigned menu information according to the user's settings. It may be an area where allocation of information is excluded.

As shown in FIG. 9, the integrated menu allocation area 44 may include a third menu allocation area 44a and a fourth menu allocation area 44b. The integrated menu allocation area 44 may be displayed when multiple deliveries are required on a specific date in the calendar shown in FIG. 8. For example, the menu information allocated to the third menu allocation area 44a is scheduled to be delivered at “12:30”, and the menu information allocated to the fourth menu allocation area 44b is scheduled to be delivered at “18:45”. "It may be scheduled for delivery.

The

menu allocation areas

41 and 42 can be expressed in various ways. For example, as in the first menu allocation area 41, an image 41a of menu information scheduled for delivery may be displayed. For another example, as in the second menu allocation area 42, an image 42a of menu information scheduled for delivery and an estimated delivery time 42b of the menu may be displayed together. For another example, as in the third menu allocation area 44a, an image 44a1 of menu information scheduled for delivery, a delivery destination 44a2 of the menu, an estimated delivery time 44a3 of the menu, and the menu 44a3 are sold. The store (44a4) and the price of the menu (44a5) may be displayed together. In addition to the examples described above, it should be noted that information may be added, deleted, or changed for the user's convenience.

The

menu allocation areas

41, 42, and 44 shown in FIGS. 8 and 9 may be buttons that receive a user's selection input. Specifically, when the

menu allocation areas

41, 42, and 44 are selected and input, the screen 40 may be converted to the screen 50 to which the correction UI is applied.

Figure 10 shows a screen 50 to which a platform modification UI that can be referenced in an embodiment of the present disclosure is applied. The modification UI may be a UI for receiving user input to modify menu information determined in the menu allocation area. The modification UI may include areas 51, 52, and 53 that display priorities in order of size of relevance corresponding to the menu allocation area. In Figure 10, three menu information is displayed according to priority, but the number of menu information that can be displayed may vary. When the screen 50 to which the initial modification UI is applied is switched, the menu information displayed in the first priority area 51 can be understood as menu information determined according to the order of size of relevance corresponding to the menu allocation area.

Users can use the edit UI in various ways to edit menu information corresponding to the menu allocation area. For example, the user can change the menu information assigned to the menu allocation area by changing the priority using a drag and drop method. For another example, the user can modify menu information assigned to the menu allocation area with pre-specified menu information. In addition to the above-described examples, menu information can be modified in any number of different ways, and any method that allows selection of specific menu information by reflecting the user's intention can be applied to the present disclosure.

The edit button 54 shown in FIG. 10 may be a button that receives a user's selection input to end modification of menu information. Specifically, when the edit button 54 is selected and input, the screen 50 to which the edit UI is applied may be switched to the screen 40 to which the diet UI is applied.

The effects according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description of the present disclosure.

In the flow chart according to the present disclosure, each step of the method or algorithm is described in sequential order, but each step may be performed in an order that can be arbitrarily combined in addition to being performed sequentially. The description of the disclosure as a flowchart or flowchart does not exclude making changes or modifications to the method or algorithm, nor does it imply that any step is required or desirable. In one embodiment, at least some of the steps may be performed in parallel, iteratively, or heuristically. In another embodiment, at least some steps may be omitted or other steps may be added.

Various embodiments according to the present disclosure may be implemented as software on a machine-readable storage medium. The software may be software for implementing various embodiments described in this disclosure. Software can be inferred from the various embodiments described in this disclosure by programmers in the technical field to which this disclosure pertains. For example, software may be a program that contains machine-readable instructions (e.g., instructions, code, or code segments). A device is a device that can operate according to commands retrieved from a storage medium, and may be, for example, a computer. In one embodiment, the device may be a computing device according to various embodiments described in this disclosure. In one embodiment, the device's processor may execute the called instruction, causing the device's components to perform a function corresponding to the instruction. A storage medium can refer to any type of recording medium in which data that can be read by a device is stored. Storage media may include, for example, ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, etc. In one embodiment, the storage medium may be implemented in a distributed form, such as in a networked computer system. At this time, the software may be distributed, stored, and executed on a computer system, etc. In another embodiment, the storage medium may be a non-transitory storage medium. Non-transitory storage media refers to a medium that exists regardless of whether data is stored semi-permanently or temporarily, and does not include signals that are transmitted temporarily.

Although the technical idea according to the present disclosure has been described above through various embodiments, the technical idea according to the present disclosure is various substitutions, modifications, and Includes changes. Additionally, it is to be understood that such substitutions, modifications and alterations may be included within the scope of the appended claims.

Claims

In an order processing method performed by an electronic device,

Based on user information, determining a user keyword set corresponding to the user information, wherein the user keyword set includes one or more user keywords representing at least part of the user information;

Calculating a degree of relevance between the user information and each of the plurality of menu information based on a correspondence relationship between each of a plurality of menu keyword sets determined to correspond to each of the plurality of menu information and the user keyword set - the plurality of menu keywords The first menu keyword set included in the set includes one or more menu keywords representing at least a portion of the first menu information included in the plurality of menu information. and

Based on the calculated size order of the plurality of degrees of relevance, determining a regular delivery menu set including two or more menu information among the plurality of menu information to correspond to the regular delivery request,

How to process your order.
According to paragraph 1,

Further comprising determining the plurality of menu keyword sets corresponding to each of the plurality of menu information,

How to process your order.
According to paragraph 2,

The first menu information is,

Store information selling the first menu, time information at which the first menu was ordered, age information of the user who ordered the first menu, name information of the first menu, image of the first menu, information of the first menu Containing at least some of price information, category information of the first menu, nutritional ingredient information of the first menu, ingredient information of the first menu, and allergy information of the first menu,

How to process your order.
According to paragraph 2,

The step of determining the plurality of menu keyword sets is:

comprising determining the first menu keyword set,

The step of determining the first menu keyword set is,

Inputting text included in the first menu information into a first classification model, wherein the first classification model is an artificial neural network model based on supervised learning; and

Based on the output value of the first classification model, determining a menu keyword included in the first menu keyword set,

How to process your order.
According to paragraph 2,

The step of determining the plurality of menu keyword sets is:

comprising determining the first menu keyword set,

The step of determining the first menu keyword set is,

Inputting an image included in the first menu information into a second classification model, where the second classification model is an artificial neural network model based on supervised learning; and

Based on the output value of the second classification model, determining a menu keyword included in the first menu keyword set,

How to process your order.
According to paragraph 1,

The user information is,

Menu information ordered by the user, allergy information of the user, information on the number of orders made by the user, information on reviews written by the user, information on the age of the user, information on the user's favorites, information on the user's address, information on the user's menu Containing at least part of order time information and price information of the menu ordered by the user,

How to process your order.
According to clause 6,

The step of calculating the degree of relevance is,

Comprising the step of calculating the plurality of degrees of relevance based on calculation of a numerical value and a weight representing the correspondence relationship between a user keyword and a menu keyword,

The weight is,

Variable based on action information included in the user information and indicating the user's activities,

How to process your order.
According to paragraph 1,

The step of calculating the degree of relevance is,

Comprising the step of calculating the plurality of degrees of relevance in response to the user's regular delivery request,

How to process your order.
According to clause 8,

In response to the user's regular delivery request, calculating the plurality of degrees of relevance includes:

Comprising the step of calculating the plurality of degrees of relevance based on a combination of the setting value included in the regular delivery request and the user keyword set and a correspondence relationship between each of the plurality of menu keyword sets,

How to process your order.
According to clause 9,

Among the plurality of weights applied to calculate relevance, the first weight corresponding to the item included in the setting value is greater than the second weight corresponding to the user keyword,

How to process your order.
According to clause 9,

The step of calculating the plurality of degrees of relevance based on the correspondence relationship between the combination and each of the plurality of menu keyword sets includes:

If the type of the item included in the setting value and the type of the user keyword are the same, deleting the user keyword from the combination,

How to process your order.
According to clause 9,

The above settings are:

Containing as items at least some of monthly budget information, desired delivery time information, allergy information, preferred nutritional information, and upper price limit information per menu,

How to process your order.
According to paragraph 1,

The step of determining the regular delivery menu set is,

determining a plurality of menu allocation areas to correspond to the regular delivery request; and

Comprising the step of allocating menu information selected from the plurality of menu information to each of the plurality of menu allocation areas,

How to process your order.
According to clause 13,

The step of allocating menu information selected from the plurality of menu information includes:

When the first menu information is allocated to a first menu allocation area included in the plurality of menu allocation areas, the first menu is stored in N menu allocation areas (N is a natural number) following the first menu allocation area. Including assigning menu information different from the information,

How to process your order.
According to clause 13,

The step of allocating menu information selected from the plurality of menu information includes:

When the first menu information is allocated to a first menu allocation area included in the plurality of menu allocation areas, reducing the degree of relevance corresponding to the first menu information,

How to process your order.
According to clause 15,

The step of reducing the degree of relevance corresponding to the first menu information includes:

When menu information of a menu allocation area following the first menu allocation area is sequentially allocated, comprising gradually increasing the degree of relevance corresponding to the first menu information,

How to process your order.
According to paragraph 1,

The step of determining the regular delivery menu set is,

Comprising the step of modifying the menu information in response to a user's correction input for menu information included in the regular delivery menu set,

How to process your order.
According to clause 17,

The step of modifying the menu information is,

Disabling modification of the menu information based on the average delivery time of the menu information,

How to process your order.
According to paragraph 1,

Further comprising transmitting a notification informing of regular delivery to the user terminal before the standard time from the desired delivery time corresponding to the regular delivery request,

How to process your order.
processor;

communication interface;

Memory; and

Includes a computer program loaded into the memory and executed by the processor,

The computer program is,

Based on user information, instructions for determining a user keyword set corresponding to the user information, wherein the user keyword set includes one or more user keywords representing at least part of the user information;

An instruction for calculating a degree of relevance between the user information and each of the plurality of menu information based on a correspondence relationship between each of a plurality of menu keyword sets determined to correspond to each of the plurality of menu information and the user keyword set - the plurality of menu keywords The first menu keyword set included in the set includes one or more menu keywords representing at least a portion of the first menu information included in the plurality of menu information. and

Based on the order of magnitude of the calculated plurality of degrees of relevance, instructions for determining a regular delivery menu set including two or more menu information among the plurality of menu information to correspond to a regular delivery request,

Electronic devices.