Menu providing device and method

Abstract

The present invention relates to a menu providing device, which includes a menu data collecting unit that collects menu data via a network and stores it in a menu database, a menu generating unit that learns the menu data and generates a menu, a menu recommendation unit that sends a recommended menu to a user terminal based on the generated menu and receives information on a menu and number of meals selected from the user terminal, a menu correction unit that receives a correction command for the recommended menu from the user terminal, corrects the recommended menu according to the correction command, and sends it to the user terminal, and an ingredient ordering unit that derives types of ingredients according to the selected menu, calculates the required quantity of each type of ingredient according to the number of meals, and transmits the calculated amount to an ingredient supplier terminal.

Description

[Technical field]

[0001] The present specification relates to a menu providing device and a menu providing method based on artificial intelligence. [Background technology]

[0002] Currently, food services operated by kindergartens, daycare centers, schools, corporate cafeterias, etc. usually have one nutritionist create the daily menu, prepare ingredients according to the menu, and serve meals to the students, pupils or employees.

[0003] Additionally, nutritionists order ingredients for the menu individually from food suppliers and pay for delivery. Summary of the Invention [Problem to be solved by the invention]

[0004] In the past, in the case of a service in which a nutritionist creates a menu and provides meals, it was very stressful for the nutritionist to create the daily menu and prepare ingredients according to the created menu. Therefore, there is a growing need for technology that can reduce the burden on nutritionists in creating menus and easily prepare ingredients.

[0005] In addition, when nutritionists prepare individual menus and directly order ingredients for the prepared menus from food suppliers, the food suppliers must supply the ingredients in small quantities, which results in high food costs. This has led to a growing need for technology that can reduce food costs by standardizing the menus of many nutritionists and supplying ingredients in large quantities.

[0006] The problems to be solved by the present invention are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0007] This specification presents a menu providing device, which may include a menu data collecting unit that collects menu data via a network and stores it in a menu database, a menu generating unit that learns the menu data and generates a menu, a menu recommending unit that sends a recommended menu to a user terminal based on the generated menu and receives information on a menu and number of meals selected from the user terminal, a menu correcting unit that receives a correction command for the recommended menu from the user terminal, corrects the recommended menu according to the correction command, and sends it to the user terminal, and an ingredient ordering unit that derives types of ingredients according to the selected menu, calculates the required quantity of each type of ingredient according to the number of meals, and transmits the calculated amount to an ingredient supplier terminal.

[0008] The menu presentation device and other embodiments may include the following features.

[0009] According to an embodiment, the menu recommendation unit composes the recommended menu based on the user's menu composition conditions inputted via the user terminal, and the menu composition conditions may include at least one of the calories, nutrient composition, taste, sugar content, level of spiciness, food combinations, seasonal ingredients, number of side dishes, price of ingredients, event dishes, seasonal dishes, school lunch targets, overlap of individual foods that compose the menu, number of meals supplied, preference, number of menu items at the cafeteria, leftovers, price of school lunch, food color combinations, allergy information regarding ingredients, area information, and menu evaluation results of other users.

[0010] According to an embodiment, the menu recommendation unit may also transmit a recommended menu to the user terminal based on a statistical result of accumulated menu composition.

[0011] Further, according to an embodiment, the menu recommendation unit can compose the recommended menu based on ingredient inventory information held by the ingredient supplier, information on ingredients to be supplied as main ingredients, ingredient supply and demand status information, and the menu composition conditions, all of which are received from the ingredient supplier terminal.

[0012] According to an embodiment, the foodstuff supply and demand status information can be determined based on foodstuff supply and demand fluctuation information including the production volume of foodstuffs, the forecasted production volume of foodstuffs, the import and export volume of foodstuffs, and the increase or decrease in the demand for foodstuffs.

[0013] According to an embodiment, the menu providing device further includes a menu recording unit that records the menu composed by the user, and the menu generation unit learns the user's menu composition pattern based on the menu composed by the user, and generates a menu based on the learning result of the menu data and the learning result of the menu composition pattern.

[0014] According to an embodiment, the communication unit receives feedback on the recommended menu from the user terminal, the menu data collection unit updates the menu database based on the feedback, and the menu generation unit generates a menu based on the updated menu database and the feedback, and updates a model for generating the menu based on the feedback.

[0015] According to further embodiment, the ingredient ordering unit receives an ingredient purchase estimate for the required quantity of each type of ingredient from the ingredient supplier terminal and provides it to the user terminal, and when the ingredient purchase estimate is approved by the user terminal, it can transmit an order for the ingredient purchase to the ingredient supplier terminal.

[0016] According to the embodiment, the menu recommendation unit groups the user terminals by region based on the location of the food ingredient supplier and recommends the same menu to user terminals belonging to the same group, and the food ingredient ordering unit derives the types of ingredients corresponding to the same menu and the number of meals according to the same menu, calculates the required quantity for each of the derived types of ingredients, and transmits the calculated required quantity to the food ingredient supplier terminals assigned to the same group.

[0017] According to an embodiment, the menu recommendation unit may further generate an image of the selected menu based on information regarding the selected menu received from the user terminal, and transmit the generated image of the menu to the user terminal.

[0018] According to an embodiment, the ingredient ordering unit may also predict the number of meals required for the selected menu, calculate the amount of ingredients required based on the predicted number of meals, and transmit the amount of ingredients required to the ingredient supplier terminal.

[0019] Meanwhile, this specification presents a menu providing method of a menu providing device that recommends a menu including a menu data collecting unit, a menu generating unit, a menu recommendation unit, a menu correction unit, and an ingredient ordering unit. The menu providing method includes a step of the menu data collecting unit collecting menu data via a network, a step of the menu generating unit learning the menu data and generating a menu, a step of the menu recommendation unit sending a recommended menu to a user terminal based on the generated menu, a step of receiving menu selection information or menu correction information and information on the number of meals related to the recommended menu from the user terminal, and a step of the ingredient ordering unit deriving types of ingredients according to the selected menu information or the corrected menu information, calculating the required quantity of each type of ingredient according to the number of meals, and transmitting the calculated amount to an ingredient supplier terminal.

[0020] The method for providing a menu and other embodiments may include the following features.

[0021] According to an embodiment, the menu recommendation unit creates the recommended menu based on the user's menu composition conditions inputted via the user terminal, and the menu composition conditions include at least one of the following: calories, nutrients, taste, sugar content, level of spiciness of the foods that make up the menu, combinations between foods, seasonal ingredients, number of side dishes, price of ingredients, event dishes, seasonal dishes, school lunch targets, overlaps between individual foods that make up the menu, number of meals supplied, preference, number of menu items at the cafeteria, leftovers, price of school lunches, color combinations of foods, allergy information related to ingredients, regional information, menu evaluation results of other users, and information on the supply and demand status of ingredients, and the information on the supply and demand status of ingredients can be determined based on information on fluctuations in supply and demand of ingredients, including the production volume of ingredients, the forecast production volume of ingredients, the import and export volume of ingredients, and the increase and decrease in demand for ingredients.

[0022] According to an embodiment, the menu recommendation unit may also transmit a recommended menu to the user terminal based on a statistical result of accumulated menu composition.

[0023] According to an embodiment, the menu providing device further includes a menu recording unit that records the menu composed by the user, and the menu generation unit can learn the user's menu composition pattern based on the user-composed menu, and generate a recommended menu based on the learning result of the menu data and the learning result of the menu composition pattern. Effect of the Invention

[0024] According to the embodiments disclosed in this specification, it is possible to eliminate the difficulty of a user preparing a menu by providing the user with an optimal menu.

[0025] In addition, according to the embodiments disclosed in this specification, a menu recommended by artificial intelligence based on the user's menu composition conditions can be provided to the user, which has the effect of making it easier for the user to prepare a menu.

[0026] Furthermore, according to the embodiments disclosed in this specification, by providing a common menu to a large number of users and allowing them to jointly purchase other ingredients for the common menu, users can obtain ingredients at low cost and ingredient suppliers can supply large quantities of ingredients, thereby increasing their sales.

[0027] On the other hand, the effects obtained by the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those having ordinary skill in the art to which the present invention pertains from the following description.

[0028] The following drawings attached to this specification illustrate preferred embodiments of the present invention and serve to further understand the technical concept of the present invention together with specific content for implementing the invention, and therefore the present invention should not be interpreted as being limited to only the matters depicted in such drawings. [Brief description of the drawings]

[0029] [Figure 1] The perceptron structure is shown. [Diagram 2] 1 shows a multi-layer perceptron structure. [Diagram 3] Here is an example of a deep neural network. [Figure 4] Here is an example of a convolutional neural network. [Diagram 5] Illustrates filter operations in convolutional neural networks. [Figure 6] 1 shows a neural network structure in which a cyclic loop exists. [Figure 7] 1 shows the operational structure of a recurrent neural network. [Figure 8] FIG. 1 is a block diagram of an AI device according to an embodiment of the present invention. [Figure 9] 1 shows a menu providing system according to an embodiment of the present invention. [Figure 10] 1 is a block diagram showing the configuration of a menu providing device according to an embodiment of the present invention. [Figure 11] An example of grouping users by region and providing them with menus and ingredients is shown below. [Figure 12] An example table showing some of the published menu data is shown below. [Figure 13] An example of an image for the generated menu is shown below. [Figure 14] 1 shows an example of an output screen that provides detailed information about the recommended menu items. [Figure 15] 1 shows an example of a user interface for menu modification for generating a customized menu. [Figure 16] 13 shows another example of a user interface for menu modification for generating a customized menu. [Figure 17] 3 shows the flow of data between components of a menu provision system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] The technology disclosed in this specification can be applied to the provision of menus for food service. However, the technology disclosed in this specification is not limited thereto, and can be applied to any device and method to which the technical idea of ​​the technology can be applied.

[0031] It should be noted that the technical terms used in this specification are merely used to describe specific embodiments and are not intended to limit the idea of ​​the technology disclosed in this specification. In addition, unless otherwise defined in this specification, technical terms used in this specification should be interpreted as a meaning generally understood by a person having ordinary knowledge in the field to which the technology disclosed in this specification belongs, and should not be interpreted as an overly comprehensive meaning or an overly narrow meaning. In addition, if a technical term used in this specification is an incorrect technical term that cannot accurately express the idea of ​​the technology disclosed in this specification, it should be understood by replacing it with a technical term that a person having ordinary knowledge in the field to which the technology disclosed in this specification belongs can correctly understand. Furthermore, general terms used in this specification should be interpreted according to the definition in a dictionary or the context, and should not be interpreted as an overly narrow meaning.

[0032] As used herein, terms including ordinal numbers such as first, second, etc. are used to describe various components, but the components should not be limited by the terms. The terms are used only to distinguish one component from another. For example, a first component can be named a second component, and similarly, the second component can be named a first component, without departing from the scope of the present invention.

[0033] Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings. Regardless of the drawing numbers, the same or similar components will be given the same reference numbers and duplicate descriptions thereof will be omitted.

[0034] In addition, when describing the technology disclosed in this specification, if it is determined that a specific description of a related publicly known technology may obscure the gist of the technology disclosed in this specification, the detailed description will be omitted. In addition, it should be noted that the attached drawings are merely intended to facilitate understanding of the concept of the technology disclosed in this specification, and the concept of the technology should not be construed as being limited by the attached drawings.

[0035] Hereinafter, with reference to the accompanying Figs. 1 to 8, a description will be given of artificial intelligence learning that can be applied to the menu generation and menu recommendation functions of the menu providing device of the present invention.

[0036] Artificial Intelligence (AI) can use numerous analyses to determine the way in which complex target tasks should be performed, thus increasing efficiency and reducing processing delays. Time-consuming tasks such as analyzing large amounts of data can be performed instantly using AI.

[0037] Below, we will take a more specific look at machine learning, a type of AI.

[0038] Machine learning refers to a series of actions to make machines learn to perform tasks that humans can do or that are difficult to do. For machine learning, data and learning models are necessary. In machine learning, data learning methods can be broadly divided into three categories: supervised learning, unsupervised learning, and reinforcement learning.

[0039] Neural network training is a process to minimize the output error. It involves repeatedly inputting training data into a neural network, calculating the error between the neural network output and the target for the training data, and backpropagating the neural network error from the output layer to the input layer in a direction to reduce the error, thereby updating the weights of each node of the neural network.

[0040] Supervised learning uses training data that is labeled with a correct answer, while unsupervised learning does not label the training data with a correct answer. That is, for example, in the case of supervised learning for data classification, the training data may be data in which each of the training data is labeled with a category. The labeled training data is input to the neural network, and an error can be calculated by comparing the output (category) of the neural network with the label of the training data. The calculated error can be backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weights of each node in each layer of the neural network can be updated by backpropagation. The amount of change in the connection weights of each node to be updated can be determined by a learning rate. The calculation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of iterations of the learning cycle of the neural network. For example, early in the training of a neural network, a high learning rate can be used to enable the neural network to quickly attain a certain level of performance, thereby improving efficiency, and later in the training, a lower learning rate can be used to improve accuracy.

[0041] The learning method may vary depending on the characteristics of the data. For example, when the objective is to accurately predict data transmitted from a transmitting end in a communication system at a receiving end, it is preferable to perform learning using supervised learning rather than unsupervised learning or reinforcement learning.

[0042] The learning model corresponds to the human brain and the most basic linear model is considered, but a machine learning paradigm that uses highly complex neural network structures such as artificial neural networks (ANNs) as learning models is called deep learning.

[0043] The neural network cores used as learning methods can be broadly divided into deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent neural networks (RNN).

[0044] An artificial neural network is an example of multiple connected perceptrons.

[0045] Figure 1 shows the perceptron structure.

[0046] Referring to Figure 1, the input vector x = (x1, x2, . . . , x d ) is input, each component is assigned a weight (W1, W2, ..., W d ), summing up the results, and then applying the activation function σ(·) is called a perceptron. A large artificial neural network structure can be expanded from the simplified perceptron structure shown in Figure 1, and input vectors can be applied to different multi-dimensional perceptrons. For ease of explanation, input values ​​or output values ​​are called nodes.

[0047] On the other hand, the perceptron structure shown in Figure 1 can be explained as being composed of a total of three layers based on the input and output values. An artificial neural network can be expressed as shown in Figure 2, with H (d+1)-dimensional perceptrons between the 1st layer and the 2nd layer, and K (H+1)-dimensional perceptrons between the 2nd layer and the 3rd layer.

[0048] FIG. 2 shows the structure of a multi-layer perceptron.

[0049] The layer where the input vector is located is called the input layer, the layer where the final output value is located is called the output layer, and all layers located between the input layer and the output layer are called hidden layers. The example in Figure 2 shows three layers, but the input layer is excluded when counting the number of layers in an artificial neural network, so there are actually two layers in total. An artificial neural network is composed of perceptrons, which are basic blocks, connected two-dimensionally.

[0050] The input layer, hidden layer, and output layer mentioned above can be applied not only to multi-layer perceptrons, but also to various artificial neural network structures such as CNN and RNN, which will be described later. The more hidden layers there are, the deeper the artificial neural network is, and the machine learning paradigm that uses a sufficiently deep artificial neural network as a learning model is called deep learning. In addition, an artificial neural network used for deep learning is called a deep neural network (DNN).

[0051] Figure 3 shows an example of a deep neural network.

[0052] The deep neural network shown in FIG. 3 is a multi-layer perceptron consisting of eight hidden layers and eight output layers. The multi-layer perceptron structure is expressed as a fully-connected neural network. In a fully-connected neural network, there is no connection between nodes located in the same layer, and only between nodes located in adjacent layers. A DNN has a fully-connected neural network structure and is composed of a combination of multiple hidden layers and activation functions, and can be usefully applied to grasp the correlation characteristics between inputs and outputs. Here, the correlation characteristics can mean the joint probability of inputs and outputs.

[0053] On the other hand, depending on how multiple perceptrons are connected to each other, it is possible to form a variety of artificial neural network structures that are different from the DNN mentioned above.

[0054] FIG. 4 shows an example of a convolutional neural network, and FIG. 5 shows a filter operation in a convolutional neural network.

[0055] In a DNN, the nodes located within one layer are arranged one-dimensionally, vertically. However, in Figure 4, we can assume that the nodes are arranged two-dimensionally, with w nodes horizontally and h nodes vertically (the convolutional neural network structure in Figure 4). In this case, a weight is added for each connection in the process of connecting an input node to a hidden layer, so a total of h × w weights must be considered. Since there are h × w nodes in the input layer, there are a total of h 2 ×w 2 weights are needed.

[0056] The convolutional neural network in FIG. 4 has a problem that the number of weights increases exponentially depending on the number of connections. Instead of considering all mode connections between adjacent layers, it assumes the existence of small filters and performs weighted sums and activation function calculations for the overlapping parts of the filters as shown in FIG. 5.

[0057] A filter has weights corresponding to the number of its size, and the weights can be learned so that a specific feature in the image can be extracted as a factor and output. In Figure 5, a 3x3 filter is applied to the top 3x3 region of the input layer, and the weighted sum and activation function for the corresponding node are calculated, resulting in an output value of z 22 Store in.

[0058] The filter scans the input layer, moves horizontally and vertically at a fixed interval, and performs weighted sum and activation function calculations, and positions the output value at the current filter position. Since this calculation method is similar to the convolution calculation for images in the field of computer vision, a deep neural network with this structure is called a convolutional neural network (CNN), and the hidden layer generated as a result of the convolution calculation is called a convolutional layer. In addition, a neural network with multiple convolutional layers is called a deep convolutional neural network (DCNN).

[0059] In the convolutional layer, the number of weights can be reduced by calculating a weighted sum at the node where the current filter is located, including only nodes located in the area covered by the filter. This allows one filter to be used to focus on features for a local area. This allows CNN to be effectively applied to processing image data where physical distance in a two-dimensional area is an important criterion. Meanwhile, CNN can apply multiple filters just before the convolutional layer, and generate multiple output results through the convolution operation of each filter.

[0060] On the other hand, depending on the attributes of the data, there may be data for which sequence characteristics are important. Considering the variability of the length of such sequence data and the context, elements in the data sequence are input one by one at each time step, and the output vector (hidden vector) of the hidden layer output at a specific time step is input together with the next element in the sequence. This method is applied to an artificial neural network and is called a recurrent neural network structure.

[0061] FIG. 6 shows a neural network structure in which a recursive loop exists.

[0062] Referring to FIG. 6, a recurrent neural network (RNN) calculates the elements (x1(t), x2(t), . . . , x) at a certain time t in a data sequence. d In the process of inputting the data (z1(t-1), z2(t-1), . . . , z H (t-1)) and apply the weighted sum and activation function. The reason for transmitting the hidden vector to the next point in time is that the information in the input vector at the previous point in time is considered to be accumulated in the hidden vector at the current point in time.

[0063] Referring to FIG. 6, the recurrent neural network operates on an input data sequence in a predetermined time order. d (t)) is input to the recurrent neural network, and the hidden vector (z1(1), z2(1), . . . , z H (1)) is the input vector (x1(2), x2(2), . . ., x d (2)) is input, and the hidden layer vectors (z1(2), z2(2), . . . , z H (2)) is determined. This process is repeated up to time 2, time 3, ..., time T.

[0064] FIG. 7 shows the operational structure of a recurrent neural network.

[0065] On the other hand, when multiple hidden layers are arranged in a recurrent neural network, it is called a deep recurrent neural network (DRNN). Recurrent neural networks are designed to be useful for applications to sequence data (e.g., natural language processing).

[0066] The neural network cores used as learning methods include DNN, CNN, RNN, as well as various deep learning techniques such as Restricted Boltzmann Machine (RBM), deep belief networks (DBN), and deep Q-Network, and can be applied to fields such as computer vision, speech recognition, natural language processing, voice / signal processing, and deriving optimal values ​​through large-volume data processing.

[0067] FIG. 8 is a block diagram of an AI device according to one embodiment of the present invention.

[0068] The AI ​​device 20 may include an electronic device including an AI module capable of performing AI processing, a server including the AI ​​module, etc. The AI ​​device 20 may be included in at least a part of the configuration of the menu providing device 100 shown in FIG. 9 and may be configured to perform at least a part of the AI ​​processing.

[0069] The AI ​​processing of the AI ​​device 20 may include all operations related to the control of the menu providing device 100 shown in Fig. 9 and all operations for providing a menu through artificial intelligence learning. For example, the menu providing device 100 may process / judge collected menu data through AI processing, generate a recommended menu, and recommend a menu. In addition, for example, the menu providing device 100 may process data acquired through interactions with other devices on the network, a public menu database, and other components provided in the user / food supplier terminal, to generate a menu and recommend a menu.

[0070] The AI ​​device 20 may include an AI processor 21, a memory 25 and / or a communication unit 27.

[0071] The AI ​​device 20 is a computing device capable of learning a neural network, and can be realized as various electronic devices such as a server, a desktop PC, a notebook computer, a tablet PC, etc. In the present invention, the AI ​​device 20 may be a menu providing device realized in the form of any of the various electronic devices.

[0072] The AI ​​processor 21 can train a neural network using a program stored in the memory 25. In particular, the AI ​​processor 21 can train a neural network for recognizing device-related data. Here, the neural network for recognizing device-related data can be designed to mimic a human brain structure on a computer and can include a plurality of network nodes having weights that mimic neurons of a human neural network. The plurality of network modes can exchange data with each other through connection relationships so as to mimic synaptic activity of neurons in which neurons exchange signals through synapses. Here, the neural network can include a deep learning model developed from a neural network model. In the deep learning model, the plurality of network nodes can exchange data with each other through convolution connection relationships while being located in different layers. Examples of neural network models include various deep learning techniques such as deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted Boltzmann machines (RBMs), deep belief networks (DBNs), and deep Q-networks, and can be applied in areas such as computer vision, speech recognition, natural language processing, and audio / signal processing.

[0073] Meanwhile, the processor performing the above-mentioned functions may be a general-purpose processor (e.g., a CPU), but may also be an AI-specific processor (e.g., a GPU) for artificial intelligence learning.

[0074] The memory 25 can store various programs and data necessary for the operation of the AI ​​device 20. The memory 25 can be realized by a non-volatile memory, a volatile memory, a flash memory, a hard disk drive (HDD), a solid state drive (SDD), or the like. The memory 25 is accessed by the AI ​​processor 21, and allows the AI ​​processor 21 to read / record / modify / delete / update data. The memory 25 can also store a neural network model (e.g., a deep learning model 26) generated by a learning algorithm for data classification / recognition according to an embodiment of the present invention.

[0075] Meanwhile, the AI ​​processor 21 may include a data learning unit 22 that learns a neural network for data classification / recognition. The data learning unit 22 can learn criteria regarding what kind of learning data to use and how to classify and recognize data using the learning data in order to determine data classification / recognition. The data learning unit 22 can learn the deep learning model by acquiring learning data to be used for learning and applying the acquired learning data to the deep learning model.

[0076] The data learning unit 22 can be manufactured in the form of at least one hardware chip and installed in the AI ​​device 20. For example, the data learning unit 22 can be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), and can also be manufactured as a part of a general-purpose processor (CPU) or a graphics processor (GPU) and installed in the AI ​​device 20. The data learning unit 22 can also be realized as a software module. When realized as a software module (or a program module including instructions), the software module can be stored in a non-transitory computer readable medium that can be read by a computer. In this case, at least one software module can be provided by an operating system or an application (application program).

[0077] The data learning unit 22 may include a learning data acquisition unit 23 and a model learning unit 24 .

[0078] The learning data acquiring unit 23 can acquire learning data necessary for a neural network model to classify and recognize data. For example, the learning data acquiring unit 23 can acquire menu data and / or sample data to be input to the neural network model as learning data.

[0079] The model learning unit 24 can learn the neural network model to have a judgment criterion regarding how to classify predetermined data using the acquired learning data. In this case, the model learning unit 24 can train the neural network model through supervised learning using at least a part of the learning data as a judgment criterion. Alternatively, the model learning unit 24 can train the neural network model through unsupervised learning in which the model learns by itself using the learning data without guidance to discover a judgment criterion. In addition, the model learning unit 24 can train the neural network model through reinforcement learning using feedback on whether the result of the situation judgment by learning is correct. Furthermore, the model learning unit 24 can train the neural network model using a learning algorithm including an error back-propagation method or a gradient decent method.

[0080] Once the neural network model is trained, the model training unit 24 can store the trained neural network model in a memory. The model training unit 24 can also store the trained neural network model in a memory of a server connected to the AI ​​device 20 via a wired or wireless network.

[0081] The data learning unit 22 may further include a learning data preprocessing unit (not shown) and a learning data selection unit (not shown) to improve the analysis results of the recognition model or to save resources or time required for generating the recognition model.

[0082] The learning data preprocessing unit can preprocess the acquired data so that the acquired data can be used for learning for situational judgment. For example, the learning data preprocessing unit can process the acquired data into a predefined format so that the model learning unit 24 can use the acquired learning data for learning for menu data recognition.

[0083] Furthermore, the learning data selection unit can select data necessary for learning from the learning data acquired by the learning data acquisition unit 23 or the learning data preprocessed by the preprocessing unit. The selected learning data can be provided to the model learning unit 24. For example, the learning data selection unit can recognize a specific field in the menu data collected via the network, and select only data related to the menu composition that is included in the specific field as learning data.

[0084] In addition, the data learning unit 22 may further include a model evaluation unit (not shown) to improve the analysis results of the neural network model.

[0085] The model evaluation unit inputs evaluation data to the neural network model, and if the analysis result output from the evaluation data does not satisfy a predetermined criterion, the model training unit 22 can be trained again. In this case, the evaluation data may be predefined data for evaluating the recognition model. As an example, the model evaluation unit may evaluate that the predetermined criterion is not satisfied if the number or ratio of evaluation data with inaccurate analysis results among the analysis results of the trained recognition model for the evaluation data exceeds a preset threshold.

[0086] The communication unit 27 can transmit the AI ​​processing result by the AI ​​processor 21 to an external electronic device. Here, the external electronic device can be defined as a menu providing device (FIG. 10, 100). On the other hand, the AI ​​device 20 can also be realized by functionally embedding it in a menu generating unit (FIG. 10, 130) provided in the menu providing device.

[0087] Meanwhile, the AI ​​device 20 shown in FIG. 8 has been described as being functionally divided into the AI ​​processor 21, memory 25, communication unit 27, etc., but it should be made clear that the above-mentioned components can be integrated into a single module called an AI module.

[0088] Hereinafter, a menu providing method according to an embodiment of the present invention will be briefly described with reference to the accompanying FIG.

[0089] FIG. 9 shows a menu providing system according to an embodiment of the present invention.

[0090] 9, the menu providing system disclosed in this specification may include a menu providing device 100, one or more user terminals 200, and an ingredient supplier terminal 300. The components shown in the figure are not essential, and the menu providing system may be realized with more or fewer components. Such components may be realized as hardware or software, or a combination of hardware and software.

[0091] The menu providing device 100 can collect publicly available menu data from a menu storage server 400 on the network, and store the data in a database. The public menu data is publicly available menu data such as menu data for nursery schools, kindergartens, elementary, middle, and high schools, and menu data for cafeterias in public hospitals and public institutions, and anyone can access and obtain the data via the network (see FIG. 13). The menu providing device 100 can also collect menu data created directly by a user who subscribes to the system, i.e., a nutritionist, from the user terminal 200 of the nutritionist, and store the data in a database.

[0092] The menu providing device 100 can generate a menu by learning the collected menu data using an artificial intelligence-based menu composition model, and transmit a recommended menu based on the generated menu to the user terminal 200. At this time, the menu providing device 100 can receive information on the menu and number of meals selected by the user from the user terminal 200. In addition, the menu providing device 100 can calculate the type of ingredients and the amount of ingredients required based on the received number of meals information and the menu, and transmit an order for ingredients for the calculated required amount for each type of ingredient to the ingredient supplier terminal 300.

[0093] Meanwhile, the above embodiment includes a process of generating a menu using an AI model and then selecting a specific menu from the recommended menu from the user terminal 200, but the present specification is not limited thereto. For example, the menu providing device 100 may generate a recommended menu based on a menu recommendation model that has already been learned, transmit the recommended menu to the user terminal 200, and calculate the amount of ingredients that need to be purchased based on the generated recommended menu. In this case, the process of selecting the recommended menu through the user terminal 200 and / or the process of inputting information on the number of meals may be omitted. As for the information on the number of meals, information on the number of meals already registered in the process of initially registering the service provided through the menu providing device 100 may be used.

[0094] The user terminal 200 can input information on the number of meals related to the recommended menu after checking the menu data received from the menu providing device 100. Meanwhile, the user (nutritionist) can input requirements for his / her menu composition and receive a menu that satisfies the requirements from the menu providing device 100. For example, according to one embodiment of the present specification, the menu providing device 100 can receive preference information of the nutritionist from the user terminal 200 and perform AI processing based on the input preference information and public data. The recommended menu generated as a result of the AI ​​processing can be different for each school. In this case, the workload of the nutritionist can be reduced by automatically transmitting the menu recommendation and the order of ingredients to the supplier through AI processing.

[0095] The food ingredient supplier terminal 300 can receive a request for quotation or an order for the purchase of ingredients for a menu selected by a user (nutritionist) from the menu providing device 100, and if an order is received after providing a quotation, the transaction to supply the relevant ingredients can be successfully completed.

[0096] The networks disclosed herein may be, for example, but not limited to, a wireless network, a wired network, a public network such as the Internet, a private network, a Global System for Mobile communication networks (GSM) network, a General Packet Radio Network (GPRN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a cellular network, a Public Switched Telephone Network (PSTN), a Personal Area Network, Bluetooth, Wi-Fi Direct, Near Field communication, Ultra-Wide band, a combination thereof, or any other network.

[0097] The menu providing device 100, one or more user terminals 200, and foodstuff supplier terminal 300 of the menu providing system are connected by the above-mentioned network and can exchange data with each other.

[0098] Hereinafter, a configuration of a menu providing device and a menu providing method according to an embodiment of the present invention will be described in detail with reference to the accompanying Figs. 10 to 17.

[0099] FIG. 10 is a block diagram showing the configuration of a menu providing device according to an embodiment of the present invention, and FIG. 11 shows an example of grouping users by region and providing menus and ingredients.

[0100] Figure 13 shows an example of an image of a generated menu, Figure 14 shows an example of an output screen providing detailed information about the recommended menu, Figure 15 shows an example of a user interface for modifying a menu to generate a customized menu, and Figure 16 shows another example of a user interface for modifying a menu to generate a customized menu.

[0101] 12 shows a table of some of the public menu data, which can be downloaded and used by anyone from a public data portal provided by the government. The menu providing device according to the embodiment of the present invention can learn the menu data collected from the portal and generate a menu optimized for the user's menu composition conditions or a menu that can be used for general purposes.

[0102] 10, the menu providing device 100 according to the embodiment of the present invention may include a communication unit 110, a menu data collection unit 120, a menu generation unit 130, a menu recommendation unit 140, an ingredient ordering unit 150, a menu database 160, a menu recording unit 170, and a menu correction unit 180. The illustrated components are not essential, and a menu providing system having more or fewer components may be realized. These components may be realized as hardware or software, or a combination of hardware and software.

[0103] The communication unit 110 can communicate with the user terminal 200 and the foodstuff supplier terminal 300 via a network to send and receive data.

[0104] The menu data collection unit 120 can connect to a network via the communication unit 110 to collect publicly available menu data, and store the collected menu data in the menu database 160.

[0105] The menu generation unit 130 can generate a menu by learning the collected menu data with an AI-based menu composition model. The menu generation unit 130 can generate a standard menu or a general-purpose menu by processing the collected menu data with the AI ​​menu composition model. The menu generation unit 130 can generate a menu by inputting materials such as the public menu data shown in FIG. 12 into the AI ​​menu composition model. For example, the AI ​​menu composition model can receive and process data such as the school, school lunch date, number of people to be lunched, dish name (composition of food in the menu), place of origin information, calorie information, nutritional information of the menu, and unit price of ingredients, and then generate a menu by date or by lunch target.

[0106] The menu recommendation unit 140 can send a recommended menu to the user terminal 200 based on the menu generated by the menu generation unit 130, and can receive information on the menu and number of meals selected by the user, i.e., the nutritionist, from the user terminal 200. The menu recommendation unit 140 can provide the standard menu or general-purpose menu generated by the menu generation unit 130 to one or more connected user terminals 200 in a batch according to the characteristics of the meal consumer.

[0107] When the menu recommendation unit 140 receives a confirmation message from the user terminal 200 regarding the recommended menu, it can generate a predicted image for the menu. The predicted image can be generated by synthesizing an image database stored for each food item, or by using a Generative Adversarial Network (GAN). Therefore, the user can effectively promote the menu to be provided to the meal recipients by utilizing the menu image sent from the menu providing device 100. For example, as shown in FIG. 13, when the menu recommendation unit 140 receives a confirmation message from the user regarding the menu selection for a menu consisting of brown rice, dried cabbage miso soup, pickled garlic, vegetable salad, bellflower salad, and boiled lotus root, the menu recommendation unit 140 reads out the images of the food confirmed in the image database already stored, and then generates an image 1300 by combining an image 1310 of a food tray, an image 1320 of brown rice, an image 1330 of dried cabbage miso soup, an image 1340 of pickled garlic, an image 1350 of a vegetable salad, an image 1360 of bellflower salad, and an image 1370 of boiled lotus root, i.e., an image of the menu selected by the user, and then transmits the image to the user terminal 200.

[0108] In addition, the menu recommendation unit 140 may provide the user with nutritional information and calorie information for each recommended menu. Furthermore, the menu recommendation unit 140 may provide the user with main color information for each food for each recommended menu. For example, as shown in FIG. 14, when a menu provided by the menu providing device 100 is output on the user terminal 200 in a state 1400, and the user selects a menu 1410 for dinner on November 6, 2020, the menu recommendation unit 140 may output a details screen 1420 for nutritional information, calorie information, and price information for the selected menu. The details screen 1420 may display characters representing the names of the dishes of the individual foods constituting the menu in the main color of the food. Furthermore, the details screen 1420 may display the nutritional components of the entire menu or the nutritional components of the individual foods in a predetermined color, thereby allowing the user to easily understand the recommended menu based on the color information and facilitating the modification of the menu. Therefore, the user can review the output nutrition information, calorie information, and cost information and then modify individual foods to change the nutrients, calories, and cost. Modification of individual foods in the recommended menu is performed by the menu modification unit 180, which can apply the modifications and transmit the modified menu to the user terminal 200 after receiving a modification command from the user for the recommended menu output on the user's screen.

[0109] In addition, the menu modification unit 180 of the menu providing device 100 according to the embodiment of the present invention can receive a modification command for the recommended menu from the user terminal 200, modify the recommended menu according to the modification command, and resend the modified menu to the user terminal 200. Furthermore, the menu modification unit 180 can provide a user interface 1500. A user can check the number of times a specific food is served in a certain period for the menu recommended by the menu recommendation unit 140 through the user interface 1500, and then change the food to another food in consideration of the frequency of serving the specific food. The menu modification unit 180 can receive a modification command for the recommended menu inputted through the user interface 1500, and modify the menu according to the corresponding command. For example, as shown in FIG. 15, if a user wants to change the "pickled cabbage kimchi" served as a side dish in the Chinese menu for November 6, 2020, to another side dish, the user can select 1510 "pickled cabbage kimchi" in the user interface 1500, delete 1520, search 1530 for a new side dish, and modify 1540 the menu to the new side dish found. In this case, when the user selects "pickled cabbage kimchi", the user interface 1500 displays 1550 the name of the food selected from the menu for a certain period of time that has been output, i.e., "pickled cabbage kimchi", in a certain color, thereby allowing the user to easily check the overlapping provision status.

[0110] In addition, the user interface 1500 may display the same food in the menu for the specific period selected by the user in the same color 1610, so that the user can see at a glance the overlapping state of the menu in the menu for the specific period. Therefore, the user can adjust the menu to provide various menus by correcting the overlapping menu in the menu for the specific period output to the user interface 1500 through the menu correction unit 180.

[0111] The food ingredient ordering unit 150 can determine the types of food ingredients that match the menu selected by the nutritionist, calculate the required quantities of each type of food ingredient according to the number of meals, and transmit the calculated quantities to the food ingredient supplier terminal 300.

[0112] In addition, the ingredient ordering unit 150 can predict the number of meals for a specific meal or a meal for a specific period, and then calculate the required quantity for each type of ingredient based on the predicted number of meals, and automatically transmit the calculated number of meals to the ingredient supplier terminal 300. The ingredient ordering unit 150 can predict the number of meals based on leftover information, remaining meal amount information, weather information, past meal number information, day of the week information, menu information, current event information, attendance information / attendance information, etc. If the cafeteria is a company, the ingredient ordering unit 150 can predict the number of meals for a specific date or a specific meal using the attendance information of the company, and if the cafeteria is an educational institution such as a school or kindergarten, the ingredient ordering unit 150 can predict the number of meals for a specific date or a specific meal using the attendance information of the educational institution. For example, the ingredient ordering unit 150 can predict the demand for a menu based on past leftover information and / or remaining meal amount information for a menu selected by recommendation or a menu modified by the user. Furthermore, the ingredient ordering unit 150 can predict the demand using weather information on the day the menu is provided. For example, if rain is forecast for the day kalguksu (a Korean noodle dish) is served, the number of meals of kalguksu served can be increased.

[0113] Furthermore, the ingredient ordering unit 150 can receive a purchase estimate for the required quantity by ingredient type from the ingredient supplier terminal 300 and provide it to the user terminal 200, and when the ingredient purchase estimate is approved by the user terminal 200, it can transmit a purchase order for the ingredient to the ingredient supplier terminal 300. In this case, the user can review the purchase estimate received from the ingredient supplier terminal 300 and then place a purchase order with the ingredient supplier who has offered the most suitable price, which has the effect of reducing ingredient purchasing costs.

[0114] For example, if the menu recommendation unit 140 provides the same menu to multiple user terminals 200 at once, the food supplier can receive a large number of orders for a small number of ingredients, which is advantageous in terms of inventory management, delivery, and costs. Such advantages can be the reason why users are willing to pay a fee to the menu provision service provider.

[0115] According to an embodiment, the menu recommendation unit 140 can configure a recommended menu based on the user's menu configuration conditions inputted via the user terminal 200, and then provide the configured menu to the user terminal 200.

[0116] The menu composition conditions can include at least one of the following: calories, nutrient composition, taste, sugar content, level of spiciness, combinations between foods, seasonal ingredients, number of side dishes, price of ingredients, event dishes, seasonal dishes, target students (meaning the people receiving school lunches, which can be classified as elementary school students, junior high school students, high school students, the general public, etc.), overlap of individual foods that make up the menu, number of meals provided per meal, preference, number of foods at the cafeteria, leftovers, price of each meal provided, color combinations of foods, allergy information regarding ingredients, information about the area where the school lunch is provided, and menu evaluation results from other users (evaluation results of the generated menu by nutritionists using the menu providing device in other locations). For example, when an input is received via the user terminal 200 requesting a menu of seasonal ingredients and three kinds of side dishes for a school lunch for children in the lower grades of elementary school as a seasonal dish for the season of the Chinese New Year, the menu recommendation unit 140 may compose a menu of one jujube, one small ginseng, glutinous brown rice, and half a 400g ginseng chicken soup as a main menu, cucumber mixed with chili peppers and pickled ginger as side dishes, and one slice of watermelon as a dessert, in consideration of the menu composition conditions from the menu data generated by the menu generation unit 130, and transmit the menu to the user terminal 200. For example, when the user examines the menu evaluation results of other users received via the user terminal 200 and commands that the menu evaluation results of other users having good results be reflected in the menu composition conditions, the menu recommendation unit 140 may compose a menu with foods having good menu evaluation results of other users, and provide it to the user. The overlap item of each food that composes the menu among the menu composition conditions means the number of times a specific food is served in a specific period, and when a user commands the menu composition to reflect the overlap of each food that composes the menu through the user terminal 200, the menu recommendation unit 140 can compose the menu so that the corresponding food is not served repeatedly in a predetermined period. Of course, even in this case, a long-term menu can be composed so that the overall statistical value of the menu composition does not deviate.The menu evaluation results of other users can be collected through a user community provided by the menu providing device 100, and the user community can collect evaluation results of users on menus selected or directly composed and shared by users, and provide the collected evaluation results to the users as a selection menu of menu composition conditions. The evaluation results can be classified by region and catering target, and can include various information such as order amount, leftovers, and customer preferences for a specific menu.

[0117] In addition, the menu generating unit 130 can generate a recommended menu through learning of collected menu data, as well as perform statistical analysis based on past menu data configured by the user, and use the analysis results in generating a recommended menu. The menu generating unit 130 can analyze the menu of the user during a predetermined period, add the provided statistical results for each food to the menu composition condition, and generate a menu based on the menu composition condition including the statistical results. The menu generating unit 130 can derive statistics for foods included in the corresponding elements of the menu composition condition for each element, and then configure the menu so that the composition of the menu to be generated later follows the derived results. For example, the menu can be configured so that the composition of the newly recommended menu maintains the existing statistical values ​​after analyzing individual foods such as bean sprout soup 39 times, Chinese cabbage kimchi 620 times, and stir-fried anchovy 65 times during a specific period on a statistical basis based on the menu composition condition. For example, if a menu was served last month that included stewed anchovies three times as a mild side dish, the menu can be structured so that stewed anchovies are served three times this month as a mild side dish.

[0118] Furthermore, according to the embodiment, the AI ​​processor can use a plurality of menu generation models to generate a menu. The plurality of menu generation models can be selected according to preference information input via the user terminal 200. For example, the menu generation model can be configured with at least one learning model that can provide different menus as output values ​​according to the target age of the school lunch. For example, when considering nutrients, calories, food amount, etc., the menus for elementary school students and high school students need to be configured differently, and even if the main menu is the same, different menu configuration models need to be used to configure the additional menus, amounts of ingredients, etc. differently.

[0119] The type of the menu generation model may be a model that provides, as an output value, a menu that can be configured by season in addition to the age of the target meal. Furthermore, the menu generation model may be a model that is trained to output an additional menu that is optimal for the type of main menu.

[0120] According to the embodiment, the menu recommendation unit 140 can create a menu by taking into consideration the current inventory information of ingredients held by the ingredient supplier from the ingredient supplier terminal 300 or the types of ingredients supplied as main ingredients, and then transmit the recommended menu to the user terminal 200. For example, the menu recommendation unit 140 can create and provide a menu by using more ingredients with a large inventory and less ingredients with a small inventory based on the current inventory information of ingredients received from the ingredient supplier terminal 300. In addition, the menu recommendation unit 140 can automatically manage the inventory of ingredients by reflecting the order quantity information of other users on the current inventory status of ingredients in real time, allowing the user to freely create a menu according to the current inventory status.

[0121] In addition, the menu recommendation unit 140 can compose a recommended menu based on information on the supply and demand status of ingredients and / or menu composition conditions. The information on the supply and demand status of ingredients can be determined based on information on fluctuations in supply and demand of ingredients, including the production volume of ingredients, the predicted production volume of ingredients, the import and export volume of ingredients, and the increase and decrease in demand for ingredients. The menu recommendation unit 140 can obtain information on the supply and demand status of ingredients from a website of agricultural product distribution information (e.g., KAMIS agricultural product distribution information) provided by a public institution such as the Korea Agricultural and Fisheries Products Trade Corporation. The menu recommendation unit 140 can obtain supply and demand status and price information of ingredients based on the agricultural product distribution information, and compose a menu at an optimal price based on the obtained information. Meanwhile, the production volume forecast information of ingredients can be predicted based on weather forecast information and / or past weather information, and the menu recommendation unit 140 can predict the supply status of ingredients based on the weather information and compose a menu based on the prediction result. For example, when a weather forecast predicts that a typhoon will cause severe damage to a specific agricultural product, the menu recommendation unit 140 does not select a menu using the specific agricultural product at the time when the supply situation of the specific agricultural product worsens, but creates a menu using other alternative ingredients, thereby reducing the cost of menu composition and contributing to the stabilization of the price of the agricultural product. In addition, when the harvest situation of a specific agricultural product is good and the agricultural product is overproduced, the menu recommendation unit 140 creates a menu using the specific agricultural product as an ingredient and provides it to the user, thereby not only reducing the cost of school lunches but also promoting the consumption of the agricultural product and contributing to the stabilization of the market. In other words, the menu recommendation unit 140 creates a menu based on the supply and demand status of ingredients, including the current supply status of ingredients, future supply forecast results, demand status of ingredients, and demand forecast results of ingredients, thereby contributing to the stabilization of the market for ingredients as well as the adjustment of the target school lunch cost.

[0122] According to the embodiment, the communication unit 110 receives feedback on the recommended menu from the user terminal 200, the menu data collection unit 120 updates the menu database based on the feedback, and the menu generation unit 130 generates an improved menu reflecting the updated menu database and the feedback. In addition, the menu generation unit 130 can learn an AI-based menu composition model that generates a menu reflecting the feedback of the user terminal 200, and update the menu composition model.

[0123] According to an embodiment, the menu recommendation unit 140 may group one or more users by region based on the location of an ingredient supplier and recommend the same menu to user terminals belonging to the same group. Also, the ingredient order unit 150 may derive the types of ingredients corresponding to the same menu and the number of meals according to the same menu, calculate the required quantity for each of the derived types of ingredients, and then transmit a request for ingredient estimates and an order for ingredient purchase to the ingredient supplier terminals assigned to the same group.

[0124] The menu recording unit 170 can record menus composed by the user, such as the user himself or herself, and can also read out the recorded portion before using the device. The menu generating unit 130 can learn the user's menu composition pattern based on the user's composed menus recorded in the menu recording unit 170, and then generate a menu based on the menu data learning result and the menu composition pattern learning result. The user can store the menus composed by the user as favorites through the favorites menu of the menu recording unit 170, and can read the favorites stored in the menu recording unit 170 and use them when composing a new menu as needed.

[0125] The menu generation unit 130 and the menu recommendation unit 140 can analyze menu data through the artificial intelligence learning and artificial intelligence processing shown in Figures 1 to 8 to generate standard menus and optimal menus, and can generate and recommend menus according to user requests.

[0126] For example, referring to FIG. 11, if the food ingredients suppliers are located in three regions, the menu recommendation unit 140 can group the multiple user terminals into three groups A, B, and C taking into account the locations of the 200 food ingredients suppliers, and then match the food ingredients supplier terminals located close to each group. Thus, the menu recommendation unit 140 can match the food ingredients supplier terminal 300-1 with the user terminal group A, match the food ingredients supplier terminal 300-2 with the user terminal group B, and match the food ingredients supplier terminal 300-3 with the user terminal group C, so that the matched users and food ingredients suppliers can supply food ingredients for the same menu. In this way, the food ingredients supplier can save time in delivering food ingredients and can deliver efficiently, resulting in a cost reduction effect. Such cost reduction has the effect of bringing economic benefits to the user as well, since the unit price of the food ingredients can be reduced.

[0127] FIG. 17 shows the flow of data between components of a menu provision system according to an embodiment of the present invention.

[0128] A menu providing method of the menu providing device 100 that includes a menu data collecting unit 120, a menu generating unit 130, a menu recommending unit 140, and an ingredient ordering unit 150 and recommends a menu will be described with reference to the data or signal flow between the components of FIG.

[0129] First, the menu data collection unit 120 can collect menu data made public via a network and store it in a database (S100).

[0130] Next, the menu generating unit 130 can generate a standard menu or a common menu by learning the collected menu data (S110).

[0131] The menu recommendation unit 140 can send a recommended menu to the user terminal 200 based on the menu generated by the menu generation unit 130 (S120), and can receive information regarding the selected menu and number of meals from the user terminal 200 (S130).

[0132] Next, the ingredient ordering unit 150 determines the types of ingredients that match the selected menu, calculates the required quantities of each ingredient type according to the number of meals (S140), and requests an estimate for purchasing ingredients from the ingredient supplier terminal 300 based on the calculated required quantities of ingredients (S150).

[0133] When the ingredient supplier terminal 300 is requested by the menu providing device 100 for an ingredient purchasing estimate, it creates an estimate for the requested ingredients and replies (S160), and the menu providing device 100 can provide the estimate received from the ingredient supplier terminal 300 to the user terminal 200 (S170).

[0134] When the user approves the quote that he / she likes best after reviewing the quotes (S180), the ingredient ordering unit 150 of the menu providing device 100 transmits an ingredient purchase order for the quote to the ingredient supplier terminal 300 that provided the quote, and orders the ingredients (S190). At this time, the user terminal 200 can receive from the menu providing device 100 a number of ingredient purchase quotations returned from the multiple ingredient supplier terminals 300, so that the user can compare multiple quotations and select the quote that he / she likes best.

[0135] When the menu provision system has completed provision of the menu and supply of ingredients, the menu provision device 100 can bill the user terminal 200 and the ingredient supplier terminal 300 for the service fee, and can also handle payment of the cost for the supply of ingredients between the user terminal 200 and the ingredient supplier terminal 300.

[0136] In the above description, steps S100 to S190 may be further divided into additional operations or combined into fewer operations depending on the embodiment of the present invention. Also, some operations may be omitted or the order of operations may be changed as necessary.

[0137] The term "module" as used herein (e.g., controller, etc.) may refer to a unit including, for example, one or a combination of two or more of hardware, software, or firmware. The term "module" may be used interchangeably with terms such as unit, logic, logical block, component, or circuit. The term "module" may be the smallest unit or a part thereof of an integrated component. The term "module" may also be the smallest unit or a part thereof that performs one or more functions. The term "module" may be realized mechanically or electronically. For example, the term "module" may include at least one of ASIC (Application-Specific Integrated Circuit) chips, FPGAs (Field-Programmable Gate Arrays), or programmable-logic devices that perform a certain operation, whether known or developed in the future.

[0138] At least a portion of the apparatus (e.g., modules or functions thereof) or methods (e.g., operations) according to various embodiments may be implemented as instructions stored in a computer-readable storage medium, for example in the form of a program module. When the instructions are executed by a processor, the one or more processors can perform a function corresponding to the instructions. The computer-readable storage medium may be, for example, a memory.

[0139] The computer readable storage medium / computer readable recording medium may include a hard disk, a floppy disk, a magnetic medium (e.g., a magnetic tape), an optical medium (e.g., a compact disc read only memory (CD-ROM)), a digital versatile disc (DVD), a magneto-optical medium (e.g., a floptical disk), a hardware device (e.g., a read only memory (ROM), a random access memory (RAM), or a flash memory), etc. Also, the program instructions may include not only machine code, such as that generated by a compiler, but also high-level language code that may be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the various embodiments, and vice versa.

[0140] The modules or program modules according to various embodiments may include at least one or more of the above-mentioned components, some of them may be omitted, or additional components may be included. Operations performed by the modules, program modules, or other components according to various embodiments may be performed sequentially, in parallel, iteratively, or in a heuristic manner. Also, some operations may be performed in other orders, omitted, or other operations may be added.

[0141] The term "a" as used herein is defined as one or more than one. Additionally, the use of introductory phrases such as "at least one" and "one or more" in the claims should not be construed as implying that the introduction of another claim element by the indefinite phrase "a" limits any particular claim containing that claim element so introduced to an invention containing only one such element, even if the same claim contains introductory phrases such as "at least one" and "one or more" and the indefinite phrase "a."

[0142] Unless otherwise expressly stated, terms such as "first" and "second" are used to arbitrarily distinguish between the elements that such terms describe. Thus, these terms are not necessarily intended to indicate a temporal or other priority of such elements, nor does the mere fact that certain measures are recited in different claims from one another indicate that a combination of such measures cannot be advantageously used. Thus, these terms are not necessarily intended to indicate a temporal or other priority of such elements. The mere fact that certain measures are recited in different claims from one another does not indicate that a combination of such measures cannot be advantageously used.

[0143] An arrangement of components to achieve the same function is effectively "associated" such that the desired functionality is achieved. Thus, any two components that are combined to achieve a particular functionality can be considered to be "associated" with one another such that the desired functionality is achieved, regardless of structure or intervening components. Similarly, two components that are so associated can be considered to be "operably connected" or "operably coupled" with one another to achieve the desired functionality.

[0144] Moreover, one of ordinary skill in the art will recognize that boundaries between the functionality of the operations described above are merely exemplary. Multiple operations may be combined in a single operation, a single operation may be distributed among additional operations, and operations may perform with at least partial overlap in time. Also, alternative embodiments may include multiple instances of a particular operation, and the order of operations may be altered in various other embodiments. However, other modifications, variations, and alternatives are possible. Accordingly, the detailed description and drawings should be regarded in an illustrative and not a restrictive sense.

[0145] The phrase "may X" indicates that condition X may be met. The phrase also indicates that condition X may not be met. For example, a reference to a system that includes a particular component must also include scenarios in which the system does not include the particular component. For example, a reference to a method that includes a particular operation must also include scenarios in which the method does not include the particular component. However, as yet another example, a reference to a system that is configured to perform a particular operation must also include scenarios in which the system is not configured to perform the particular task.

[0146] The terms "including," "having," "comprising," "consisting," and "consisting essentially of" are used interchangeably. For example, any method may include at least the acts included in the drawings and / or description, and may include only the acts included in the drawings and / or description.

[0147] Those of ordinary skill in the art will recognize that the boundaries between logic blocks are merely exemplary, and that alternative embodiments may merge logic blocks or circuit elements, or provide alternative decompositions of functionality onto various logic blocks or circuit elements. Thus, it should be understood that the architectures illustrated herein are merely exemplary, and that in fact many other architectures which achieve the same functionality may be implemented.

[0148] Also, for example, in one embodiment, the illustrated examples may be implemented as circuits located on a single integrated circuit or within the same device. Alternatively, the examples may be implemented as any number of separate integrated circuits or separate devices interconnected with each other in any suitable manner, and other variations, modifications, variations, and alternatives are possible. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense.

[0149] Furthermore, for example, the above examples or portions thereof may be implemented as software or code representations of physical circuits or logical representations translatable into physical circuits, such as in any suitable type of hardware engineering language.

[0150] Furthermore, the present invention is not limited to physical devices or units implemented in non-programmable hardware, but may be applied to programmable devices or units that can perform desired device functions by operating in accordance with appropriate program code, such as mainframes, minicomputers, servers, workstations, personal computers, notepads, personal digital assistants (PDAs), electronic games, automobiles and other embedded systems, mobile phones and various other wireless devices, etc., which are generally referred to herein as "computer systems."

[0151] The systems, apparatus, or devices referred to in this specification include at least one hardware component.

[0152] A connection as described herein may be any type of connection suitable for transmitting signals to or from a respective node, unit or device, for example via an intermediate device. Thus, unless implicitly or otherwise stated, a connection may be, for example, a direct connection or an indirect connection. A connection may be described or depicted with reference to a single connection, multiple connections, unidirectional connections or bidirectional connections. However, different embodiments may vary the implementation of a connection. For example, instead of a bidirectional connection, a separate unidirectional connection may be used, or vice versa. Also, multiple connections may be replaced by a single connection that transmits multiple signals sequentially or in a time multiplexed manner. Similarly, a single connection that transmits multiple signals may be separated into multiple connections that transmit subsets of such signals. Thus, many options exist for transmitting signals.

[0153] Those of ordinary skill in the art will recognize that the boundaries between logic blocks are merely exemplary, and that alternative embodiments may merge logic blocks or circuit elements, or provide alternative decompositions of functionality onto various logic blocks or circuit elements. Thus, it should be understood that the architectures illustrated herein are merely exemplary, and that many other architectures may be realized which in fact achieve the same functionality.

[0154] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or acts listed in the claim.

[0155] As above, preferred embodiments of the technology of the present specification have been described with reference to the accompanying drawings. Here, the terms and words used in the specification and claims should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted as meanings and concepts that are in line with the technical ideas of the present invention. The scope of the present invention is not limited to the embodiments disclosed in the specification, and the present invention can be modified, changed, or improved in various forms within the scope of the ideas of the present invention and the scope of the claims.

Claims

1. A menu data collection unit that collects menu data via a network and stores the data in a menu database; A menu recording unit that records a user-configured menu configured by a user as a favorite menu; A menu generation unit that learns the menu data, learns a menu composition pattern of a user based on the user-configured menu, and generates a menu based on the learning result of the menu data and the learning result of the menu composition pattern; A menu recommendation unit that sends a recommended menu to a user terminal based on the generated menu and receives information on the selected menu and the number of meals from the user terminal; A menu modification unit that receives a modification command for the recommended menu from the user terminal, modifies the recommended menu according to the modification command, and transmits the modified menu to the user terminal; an ingredient ordering unit that derives the types of ingredients according to the selected menu, calculates the required quantities of each ingredient type according to the number of meals, and transmits the calculated quantities to an ingredient supplier terminal; Including, the menu recommendation unit displays characters representing the names of the dishes of the individual foods constituting the recommended menu in a primary color specific to the food, and outputs to the user terminal a detailed screen displaying nutritional components of the entire recommended menu or nutritional components of each food in a predetermined color; The menu recommendation unit generates an image of the selected menu based on information about the selected menu received from the user terminal, and transmits the generated image of the menu to the user terminal. Offering device.

2. The menu recommendation unit includes: The recommended menu is composed based on the menu composition conditions inputted via the user terminal; The menu composition conditions are: The menu providing device of claim 1, characterized in that it is configured to include at least one of the following information: calories of the foods that make up the menu, nutrient composition, taste, sugar content, level of spiciness, combinations between foods, seasonal ingredients, number of side dishes, price of ingredients, event dishes, seasonal dishes, meals served, overlap of individual foods that make up the menu, number of meals served, preference, number of menu items at the cafeteria, leftovers, price of meals, food color combinations, allergy information regarding ingredients, regional information, and menu evaluation results of other users.

3. The menu recommendation unit includes: The menu providing device according to claim 1 , further comprising a step of transmitting a recommended menu to the user terminal based on a statistical result of accumulated menu configurations.

4. The menu recommendation unit includes: The menu providing device according to claim 2, characterized in that the recommended menu is constructed based on ingredient inventory information held by the ingredient supplier, information on ingredients to be supplied as main ingredients, ingredient supply and demand status information, and the menu construction conditions, all of which are provided from the ingredient supplier terminal.

5. The food supply and demand status information is 5. The menu providing device according to claim 4, wherein the menu is determined based on information on fluctuations in food supply and demand, including the production volume of food ingredients, the predicted production volume of food ingredients, the import and export volumes of food ingredients, and the increase or decrease in demand for food ingredients.

6. The communication unit receives feedback on the recommended menu from the user terminal, The menu data collection unit updates the menu database based on the feedback; The menu providing device according to claim 1 , wherein the menu generating unit generates a menu based on an updated menu database and the feedback, and updates a model for generating the menu based on the feedback.

7. The ingredient ordering unit includes: receiving a foodstuff purchase estimate for the required quantity by foodstuff type from the foodstuff supplier terminal and providing the estimate to the user terminal; 2. The menu providing device according to claim 1, wherein when the ingredient purchase estimate is approved from the user terminal, an order for ingredient purchase is transmitted to the ingredient supplier terminal.

8. The menu recommendation unit groups the user terminals by region based on the locations of foodstuff suppliers, and recommends the same menu to user terminals belonging to the same group; The menu providing device according to claim 1, characterized in that the ingredient ordering unit derives the types of ingredients corresponding to the same menu and the number of meals according to the same menu, calculates the required quantity for each derived type of ingredient, and transmits it to the ingredient supplier terminal assigned to the same group.

9. The ingredient ordering unit includes: Predict the number of meals for a selected menu, 2. The menu providing device according to claim 1, further comprising a step of calculating the quantity of ingredients required based on the predicted number of meals and transmitting the calculated quantity of ingredients to the ingredient supplier terminal.

10. A menu providing method for a menu providing device that includes a menu data collecting unit, a menu generating unit, a menu recommending unit, a menu correcting unit, and an ingredient ordering unit and recommends a menu, A step in which the menu data collection unit collects menu data via a network; A step of recording the user-configured menu configured by the user as a favorite menu in a menu recording unit of the menu providing device; The menu generation unit learns the menu data, learns a menu configuration pattern of the user based on the user-configured menu, and generates a menu based on the learning result of the menu data and the learning result of the menu configuration pattern; sending a recommended menu to a user terminal based on the menu generated by the menu recommendation unit; receiving menu selection information or menu modification information and information regarding the number of meals regarding the recommended menu from the user terminal; The food ordering unit derives the types of food ingredients according to the selected menu information or the revised menu information, calculates the required quantity of each type of food ingredient according to the number of meals, and transmits the calculated quantity to a food ingredient supplier terminal; The menu recommendation unit displays characters representing names of individual foods constituting the recommended menu in a primary color specific to the food, and outputs a detailed screen to the user terminal, the detailed screen displaying nutritional components of the entire recommended menu or nutritional components of each food in a predetermined color; The menu recommendation unit generates an image of the selected menu based on information about the selected menu received from the user terminal, and transmits the generated image of the menu to the user terminal; A menu providing method for a menu providing device comprising:

11. The menu recommendation unit configures the recommended menu based on a menu configuration condition of the user inputted via the user terminal, The menu composition conditions include at least one of the following: calories, nutrients, taste, sugar content, level of spiciness of the foods that compose the menu, combinations between foods, seasonal ingredients, number of side dishes, prices of ingredients, event dishes, seasonal dishes, meals to be served, duplication of individual foods that compose the menu, number of meals provided, preference, number of menu items at the cafeteria, leftovers, price of meals, color combinations of foods, allergy information about ingredients, area information, menu evaluation results of other users, and information on the supply and demand status of ingredients; The menu providing method of the menu providing device described in claim 10, characterized in that the food ingredient supply and demand status information is determined based on food ingredient supply and demand fluctuation information including the production volume of food ingredients, the predicted production volume of food ingredients, the import and export volume of food ingredients, and the increase or decrease in demand for food ingredients.

12. The menu recommendation unit includes: The method of claim 11, further comprising transmitting the recommended menu to the user terminal based on a statistical result of the accumulated menu composition.

Images