Method and apparatus for recommending recipe, ingredient management system, computer readable storage medium

Abstract

The application relates to the technical field of intelligent catering, and discloses a method for recommending recipes, which comprises the following steps: determining a recipe set to be recommended according to environment information and food material reserve information; determining a user representation according to user information and user behavior; predicting the click rate of each recipe in the recipe set to be recommended according to the user representation; and recommending recipes to the user according to the click rate of each recipe. In this way, the recipes recommended to the user not only ensure that the applied food materials are locally easy to purchase, cheap, fresh and affordable, but also effectively avoid the problems of cost increase or taste reduction caused by the use of non-seasonal or local food materials. Therefore, the recipes recommended to the user not only meet the personalized needs of the user, but also integrate regional characteristics and practicality considerations, so that the recommended recipes are more accurate. The application also discloses a device for recommending recipes, a food material management system and a computer readable storage medium.

Description

Technical Field

[0001] This application relates to the field of intelligent catering technology, such as a method and apparatus for recommending recipes, an ingredient management system, and a computer-readable storage medium. Background Technology

[0002] As living standards continue to improve, people are paying more and more attention to food and dishes. Although there are many cooking guides online and the food delivery industry can provide a variety of dishes, many people still often feel confused and lost when faced with choices for their three meals a day.

[0003] To better suit users' tastes and preferences when dining out, a recipe recommendation method has been disclosed. Applied to a recipe recommendation system, the method includes: responding to a recipe recommendation request from a target user; acquiring recommendation audio data sent by the target user and extracting feature information from the audio data; determining the target user's user identifier and recipe requirement information in the recipe recommendation system based on the feature information, and acquiring historical recommendation data corresponding to the target user stored in the recipe recommendation system based on the user identifier; inputting the recipe requirement information and the historical recommendation data into a pre-trained recipe tag model to generate a target recipe tag set, the target recipe tag set including multiple tags for recipe generation; retrieving target recipes matching the target recipe tag set from a recipe database and recommending the target recipes to the target user; wherein the recipe database records multiple recipes consisting of at least one dish.

[0004] In the process of implementing the embodiments of this disclosure, at least the following problems were found in the related art:

[0005] While related technologies can generate target recipes based on feature information in user-generated audio data and recipe tag models to balance users' dietary nutrition, the ingredients used in the generated recipes are often limited by many factors, making them difficult to cook and thus difficult to accurately meet the actual needs of each user.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0008] This disclosure provides a method and apparatus for recommending recipes, an ingredient management system, and a computer-readable storage medium to improve the accuracy of recipe recommendations for users.

[0009] In some embodiments, the method for recommending recipes includes: determining a set of recipes to be recommended based on environmental information and ingredient reserve information; determining user representation based on user information and user behavior; predicting the click-through rate of each recipe in the set of recipes to be recommended based on the user representation; and recommending recipes to the user based on the click-through rate of each recipe.

[0010] In some embodiments, the apparatus for recommending recipes includes a processor and a memory storing program instructions, the processor being configured to execute the aforementioned method for recommending recipes when the program instructions are executed.

[0011] In some embodiments, the food management system includes: a food management system body; and the aforementioned device for recommending recipes, which is installed on the food management system body.

[0012] In some embodiments, the computer-readable storage medium stores program instructions that, when executed, perform the aforementioned method for recommending recipes.

[0013] The method and apparatus for recommending recipes, the food ingredient management system, and the computer-readable storage medium provided in this disclosure can achieve the following technical effects:

[0014] First, a set of recipes to be recommended is determined based on environmental and ingredient availability information. This ensures that the recipes contain ingredients that the user can use and that are seasonal, affordable, and readily available in the local market, meeting objective cooking conditions. Then, user expressions are determined based on user information and behavior to understand the user's current interests. Next, the click-through rate of each recipe in the recommended set is predicted based on these user expressions, indicating the user's level of interest in each recipe. Finally, recipes are recommended to the user based on their click-through rates. This approach ensures that the recommended recipes use locally available, affordable, fresh, and reasonably priced ingredients, effectively avoiding potential cost increases or compromised taste caused by using out-of-season or imported ingredients. Thus, the recommended recipes satisfy the user's personalized needs while incorporating regional characteristics and practical considerations, making the recommended recipes more accurate.

[0015] The above general description and the description below are exemplary and illustrative only and are not intended to limit this application. Attached Figure Description

[0016] One or more embodiments are illustrated by way of example with reference to the accompanying drawings. These illustrations and drawings do not constitute a limitation on the embodiments. Elements having the same reference numerals in the drawings are shown as similar elements. The drawings are not to be scaled. And wherein:

[0017] Figure 1 This is a schematic diagram illustrating the collection of food information by the food management system provided in this embodiment of the disclosure;

[0018] Figure 2 This is a schematic diagram of the food management system environment provided in this embodiment of the disclosure;

[0019] Figure 3 This is a schematic diagram of a method for recommending recipes provided in an embodiment of this disclosure;

[0020] Figure 4 This is a schematic diagram illustrating the determination of a set of recipes to be recommended based on environmental information and food reserve information, provided in an embodiment of this disclosure.

[0021] Figure 5 This is a schematic diagram illustrating the determination of user representation based on user information and user behavior, provided in an embodiment of this disclosure.

[0022] Figure 6 This is a schematic diagram of another method for recommending recipes provided in an embodiment of this disclosure;

[0023] Figure 7 This is a schematic diagram of another method for recommending recipes provided in an embodiment of this disclosure;

[0024] Figure 8 This is a schematic diagram of another method for recommending recipes provided in an embodiment of this disclosure;

[0025] Figure 9 This is a schematic diagram of an apparatus for recommending recipes provided in an embodiment of this disclosure;

[0026] Figure 10 This is a schematic diagram of another device for recommending recipes provided in an embodiment of this disclosure;

[0027] Figure 11 This is another schematic diagram of a food management system environment provided in an embodiment of this disclosure. Detailed Implementation

[0028] To provide a more detailed understanding of the features and technical content of the embodiments of this disclosure, the implementation of the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are for illustrative purposes only and are not intended to limit the embodiments of this disclosure. In the following technical description, for ease of explanation, several details are used to provide a full understanding of the disclosed embodiments. However, one or more embodiments may still be implemented without these details. In other cases, well-known structures and devices may be simplified in their depiction to simplify the drawings.

[0029] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0030] Unless otherwise stated, the term "multiple" means two or more.

[0031] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0032] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0033] The term "correspondence" can refer to an association or binding relationship. The correspondence between A and B means that there is an association or binding relationship between A and B.

[0034] Combination Figure 1 As shown, this disclosure provides a food ingredient management system capable of collecting and storing food ingredient information. The collection methods include:

[0035] ① User-uploaded information: Users can input information about their home food supplies, including the type, quantity, and freshness of the ingredients, into the food management system to ensure the real-time and accuracy of the information. This information will be stored on the food management system's local machine or cloud server for easy access and use at any time.

[0036] ② Proactive Data Collection: Utilizing cameras and odor detectors integrated into food storage devices (such as smart refrigerators, smart freezers, and smart cabinets), information on food stored in the home is collected in real-time or periodically and uploaded to the food management system. The food management system meticulously categorizes food items based on multiple dimensions, including type, quantity, freshness, color, size, shape, and origin, and stores this information to ensure users can always monitor the latest status of their food. The system can also use intelligent algorithms to analyze and determine if food is in optimal storage condition, issuing timely reminders. It also identifies expired food and suitable storage conditions, prompting users to adjust storage conditions to extend shelf life. Furthermore, it reminds users to pay attention to food expiration dates, preventing waste and food safety risks.

[0037] ③ Third-Party Partnerships: Establish communication partnerships with local supermarkets, markets, and third-party applications. Upload ingredient information to the cloud server via data interfaces or APIs (Application Programming Interfaces) for real-time updates. The ingredient management system receives data from the cloud server in real time, including but not limited to prices, inventory, and promotional information. This allows users to stay informed about market trends for ingredients, thus improving the timeliness and comprehensiveness of ingredient data.

[0038] Given the advanced and efficient modern logistics system, off-season vegetables and imported fruits have increasingly become the norm in local markets. To keep pace with this trend and ensure the timeliness and comprehensiveness of food information, the food management system will implement a dynamic database update strategy, capturing and integrating the latest food information in real time. Through an efficient data processing mechanism, both newly available local specialties and exotic fruits and vegetables from afar will be quickly incorporated into the system's view and reflected in the database instantly. This initiative aims to provide a wider range of choices for the system's recipe recommendations and offer users a rich and dynamic selection of food, ensuring that users can always stay abreast of market dynamics and enjoy the freshest and most comprehensive food information.

[0039] ④ Local Collection: Information on unique ingredients from various regions, such as local specialties, major crops, and seasonal fruits and vegetables, is collected and organized through professional teams or community contributions. This data is uploaded to the ingredient management system's database, effectively compensating for the shortcomings of local natural collections and third-party data sources in terms of specialty ingredients. This enriches the diversity of the ingredient database, providing users with a more comprehensive selection. Users can share their own ingredient information and cooking experiences, increasing data diversity and real-time updates, while also enhancing user interaction and engagement.

[0040] Optionally, the food management system has a voice module to provide voice reminders to the user.

[0041] Optionally, the food management system has a touchscreen to interact with users, facilitating operations such as searching for ingredients and selecting recipes.

[0042] Optionally, the food ingredient management system can utilize deep learning algorithms (such as convolutional neural networks, recurrent neural networks, etc.) to more accurately capture users' complex preferences and the complex relationships between ingredients, thereby providing more accurate and personalized recommendations.

[0043] Optionally, the food ingredient management system utilizes sentiment analysis and semantic understanding technologies to better understand users' emotions and intentions during interactions, thereby making recommendations more personalized and human-centered. For example, when a user expresses a preference for a certain ingredient, the system can analyze the degree of this preference and adjust its recommendation strategy accordingly.

[0044] Combination Figure 2 As shown, the implementation environment may include a food management system 10, a router 20, and a cloud server 30.

[0045] The food management system 10 includes a Wi-Fi (Wireless Fidelity) module and an NFC module. The Wi-Fi module is a transmission conversion product, enabling connection to the internet; the NFC module is a near-field communication product. The Wi-Fi and NFC modules are integrated into the same module, and the module program can obtain information such as the connection status between the Wi-Fi module and the router 20. The food management system 10 can be used for smart home devices such as smart TVs, smart refrigerators, and smart speakers that integrate both Wi-Fi and NFC modules.

[0046] Router 20 is a device that connects various local area networks (LANs) and wide area networks (WANs) within the Internet. It automatically selects and sets routes based on channel conditions, sending signals in the optimal path and sequence. The food management system 10 can establish a communication connection with the cloud server 30 through router 20.

[0047] The cloud server 30 can be a single server, a server cluster consisting of several servers, or a cloud computing service center. This disclosure does not limit the scope of the embodiments.

[0048] It should be understood that Figure 2 The number of food management systems, routers, and cloud servers shown is merely illustrative; any number of food management systems, routers, and servers can be used depending on actual needs.

[0049] It should be noted that the method for configuring network access for the food management system provided in this disclosure is generally executed jointly by the food management system, the router, and the cloud server. Correspondingly, the network access device for home appliances is generally installed in the food management system, the router, and the cloud server.

[0050] Combination Figure 3 As shown, this disclosure provides a method for recommending recipes, including:

[0051] S101, the food ingredient management system determines the set of recipes to be recommended based on environmental information and food ingredient reserve information.

[0052] S102, the food ingredient management system determines the user's representation based on user information and user behavior.

[0053] S103, the ingredient management system predicts the click-through rate of each recipe in the set of recipes to be recommended based on user feedback.

[0054] S104, the ingredient management system recommends recipes to users based on the click-through rate of each recipe.

[0055] Users can send voice messages to the food ingredient management system to request recipe recommendations. The system responds to these requests and recommends recipes accordingly. Alternatively, the system can automatically recommend recipes at preset times, such as 6:30 AM for breakfast, 11:30 AM for lunch, and 6:00 PM for dinner.

[0056] First, the food ingredient management system obtains environmental information via the network and accesses data stored in the cloud server's database or its own storage to retrieve food ingredient reserve information. Environmental information includes location, season, and weather. Food ingredient reserve information includes the types and quantities of ingredients available at the user's home, nearby supermarkets, and farmers' markets. Environmental information reflects the ingredients generally available in the current area. Food ingredient reserve information indicates the ingredients the user can use to prepare dishes. Based on the environmental and food ingredient reserve information, a set of recommended recipes is determined. This set consists of dishes made with ingredients available to the user and that are in season, affordable, and of good quality in the current local market. It is understood that the set of recommended recipes includes multiple recipes. Knowledge graph technology is used to associate the entities of the recommended recipes with their associated entity information (such as ingredients, cuisine, and flavor). Through single-hop aggregation, the relevant information of each recommended recipe is aggregated to form an initial representation of the recommended recipe.

[0057] The food ingredient management system matches user requests from a database to determine user information, such as gender, age, taste preferences, and health status—unique characteristics of each user. It also acquires user behavior data, such as browsing behavior (books, videos, etc.), which reflects the user's current interests. Based on this user information and behavior—combining user characteristics and current interests—a user representation is determined to indicate the user's interest in recipes.

[0058] Based on user feedback, predict the click-through rate (CTR) of each recipe in the recommended recipe set. A higher CTR indicates a greater probability that the user will view that recipe, meaning a higher level of interest in it. Thus, recipes can be recommended to users based on the predicted CTR of each recipe.

[0059] The method for recommending recipes provided in this disclosure first determines a set of recipes to be recommended based on environmental and ingredient availability information. This ensures that the recipes contain ingredients that the user can use and that are seasonal, affordable, and readily available in the local market, meeting objective cooking conditions. Then, user representations are determined based on user information and behavior to understand the user's current interests. Next, the click-through rate of each recipe in the set is predicted based on these user representations, thus predicting the user's level of interest in each recipe. Finally, recipes are recommended to the user based on their click-through rates. This ensures that the recommended recipes use locally sourced, readily available, affordable, fresh, and reasonably priced ingredients, effectively avoiding potential cost increases or compromised taste caused by using out-of-season or imported ingredients. Therefore, the recommended recipes satisfy the user's personalized needs while incorporating regional characteristics and practical considerations, making the recommended recipes more accurate.

[0060] Combination Figure 4 As shown in S101, the food ingredient management system determines the set of recipes to be recommended based on environmental information and food ingredient reserve information, including:

[0061] S111, the food management system determines local seasonal ingredients based on environmental information.

[0062] S121, the food management system determines the existing food items in user households and supermarkets based on food reserve information.

[0063] S131, the ingredient management system determines the set of recipes to be recommended based on local seasonal ingredients and available ingredients.

[0064] Environmental information includes location, season, and weather, which helps determine the seasonal ingredients available in the user's location. Seasonal ingredients are generally inexpensive, plentiful, and fresher. Ingredient reserve information includes the types and quantities of ingredients available at the user's home, nearby supermarkets, and farmers' markets. This information helps determine the ingredients available to the user's home and supermarkets. Based on this, a set of recipes to be recommended is determined. This set of recipes satisfies both economic efficiency and the need for immediate preparation.

[0065] Optionally, combined Figure 5 As shown in S102, the food ingredient management system determines the user representation based on user information and user behavior, including:

[0066] S112, The food ingredient management system determines the context representation based on the context of the user's browsing behavior.

[0067] S122, the food ingredient management system determines the weight value of the user's browsing content based on the user's historical interest representation, user attribute representation, and context representation.

[0068] S132, The food management system determines the final user representation based on the user's historical interest representation and weight value.

[0069] When considering what dishes to cook, users typically consult cookbooks, browse food websites, watch food videos, and access related text, images, and / or videos on food delivery platforms. Furthermore, during this browsing activity, users often spend considerable time focusing on sections that interest them. By detecting the context of user browsing behavior through image capture and other methods, a contextual representation can be determined in real time. This representation reflects the user's current specific needs and the context in which they are considering food.

[0070] User information includes: user historical interest representation and user attribute representation. User historical interest representation is a user's habitual and valuable interest profile. User attribute representation is a unique and personalized feature representation of the user. The user historical interest representation, user attribute representation, and contextual representation are concatenated to obtain a concatenated vector. This concatenated vector is then activated to obtain the weight values ​​of the content viewed by the user.

[0071] The higher the weight value, the greater the user's interest in the content. Therefore, the final user representation can be determined based on the user's historical interest representation and the weight value, thus obtaining the representation of the most suitable user.

[0072] In this way, by combining the context of the user's browsing behavior, the user's historical interest representation, and the user's attribute representation, a weight value for the user's browsing content is obtained. This weight value also matches the user's current interests and needs. Then, the user's historical interest representation is refined using this weight value, resulting in the final user representation that best matches the user's current interests and needs. This creates a comprehensive and accurate description of the user's current state, which can improve the accuracy of subsequent recipe recommendations.

[0073] Optionally, S132, the food management system determines the end-user representation based on the user's historical interest representation and weight values, including:

[0074] The food ingredient management system integrates weight values ​​with long-term historical interest representations and short-term historical interest representations.

[0075] The food ingredient management system aggregates the merged results with user attribute representations to obtain the final user representation.

[0076] This study uses profile network technology to extract long-term historical interest representations and user attribute representations from users' historical behavior data. Simultaneously, it employs an LSTM (Long Short-Term Memory) sequence model to analyze recent user behavior and obtain short-term historical interest representations. The weight values ​​of the user's currently viewed content are then fused with the long-term and short-term historical interest representations. The fused result represents a comprehensive picture of the user's historical and current interests. This fused result is then aggregated with the user attribute representation to obtain the final user representation. Thus, the final user representation is a comprehensive reflection of user interests and characteristics, more accurately representing the user's personalized needs.

[0077] Optionally, S103, the ingredient management system predicts the click-through rate of each recipe in the set of recipes to be recommended based on user feedback, including:

[0078] The food management system combines user responses with and activates the various recipes in the set of recipes to be recommended, thus obtaining the click-through rate of each recipe.

[0079] The user representation is concatenated with each recipe in the set of recipes to be recommended, and then activated. This yields the click-through rate (CTR) for each recipe. Here, the user representation refers to the final user representation. The predicted CTR reflects the user's potential interest in each of the recommended recipes.

[0080] Optionally, S104, the ingredient management system recommends recipes to users based on the click-through rate of each recipe, including:

[0081] The ingredient management system identifies recipes that meet preset click-through rates as target recipes.

[0082] The food ingredient management system recommends target recipes to users.

[0083] The system retrieves pre-stored preset conditions. If the click-through rate (CTR) meets these conditions, the corresponding recipe is designated as the target recipe. A higher predicted CTR indicates greater user interest in the recipe. Optionally, the preset conditions include the top N recipes with the highest CTR, sorted from highest to lowest. The value of N can be changed and set by the user. For example, if N is 5, the top 5 recipes with the highest CTRs are designated as target recipes. This approach, recommending target recipes to users, better aligns with their personalized needs, completing the mapping process from user interests to specific recommended recipes.

[0084] Combination Figure 6 As shown, this disclosure provides another method for recommending recipes, including:

[0085] S101, the food ingredient management system determines the set of recipes to be recommended based on environmental information and food ingredient reserve information.

[0086] S102, the food ingredient management system determines the user's representation based on user information and user behavior.

[0087] S103, the ingredient management system predicts the click-through rate of each recipe in the set of recipes to be recommended based on user feedback.

[0088] S104, the ingredient management system recommends recipes to users based on the click-through rate of each recipe.

[0089] S105, the food ingredient management system determines the user's first level of satisfaction with the recommended recipe based on user feedback.

[0090] S106, If the ingredient management system is dissatisfied with the recommended recipe in the first satisfaction rating, it will recommend a new recipe.

[0091] S107, the ingredient management system provides users with tutorials on how to make the recommended recipes when the first satisfaction level indicates satisfaction with the recommended recipes.

[0092] After the food ingredient management system recommends recipes to users via voice, video, or other means, users can provide feedback on their satisfaction with the recommended recipes through voice, gestures, or screen taps. The food ingredient management system receives and analyzes this feedback to determine the user's initial satisfaction level with the recommended recipes.

[0093] If the first satisfaction level indicates that the user is dissatisfied with one or more recipes, then the recipes are re-recommended. Optionally, the method for re-recommending recipes is to: determine the number of dissatisfied recipes, and based on the predicted click-through rate, replenish the same number of recipes in the next order and recommend them to the user. Optionally, the method for re-recommending recipes is to: re-execute S101 to determine a new set of recipes to be recommended; determine the recipes that the user is dissatisfied with, remove the dissatisfied recipes from the new set of recipes to be recommended, and then re-execute S102 to S104. In this way, the user's subjective and individual needs can be met, and satisfactory recipes can be provided to the user.

[0094] If a user is dissatisfied with a recipe, it might be due to dissatisfaction with one or more ingredients. The ingredient management system analyzes user feedback to determine if the user is indeed dissatisfied with an ingredient. If so, it replaces the unsatisfactory ingredient or adjusts its spiciness level based on the user's preference. For example, if a recommended recipe is "Stir-fried Pork with Small Bird's Eye Chili," and the user finds the bird's eye chili too spicy, one solution is to replace it with garlic sprouts, changing the recipe to "Stir-fried Pork with Garlic Sprouts." Another solution is to reduce the spiciness level of the chili, changing the recipe to "Stir-fried Pork with Green Peppers." Thus, when a user finds the preparation of a certain ingredient cumbersome or has personal preferences (such as the spiciness of chili peppers), the ingredient management system demonstrates its high flexibility and intelligence, immediately adjusting the recipe based on the available ingredients in the user's location. This not only intelligently recommends suitable alternative ingredients but also ensures that these alternatives are flavorfully similar to the original ingredients, while also considering the user's taste preferences and health needs.

[0095] If the first satisfaction level indicates user satisfaction with the recommended recipe, a detailed cooking tutorial is provided, visually demonstrating each step of the cooking process. A clear list of essential ingredients is also included to ensure easy preparation and enjoyment of cooking. Optionally, if the ingredient management system is a device with a screen, such as a smart TV or smart refrigerator, the system automatically plays the cooking tutorial. Alternatively, the system can communicate with other devices with screens (such as TVs or mobile phones), sending recommended recipes and instructions to play related recipe videos to these devices. This makes it easier for users to understand the recipe preparation process, making the recipe recommendation process more user-friendly and intelligent.

[0096] Combination Figure 7 As shown, this disclosure provides another method for recommending recipes, including:

[0097] S101, the food ingredient management system determines the set of recipes to be recommended based on environmental information and food ingredient reserve information.

[0098] S102, the food ingredient management system determines the user's representation based on user information and user behavior.

[0099] S103, the ingredient management system predicts the click-through rate of each recipe in the set of recipes to be recommended based on user feedback.

[0100] S104, the ingredient management system recommends recipes to users based on the click-through rate of each recipe.

[0101] S105, the food ingredient management system determines the user's first level of satisfaction with the recommended recipe based on user feedback.

[0102] S106, If the ingredient management system is dissatisfied with the recommended recipe in the first satisfaction rating, it will recommend a new recipe.

[0103] S107, the ingredient management system provides users with tutorials on how to make the recommended recipes when the first satisfaction level indicates satisfaction with the recommended recipes.

[0104] S108: After executing S107, the food management system determines the user's second level of satisfaction with the production tutorial based on user feedback.

[0105] S109, if the second satisfaction rating indicates dissatisfaction with the tutorial, the recipe is recommended again.

[0106] S110, in the case of a satisfactory production tutorial as the second satisfaction indicator, guides the user based on the user's ingredient reserve information.

[0107] After the food ingredient management system provides users with recipe tutorials, users can provide feedback on their satisfaction with the tutorials via voice, gestures, or screen taps. The food ingredient management system receives and analyzes this feedback to determine the user's level of satisfaction with the tutorial.

[0108] If the second satisfaction level indicates user dissatisfaction with the recipe preparation tutorial, for example, if the user says "this dish is too complicated to make," then the recipe is re-recommended. Optionally, the method for re-recommending recipes is: determine the number of recipes with unsatisfactory preparation tutorials, and based on the predicted click-through rate, add the same number of recipes to the next list and recommend them to the user. Optionally, the method for re-recommending recipes is: re-execute S101 to determine a new set of recipes to be recommended. Once the unsatisfactory recipes are identified, they are removed from the new set of recipes to be recommended, and then S102 to S104 are re-executed. In this way, the user's need for ease of preparation can be met, providing the user with satisfactory recipes.

[0109] If the second satisfaction level represents user satisfaction with the tutorial, then the user's ingredient reserves are further analyzed to determine if the ingredients stored at the user's home are sufficient to make the corresponding recipe. Then, guidance is provided to the user based on their ingredient reserves.

[0110] In this way, after providing users with recipe tutorials, a mechanism is added to assess user satisfaction with the tutorials. Based on the user's second-highest satisfaction level, recipes are recommended again, or the user's ingredient inventory information guides their next steps. This creates a thoughtful service for users creating recipes, making the ingredient management system more user-friendly and intelligent.

[0111] Optionally, S110, the food ingredient management system provides guidance to the user based on the user's food ingredient reserve information, including:

[0112] The ingredient management system determines the target ingredient information corresponding to the recommended recipe.

[0113] When a user's stored food information does not meet the target food information, the food management system determines the user's expectation of going out to buy food.

[0114] The food ingredient management system guides users based on their expectations for purchasing food outside the home.

[0115] If the user is satisfied with the recipe tutorial, the ingredients used in the recipe are determined, and their information is defined as target ingredient information. Simultaneously, the user's stored ingredient information is retrieved from memory, and it is determined whether the user's stored ingredient information meets the target ingredient information. The information elements for this determination include: ingredient type, quantity, ripeness, and freshness. If the number of mismatches between the above information and the target ingredient information is greater than or equal to a preset quantity, the stored ingredient information is considered not to meet the target ingredient information. Optionally, to ensure the quality and effect of the recipe, the preset quantity is set to 1, ensuring that all information of the stored ingredients completely matches all information of the target ingredients before the user prepares the recipe. It should be noted that the preset quantity can be set by the user according to their expected quality of the recipe preparation.

[0116] If a user's stockpiled ingredients do not meet the target ingredient requirements, the system will further inquire with the user via voice, message dialog, or other means whether they wish to go out to purchase ingredients. After the user provides feedback to the ingredient management system, the system analyzes the feedback to determine the user's level of willingness to go out to buy ingredients. Then, based on the user's level of willingness, the system provides further guidance to the user.

[0117] In this way, after users are satisfied with the recipe tutorial, a mechanism is added to judge the matching degree between the user's stocked ingredients and the target ingredients. If the judgment result is not satisfactory, the user is guided based on their expectation of going out to buy ingredients, forming a chain of services including recipe recommendations, recipe tutorials, and ingredient purchases, so that users can experience a more intelligent and considerate service in terms of dining.

[0118] Optionally, the food ingredient management system provides operational guidance to users based on their expectations for purchasing food outside, including:

[0119] When the expectation level indicates that a user wants to go out to buy ingredients, the food management system recommends places to buy ingredients that meet the user's target information, and / or provides the user with a tutorial on identifying the ingredients to be purchased.

[0120] When a user's expectation level indicates that they do not want to go out to buy ingredients, the food management system sends the information of the ingredients to be purchased and a request for home delivery to the purchase location that meets the target ingredient information.

[0121] If a user's expectation level indicates a desire to purchase groceries outside the home, the grocery management system can leverage its powerful geolocation services to access local or server-side maps and recommend locations that offer the desired groceries, allowing the user to easily travel to those locations. The system can also access cloud server data to provide users with tutorials on identifying the type, ripeness, and freshness of the groceries, offering these tutorials directly to the user. The system can provide both purchase locations and groceries identification tutorials simultaneously, or choose one. This provides ongoing support for users after their grocery shopping experience, ensuring they purchase the correct and high-quality groceries.

[0122] If a user's expectation level indicates that they do not wish to go out to buy groceries, the groceries management system generates a list of groceries to be purchased and sends this list, along with a home delivery request, to the locations that meet the target groceries criteria via the server. This achieves automated and intelligent purchasing, saving the user time.

[0123] Optionally, combined Figure 8 As shown, this disclosure provides another method for recommending recipes, including:

[0124] S101, the food ingredient management system determines the set of recipes to be recommended based on environmental information and food ingredient reserve information.

[0125] S102, the food ingredient management system determines the user's representation based on user information and user behavior.

[0126] S103, the ingredient management system predicts the click-through rate of each recipe in the set of recipes to be recommended based on user feedback.

[0127] S104, the ingredient management system recommends recipes to users based on the click-through rate of each recipe.

[0128] S1110, the food management system guides users based on their food reserve information.

[0129] After recommending recipes to users, guidance can be provided directly based on their ingredient reserves: First, determine the target ingredients for the recommended recipes. If the user's reserves do not meet the target ingredients, determine the user's expectation of purchasing ingredients outside the store. Then, guide the user based on their expectation of purchasing ingredients outside the store. Specific details can be found above and will not be repeated here.

[0130] The following examples illustrate the application of a food ingredient management system (hereinafter referred to as "the system") in daily life:

[0131] User: Any recommendations for tonight?

[0132] System: Here I recommend dish A, dish B, and dish C to you (the corresponding finished dish images will be displayed on the system's own screen or other system screens).

[0133] User: I don't like dish A.

[0134] System: Okay, then I recommend dish D to you (the corresponding finished dish image is displayed on the screen).

[0135] User: How is dish B made? What ingredients are needed?

[0136] System: Okay, here's a preview (jumps to the corresponding production video).

[0137] User: This dish is a bit spicy, is there any way to fix it? / I don't like it.

[0138] System: No problem, you can replace ingredient 'a' in this dish with ingredient 'b'.

[0139] User: I don't have any ingredients (b) at home. Where is the nearest farmers market / supermarket?

[0140] System: We recommend you go to location X. Of course, you can also go to Y or Z (the screen displays the corresponding address).

[0141] User: I've never bought these before, how can I tell the difference between good and bad?

[0142] System: Okay, here you go (jumps to the corresponding identification video).

[0143] User: Forget it, it's too much trouble. Let them deliver it to my door.

[0144] System: Okay (Redirects to the purchase page for this ingredient, automatically generates and submits the purchase list, and generates an invoice).

[0145] User: (Selects and pays via QR code).

[0146] Combination Figure 9 As shown in the illustration, this disclosure provides an apparatus 90 for recommending recipes, including: a first determining module 91, a second determining module 92, a prediction module 93, and a recommendation module 94. The first determining module 91 is configured to determine a set of recipes to be recommended based on environmental information and ingredient reserve information. The second determining module 92 is configured to determine user representation based on user information and user behavior. The prediction module 93 is configured to predict the click-through rate of each recipe in the set of recipes to be recommended based on the user representation. The recommendation module 94 is configured to recommend recipes to the user based on the click-through rate of each recipe.

[0147] The apparatus 90 for recommending recipes provided in this embodiment of the present disclosure is advantageous in first determining a set of recipes to be recommended based on environmental information and ingredient reserve information. This ensures that the recipes contain ingredients that the user can use and that are seasonal, affordable, and of good quality, meeting objective cooking conditions. Then, user representations are determined based on user information and behavior to obtain the user's current interest. Furthermore, the click-through rate of each recipe in the set of recipes to be recommended is predicted based on the user's representation, thus predicting the user's level of interest in each recipe. Recipes are then recommended to the user based on the click-through rate of each recipe. In this way, the recommended recipes ensure that the ingredients used are locally available, inexpensive, fresh, and affordable, while effectively avoiding potential cost increases or compromised taste caused by using out-of-season or imported ingredients. Therefore, the recommended recipes not only meet the user's personalized needs but also incorporate regional characteristics and practical considerations, making the recommended recipes more accurate.

[0148] Combination Figure 10 As shown, this disclosure provides an apparatus 100 for recommending recipes, including a processor 101 and a memory 102. Optionally, the apparatus 100 may further include a communication interface 103 and a bus 104. The processor 101, communication interface 103, and memory 102 can communicate with each other via the bus 104. The communication interface 103 can be used for information transmission. The processor 101 can call logical instructions in the memory 102 to execute the method for recommending recipes described in the above embodiments.

[0149] Furthermore, the logical instructions in the aforementioned memory 102 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0150] The memory 102, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor 101 executes functional applications and data processing by running the program instructions / modules stored in the memory 102, that is, it implements the method for recommending recipes in the above embodiments.

[0151] The memory 102 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 102 may include high-speed random access memory and may also include non-volatile memory.

[0152] Combination Figure 11 As shown, this disclosure provides a food ingredient management system 10, including: a food ingredient management system body, and the aforementioned device 90 (100) for recommending recipes. The device 90 (100) for recommending recipes is installed in the food ingredient management system body. The installation relationship described herein is not limited to placement inside the food ingredient management system body, but also includes installation connections with other components of the product 100, including but not limited to physical connections, electrical connections, or signal transmission connections. Those skilled in the art will understand that the device 90 (100) for recommending recipes can be adapted to feasible product bodies to achieve other feasible embodiments.

[0153] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to perform the above-described method for recommending recipes.

[0154] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc., and other media capable of storing program code.

[0155] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0156] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0157] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for recommending recipes, characterized in that, include: Based on environmental and food reserve information, a set of recipes to be recommended was determined; Determine user representation based on user information and user behavior; Based on user feedback, predict the click-through rate of each recipe in the set of recipes to be recommended; Recipes are recommended to users based on their click-through rates.

2. The method according to claim 1, characterized in that, Based on environmental and food availability information, a set of recommended recipes was determined, including: Based on environmental information, determine local seasonal ingredients; Based on food reserve information, determine the existing food supplies in users' households and supermarkets; Based on local seasonal ingredients and available ingredients, a set of recipes to be recommended was determined.

3. The method according to claim 1, characterized in that, User information includes: user historical interest representation and user attribute representation; user behavior includes: user browsing behavior; based on user information and user behavior, user representation is determined, including: Determine the context representation based on the context of the user's browsing behavior; The weight value of the user to the content viewed is determined based on the user's historical interest representation, user attribute representation, and context representation; The final user representation is determined based on the user's historical interest representation and weight values.

4. The method according to claim 3, characterized in that, User historical interest representation includes: long-term historical interest representation and short-term historical interest representation; based on the user historical interest representation and weight values, the final user representation is determined, including: The weight values ​​are integrated with both long-term and short-term historical interest representations. The fused result is then aggregated with the user attribute representation to obtain the final user representation.

5. The method according to claim 1, characterized in that, Based on user feedback, the click-through rate of each recipe within the recommended recipe collection is predicted, including: The user's representation is concatenated with and activated with each recipe in the set of recipes to be recommended, and the click-through rate of each recipe is obtained.

6. The method according to claim 1, characterized in that, Based on the click-through rate of each recipe, recipes are recommended to users, including: Recipes that meet the preset click-through rate criteria are identified as target recipes; Recommend target recipes to users.

7. The method according to any one of claims 1 to 6, characterized in that, After recommending recipes to users, the method further includes: Based on user feedback, determine the user's first level of satisfaction with the recommended recipes; If the first satisfaction rating indicates dissatisfaction with the recommended recipe, a new recipe will be recommended. If the user is satisfied with the recommended recipe, the system will provide a tutorial on how to make the recommended recipe.

8. The method according to claim 7, characterized in that, After providing users with recipe tutorials, the method further includes: Based on user feedback, determine the user's second level of satisfaction with the tutorial creation process; If the second satisfaction rating indicates dissatisfaction with the tutorial, the recipe will be recommended again. In the case of a satisfactory production tutorial, the second satisfaction level is used to guide the user based on their ingredient inventory information.

9. The method according to claim 8, characterized in that, Provide guidance to users based on their food inventory information, including: Determine the target ingredient information for the recommended recipe; If the user's stock of ingredients does not meet the target ingredient information, determine the user's expectation of going out to buy ingredients; Guide users based on their expectations of going out to buy groceries.

10. The method according to claim 9, characterized in that, Based on the user's expectation of going out to buy groceries, provide operational guidance to the user, including: When the expectation level indicates that the user wants to go out to buy groceries, recommend places to buy groceries that meet the target groceries information, and / or provide the user with a tutorial on identifying the groceries to be bought; When the expectation level indicates that the user does not want to go out to buy groceries, the system sends the information of the groceries to be purchased and a request for home delivery to the purchase location that meets the target groceries information.

11. An apparatus for recommending recipes, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when executing the program instructions, perform the method for recommending recipes as described in any one of claims 1 to 10.

12. A food ingredient management system, characterized in that, include: The food ingredient management system itself; The device for recommending recipes as described in claim 11 is installed on the main body of the food ingredient management system.

13. A computer-readable storage medium storing program instructions, characterized in that, When the program instructions are executed, they cause the computer to perform the method for recommending recipes as described in any one of claims 1 to 10.

Images