Method, apparatus, device and storage medium for recommendation

Abstract

According to embodiments of the present disclosure, a method, device, equipment, storage medium and program product for recommendation are provided. The method comprises: in response to detecting a first predetermined operation in a first interface of a target application, presenting a second interface comprising at least one entry related to meal suggestions; in response to detecting a predetermined type of input at the at least one entry, presenting at least one set of candidate meal recommendations; and in response to detecting a selection operation for one of the at least one set of candidate meal recommendations, presenting an acquisition path associated with the selected set of candidate meal recommendations in the first interface. Thus, the present disclosure can deeply integrate the personal health records of users with the takeout ordering scenario, realize personalized and scientific meal recommendations, and shorten the decision-making path of users from the demand for healthy diet to the completion of ordering.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to recommended methods, apparatus, devices and computer-readable storage media. Background Technology

[0002] Currently, when users seek healthy eating and order takeout, they typically need to check the nutritional information of food in a separate health app, and then manually filter and compare it on the takeout platform—a cumbersome and time-consuming process. Furthermore, the "healthy" and "light meal" labels provided by some takeout platforms are self-labeled by the merchants, lacking unified scientific certification standards and failing to personalize the information to match users' health conditions, nutritional needs, and taste preferences.

[0003] Existing food delivery platform recommendation systems are mostly based on collaborative filtering or popular lists. Their recommendation logic focuses on commercial conversion and generalized user preferences, without being deeply integrated with clinical nutrition standards and users' personal health records. This leads to problems such as low decision-making efficiency, lack of health risk management, a disconnect between health goals and consumption behavior, and a lack of scientific rigor and personalization in recommendations. Summary of the Invention

[0004] In a first aspect of this disclosure, a method for making recommendations is provided. The method includes: in response to detecting a first predetermined operation in a first interface of a target application, presenting a second interface, the second interface including at least one entry point related to meal recommendations; in response to detecting input of a predetermined type at the at least one entry point, presenting at least one set of candidate meal recommendations; and in response to detecting a selection operation for one of the at least one set of candidate meal recommendations, presenting an acquisition path associated with the selected set of candidate meal recommendations in the first interface.

[0005] In a second aspect of this disclosure, an apparatus for making recommendations is provided. The apparatus includes: a first presentation module configured to present a second interface in response to detecting a first predetermined operation in a first interface of a target application, the second interface including at least one entry point related to a meal suggestion; a second presentation module configured to present at least one set of candidate meal recommendations in response to detecting input of a predetermined type at the at least one entry point; and a third presentation module configured to present an acquisition path associated with the selected set of candidate meal recommendations in the first interface in response to detecting a selection operation for one of the at least one set of candidate meal recommendations.

[0006] In a third aspect of this disclosure, an electronic device is provided. The electronic device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method of the first aspect of this disclosure when executed by the at least one processing unit.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program that can be executed by a processor to perform the method according to a first aspect of this disclosure.

[0008] In a fifth aspect of this disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method according to a first aspect of this disclosure.

[0009] It should be understood that the content described in this section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown; Figure 2 A schematic diagram of an example interface of a target application according to some embodiments of the present disclosure is shown; Figure 3 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 4 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 5 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 6 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 7 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 8 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 9 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 10 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 11 A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 12A schematic diagram of an example interface according to some embodiments of the present disclosure is shown; Figure 13 A schematic diagram of an image input interface according to some embodiments of the present disclosure is shown; Figure 14 A schematic diagram of an image analysis interface according to some embodiments of the present disclosure is shown; Figure 15 A schematic diagram of an analysis results interface according to some embodiments of the present disclosure is shown; Figure 16 A schematic diagram of the architecture of a recommendation system according to some embodiments of the present disclosure is shown; Figure 17 A flowchart of a recommended method according to some embodiments of the present disclosure is shown; Figure 18 Block diagrams of a recommended apparatus according to some embodiments of the present disclosure are shown; and Figure 19 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. Detailed Implementation

[0011] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0012] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0013] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0014] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0015] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0018] In existing technologies, when users pursue healthy eating and order takeout, they typically need to switch between multiple apps, manually search, and calculate, resulting in a time-consuming and costly decision-making process. Current technologies lack the ability to analyze individual user health data and cannot effectively warn of potential allergens, nutritional imbalances, and other risks. Even if users set health goals, there are no effective tools to directly translate abstract goals into actionable, orderable meal plans. Recommendations based on commercial behavior and popular preferences cannot generate customized plans that meet scientific standards and accurately match individual health characteristics.

[0019] In view of this, embodiments of the present disclosure provide a method for making recommendations, the method comprising: if a first predetermined operation is detected in a first interface of a target application (e.g., example interface 200A), presenting a second interface (e.g., example interfaces 200B-200D), the second interface including at least one entry related to meal recommendations. If input of a predetermined type is detected at at least one entry, presenting at least one set of candidate meal recommendations. Further, if a selection operation for one of the at least one set of candidate meal recommendations is detected, presenting an acquisition path associated with the selected set of candidate meal recommendations on the first interface.

[0020] Therefore, this disclosure deeply integrates users' personal health records and nutritional knowledge with the food delivery ordering scenario to achieve personalized and scientific meal recommendations. This significantly shortens the decision-making path and time from generating a healthy eating need to completing an order, improving efficiency. Furthermore, by constructing an automated and highly accurate health risk identification and avoidance mechanism, food safety can be ensured. Correspondingly, this method can dynamically adjust the recommendation strategy based on users' real-time behavior (such as adding high-oil foods to their cart), thus improving the accuracy of recommended meals as the frequency of user use increases.

[0021] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In this example environment 100, server 130 is capable of establishing a communication connection with one or more terminal devices (collectively or individually referred to as terminal device 110). At least one application 120 may be installed on terminal device 110. User 140 may interact with application 120 via terminal device 110 and / or an attachment device of terminal device 110. Application 120 may be a content presentation application, an online shopping application, or any other suitable application.

[0022] exist Figure 1 In environment 100, application 120 can also be accessed in other ways, such as through a webpage. If application 120 is active, terminal device 110 can display the interface 150 of application 120. Interface 150 may include various interfaces provided by application 120, such as content presentation interface, content creation interface, service request submission interface, request processing result interface, message interface, personal homepage, etc.

[0023] In some embodiments, terminal device 110 communicates with server 130 to provide services to application 120. Terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 can also support any type of user-facing interface (such as "wearable" circuitry). Server 130 can be various types of computing systems / servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0024] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0025] The following will combine Figures 2-15 The present invention will be described. For ease of discussion, reference will be made to... Figure 1 These embodiments are described in the context of environment 100. These embodiments can be implemented in... Figure 1 The terminal device 110 is used as an example for the following discussion.

[0026] refer to Figure 2 The example shown is a sample interface 200A of the target application. Sample interface 200A can be a food delivery platform's menu browsing interface, presenting information on multiple food items obtainable from the target application. Sample interface 200A may include a search bar at the top and a recommendation entry 210. Recommendation entry 210 can serve as an entry point to trigger the presentation of a second interface. Sample interface 200A can also display multiple merchant cards, each displaying a menu thumbnail, price information, and an add-to-cart button. A shopping cart icon can be placed in the lower right corner of sample interface 200A. Thus, users can easily access the intelligent recommendation interface from the food browsing interface without switching applications.

[0027] In some embodiments, the recommendation mechanism can be triggered in two ways. First, a recommendation can be triggered when a user adds food items to their cart (e.g., the food is oily and can be paired with stir-fried vegetables). Second, if the user hasn't added any food items, a floating window can be displayed on the interface. Clicking this window allows the system to recommend suitable dishes for the day. The first reservation operation may include selecting at least one dish from a set of multiple options, or triggering the entry point 210 used to display the second interface. This combines proactive and reactive recommendations to meet user needs in different scenarios.

[0028] refer to Figure 3 An example of an example interface 200B (i.e., the second interface) is shown. Example interface 200B can be an interactive interface for an agent application, including at least one entry point related to meal suggestions. Example interface 200B may include a title area and navigation elements. Below the title, the interface may present a greeting message from the agent along with several suggestion query options presented as selectable buttons, including options related to cuisine preferences and dietary restrictions (such as lactose intolerance). At the bottom of example interface 200B, a text input field 221 can be provided where the user can enter a query, with placeholder text asking the user what they want to eat today. Next to the text input field 221, a function navigation plugin 223 is located on the right, providing additional interactive options.

[0029] Text input field 221 can receive natural language information indicating at least one of the following: the user's dining preferences; the user's expected level of physical health; and the user's nutritional needs. This allows users to express complex dietary needs in natural language, lowering the barrier to interaction. Function navigation plugin 223 provides access to additional functions, such as image recognition, shopping cart health checks, recording, and user data input, thus offering multiple interaction methods and enhancing the flexibility of the user experience.

[0030] refer to Figure 4 The example interface 200C is shown, illustrating a chat-based interactive screen for an agent application. Example interface 200C may include a user input message 231 displayed in a message bubble near the top of the screen, containing text requesting restaurant recommendations. Below the user input message 231, the interface may display a thinking indicator followed by placeholder text indicating that the agent is processing the request and generating a response. At the bottom of example interface 200C, a stop response button 232 may be located to the right of the input field area, allowing the user to interrupt the ongoing response generation process.

[0031] refer to Figure 5 The example interface 200D is shown, displaying personalized meal recommendations. Example interface 200D may include a title section containing recommendation text based on the user's health goals and dietary restrictions. Below the title, a first restaurant card 241 may display meal information, including ingredient information, nutritional components (including carbohydrate and protein content), and price information. Next to the first restaurant card 241, a second restaurant card 242 may display similar nutritional details. The first restaurant card 241 may include an add-to-cart button 243, allowing the user to add the recommended meal to their shopping cart. Below each restaurant card, a recommendation reason 244 may be displayed, providing an explanation of why each meal is recommended to the user.

[0032] In some embodiments, terminal device 110 may display an order control (not shown) associated with each restaurant card, allowing users to directly order a single dish or all dishes. In some examples, the candidate dishes presented by terminal device 110 may come from the same merchant or different merchants. In some examples, user 140 may send a request to recommend dishes and generate an order. In this scenario, upon receiving the request, terminal device 110 may receive a set of recommended dishes that meet the user's needs and present an order for that set of recommended dishes. This allows users to easily add all recommended dishes to their shopping cart or place a bulk order.

[0033] In some embodiments, food delivery platforms can generate prompts based on user data. These prompts instruct the model to act as an agent tailored to the current user and, referencing a multi-dimensional knowledge base (e.g., nutrition guidelines, nutritional standards, or any other suitable knowledge base), to reason about and generate meal pairings. The prompts are instructions or text input to the model, guiding it to produce specific, desired outputs. This enables accurate recommendations based on personalized user data. This can be achieved by a single agent analyzing and recommending to the user, or by multiple agents analyzing and recommending separately. For example, a risk agent can analyze potential risks, a nutrition agent can perform nutritional analysis, and a meal agent can recommend suitable meals, finally integrating the results and sending them to the user. This specialized division of labor improves the scientific rigor and comprehensiveness of the recommendations.

[0034] refer to Figure 6 The example shown is a sample interface 300A. Sample interface 300A may include a title area and navigation controls. Below the title, the interface may display a greeting message, followed by suggestion buttons containing various query options. A text input field may be located near the bottom of sample interface 300A, with a prompt asking the user what they want to eat today. At the bottom of sample interface 300A, the navigation bar may include image recognition controls 311 for capturing or selecting food images for analysis, additional function buttons for shopping cart health checks and recording, and user data input controls 312 for accessing and entering user health and preference information.

[0035] Image recognition control 311 allows users to capture or select food images for analysis, enabling them to quickly obtain nutritional analysis of meals by taking photos. User data input control 312 provides access to an interface for inputting and managing user health data, dietary preferences, and health goals, facilitating user management and updating of personal health data and improving recommendation accuracy.

[0036] refer to Figure 7 The example shown is of interface 300B (an example of a third interface), which displays a user data screen. Interface 300B can display user profile information at the top of the screen, including age, weight, ideal weight, height, goals, exercise status, and expected achievement time. Below the profile section, the interface can display daily intake information and dietary restrictions. In the lower right corner of interface 300B, an update data button 321 can be provided, allowing users to refresh or modify their stored information.

[0037] refer to Figure 8The example interface 300C (which is an example interface of a third interface) is shown for user data input. Example interface 300C can display a user data page with navigation controls and a title. Below the title, a profile completion section with a progress indicator can be displayed. The interface can present prompts requesting information input, and the gender selection option is displayed as a rounded rectangle button. Below the gender selection, the interface can include input fields for age, height, and weight. At the bottom of example interface 300C, a next button 331 can be provided, allowing the user to continue to the next step after entering the required information.

[0038] refer to Figure 9 The example interface 300D (which is an example interface of a third interface) is shown for collecting user data related to daily activity levels. Example interface 300D can display questions asking the user about their usual activity levels, with multiple options presented in card format. A sedentary option 343 can be located at the top of the selection area, below which is a light activity option 342. A moderate activity option 341 can be highlighted with a bold border to indicate that it is currently selected. At the bottom of example interface 300D, a next button 331 can be provided, allowing the user to continue to the next step after making a selection.

[0039] refer to Figure 10 The example shown is a sample interface 300E (which is an example of a third interface) for user data input related to health goals and target weight settings. Sample interface 300E may include a question prompting the user to select a goal, with three options presented vertically. The fat loss option 351 may be displayed at the top and possibly indicated by a highlighted border to show that it is currently selected. The muscle gain option 352 may be located below the fat loss option 351. A third option, used to maintain the current state, may be displayed below the muscle gain option 352. Sample interface 300E may also include a question asking the user about their ideal weight, with a weight slider 353 located below this question. The weight slider 353 may display a range from 38 kg to 72 kg and show the currently selected weight. A next button 331 may be located at the bottom of sample interface 300E.

[0040] refer to Figure 11 The example shown is Interface 300F (an example of a third interface), specifically designed for user data input to select a target date. Interface 300F displays a title at the top, a back navigation arrow on the left, and a menu icon on the right. Below the title, the interface presents a question asking for the expected date, followed by a date selection mechanism with scrollable columns for year, month, and day. Below the date selector, explanatory text explains that a customized diet plan will maximize the user's chances of success before the selected date. At the bottom of Interface 300F, a confirmation button 361 allows the user to submit their selected target date.

[0041] refer to Figure 12 The example interface 300G (which is an example interface of the third interface) is shown, displaying a user data screen. Example interface 300G can display user profile information, including age, weight, ideal weight, height, goals, exercise level, and expected achievement date. User input 371 can indicate an exercise level of moderate activity. User input 372 can display the expected achievement date. User input 373 can display the goal as fat loss. Example interface 300G may also include sections on daily intake and dietary restrictions. This is achieved through the structured data collection process described above ( Figure 7-12 This ensures the integrity and accuracy of users' health information, providing a reliable data foundation for personalized recommendations.

[0042] refer to Figure 13 An example of an image input interface 400A is shown. The image input interface 400A may include a title section with a return navigation arrow on the left and a menu icon on the right. Below the title, a circular icon followed by a greeting message may be displayed. The image input interface 400A may include an analysis section with a large rectangular area for displaying analysis content. At the bottom of the image input interface 400A, an album button 411 may be located on the left and a camera button 412 may be located on the right, providing users with options to select images from the album or capture new images for analysis.

[0043] refer to Figure 14 An example of an image analysis interface 400B is shown, displaying the agent's interactive screen during food analysis. The image analysis interface 400B can display a title with a return navigation arrow and a menu icon. Below the title, a circular avatar icon and a greeting message can be displayed. An analysis status indicator 421 can be displayed below the greeting, indicating that the system is currently processing information. Below the analysis status indicator 421, a placeholder image icon representing a food photo can be displayed within a rectangle, indicating that the agent is analyzing the uploaded food image to provide nutritional advice or a health assessment to the user.

[0044] refer to Figure 15The diagram illustrates an example of an analysis results interface 400C, displaying the analysis results screen for a meal. The analysis results interface 400C may include a title area and navigation elements. Below the title, an avatar and greeting message may be displayed. The analysis results area 431 may occupy the central portion of the analysis results interface 400C and may display the meal's nutritional information, including carbohydrate content, protein content, and calorie value. The analysis results area 431 may also display food ingredient information and descriptive text explaining the meal's composition. At the bottom of the analysis results interface 400C, a re-analysis button 432 may be located on the left, and a confirmation / record button may be located on the right, allowing users to request a new analysis or confirm and save the current analysis results.

[0045] In some embodiments, when the input includes an image of a meal, the system can, in response to detecting the input of the meal image at at least one entry point, present a health index analysis result for the meal and at least one set of candidate meal recommendations. The at least one set of candidate meal recommendations can be generated based at least on the health index analysis result. As an example, if terminal device 110 receives an input of a meal image (e.g., input provided by user 140 through image recognition control 311, or a meal image automatically collected by terminal device 110, or any other appropriate input), it can present a health index analysis result for that meal image (e.g., ingredient composition, nutritional components, etc.). Accordingly, terminal device 110 can also provide user 140 with candidate meal recommendations associated with the meal image, such as meals that can be paired with the meal. Thus, the user can intuitively understand the nutritional components of the meal, assisting in health decision-making.

[0046] The following will be referenced Figure 16 This section describes in detail how to determine at least one set of recommended candidate dishes. For ease of understanding, the following discussion will use the scenario where a user has currently added a dish to their cart as an example to illustrate how the recommendation mechanism is triggered. It should be understood that even if a user has not currently added a dish to their cart, the following method can still be used to determine at least one set of recommended candidate dishes.

[0047] refer to Figure 16The diagram illustrates an example architecture 500 for meal recommendation. Example architecture 500 can be implemented at terminal device 110. Example architecture 500 may include adding meal items 510, text embedding 511, prompt words 512, a data module 519, a visual analysis engine 513, shopping cart items 514, and multiple agents, including agent 515-1, agent 515-2, and agent 515-5. Data module 519 can be associated with meal data 516, nutrition guidelines 517, and user data 518. In some embodiments, the terminal device 110 can obtain and integrate user data from multiple data sources through interface calls, including obtaining user health record data (including physical examination reports such as blood sugar, uric acid, blood lipid indicators, allergy history, past medical history, etc.) from a health platform, obtaining user historical order data and real-time behavior data (such as browsing, searching, favorites, adding to cart) from a food delivery platform, and obtaining the user's expected physical health level (also known as health goals, such as fat loss, muscle gain, blood sugar control) and dietary preferences (such as taste restrictions) through user active input or preset.

[0048] In some embodiments, when user 140 performs an operation such as adding a food item via add item 510, terminal device 110 can invoke a Large Language Model (LLM) to process this input. A Large Language Model is an artificial intelligence model capable of understanding and generating natural language. Text embedding 511 can convert text information into a format suitable for agent processing. Prompt words 512 can be generated based on the processed input and user context to guide the agent in generating recommendations.

[0049] Data module 519 can maintain multiple data sources organized into data blocks. Food data 516 can contain information on available food items from various merchants, including all available items from all merchants on the food delivery platform, as well as the ingredient list and nutritional information for each item. Nutritional guidelines 517 can provide reference standards based on guidelines such as the "Chinese Dietary Guidelines." User data 518 can include user profile information (such as height, weight, food preferences, etc.), health goals (set by the user, such as weight loss), health record data (such as physical examination reports, including blood sugar, uric acid, blood lipid levels, allergy history, past medical history, etc.), historical data, and real-time data (current items added to cart, favorites, etc.). Each data source can be associated with a corresponding vector database within data module 519 to achieve efficient retrieval and matching.

[0050] Agents 515-1, 515-2, and 515-5 can work collaboratively to analyze user data and generate personalized meal recommendations. These agents can perform different functions, such as risk analysis, nutritional analysis, and meal recommendations. Example architecture 500 may include a visual analytics engine 513 that processes information related to the items in the shopping cart 514, enabling the system to consider user-selected items when generating recommendations. In some examples, terminal device 110 can assist in identifying information related to the items in the shopping cart 514 based on user-input tags or in combination with dish names. Recommendations generated by the agents can be added to the shopping cart 514 for the user to view and purchase. Thus, through multi-source data fusion, comprehensive data support is provided for personalized recommendations.

[0051] In some embodiments, terminal device 110 may use Large Language Modeling (LLM) to generate highly personalized recommendations, rather than simple product matching. In some examples, terminal device 110 may employ a system based on rule engines and knowledge graphs to generate recommendations. Terminal device 110 may use machine learning models for feature mining, analyzing a large number of historical recommendation records from professional nutritionists to uncover different nutritionists' recommendation strategies, risk warning styles, and personalized expression characteristics, thereby forming different agent templates. Thus, when terminal device 110 provides user 140 with at least one set of candidate meals, it can select at least one agent from these agent templates based on the current input and user data.

[0052] Terminal device 110 can construct dynamic prompts based on real-time, multi-dimensional user data (user profile, health goals, current scene) obtained from data module 519. Terminal device 110 can automatically generate structured prompts, instructing the model to simulate a specific style of "intelligent agent" and referencing a multi-dimensional knowledge base to reason about and generate meal combinations. This enables customized recommendation strategies based on different user characteristics. For example, the prompt can instruct the model to act as a nutritionist skilled in providing advice to people with high uric acid, specifying user characteristics such as gender, age, weight, recent uric acid test value, historical order preferences, current goals, and budget constraints. An example prompt could be: "Act as a nutritionist skilled in providing advice to people with high uric acid. The user is a 35-year-old male, weighs 80kg, and his recent uric acid level is 520μmol / L. His historical orders show a preference for braised dishes. His goal this time is to 'control uric acid,' and his lunch budget is 40 yuan. Please recommend a set meal including a staple food, main dish, and soup from the available options, clearly explaining why these dishes were chosen, and calculating the total calories and estimated purine content."

[0053] Terminal device 110 can acquire candidate meal recommendations output by the LLM based on generated prompts. For example, these candidate meal recommendations may include, but are not limited to, the name, description, and nutritional data for each meal. In some embodiments, terminal device 110 can use a nutrition scoring model (trained based on machine learning algorithms) to score each meal, assessing its match with the user's goals (e.g., calorie match greater than 85%) and risk avoidance accuracy (e.g., allergen avoidance accuracy greater than 95%). The nutrition scoring model can be configured to output a match score and risk index for a specific health goal based on the input meal information. In some examples, the nutrition scoring model can be deployed in environment 100 or within the LLM.

[0054] In this way, by adopting a dual-model collaboration mechanism of nutrition scoring model and LLM recommendation, we can ensure that the recommendation results are both flexible and reliable.

[0055] In summary, by fusing multi-source data (e.g., user health information, dynamic behavioral data, and multi-dimensional knowledge bases) to generate dynamic prompts, truly personalized, scientific, and interpretable dietary recommendations can be achieved. Furthermore, by analyzing real nutritionist data, extracting their strategies and styles, and having the model simulate specific agents during recommendations, the results can be made more personalized and credible.

[0056] Figure 17 A flowchart of a recommended method 600 according to some embodiments of the present disclosure is shown. Method 600 can be implemented in environment 100, for example, method 600 can be implemented at server 130 or terminal device 110. It should be understood that the actions described with respect to server 130 can be performed at least partially by entities other than server 130, for example, at least partially by terminal device 110, other terminal devices, or other servers, or can be performed by server 130 in collaboration with the aforementioned devices.

[0057] In step 610, in response to detecting a first predetermined operation in the sample interface (200A) of the target application, sample interfaces (200B-200D) can be presented. The sample interface may include at least one entry point related to meal recommendations. The sample interface may present information on multiple meals obtainable from the target application, and the first predetermined operation may include a selection operation on at least one of the multiple meals or a triggering of the entry point used to present the sample interface. Thus, the user can easily access the recommendation process.

[0058] In step 620, in response to detecting input of a predetermined type at at least one entry point, at least one set of candidate meal recommendations can be presented. The input can be natural language information indicating at least one of the user's dining preferences, the user's expected level of health, or the user's nutritional needs. An example interface can present a set of prompts associated with the input, and presenting at least one set of candidate meal recommendations can include presenting at least one set of candidate meal recommendations in response to detecting a selection action for at least one prompt in the set. Thus, the system is able to generate accurate personalized recommendations based on user input.

[0059] In step 630, in response to detecting a selection operation for at least one set of candidate meal recommendations, the system can present the acquisition path associated with the selected set of candidate meal recommendations on the example interface. The system can intuitively display the AI-generated recommended meal plan to the user through a front-end interface (such as an H5 page or a native APP page), and provide "One-click Add to Cart" or "One-click Order" function buttons. When the user triggers the "One-click Add to Cart" command, the system can automatically add dishes from different food delivery merchants in batches to the shopping cart through the back-end interface. The user can then confirm and pay in the shopping cart to complete the order. This achieves a seamless transition from recommendation to order placement, significantly improving user decision-making efficiency.

[0060] In some embodiments, the first interface presents information on multiple dishes that can be obtained from the target application, and the first predetermined operation includes at least one of the following: a selection operation on at least one of the multiple dishes; or a triggering of an entry point for presenting the second interface.

[0061] In some embodiments, the input is natural language information, which indicates at least one of the following: the user's dining preferences; the user's expected level of physical health; and the user's nutritional needs.

[0062] In some embodiments, the second interface presents a set of prompts associated with the input, and presenting at least one set of candidate meal recommendations includes: in response to detecting a selection operation for at least one prompt in the set of prompts, presenting at least one set of candidate meal recommendations.

[0063] In some embodiments, at least one set of candidate menu recommendations is generated by an agent that is selected based on input and specific user data.

[0064] In some embodiments, at least one prompt word is generated based on specific user data.

[0065] In some embodiments, specific user data includes at least one of the following: the user's health information; the user's expected level of physical health; and the user's historical food selection information on the target application.

[0066] In some embodiments, method 600 further includes: presenting an entry point for inputting specific user data on a first interface or a second interface; and, in response to receiving a selection operation for the entry point, presenting a third interface, the third interface presenting multiple health parameter input paths.

[0067] In some embodiments, the input includes an image of a meal, and presenting at least one set of candidate meal recommendations based on the input includes: in response to the input of a meal image detected at at least one entrance, presenting a health index analysis result for the meal and at least one set of candidate meal recommendations, wherein the at least one set of candidate meal recommendations is generated at least based on the health index analysis result.

[0068] In some embodiments, method 600 further includes: presenting a reason for recommending at least one set of candidate dishes while presenting at least one set of candidate dish recommendations.

[0069] In some embodiments, the efficiency of providing meal recommendations to users can be improved through the present disclosure. For example, a decision-making process that originally took more than 30 minutes can be compressed to less than 30 seconds, thereby achieving a seamless closed loop from "health goals → scientific meal plans → takeout orders". The terminal device 110 can record the user's adoption behavior, subsequent order data, and health outcome feedback (such as weight changes actively entered by the user). This data can be used to continuously train and optimize the nutrition scoring model and LLM recommendation strategy, thereby making the recommendation results increasingly accurate and forming a positive cycle of "data-driven optimization".

[0070] Figure 18 A block diagram of a recommended apparatus 700 according to some embodiments of the present disclosure is shown. The apparatus 700 may be implemented as a terminal device 110 or included in a terminal device 110.

[0071] The device 700 may include a first presentation module 710 configured to present an example interface (200B-200D) in response to detecting a first predetermined operation in an example interface (200A) of a target application. The example interface includes at least one entry related to menu suggestions.

[0072] The device 700 may also include a second presentation module 720 configured to present at least one set of candidate menu recommendations in response to detecting a predetermined type of input at at least one entrance.

[0073] The device 700 may also include a third presentation module 730 configured to, in response to detecting a selection operation for one of at least one set of candidate food recommendations, present an acquisition path associated with the selected set of candidate food recommendations on a sample interface.

[0074] In some embodiments, the first interface presents information on multiple dishes that can be obtained from the target application, and the first predetermined operation includes at least one of the following: a selection operation on at least one of the multiple dishes; or a triggering of an entry point for presenting the second interface.

[0075] In some embodiments, the input is natural language information, which indicates at least one of the following: the user's dining preferences; the user's expected level of physical health; and the user's nutritional needs.

[0076] In some embodiments, the second interface presents a set of prompts associated with the input, and the second presentation module 720 is further configured to present at least one set of candidate menu recommendations in response to detecting a selection operation for at least one of the prompts in the set.

[0077] In some embodiments, at least one set of candidate menu recommendations is generated by an agent that is selected based on input and specific user data.

[0078] In some embodiments, at least one prompt word is generated based on specific user data.

[0079] In some embodiments, specific user data includes at least one of the following: the user's health information; the user's expected level of physical health; and the user's historical food selection information on the target application.

[0080] In some embodiments, the device 700 may further include a fourth presentation module configured to present an entry point for inputting specific user data on a first interface or a second interface; and to present a third interface in response to receiving a selection operation for the entry point, the third interface presenting multiple health parameter input paths.

[0081] In some embodiments, the input includes an image of a meal, and the second presentation module 720 is further configured to, in response to the input of a meal image detected at at least one entrance, present a health index analysis result for the meal and at least one set of candidate meal recommendations, the at least one set of candidate meal recommendations being generated at least based on the health index analysis result.

[0082] In some embodiments, the device 700 may further include a fifth presentation module configured to present the reasons for recommending at least one set of candidate dishes while presenting at least one set of candidate dish recommendations.

[0083] The modules included in device 700 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 700 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0084] Figure 19 A block diagram of an electronic device 800 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 19 The electronic device 800 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein.

[0085] like Figure 19 As shown, electronic device 800 is in the form of a general-purpose electronic device. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 800.

[0086] Electronic device 800 typically includes multiple computer storage media. Such media can be any available media accessible to electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 820 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 830 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media capable of storing information and / or data and accessible within electronic device 800.

[0087] Electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 19As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 820 may include computer program product 825 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0088] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 800 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 800 can operate in a networked environment using logical connections to one or more other servers, networked personal computers (PCs), or another network node.

[0089] Input device 850 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 860 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 800 can also communicate with one or more external devices (not shown) via communication unit 840 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 800, or with any device that enables electronic device 800 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0090] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores one or more computer instructions, wherein the one or more computer instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transient computer-readable medium and includes computer-executable instructions that are executed by a processor to implement the methods described above.

[0091] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0092] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0093] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0094] 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 various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated 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. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may 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.

[0095] Various implementations of this disclosure have been described above. The foregoing description is exemplary and not exhaustive, nor is it limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the implementations disclosed herein.

Claims

1. A method for making recommendations, comprising: In response to detecting a first pre-defined operation in a first interface of the target application, a second interface is presented, the second interface including at least one entry related to meal suggestions; In response to detecting a predetermined type of input at the at least one entrance, present at least one set of candidate meal recommendations; as well as In response to detecting a selection operation for one of the at least one set of candidate meal recommendations, an acquisition path associated with the selected set of candidate meal recommendations is presented on the first interface.

2. The method of claim 1, wherein the first interface presents information on a plurality of meals that can be obtained from the target application, and the first predetermined operation includes at least one of the following: The operation of selecting at least one of the multiple meal items; or Triggered for the entry point used to present the second interface.

3. The method of claim 1, wherein the input is natural language information, the natural language information indicating at least one of the following: User's dining preference information; User's expected level of physical health; The user's nutritional needs for meals.

4. The method of claim 1, wherein the second interface presents a set of prompts associated with the input, and wherein presenting the at least one set of candidate meal recommendations includes: In response to detecting a selection operation for at least one of the set of prompt words, the at least one set of candidate meal recommendations is presented.

5. The method of claim 1, wherein the at least one set of candidate menu recommendations is generated by an agent selected based on the input and specific user data.

6. The method of claim 5, wherein the at least one prompt word is generated based on the specific user data.

7. The method according to claim 5 or 6, wherein the specific user data includes at least one of the following: User's health information; User's expected level of physical health; User's historical food selection information on the target application.

8. The method according to claim 7, wherein the method further comprises: An entry point for inputting the specific user data is presented on the first interface or the second interface; In response to receiving a selection operation for the entry point, a third interface is presented, which displays multiple health parameter input paths.

9. The method of claim 1, wherein the input includes an image of a dish, and at least one set of candidate dish recommendations is presented based on the input, comprising: In response to the input of a food image detected at the at least one entrance, a health index analysis result for the food and the at least one set of candidate food recommendations are presented, the at least one set of candidate food recommendations being generated at least based on the health index analysis result.

10. The method according to claim 1, further comprising: While presenting the at least one set of candidate meal recommendations, the reasons for recommending the at least one set of candidate meal recommendations are also presented.

11. An apparatus for recommendation, comprising: A first presentation module is configured to present a second interface in response to detecting a first predetermined operation in a first interface of a target application, the second interface including at least one entry related to meal suggestions. The second presentation module is configured to present at least one set of candidate meal recommendations in response to detecting a predetermined type of input at the at least one entrance. as well as The third presentation module is configured to, in response to detecting a selection operation for one of the at least one set of candidate meal recommendations, present an acquisition path associated with the selected set of candidate meal recommendations on the first interface.

12. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 10.

14. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 10.

Images