Information recommendation method, device and storage medium

Abstract

This invention provides an information recommendation method, apparatus, and storage medium applied to a display terminal connected to a wearable device and a refrigerator. The method includes: obtaining user status data from the wearable device and food inventory data from the refrigerator; analyzing the user status data based on a data analysis model and obtaining the analysis results; generating a recipe recommendation instruction based on the food inventory data and the analysis results, and displaying the recipe recommendation instruction containing the recommended food ingredients and cooking information on the display terminal. This invention achieves customized recipe recommendations based on the user's health status and the available food in the refrigerator, meeting the user's healthy eating requirements. Simultaneously, playing a video of the recipe preparation process on the display terminal enhances the user experience.

Description

Technical Field

[0001] This invention relates to the field of smart home technology, and in particular to an information recommendation method, apparatus, and storage medium. Background Technology

[0002] As people's living standards and consumption levels improve, the food in refrigerators is becoming more abundant, and people are paying more and more attention to healthy eating. However, existing refrigerators only have the function of managing food, and fail to link the user's health status, the food stored in the refrigerator, and healthy recipes. They cannot realize personalized recipe customization and healthy eating recommendations based on the user's own health status, which affects the user experience. Summary of the Invention

[0003] This invention provides an information recommendation method, apparatus, and storage medium to address the shortcomings of existing technologies that cannot associate refrigerator food, user's physical condition, and healthy food, thus failing to achieve personalized healthy recipe customization based on user's physical condition.

[0004] According to a first aspect of the present invention, an information recommendation method is applied to a display terminal, wherein the display terminal is connected to a wearable device and a refrigerator respectively; The method includes: Obtain user status data of the wearable device and food inventory data in the refrigerator; The user status data is analyzed based on a data analysis model, and the analysis results are obtained. Based on the ingredient inventory data and the analysis results, a recipe recommendation instruction is generated, and the ingredient recommendation cooking information contained in the recipe recommendation instruction is played on the display terminal.

[0005] According to one embodiment of the present invention, the analysis of the user status data based on the data analysis model specifically includes: Based on the user status data and health status indicators, unstructured physical status data and structured nutritional requirement data of the user are obtained, and a mapping rule base is established according to the unstructured physical status data and the structured nutritional requirement data. Based on the mapping rule base, output the body status parameters and nutritional requirement parameters corresponding to the user status data, and generate the analysis results based on the body status parameters and nutritional requirement parameters.

[0006] Specifically, this embodiment provides an implementation method for analyzing the user status data based on a data analysis model.

[0007] According to one embodiment of the present invention, generating recipe recommendation instructions based on the ingredient inventory data and the analysis results specifically includes: If the ingredient inventory data meets the analysis results, a recommended recipe is generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the recommended recipe. If the ingredient inventory data does not meet the analysis results, an alternative recipe and / or ingredient purchase list are generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the alternative recipe and / or the ingredient purchase list.

[0008] Specifically, this embodiment provides an implementation method for generating recipe recommendation instructions based on the ingredient inventory data and the analysis results.

[0009] According to one embodiment of the present invention, the step of playing the recipe recommendation instruction containing the recommended ingredient cooking information on the display terminal specifically includes: When the recipe recommendation instruction points to the recommended recipe, the cooking video corresponding to the recommended recipe is obtained and the cooking video is played on the display terminal; When the recipe recommendation instruction points to the alternative recipe and a playback instruction is received, the cooking video corresponding to the alternative recipe is obtained and the cooking video is played on the display terminal; When the recipe recommendation instruction points to the ingredient purchase list and a playback instruction is received, the system links to the purchase port based on the ingredient purchase list and displays the purchase page corresponding to the purchase port on the display terminal.

[0010] Specifically, this embodiment provides an implementation method for playing the recipe recommendation instruction containing recommended ingredient cooking information on the display terminal.

[0011] According to one embodiment of the present invention, the cooking video is a pre-stored video stored in the display terminal or cloud server; And / or, the cooking video is a test video transmission video.

[0012] Specifically, this embodiment provides an implementation method for a cooking video.

[0013] According to one embodiment of the present invention, after recommending cooking information based on the recipe recommendation instruction, the method further includes: Based on the recipe switching instruction obtained, the recommended cooking information of the ingredients contained in the ingredient switching instruction after the switch is played on the display terminal; The recipe switching command comes from any one of the display terminal, the wearable device, and the refrigerator.

[0014] Specifically, this embodiment provides an implementation method based on the ingredient recommendation cooking information of the recipe recommendation instruction.

[0015] According to one embodiment of the present invention, after recommending cooking information based on the recipe recommendation instruction, the method further includes: Based on the preference instruction obtained to update the recipe recommendation instruction, the updated recipe recommendation instruction containing the recommended cooking information of ingredients is played on the display terminal. The preference instruction includes user-defined preferred ingredients and / or preferred recipes. The preference instruction comes from any one of the display terminal, the wearable device, and the refrigerator.

[0016] Specifically, this embodiment provides an implementation method based on the ingredient recommendation cooking information of the recipe recommendation instruction.

[0017] According to one embodiment of the present invention, after recommending cooking information based on the recipe recommendation instruction, the method further includes: Based on the obtained device switching instruction for switching playback devices, the target device identified by the device switching instruction is obtained; Based on the playback file format of the target device, the recommended cooking information for the ingredients is played.

[0018] Specifically, this embodiment provides an implementation method based on the ingredient recommendation cooking information of the recipe recommendation instruction.

[0019] According to a second aspect of the present invention, an information recommendation device includes: The data acquisition module is used to acquire user status data of wearable devices and food inventory data in the refrigerator; The data analysis module is used to analyze the user status data based on the data analysis model and obtain the analysis results; The instruction generation module is used to generate recipe recommendation instructions based on the ingredient inventory data and the analysis results, and to play the ingredient recommendation cooking information contained in the recipe recommendation instructions on the display terminal, which is connected to the wearable device and the refrigerator respectively.

[0020] A third aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the information recommendation method as described above.

[0021] The above-mentioned one or more technical solutions of the present invention have at least one of the following technical effects: The information recommendation method, device and storage medium provided by the present invention obtains the user's physical condition and the existing food in the refrigerator, realizes customized recipe recommendations based on the user's health condition, meets the user's requirements for healthy eating, and at the same time plays a video of the recipe preparation process on the display terminal, thereby improving the user experience. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is one of the flowcharts illustrating the information recommendation method provided by the present invention.

[0024] Figure 2 This is the second flowchart illustrating the information recommendation method provided by the present invention.

[0025] Figure 3 This is a schematic diagram of the information recommendation device provided by the present invention.

[0026] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0027] Figure label: 10. Data acquisition module; 20. Data analysis module; 30. Instruction generation module.

[0028] 810, Processor; 820, Communication interface; 830, Memory; 840, Communication bus. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0030] In the description of the embodiments of the present invention, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0031] The following is combined Figure 1 and Figure 2 The technical solution of the present invention will be described in detail below.

[0032] like Figure 1 As shown, the present invention provides an information recommendation method applied to a display terminal, which is connected to a wearable device and a refrigerator respectively; The methods include: Obtain user status data from wearable devices and food inventory data in the refrigerator; The user status data is analyzed based on the data analysis model, and the analysis results are obtained. Based on ingredient inventory data and analysis results, recipe recommendation instructions are generated, and the ingredient recommendation cooking information contained in the recipe recommendation instructions is played on the display terminal.

[0033] It should be noted that as living standards improve, people are paying increasing attention to healthy eating. Currently, the market mainly offers the following types of related applications: 1. Simple recipe app: It provides a huge number of recipes, but users need to search for them themselves. It cannot make personalized recommendations based on the user's current physical condition.

[0034] 2. Simple health management apps: These can record data such as weight and exercise, but they are usually disconnected from dietary recommendations and cannot be linked to the actual ingredients that users have at home.

[0035] 3. Refrigerator Food Management System: It can identify the food in the refrigerator, manage inventory, and remind you of the expiration date, but its functions are limited to food management itself and lack in-depth exploration of users' health needs and proactive services.

[0036] The above method also has obvious drawbacks, specifically: 1. Information fragmentation: Health data, recipe data, and ingredient data are independent of each other, making it impossible to form effective decision support.

[0037] 2. Lack of personalization: The recommendations are static and cannot respond to the user's dynamically changing physical state (such as fatigue, fever, post-exercise, etc.).

[0038] 3. Poor feasibility: The recommended recipes may lack key ingredients, requiring users to make additional purchases, which reduces the actual adoption rate of the recommendations.

[0039] Therefore, based on the aforementioned deficiencies of the prior art, this invention provides a solution that can dynamically combine the user's physical condition, health needs, and existing food inventory to generate a practical and personalized healthy eating plan. This solution overcomes the shortcomings of the prior art and provides an intelligent, personalized, and highly executable healthy eating recommendation plan.

[0040] Furthermore, the system dynamically links user health data, refrigerator food data, and recipe knowledge base. When a user has a need, it will combine user health data and existing refrigerator food data to recommend healthy recipes and operating steps or videos to the user, thereby improving the user experience.

[0041] It should be noted that this invention displays the corresponding video of the recipe through a display terminal. Compared to a refrigerator displaying recipe videos, a refrigerator requires an embedded chip, which, due to limitations in power consumption and size, makes it difficult to support complex algorithms (such as multi-dimensional user body data modeling, ingredient matching weight calculation, and personalized recipe iterative optimization). The improved solution migrates computing power to the television, which, as the central hub of the home's smart system, possesses stronger CPU / GPU computing power and larger storage capacity.

[0042] Furthermore, a lightweight AI model can be deployed on the TV to dynamically adjust the recommendation weights based on user feedback on recommended recipes (whether they are adopted, changes in body data after consumption), thus achieving a closed loop of "recipe recommendation - user feedback - model optimization". This invention can reduce the hardware cost and power consumption of refrigerators, eliminating the need to equip refrigerators with high-performance chips, reducing investment in refrigerator hardware research and development and production, while also reducing refrigerator standby power consumption and improving device battery life.

[0043] In some possible embodiments of the present invention, the analysis of user status data based on a data analysis model specifically includes: Based on user status data and health status indicators, unstructured physical status data and structured nutritional needs data of users are obtained, and a mapping rule base is established based on the unstructured physical status data and structured nutritional needs data. Based on the mapping rule base, output the body status parameters and nutritional requirement parameters corresponding to the user status data, and generate analysis results based on the body status parameters and nutritional requirement parameters.

[0044] Specifically, this embodiment provides an implementation method for analyzing user status data based on a data analysis model. By acquiring user status parameters through wearable devices, the user's physical condition and corresponding health status indicators can be analyzed based on the data analysis model. Then, a corresponding mapping rule library is established based on unstructured physical status data and structured nutritional requirement data. Subsequently, the corresponding analysis results are matched based on the physical status parameters and nutritional requirement parameters corresponding to the real-time acquired user status data.

[0045] It should be noted that the system simultaneously processes body data from wearable devices (heart rate, blood pressure, exercise consumption, sleep quality, etc.) and food data from the refrigerator (type, shelf life, nutritional components, allergens, etc.). It can also be extended to access users' historical dietary preference data, seasonal food data, and medical nutrition knowledge bases to output more accurate personalized recipes, thus achieving the fusion analysis of diverse data.

[0046] Furthermore, the data analysis model is an NLP analysis model. NLP analysis refers to using Natural Language Processing (NLP) technology to parse, mine, and model text data related to human health, thereby achieving the assessment, monitoring, or early warning of physical condition.

[0047] In some possible embodiments of the present invention, recipe recommendation instructions are generated based on ingredient inventory data and analysis results, specifically including: If the ingredient inventory data meets the analysis results, a recommended recipe is generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the recommended recipe. If the ingredient inventory data does not meet the analysis results, generate alternative recipes and / or ingredient purchase lists based on the ingredient inventory data, and generate recipe recommendation instructions based on the alternative recipes and / or ingredient purchase lists.

[0048] Specifically, this embodiment provides an implementation method for generating recipe recommendation instructions based on ingredient inventory data and analysis results. According to the ingredient inventory data, it determines whether to generate a recommended recipe, an alternative recipe, or an ingredient purchase list, and then recommends an appropriate recipe recommendation instruction to the user.

[0049] In this embodiment, when the food inventory data meets the dietary needs corresponding to the user's physical condition analysis results, a recommended recipe is directly generated based on the existing food and a recipe recommendation instruction is output. Personalized and healthy recipe recommendations can be completed without additional food purchases, improving food utilization, reducing food waste, and enhancing the timeliness and practicality of recipe recommendations.

[0050] In this embodiment, when the food inventory data does not meet the dietary needs corresponding to the user's physical condition analysis results, an alternative recipe and / or food purchase list can be automatically generated, and a corresponding recipe recommendation instruction can be generated based on the alternative recipe and / or food purchase list, so as to avoid recommendation failure due to insufficient ingredients and ensure the continuity and robustness of the recipe recommendation process.

[0051] In this embodiment, by differentiating between two scenarios—whether the food inventory meets the demand—the recipe recommendations become more flexible, intelligent, and tailored to actual usage scenarios. This not only adapts to the user's currently available ingredients but also provides clear guidance on replenishing ingredients, thereby enhancing the user experience and the system's intelligence.

[0052] It should be noted that the recommended recipes refer to recipes generated by the system based on the types, quantities, and nutritional components of currently available ingredients, combined with the user's health status, when the ingredient inventory data meets the dietary needs corresponding to the user's physical condition analysis results. These recipes can be prepared directly without the need to supplement ingredients.

[0053] Furthermore, the recommended recipes are perfectly matched to the user's current ingredient inventory, providing direct guidance for the user to complete the cooking process and ensuring the recipes' feasibility and timeliness.

[0054] It should be added that alternative recipes refer to recipes generated by the system within the existing food inventory range that can replace the target recipe and meet the user's physical condition requirements when the food inventory data is insufficient to meet the dietary needs corresponding to the user's physical condition analysis results.

[0055] Furthermore, alternative recipes do not rely on additional ingredient purchases; they simply recombine existing ingredients to provide usable and compliant dietary solutions even in situations where ingredients are scarce. This avoids recommendations failing due to ingredient shortages and improves the system's robustness and usability.

[0056] It should also be noted that the ingredient procurement list refers to a list of ingredients to be replenished automatically generated by the system based on the difference between the ingredients required for the target recipe and the current ingredient inventory when the ingredient inventory data does not meet the dietary needs corresponding to the user's physical condition analysis results.

[0057] Furthermore, the ingredient procurement list should include at least the name, quantity, and type of the ingredients to be replenished, providing users with clear and direct guidance on ingredient replenishment. This allows users to quickly replenish the ingredients according to the list, so that they can subsequently create target recipes that suit their own physical condition, thereby improving the intelligent experience and ease of use.

[0058] In some possible embodiments of the present invention, playing the recipe recommendation instruction containing the recommended ingredient cooking information on the display terminal specifically includes: When the recipe recommendation command points to a recommended recipe, obtain the cooking video corresponding to the recommended recipe and play the cooking video on the display terminal; When the recipe recommendation instruction points to an alternative recipe and a playback instruction is received, the cooking video corresponding to the alternative recipe is obtained and played on the display terminal. When the recipe recommendation command points to the ingredient purchase list and a playback command is received, the system links to the purchase port based on the ingredient purchase list and displays the purchase page corresponding to the purchase port on the display terminal.

[0059] Specifically, this embodiment provides an implementation method for playing recipe recommendation instructions containing ingredient recommendation cooking information on a display terminal. By displaying and interacting with different directions of the recipe recommendation instructions in a scenario-based and selectable manner, the output content of the display terminal is accurately matched with the actual needs of the user.

[0060] In this embodiment, when the recipe recommendation instruction points to a recommended recipe, the corresponding cooking video is automatically retrieved and played, eliminating the need for users to manually search, select, or input operations. This simplifies the operation process, enhances the intuitiveness and immediacy of cooking guidance, and allows users to directly follow the video to prepare the ingredients.

[0061] In this embodiment, when the recipe recommendation instruction points to an alternative recipe, the corresponding cooking video is played only after the playback instruction is received. The user confirmation mechanism avoids invalid playback and waste of resources, making the system interaction more in line with the user's true intentions and improving the user's flexibility and sense of control.

[0062] In this embodiment, when the recipe recommendation instruction points to the ingredient purchase list, the system automatically links to the purchase port and displays the purchase page after receiving the playback instruction. The prompt of insufficient ingredients is directly transformed into an executable purchase entry, realizing a one-stop connection from recipe recommendation to ingredient replenishment, improving the system's intelligence and ease of use. Users can access the purchase software through the display terminal to purchase the corresponding dishes.

[0063] It should be noted that the overall solution implements differentiated processing for video playback, conditional trigger playback, and redirection to the purchasing page based on the different types of recommended recipes, alternative recipes, and ingredient purchase lists. This ensures that the output content is highly compatible with the instruction type, avoids information confusion and misoperation, and improves the stability of system operation and user experience.

[0064] In some possible embodiments of the present invention, the cooking video is a pre-stored video stored on a display terminal or a cloud server; And / or, cooking videos can be used to try transmitting videos.

[0065] Specifically, this embodiment provides an implementation method for cooking videos. By configuring the cooking videos as pre-stored videos on a display terminal or cloud server and / or real-time transmitted videos, the acquisition methods of cooking videos become more flexible and diverse, and can adapt to different network environments, storage conditions and usage scenarios.

[0066] In this embodiment, using pre-stored videos can reduce reliance on network bandwidth, decrease video loading latency, and improve playback smoothness and stability.

[0067] In this embodiment, using real-time video transmission can save local storage space and support real-time updates and expansion of video content, ensuring the richness and timeliness of cooking guidance content.

[0068] It should be noted that by simultaneously supporting pre-stored video and real-time video transmission, the system can adaptively select the optimal video acquisition method based on the actual operating environment, thereby improving the user viewing experience while enhancing the system's compatibility and scene adaptability.

[0069] In some possible embodiments of the present invention, after recommending cooking information based on recipe recommendation instructions and ingredient recommendations, the method further includes: Based on the recipe switching command obtained, the recommended cooking information of the ingredients contained in the switched ingredient switching command is played on the display terminal; Recipe switching commands can be sent from any of the display terminal, wearable devices, and refrigerators.

[0070] Specifically, this embodiment provides an implementation method based on recipe recommendation instructions and ingredient recommendation cooking information. After outputting the ingredient recommendation cooking information, it supports switching and playing the corresponding ingredient recommendation cooking information according to recipe switching instructions generated from any one of the display terminal, wearable device, and refrigerator. This enables the technical effect of switching recipes freely across multiple devices and scenarios.

[0071] In this embodiment, recipes can be switched in real time according to user needs during the recipe recommendation process without having to restart the recommendation process. This simplifies user operations, improves recipe switching efficiency and flexibility, and records user behavior based on the user's recipe switching instructions to optimize the data analysis model, so as to provide users with output results that better meet their needs in the future.

[0072] In this embodiment, the source of the recipe switching command is configured to be any one of the display terminal, wearable device and refrigerator, so as to realize unified control of multiple terminals and cross-device linkage switching. Users can initiate the operation from the nearest location in the current scene, which improves the convenience of interaction and scene adaptability.

[0073] Furthermore, users can change the content displayed on the display terminal by issuing recipe switching commands, providing a better user experience.

[0074] In some possible embodiments of the present invention, after recommending cooking information based on recipe recommendation instructions and ingredient recommendations, the method further includes: Based on the preference instruction that obtains the updated recipe recommendation instruction, the updated recipe recommendation instruction containing the recommended ingredients and cooking information is played on the display terminal. The preference instruction includes the user's set preferred ingredients and / or preferred recipes. Preference commands can be derived from any of the display terminal, wearable devices, and refrigerators.

[0075] Specifically, this embodiment provides an implementation method after the ingredient recommendation cooking information is based on the recipe recommendation command. After outputting the ingredient recommendation cooking information, this embodiment supports updating the recipe recommendation command based on preference commands initiated by multiple terminals, and synchronously plays the updated ingredient recommendation cooking information.

[0076] In this embodiment, the preference instruction refers to the control instruction initiated by the user to adjust the direction of the recipe recommendation and make it more in line with their own dietary preferences. It is used to update the original recipe recommendation instruction. Its core includes the user's preferred ingredients and / or preferred recipes. Among them, preferred ingredients refer to the ingredients that the user subjectively prefers to eat and wants to be included in the recipe (such as the user's preference for beef and broccoli), and preferred recipes refer to the types of recipes that the user subjectively likes and wants to be recommended first (such as the user's preference for light stir-fries and low-fat salads).

[0077] In this embodiment, the preference command originates from any of the following terminals: display terminal (such as the operation panel of a smart TV, or input from a remote control), wearable device (such as touch commands or voice commands from a smartwatch), or smart refrigerator (such as input from a refrigerator touch screen). After initiation, the command is synchronously transmitted to the display terminal, triggering an update of the recipe recommendation command.

[0078] It should be noted that in this scenario, users can choose their preferred flavor and ingredients from the recommended recipes provided, thus satisfying both their preferences and nutritional needs.

[0079] Furthermore, users can change the content displayed on the display terminal by issuing preference commands, providing a better user experience. At the same time, user behavior is recorded based on user preference commands, and the data analysis model is optimized to provide users with output results that better meet their needs in the future.

[0080] In some possible embodiments of the present invention, after recommending cooking information based on recipe recommendation instructions and ingredient recommendations, the method further includes: Based on the device switching command for switching playback devices, obtain the target device identified by the device switching command; Based on the target device's playback file format, it plays recommended cooking information for ingredients.

[0081] Specifically, this embodiment provides an implementation method based on recipe recommendation instructions and ingredient recommendation cooking information. By switching to the corresponding target device according to the device switching instructions issued by the user, it realizes the playback of content of corresponding format files according to different target devices, and further improves the user experience.

[0082] In this embodiment, the device switching command refers to a control command initiated by the user to switch the playback carrier of the recommended cooking information for ingredients from the current display terminal to another specified smart device. The command contains a clear target device identifier (such as device name, device ID) to accurately locate the playback device to which the user needs to switch.

[0083] In this embodiment, the target device refers to the smart device specified in the device switching instruction, which is used to undertake the task of playing cooking information recommended by ingredients. In combination with the multi-terminal linkage architecture of this system, the target device is preferably a kitchen auxiliary smart device (such as a kitchen sub-screen, a smart oven with its own display screen) that establishes a communication connection with the display terminal, wearable device, smart refrigerator, etc., or a display terminal in other rooms.

[0084] In this embodiment, the playback file format refers to the file format that the target device supports and can play normally the recommended cooking information (cooking videos, text steps, etc.) (such as video formats MP4 and AVI, text formats TXT and PDF, etc.). The system can automatically identify the format compatibility range of the target device.

[0085] It should be noted that this invention breaks the limitations of a single display terminal by supporting users to initiate device switching commands and switch the playback medium for recommended cooking information, thus adapting to the user's needs in different scenarios (such as switching from the living room display terminal to the kitchen sub-screen for easy viewing while cooking; or switching to the bedroom display terminal for easy previewing of recipes), thereby improving the flexibility and adaptability of use.

[0086] Furthermore, when switching playback, the recommended cooking information is adapted to the playback file format of the target device to ensure that the recommended cooking information can be played normally and smoothly on the target device, avoiding problems such as playback failure, image distortion, and text misalignment caused by format incompatibility, thereby improving the stability and compatibility of system playback.

[0087] In some embodiments of the present invention, such as Figure 2 As shown, this solution provides an information recommendation method, including: Prerequisites: 1. The TV version already includes refrigerator food management functions, a recipe library, and a health management application; 2. The TV version supports microphone input: voice command function; The specific process steps are described below: start Step S1: Receive the user's physical health status information.

[0088] Step S2: Analyze the body's condition through NLP to identify health indicators and nutritional needs.

[0089] A rule base for mapping from "unstructured descriptions of body states" (such as "fatigue") to "structured nutritional requirement tags" (such as "protein supplementation" and "blood replenishment") has been established. This rule base can be built by nutrition experts and continuously optimized through machine learning.

[0090] Step S3: Obtain a real-time food inventory list from the smart refrigerator system.

[0091] Step S4: Does the health requirement match the available ingredients? This decision box leads to two branches: Yes: Flow to step S5a.

[0092] No: Flow to step S5b.

[0093] Step S5a: Based on matching ingredients, select the best healthy recipes from the recipe library.

[0094] Step S5b: Generate a list of ingredients that need to be purchased and provide alternative recipes that include some of the existing ingredients.

[0095] Step S6: Present the final recommended results (recipe + shopping list) to the user, including the recipe's operation steps or video.

[0096] Step S7: Record user feedback behavior and optimize the model. The arrow points back to step S2 or S4 from this step, indicating that feedback learning is an ongoing process.

[0097] Finish.

[0098] It should be noted that this invention dynamically and interconnects user health data, refrigerator food data, and a recipe knowledge base. Simultaneously, it establishes a mapping rule base from "unstructured descriptions of physical states" (such as "fatigue") to "structured nutritional requirement tags" (such as "protein supplementation" and "blood replenishment"). This rule base can be constructed by nutrition experts and continuously optimized through machine learning.

[0099] The information recommendation device provided by the present invention is described below. The information recommendation device described below and the information recommendation method described above can be referred to in correspondence.

[0100] like Figure 3 As shown, the present invention provides an information recommendation device, comprising: Data acquisition module 10 is used to acquire user status data of wearable devices and food inventory data in the refrigerator; The data analysis module 20 is used to analyze user status data based on the data analysis model and obtain analysis results; The instruction generation module 30 is used to generate recipe recommendation instructions based on ingredient inventory data and analysis results, and to play the ingredient recommendation cooking information contained in the recipe recommendation instructions on the display terminal. The display terminal is connected to the wearable device and the refrigerator respectively.

[0101] It is possible to analyze user status data based on data analysis models, specifically including: Based on user status data and health status indicators, unstructured physical status data and structured nutritional needs data of users are obtained, and a mapping rule base is established based on the unstructured physical status data and structured nutritional needs data. Based on the mapping rule base, output the body status parameters and nutritional requirement parameters corresponding to the user status data, and generate analysis results based on the body status parameters and nutritional requirement parameters.

[0102] Specifically, this embodiment provides an implementation method for analyzing user status data based on a data analysis model.

[0103] Based on ingredient inventory data and analysis results, recipe recommendation instructions may be generated, specifically including: If the ingredient inventory data meets the analysis results, a recommended recipe is generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the recommended recipe. If the ingredient inventory data does not meet the analysis results, generate alternative recipes and / or ingredient purchase lists based on the ingredient inventory data, and generate recipe recommendation instructions based on the alternative recipes and / or ingredient purchase lists.

[0104] Specifically, this embodiment provides an implementation method for generating recipe recommendation instructions based on ingredient inventory data and analysis results.

[0105] Possibly, the recipe recommendation instruction, which includes recommended ingredient cooking information, can be played on the display terminal, specifically including: When the recipe recommendation command points to a recommended recipe, obtain the cooking video corresponding to the recommended recipe and play the cooking video on the display terminal; When the recipe recommendation instruction points to an alternative recipe and a playback instruction is received, the cooking video corresponding to the alternative recipe is obtained and played on the display terminal. When the recipe recommendation command points to the ingredient purchase list and a playback command is received, the system links to the purchase port based on the ingredient purchase list and displays the purchase page corresponding to the purchase port on the display terminal.

[0106] Specifically, this embodiment provides an implementation method for playing recipe recommendation instructions containing recommended ingredient cooking information on a display terminal.

[0107] The cooking video may be a pre-stored video on a display terminal or cloud server; And / or, cooking videos can be used to try transmitting videos.

[0108] Specifically, this embodiment provides an implementation method for a cooking video.

[0109] It is possible that, based on the recipe recommendation instructions and ingredient recommendations, the cooking information may also include: Based on the recipe switching command obtained, the recommended cooking information of the ingredients contained in the switched ingredient switching command is played on the display terminal; Recipe switching commands can be sent from any of the display terminal, wearable devices, and refrigerators.

[0110] Specifically, this embodiment provides an implementation method based on the recipe recommendation instruction and the recommended cooking information.

[0111] It is possible that, based on the recipe recommendation instructions and ingredient recommendations, the cooking information may also include: Based on the preference instruction that obtains the updated recipe recommendation instruction, the updated recipe recommendation instruction containing the recommended ingredients and cooking information is played on the display terminal. The preference instruction includes the user's set preferred ingredients and / or preferred recipes. Preference commands can be derived from any of the display terminal, wearable devices, and refrigerators.

[0112] Specifically, this embodiment provides an implementation method based on the recipe recommendation instruction and the recommended cooking information.

[0113] It is possible that, based on the recipe recommendation instructions and ingredient recommendations, the cooking information may also include: Based on the device switching command for switching playback devices, obtain the target device identified by the device switching command; Based on the target device's playback file format, it plays recommended cooking information for ingredients.

[0114] Specifically, this embodiment provides an implementation method based on the recipe recommendation instruction and the recommended cooking information.

[0115] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions from the memory 830 to execute an information recommendation method.

[0116] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several 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 methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0117] In possible embodiments, the server can be local or remote relative to the terminal. For example, the server can access information stored in the user terminal, a database, or any combination thereof via a network.

[0118] In possible embodiments, the server can be implemented on a cloud platform; by way of example only, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, or any combination thereof.

[0119] In possible embodiments, the network can be any type of wired or wireless network, or a combination thereof. By way of example only, the network may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), wireless local area networks (WLANs), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof.

[0120] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the information recommendation methods provided by the above methods.

[0121] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the information recommendation methods provided by the methods described above.

[0122] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0123] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0124] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "method," "specific method," or "some methods," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or method is included in at least one embodiment or method of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or method. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or methods. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or methods described in this specification, as well as the features of different embodiments or methods.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An information recommendation method, characterized in that, The device is used in a display terminal, which is connected to a wearable device and a refrigerator, respectively. The method includes: Obtain user status data of the wearable device and food inventory data in the refrigerator; The user status data is analyzed based on a data analysis model, and the analysis results are obtained. Based on the ingredient inventory data and the analysis results, a recipe recommendation instruction is generated, and the ingredient recommendation cooking information contained in the recipe recommendation instruction is played on the display terminal.

2. The information recommendation method according to claim 1, characterized in that, The analysis of the user status data based on the data analysis model specifically includes: Based on the user status data and health status indicators, unstructured physical status data and structured nutritional requirement data of the user are obtained, and a mapping rule base is established according to the unstructured physical status data and the structured nutritional requirement data. Based on the mapping rule base, output the body status parameters and nutritional requirement parameters corresponding to the user status data, and generate the analysis results based on the body status parameters and nutritional requirement parameters.

3. The information recommendation method according to claim 1, characterized in that, The step of generating recipe recommendation instructions based on the ingredient inventory data and the analysis results specifically includes: If the ingredient inventory data meets the analysis results, a recommended recipe is generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the recommended recipe. If the ingredient inventory data does not meet the analysis results, an alternative recipe and / or ingredient purchase list are generated based on the ingredient inventory data, and a recipe recommendation instruction is generated based on the alternative recipe and / or the ingredient purchase list.

4. The information recommendation method according to claim 3, characterized in that, The step of playing the recipe recommendation instruction containing the recommended ingredient cooking information on the display terminal specifically includes: When the recipe recommendation instruction points to the recommended recipe, the cooking video corresponding to the recommended recipe is obtained and the cooking video is played on the display terminal; When the recipe recommendation instruction points to the alternative recipe and a playback instruction is received, the cooking video corresponding to the alternative recipe is obtained and the cooking video is played on the display terminal; When the recipe recommendation instruction points to the ingredient purchase list and a playback instruction is received, the system links to the purchase port based on the ingredient purchase list and displays the purchase page corresponding to the purchase port on the display terminal.

5. The information recommendation method according to claim 4, characterized in that, The cooking video is a pre-stored video stored on the display terminal or cloud server; And / or, the cooking video is a test video transmission video.

6. The information recommendation method according to any one of claims 1 to 5, characterized in that, Following the ingredient recommendation cooking information based on the recipe recommendation instruction, the process specifically includes: Based on the recipe switching instruction obtained, the recommended cooking information of the ingredients contained in the ingredient switching instruction after the switch is played on the display terminal; The recipe switching command comes from any one of the display terminal, the wearable device, and the refrigerator.

7. The information recommendation method according to any one of claims 1 to 5, characterized in that, Following the ingredient recommendation cooking information based on the recipe recommendation instruction, the process specifically includes: Based on the preference instruction obtained to update the recipe recommendation instruction, the updated recipe recommendation instruction containing the recommended cooking information of ingredients is played on the display terminal. The preference instruction includes user-defined preferred ingredients and / or preferred recipes. The preference instruction comes from any one of the display terminal, the wearable device, and the refrigerator.

8. The information recommendation method according to any one of claims 1 to 5, characterized in that, Following the ingredient recommendation cooking information based on the recipe recommendation instruction, the process specifically includes: Based on the obtained device switching instruction for switching playback devices, the target device identified by the device switching instruction is obtained; Based on the playback file format of the target device, the recommended cooking information for the ingredients is played.

9. An information recommendation device, characterized in that, include: The data acquisition module is used to acquire user status data of wearable devices and food inventory data in the refrigerator; The data analysis module is used to analyze the user status data based on the data analysis model and obtain the analysis results; The instruction generation module is used to generate recipe recommendation instructions based on the ingredient inventory data and the analysis results, and to play the ingredient recommendation cooking information contained in the recipe recommendation instructions on the display terminal, which is connected to the wearable device and the refrigerator respectively.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the information recommendation method as described in any one of claims 1 to 8.

Images