Personalized pet meal whole-process service system and method

Abstract

The invention discloses a pet personalized meal whole-process service system and method, and relates to the technical field of intelligent pet services, and the system comprises a cloud data and service module and an intelligent cooking execution module. The cloud data and service module is used for establishing and managing pet structured archives, generating quantitative recipes through a catering algorithm based on archive data, associating an e-commerce system to carry out clean vegetable commodity matching and order process management, and storing full-process data, and the full-process data comprises archive updating, cooking feedback and order recording. According to the pet personalized meal whole-process service system and method provided by the invention, through integration of intelligent hardware, cloud data management and e-commerce service, comprehensive personalization and scientization of pet feeding are realized, the problem of unbalanced nutrition in traditional pet feeding is effectively solved, and the pet can be fed according to the specific health condition and nutritional requirements of the pet. A nutrition formula is dynamically generated and adjusted, and pet health is promoted.

Description

Technical Field

[0001] This invention relates to the field of intelligent pet service technology, specifically to a personalized pet meal service system and method throughout the entire process. Background Technology

[0002] In the pet care sector, as pet owners become increasingly concerned about their pets' health, the demand for personalized and scientifically formulated pet meals is becoming more prominent. Currently, the market offers products such as cooking equipment and food sales channels specifically for pets. Pet-specific cooking equipment provides basic heating and cooking functions, offering convenience for pet meal preparation; while pet food e-commerce platforms focus on selling standardized pet food, meeting the basic needs of pets' daily feeding. These products provide corresponding service support to pet owners in their respective fields, promoting the initial development of the pet service industry.

[0003] However, existing technologies and products are fragmented and lack effective synergy. Pet cooking equipment is relatively simple in function, often operating in fixed modes, requiring users to manually prepare ingredients, making it difficult to ensure scientific nutritional balance, and the operation process is relatively cumbersome. Pet food e-commerce platforms can only provide standardized products, unable to personalize them based on real-time pet health data, nor can they integrate with home cooking equipment. This disconnect between equipment and the food supply chain causes numerous inconveniences for pet owners. Even with cooking equipment, they struggle with ingredient matching and nutritional ratios, and after obtaining a recipe, they still need to manually process the ingredients, resulting in a poor overall experience. There is a lack of an integrated solution that combines personalized nutrition plans, intelligent cooking operations, and convenient supply chain services. To address this, we propose a personalized pet meal end-to-end service system and method. Summary of the Invention

[0004] To address the aforementioned technical issues, this paper provides a personalized pet meal service system and method covering the entire process. This solution resolves the problems of limited functionality in cooking equipment, reliance on manual ingredient preparation, and difficulty in ensuring nutritional accuracy; and e-commerce platforms offering only standardized food, unable to customize based on pet health data, and not integrated with cooking equipment. This disconnect leaves users facing difficulties with ingredient preparation and manual processing, highlighting the lack of an integrated solution.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A personalized pet meal service system includes: a cloud data and service module and an intelligent cooking execution module;

[0007] The cloud data and service module is used to establish and manage structured pet profiles, generate quantitative recipes based on the profile data through a meal planning algorithm, link the e-commerce system to match pre-prepared vegetable products and manage the order process, and store full-process data, including: profile updates, cooking feedback and order records;

[0008] The intelligent cooking execution module is electrically connected to the cloud data and service module. It is used to receive the cooking mode parameters sent down, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process, and automatically start the self-cleaning and high-temperature drying program after cooking to complete the equipment hygiene maintenance.

[0009] Preferably, the cloud data and service module includes: a pet file management unit, an intelligent meal preparation unit, an e-commerce and order unit, and a back-end management unit;

[0010] The pet record management unit is used to establish and maintain a structured pet record database, supporting the creation, modification, and updating of record data by the user terminal;

[0011] The intelligent meal preparation unit has a built-in standardized ingredient library, a multi-category recipe template library, and a nutrition mapping algorithm. Based on pet profile data, it uses the algorithm to match the ingredient library and the recipe template library to generate a quantitative recipe containing the types of ingredients, precise weights, and corresponding cooking mode recommendations.

[0012] The e-commerce and order unit is used to bind the quantitative recipes generated by the intelligent meal preparation unit with the pre-processed clean vegetables in the e-commerce system through a unique identifier, enabling users to place orders for the clean vegetables corresponding to the recipes with one click.

[0013] The back-end management unit is used for managing pre-prepared vegetable product information, processing order acceptance and dispatch, querying customer files, and maintaining meal preparation rules and recipe templates.

[0014] Preferably, the pet file management unit specifically includes:

[0015] Based on the user-preset interactive interface, a basic pet information input portal is provided. Pet information is obtained by filling in the basic information input portal. The pet information includes: pet breed, weight, age, health status and functional requirements.

[0016] Based on the obtained pet information, the system performs format validation on the pet basic information submitted by the user according to preset data validation rules, and obtains the validated pet basic information; if the validation fails, it returns to the user and prompts the specific error reason.

[0017] The verification rules include: weight must be a positive number and the unit must be uniformly kg; age must match the segmentation rules of childhood / youth / adulthood / elderly; and health status must be selected from a preset list or added and marked by customization.

[0018] Preferably, the pet file management unit further includes:

[0019] The verified pet basic information is structured and automatically associated with the user account ID of the current user. The user account ID is a 32-bit character unique identifier pre-assigned by the system. It is directly extracted from the user's login state cache and associated with the current pet information dataset.

[0020] Generate a unique identifier for your pet's profile. The generation rule is: calculated based on a combination of the system's current timestamp, a fragment of the device's MAC address, and a random number.

[0021] The basic information fields are standardized, including: converting the variety field into the system's preset standard variety name, uniformly retaining one decimal place for the weight field, and converting the age field into standard segmented text according to the selection result;

[0022] The data is encapsulated in a hierarchical format of user account ID + unique pet profile identifier + basic information fields. The hierarchical relationship is defined by a JSON data structure. The top level is the user account ID, the next level is the unique pet profile identifier, and the bottom level is the key-value pairs of each basic information field, generating standardized profile data entries.

[0023] A distributed structured database is constructed based on the standardized archival data entry structure.

[0024] Preferably, the intelligent meal preparation unit specifically includes:

[0025] The standardized food database includes: unique food identifier, name, nutritional information table, applicable pet type, and food status field. The nutritional data and status of the food are updated through the backend management unit.

[0026] The multi-category recipe template library is categorized by pet age, health status, and functional needs. Each template includes a unique template ID, a combination of category tags, a baseline nutritional ratio, an example of ingredient combination, and a recommended cooking mode number.

[0027] Based on the standardized file data pushed by the pet file management unit, preprocess it to generate standardized input data;

[0028] Multi-dimensional nutrition matching weights are set according to the degree of influence of pet nutritional needs, and the weights of the sub-indicators under each first-level dimension are split based on the analytic hierarchy process to determine the weight coefficient of each sub-indicator and form a weight matrix.

[0029] Preferably, the intelligent meal preparation unit further includes:

[0030] Collect breed-specific nutritional requirements data from pet nutrition industry standards, disease-specific nutritional adaptation rules from veterinary clinical guidelines, and formula and feedback data from historical meal planning data in the system, and integrate these three types of data into an algorithm training dataset.

[0031] The core architecture of the algorithm is constructed using a feature matching layer and a quantization calculation layer. The feature matching layer is responsible for matching the standardized input data with the dimensions and sub-indicators in the weight matrix, while the quantization calculation layer is responsible for numerical solutions based on nutritional requirements and food nutrition data.

[0032] Using the recipes in the training dataset as a reference, the matching threshold and calculation coefficients in the algorithm are adjusted by gradient descent, while cross-validation is used to eliminate the impact of data fluctuations on the algorithm.

[0033] The nutritional component field of the standardized food ingredient library, the baseline nutritional percentage field of the multi-category recipe template library, and the dimension weight field of the weight matrix are bound to the input interface, calculation logic, and output constraints of the algorithm to obtain the nutritional mapping algorithm.

[0034] Preferably, the e-commerce and order unit specifically includes:

[0035] Establish a mapping table between recipes and pre-prepared vegetable products. The table includes fields such as recipe ID, unique identifier of pre-prepared vegetable product, corresponding ingredient identifier, pre-processed vegetable specifications, corresponding weight of pre-prepared vegetable, and nutrient retention rate of ingredients.

[0036] After the user confirms the quantitative recipe on the interactive interface, the system triggers a one-click order command. The system automatically reads the mapping table, grabs the information of the corresponding pre-prepared vegetable products in batches according to the ingredient list in the recipe, and generates a combined order. The order includes fields such as order unique identifier, user account ID, recipe ID, pre-prepared vegetable product list, total order amount, delivery address, and delivery time window.

[0037] Combination orders are pushed to the order processing queue and sorted according to the principle of first-come, first-served. The order is synchronized to the back-end management unit to obtain the real-time status of the pre-prepared vegetable inventory. If the inventory of a certain pre-prepared vegetable product is lower than the quantity required by the order, the product is automatically marked as insufficient. The pre-prepared vegetable products corresponding to alternative ingredients that meet the nutritional matching requirements are selected from the ingredient library, and alternative solutions are generated and pushed to the user for confirmation and selection.

[0038] After the user confirms the order and completes the payment, the system updates the order status to "paid and awaiting delivery", generates a payment voucher, synchronizes the order data to the delivery dispatch system, generates a delivery order, and assigns the delivery order to the delivery person's account in the corresponding area.

[0039] Preferably, the intelligent cooking execution module includes:

[0040] Multi-mode cooking control unit, human-computer interaction unit, and automatic hygiene maintenance unit;

[0041] The multi-mode cooking control unit is equipped with a programmable controller and 7 preset cooking modes. Each mode corresponds to independent temperature and time control logic. It has a built-in food status sensor to collect cooking process data in real time and feed it back to the controller to dynamically adjust cooking parameters.

[0042] The human-computer interaction unit is equipped with a physical control panel, which supports cooking mode selection, cooking status display, remaining time prompt and fault alarm functions.

[0043] The automatic hygiene maintenance unit is used to activate the self-cleaning program after cooking to remove food residue from the inner pot of the equipment, and then use a high-temperature drying program to remove moisture from the equipment, thus completing the hygiene maintenance of the equipment.

[0044] Preferably, the multi-mode cooking control unit specifically includes:

[0045] The programmable controller stores a table of temperature and time parameters for 7 preset cooking modes. The table includes: mode number, applicable food type, temperature setting range, basic time range, allowable temperature fluctuation range, and a list of compatible food types.

[0046] The programmable controller compares the real-time collected inner tank temperature with the set value in the parameter table, calculates the temperature deviation, and adjusts the output power of the heating component according to the preset proportional coefficient, integral time, and derivative time.

[0047] A comprehensive approach to personalized pet meal services, including:

[0048] S1. Obtain basic pet information, establish and maintain structured pet profiles, support the creation, modification and updating of profile information, and form dynamically updated pet profile data;

[0049] S2. Based on the generated pet profile data, the system calls the preset standardized ingredient library and multi-category recipe template library, performs matching calculations through a nutrition mapping algorithm, and generates a quantitative recipe that includes the types of ingredients, precise weights, and corresponding cooking mode recommendations.

[0050] S3. Bind the generated quantitative recipe with the pre-processed clean vegetable products using a unique identifier, generate a clean vegetable purchase order, complete order generation, payment processing and delivery status tracking, and synchronize order data to the server;

[0051] S4. Receive cooking mode parameters that match the quantitative recipe, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process and feed them back to the server, and start the self-cleaning and high-temperature drying program after cooking is completed.

[0052] S5 stores data throughout the entire process, including pet profile update data, cooking feedback data, and order records. Based on this data, it optimizes the nutrition mapping algorithm and recipe templates, providing data support for the subsequent generation of quantitative recipes.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] The pet personalized meal service system and method proposed in this invention integrates smart hardware, cloud data management, and e-commerce services to achieve comprehensive personalization and scientific management of pet feeding. It effectively solves the problems of unbalanced nutrition and monotonous formulas in traditional pet feeding. It can dynamically generate and adjust nutritional formulas according to the pet's specific health condition and nutritional needs. It closely integrates smart cooking equipment with convenient supply chain services, simplifying the operation process for pet owners. From nutritional calculation to ingredient procurement to cooking execution, the entire process is automated, greatly improving the user experience. It also has self-optimization capabilities, continuously collecting and analyzing feeding data, constantly optimizing the meal preparation algorithm, and providing more accurate nutritional solutions. This not only promotes pet health but also drives the intelligent and personalized development of the pet service industry. Attached Figure Description

[0055] Figure 1 This is a system framework diagram of the present invention;

[0056] Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0057] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0058] Reference Figure 1 As shown, a personalized pet meal service system includes: a cloud data and service module and an intelligent cooking execution module;

[0059] The cloud data and service module is used to establish and manage structured pet profiles, generate quantitative recipes based on the profile data through a meal planning algorithm, link the e-commerce system to match pre-prepared vegetable products and manage the order process, and store full-process data, including: profile updates, cooking feedback and order records;

[0060] The cloud data and service module includes: a pet file management unit, an intelligent meal preparation unit, an e-commerce and order unit, and a back-end management unit;

[0061] The pet record management unit is used to establish and maintain a structured pet record database, supporting the creation, modification, and updating of record data by the user terminal;

[0062] The pet record management unit specifically includes:

[0063] Based on the user-preset interactive interface, a basic pet information input portal is provided. Pet information is obtained by filling in the basic information input portal. The pet information includes: pet breed, weight, age, health status and functional requirements.

[0064] Based on the obtained pet information, the system performs format validation on the pet basic information submitted by the user according to preset data validation rules, and obtains the validated pet basic information; if the validation fails, it returns to the user and prompts the specific error reason.

[0065] The verification rules include: weight must be a positive number and the unit must be uniformly kg; age must match the segmentation rules of childhood / youth / adulthood / elderly; and health status must be selected from a preset list or added and marked by customization.

[0066] The pet record management unit also includes:

[0067] The verified pet basic information is structured and automatically associated with the user account ID of the current user. The user account ID is a 32-bit character unique identifier pre-assigned by the system. It is directly extracted from the user's login state cache and associated with the current pet information dataset.

[0068] Generate a unique identifier for your pet's profile. The generation rule is: calculated based on a combination of the system's current timestamp, a fragment of the device's MAC address, and a random number.

[0069] The basic information fields are standardized, including: converting the variety field into the system's preset standard variety name, uniformly retaining one decimal place for the weight field, and converting the age field into standard segmented text according to the selection result;

[0070] The data is encapsulated in a hierarchical format of user account ID + unique pet profile identifier + basic information fields. The hierarchical relationship is defined by a JSON data structure. The top level is the user account ID, the next level is the unique pet profile identifier, and the bottom level is the key-value pairs of each basic information field, generating standardized profile data entries.

[0071] A distributed structured database is constructed based on the standardized archival data entry structure.

[0072] The intelligent meal preparation unit has a built-in standardized ingredient library, a multi-category recipe template library, and a nutrition mapping algorithm. Based on pet profile data, it uses the algorithm to match the ingredient library and the recipe template library to generate a quantitative recipe containing the types of ingredients, precise weights, and corresponding cooking mode recommendations.

[0073] The intelligent meal preparation unit specifically includes:

[0074] The standardized food database includes: unique food identifier, name, nutritional information table, applicable pet type, and food status field. The nutritional data and status of the food are updated through the backend management unit.

[0075] The multi-category recipe template library is categorized by pet age, health status, and functional needs. Each template includes a unique template ID, a combination of category tags, a baseline nutritional ratio, an example of ingredient combination, and a recommended cooking mode number.

[0076] Based on the standardized file data pushed by the pet file management unit, preprocess it to generate standardized input data;

[0077] Multi-dimensional nutrition matching weights are set according to the degree of influence of pet nutritional needs, and the weights of the sub-indicators under each first-level dimension are split based on the analytic hierarchy process to determine the weight coefficient of each sub-indicator and form a weight matrix.

[0078] The following methods can be used to determine the impact of pet nutritional needs, and then set multi-dimensional nutritional matching weights:

[0079] Referring to pet nutrition industry standards and veterinary expert consensus, the criteria for determining the priority of core influencing dimensions are clarified: the core indicator is the "rigidity of nutritional needs". The impact of meeting rigid needs for survival and disease recovery on nutritional matching is higher than that of meeting flexible needs for functional optimization and breed characteristics.

[0080] The rigidity of nutritional needs across different dimensions was categorized as follows: the health status dimension corresponds to rigid needs such as disease recovery and physical improvement, and has the highest impact; the age segment dimension corresponds to physiological rigid needs such as growth and development and functional decline, and has the second highest impact; the functional needs dimension corresponds to flexible optimization needs such as coat enhancement and calcium supplementation, and has the next highest impact; and the pet breed dimension corresponds to breed-specific metabolic differences, and has the lowest impact.

[0081] The third step is to verify and adjust the results by combining historical meal planning data: statistically analyze pet health feedback data such as disease improvement rate and growth achievement rate under different weight settings, and iteratively optimize the impact of each dimension to ensure that the judgment results match the actual nutritional needs.

[0082] Based on the above judgment results, the weight ratio of nutrition matching for each dimension is set.

[0083] The intelligent meal preparation unit also includes:

[0084] Collect breed-specific nutritional requirements data from pet nutrition industry standards, disease-specific nutritional adaptation rules from veterinary clinical guidelines, and formula and feedback data from historical meal planning data in the system, and integrate these three types of data into an algorithm training dataset.

[0085] The core architecture of the algorithm is constructed using a feature matching layer and a quantization calculation layer. The feature matching layer is responsible for matching the standardized input data with the dimensions and sub-indicators in the weight matrix, while the quantization calculation layer is responsible for numerical solutions based on nutritional requirements and food nutrition data.

[0086] Using the recipes in the training dataset as a reference, the matching threshold and calculation coefficients in the algorithm are adjusted by gradient descent, while cross-validation is used to eliminate the impact of data fluctuations on the algorithm.

[0087] The nutritional component field of the standardized food ingredient library, the baseline nutritional percentage field of the multi-category recipe template library, and the dimension weight field of the weight matrix are bound to the input interface, calculation logic, and output constraints of the algorithm to obtain the nutritional mapping algorithm.

[0088] The nutrient mapping algorithm is invoked, and the standardized input data and weight matrix are substituted into the calculation. The algorithm first selects the recipe template with the highest matching degree from the multi-class recipe template library based on the weight ratio and sub-index coefficient of health status and age dimension, and retrieves the benchmark nutrient ratio and food combination example of the template.

[0089] With the template benchmark nutrient ratio as the target, and combined with the nutrient composition data of ingredients in the standardized ingredient library, the algorithm calculates the precise weight of each ingredient using a linear programming algorithm. The calculation constraints are: the proportion of a single ingredient does not exceed 40% of the total weight, there are no less than 2 kinds of similar nutrient ingredients, and the total weight of ingredients matches the daily food intake standard corresponding to the pet's weight.

[0090] After the calculation is completed, an initial ingredient combination list is generated. The algorithm automatically checks the list for rationality, checking whether there are any incompatibilities between ingredients, whether the deviation of nutritional components is within the allowable range, and whether the ingredients are in a usable state. If the check passes, the recipe generation stage begins. If the check fails, the algorithm readjusts the ingredient combination and weight.

[0091] A quantified recipe is generated based on the verified ingredient combination list. The recipe includes a unique recipe ID, a unique identifier for the pet's profile, an ingredient list, a total nutritional composition table, a recommended cooking mode number, a recipe generation time, and an expiration date. The quantified recipe is stored in a cloud-based recipe database and simultaneously synchronized to the recipe association interface of the e-commerce platform and order unit. A recipe preview is also generated and pushed to the user's interactive interface for the user to view and confirm.

[0092] The e-commerce and order unit is used to bind the quantitative recipes generated by the intelligent meal preparation unit with the pre-processed clean vegetables in the e-commerce system through a unique identifier, enabling users to place orders for the clean vegetables corresponding to the recipes with one click.

[0093] The back-end management unit is used for managing pre-prepared vegetable product information, processing order acceptance and dispatch, querying customer files, and maintaining meal preparation rules and recipe templates.

[0094] The e-commerce and order unit specifically includes:

[0095] Establish a mapping table between recipes and pre-prepared vegetable products. The table includes fields such as recipe ID, unique identifier of pre-prepared vegetable product, corresponding ingredient identifier, pre-processed vegetable specifications, corresponding weight of pre-prepared vegetable, and nutrient retention rate of ingredients.

[0096] After the user confirms the quantitative recipe on the interactive interface, the system triggers a one-click order command. The system automatically reads the mapping table, grabs the information of the corresponding pre-prepared vegetable products in batches according to the ingredient list in the recipe, and generates a combined order. The order includes fields such as order unique identifier, user account ID, recipe ID, pre-prepared vegetable product list, total order amount, delivery address, and delivery time window.

[0097] Combination orders are pushed to the order processing queue and sorted according to the principle of first-come, first-served. The order is synchronized to the back-end management unit to obtain the real-time status of the pre-prepared vegetable inventory. If the inventory of a certain pre-prepared vegetable product is lower than the quantity required by the order, the product is automatically marked as insufficient. The pre-prepared vegetable products corresponding to alternative ingredients that meet the nutritional matching requirements are selected from the ingredient library, and alternative solutions are generated and pushed to the user for confirmation and selection.

[0098] After the user confirms the order and completes the payment, the system updates the order status to "paid and awaiting delivery", generates a payment voucher, synchronizes the order data to the delivery dispatch system, generates a delivery order, and assigns the delivery order to the delivery person's account in the corresponding area.

[0099] The intelligent cooking execution module is electrically connected to the cloud data and service module. It is used to receive the cooking mode parameters sent down, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process, and automatically start the self-cleaning and high-temperature drying program after cooking to complete the equipment hygiene maintenance.

[0100] The intelligent cooking execution module includes:

[0101] Multi-mode cooking control unit, human-computer interaction unit, and automatic hygiene maintenance unit;

[0102] The multi-mode cooking control unit is equipped with a programmable controller and 7 preset cooking modes. Each mode corresponds to independent temperature and time control logic. It has a built-in food status sensor to collect cooking process data in real time and feed it back to the controller to dynamically adjust cooking parameters.

[0103] The human-computer interaction unit is equipped with a physical control panel, which supports cooking mode selection, cooking status display, remaining time prompt and fault alarm functions.

[0104] The automatic hygiene maintenance unit is used to activate the self-cleaning program after cooking to remove food residue from the inner pot of the equipment, and then use a high-temperature drying program to remove moisture from the equipment, thus completing the hygiene maintenance of the equipment.

[0105] The multi-mode cooking control unit specifically includes:

[0106] The programmable controller stores a table of temperature and time parameters for 7 preset cooking modes. The table includes: mode number, applicable food type, temperature setting range, basic time range, allowable temperature fluctuation range, and a list of compatible food types.

[0107] The programmable controller compares the real-time collected inner tank temperature with the set value in the parameter table, calculates the temperature deviation, and adjusts the output power of the heating component according to the preset proportional coefficient, integral time, and derivative time.

[0108] The human-computer interaction unit specifically includes: a physical control panel with independent buttons, namely a mode selection button, a start button, a pause button, a fault reset button, and a cleaning mode shortcut button. Each button corresponds to an independent trigger signal. After being pressed, the anti-shake processing circuit eliminates false triggers and generates standardized operation instructions.

[0109] The touch screen uses a capacitive touch design and is divided into three functional interfaces: mode selection interface, cooking status interface, and fault alarm interface. The mode selection interface includes: displaying the names of 7 cooking modes, corresponding icons, and applicable scenarios; the cooking status interface includes: displaying the current temperature, remaining time, and food status progress bar in real time; the fault alarm interface includes: displaying fault codes and fault type descriptions.

[0110] Button operation signals and display screen display signals are transmitted to the main control chip of the intelligent cooking execution module via the I2C bus. After receiving the instruction, the main control chip feeds back the execution result to the display screen in real time and updates the display content. The operation response delay does not exceed 500ms.

[0111] When a fault occurs, in addition to displaying the fault information, an intermittent alarm sound is emitted via a buzzer. At the same time, the fault code and the time of the fault occurrence are stored in the device's local log, and historical fault records can be queried through a touch interface.

[0112] The automatic hygiene maintenance unit specifically includes:

[0113] After the cooking program is finished, the main control chip automatically triggers the self-cleaning program. The built-in high-pressure spray device sprays neutral cleaning liquid at a pressure of 0.3MPa, and the spray angle covers the entire inner pot. At the same time, the inner pot rotates at a speed of 30rpm, and with the raised scrubbing structure on the inner pot wall, it scrubs the remaining food residue 360°. The scrubbing time is set to 8 minutes.

[0114] After scrubbing, open the solenoid valve of the drain pipe to discharge the waste liquid containing residue into the external collection box of the equipment. At the same time, start the spray device to spray clean water and rinse for 2 minutes. After rinsing, close the solenoid valve.

[0115] After rinsing, the electric heating element is activated to raise the temperature of the inner tank to ≥80℃. The blower is turned on to accelerate the air circulation in the inner tank. The humidity sensor collects the humidity data of the inner tank once per minute. When the humidity is below 30%RH, a drying completion signal is generated.

[0116] After receiving the drying completion signal, the main control chip shuts down the electric heating component and the blower, automatically records the cleaning time, drying duration, and final humidity data of the inner tank, and feeds it back to the human-machine interface unit, displaying the message "Equipment is ready for cleaning".

[0117] Reference Figure 2 As shown, a personalized pet meal service method includes:

[0118] S1. Obtain basic pet information, establish and maintain structured pet profiles, support the creation, modification and updating of profile information, and form dynamically updated pet profile data;

[0119] S2. Based on the generated pet profile data, the system calls the preset standardized ingredient library and multi-category recipe template library, performs matching calculations through a nutrition mapping algorithm, and generates a quantitative recipe that includes the types of ingredients, precise weights, and corresponding cooking mode recommendations.

[0120] S3. Bind the generated quantitative recipe with the pre-processed clean vegetable products using a unique identifier, generate a clean vegetable purchase order, complete order generation, payment processing and delivery status tracking, and synchronize order data to the server;

[0121] S4. Receive cooking mode parameters that match the quantitative recipe, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process and feed them back to the server, and start the self-cleaning and high-temperature drying program after cooking is completed.

[0122] S5 stores data throughout the entire process, including pet profile update data, cooking feedback data, and order records. Based on this data, it optimizes the nutrition mapping algorithm and recipe templates, providing data support for the subsequent generation of quantitative recipes.

[0123] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A personalized pet meal service system covering the entire process, characterized in that, include: Cloud data and services module and intelligent cooking execution module; The cloud data and service module is used to establish and manage structured pet profiles, generate quantitative recipes based on the profile data through a meal planning algorithm, link the e-commerce system to match pre-prepared vegetable products and manage the order process, and store full-process data, including: profile updates, cooking feedback and order records; The intelligent cooking execution module is electrically connected to the cloud data and service module. It is used to receive the cooking mode parameters sent down, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process, and automatically start the self-cleaning and high-temperature drying program after cooking to complete the equipment hygiene maintenance.

2. The personalized pet meal service system according to claim 1, characterized in that, The cloud data and service module includes: a pet file management unit, an intelligent meal preparation unit, an e-commerce and order unit, and a back-end management unit; The pet record management unit is used to establish and maintain a structured pet record database, supporting the creation, modification, and updating of record data by the user terminal; The intelligent meal preparation unit has a built-in standardized ingredient library, a multi-category recipe template library, and a nutrition mapping algorithm. Based on pet profile data, it uses the algorithm to match the ingredient library and the recipe template library to generate a quantitative recipe that includes the types of ingredients, precise weights, and corresponding cooking mode recommendations. The e-commerce and order unit is used to bind the quantitative recipes generated by the intelligent meal preparation unit with the pre-processed clean vegetables in the e-commerce system through a unique identifier, enabling users to place orders for the clean vegetables corresponding to the recipes with one click. The back-end management unit is used for managing pre-prepared vegetable product information, processing order acceptance and dispatch, querying customer files, and maintaining meal preparation rules and recipe templates.

3. The personalized pet meal service system according to claim 2, characterized in that, The pet record management unit specifically includes: Based on the user-preset interactive interface, a basic pet information input portal is provided. Pet information is obtained by filling in the basic information input portal. The pet information includes: pet breed, weight, age, health status and functional requirements. Based on the obtained pet information, the system performs format validation on the pet basic information submitted by the user according to preset data validation rules, and obtains the validated pet basic information; if the validation fails, the system returns to the user and prompts the specific error reason. The verification rules include: weight must be a positive number and the unit must be uniformly kg; age must match the segmentation rules of childhood / youth / adulthood / elderly; and health status must be selected from a preset list or added and marked by customization.

4. The personalized pet meal service system according to claim 3, characterized in that, The pet record management unit also includes: The verified pet basic information is structured and automatically associated with the user account ID of the current user. The user account ID is a 32-bit character unique identifier pre-assigned by the system. It is directly extracted from the user's login state cache and associated with the current pet information dataset. Generate a unique identifier for your pet's profile. The generation rule is: calculated based on a combination of the system's current timestamp, a fragment of the device's MAC address, and a random number. The basic information fields are standardized, including: converting the variety field into the system's preset standard variety name, uniformly retaining one decimal place for the weight field, and converting the age field into standard segmented text according to the selection result; The data is encapsulated in a hierarchical format of user account ID + unique pet profile identifier + basic information fields. The hierarchical relationship is defined by a JSON data structure. The top level is the user account ID, the next level is the unique pet profile identifier, and the bottom level is the key-value pairs of each basic information field, generating standardized profile data entries. A distributed structured database is constructed based on the standardized archival data entry structure.

5. The personalized pet meal service system according to claim 4, characterized in that, The intelligent meal preparation unit specifically includes: The standardized food database includes: unique food identifier, name, nutritional information table, applicable pet type, and food status field. The nutritional data and status of the food are updated through the backend management unit. The multi-category recipe template library is categorized by pet age, health status, and functional needs. Each template includes a unique template ID, a combination of category tags, a baseline nutritional ratio, an example of ingredient combination, and a recommended cooking mode number. Based on the standardized file data pushed by the pet file management unit, preprocess it to generate standardized input data; Multi-dimensional nutrition matching weights are set according to the degree of influence of pet nutritional needs, and the weights of the sub-indicators under each first-level dimension are split based on the analytic hierarchy process to determine the weight coefficient of each sub-indicator and form a weight matrix.

6. The personalized pet meal service system according to claim 5, characterized in that, The intelligent meal preparation unit also includes: Collect breed-specific nutritional requirements data from pet nutrition industry standards, disease-specific nutritional adaptation rules from veterinary clinical guidelines, and formula and feedback data from historical meal planning data in the system, and integrate these three types of data into an algorithm training dataset. The core architecture of the algorithm is constructed using a feature matching layer and a quantization calculation layer. The feature matching layer is responsible for matching the standardized input data with the dimensions and sub-indicators in the weight matrix, while the quantization calculation layer is responsible for numerical solutions based on nutritional requirements and food nutrition data. Using the recipes in the training dataset as a reference, the matching threshold and calculation coefficients in the algorithm are adjusted by gradient descent, while cross-validation is used to eliminate the impact of data fluctuations on the algorithm. The nutritional component field of the standardized food ingredient library, the baseline nutritional percentage field of the multi-category recipe template library, and the dimension weight field of the weight matrix are bound to the input interface, calculation logic, and output constraints of the algorithm to obtain the nutritional mapping algorithm.

7. The personalized pet meal service system according to claim 6, characterized in that, The e-commerce and order unit specifically includes: Establish a mapping table between recipes and pre-prepared vegetable products. The table includes fields such as recipe ID, unique identifier of pre-prepared vegetable product, corresponding ingredient identifier, pre-processed vegetable specifications, corresponding weight of pre-prepared vegetable, and nutrient retention rate of ingredients. After the user confirms the quantitative recipe on the interactive interface, the system triggers a one-click order command. The system automatically reads the mapping table, grabs the information of the corresponding pre-prepared vegetable products in batches according to the ingredient list in the recipe, and generates a combined order. The order includes fields such as order unique identifier, user account ID, recipe ID, pre-prepared vegetable product list, total order amount, delivery address, and delivery time window. Combination orders are pushed to the order processing queue and sorted according to the principle of first-come, first-served. The order is synchronized to the back-end management unit to obtain the real-time status of the pre-prepared vegetable inventory. If the inventory of a certain pre-prepared vegetable product is lower than the quantity required by the order, the product is automatically marked as insufficient. The pre-prepared vegetable products corresponding to alternative ingredients that meet the nutritional matching requirements are selected from the ingredient library, and alternative solutions are generated and pushed to the user for confirmation and selection. After the user confirms the order and completes the payment, the system updates the order status to "paid and awaiting delivery", generates a payment voucher, synchronizes the order data to the delivery dispatch system, generates a delivery order, and assigns the delivery order to the delivery person's account in the corresponding area.

8. The personalized pet meal service system according to claim 7, characterized in that, The intelligent cooking execution module includes: a multi-mode cooking control unit, a human-computer interaction unit, and an automatic hygiene maintenance unit; The multi-mode cooking control unit is equipped with a programmable controller and 7 preset cooking modes. Each mode corresponds to independent temperature and time control logic. It has a built-in food status sensor to collect cooking process data in real time and feed it back to the controller to dynamically adjust cooking parameters. The human-computer interaction unit is equipped with a physical control panel, which supports cooking mode selection, cooking status display, remaining time prompt and fault alarm functions. The automatic hygiene maintenance unit is used to activate the self-cleaning program after cooking to remove food residue from the inner pot of the equipment, and then use a high-temperature drying program to remove moisture from the equipment, thus completing the hygiene maintenance of the equipment.

9. A personalized pet meal service system according to claim 8, characterized in that, The multi-mode cooking control unit specifically includes: The programmable controller stores a table of temperature and time parameters for 7 preset cooking modes. The table includes: mode number, applicable food type, temperature setting range, basic time range, allowable temperature fluctuation range, and a list of compatible food types. The programmable controller compares the real-time collected inner tank temperature with the set value in the parameter table, calculates the temperature deviation, and adjusts the output power of the heating component according to the preset proportional coefficient, integral time, and derivative time.

10. A method for providing personalized pet meals throughout the entire process, characterized in that, include: S1. Obtain basic pet information, establish and maintain structured pet profiles, support the creation, modification and updating of profile information, and form dynamically updated pet profile data; S2. Based on the generated pet profile data, the system calls the preset standardized ingredient library and multi-category recipe template library, performs matching calculations through a nutrition mapping algorithm, and generates a quantitative recipe that includes the types of ingredients, precise weights, and corresponding cooking mode recommendations. S3. Bind the generated quantitative recipe with the pre-processed clean vegetable products using a unique identifier, generate a clean vegetable purchase order, complete order generation, payment processing and delivery status tracking, and synchronize order data to the server; S4. Receive cooking mode parameters that match the quantitative recipe, automatically execute the corresponding cooking program, collect the status of ingredients and equipment operation data in real time during the cooking process and feed them back to the server, and start the self-cleaning and high-temperature drying program after cooking is completed. S5 stores data throughout the entire process, including pet profile update data, cooking feedback data, and order records. Based on this data, it optimizes the nutrition mapping algorithm and recipe templates, providing data support for subsequent quantitative recipe generation.

Images