A large model-based cooking recipe recommendation processing method and system

Abstract

The application provides a cooking scheme recommendation processing method and system based on a large model, and belongs to the technical field of data management, and specifically comprises the following steps: determining available cooking schemes and scheme matching values in the cooking schemes according to different cooking schemes and matching conditions of different matching disease types and dishes, taking other available cooking schemes that can be switched in the cooking processing process of the available cooking schemes as associated cooking schemes, determining a recommended cooking scheme in the available cooking schemes according to the number of the associated cooking schemes of the available cooking schemes and switching processing conditions, and automatically generating an alternative cooking scheme based on a large model when a user performs cooking processing of the recommended cooking scheme and an abnormality exists, so that personalized recommendation of cooking processing is realized.

Description

Technical Field

[0001] This invention belongs to the field of data management technology, and in particular relates to a method and system for recommending cooking plans based on a large model. Background Technology

[0002] Existing range hoods often only extract cooking fumes and cannot generate cooking plans based on user needs, thus failing to meet users' personalized cooking requirements. To address this issue, patent application CN202411797317.2, "Control Method and System for an Internet of Things-Based Smart Rice Cooker," analyzes user commands, identifies ingredient types and weights, and uses gene sequence optimization and fitness assessment to automatically generate and select the optimal cooking plan, achieving a personalized and intelligent cooking experience and improving user experience. However, it suffers from the following technical problems: When cooking, existing technical solutions neglect to combine users' historical cooking data to generate differentiated cooking recommendations. Differences in cooking skills result in discrepancies in the matching degree between different cooking solutions and users. Therefore, if the above factors are ignored, it is impossible to generate personalized cooking solutions.

[0003] To address the aforementioned technical problems, this application provides a cooking scheme recommendation processing method and system based on a large model. Summary of the Invention

[0004] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, in the first aspect, this application provides a cooking scheme recommendation processing method based on a large model, which specifically includes: S1 uses the range hood's monitoring device to determine the user's historical cooking data. If the user's health status is found to be abnormal based on specific types of historical cooking data within a preset time period, it proceeds to the next step. S2 determines the user's matched disease type based on the matching of specific types of historical cooking data with different disease types, and determines the available cooking schemes and scheme matching values ​​in the cooking schemes by matching different cooking schemes with different matched disease types and dishes; S3, based on the user's processing data and processing deviation data under different cooking schemes, determines that the user's cooking proficiency does not meet the requirements, and then proceeds to the next step; S4 takes other available cooking schemes that can be switched during the cooking process as associated cooking schemes, and determines the recommended cooking scheme among the available cooking schemes based on the number of associated cooking schemes and the switching processing conditions. When there is an anomaly when the user performs cooking processing with the recommended cooking scheme, an alternative cooking scheme is automatically generated based on the large model.

[0005] The beneficial effects of this invention are as follows: By matching different cooking methods with different disease types and dishes, the available cooking methods are determined. This allows for the screening of available cooking methods from the perspective of the user's health status, avoiding the technical problem of potential impacts on the user's health due to the mismatch between the cooking method and the user's health status. It also lays the foundation for further determination of recommended cooking methods.

[0006] When an anomaly occurs during the cooking process of the recommended cooking plan, alternative cooking plans are automatically generated based on the large model. This avoids the technical problem of the user continuing to cook when there is an anomaly in the recommended cooking plan, which would lead to the cooking result not meeting the requirements. By using the large model to generate alternative cooking plans, users can easily find alternative cooking plans in a timely and accurate manner, thus improving the cooking results for users with insufficient cooking skills.

[0007] A further technical solution is that the monitoring device is the camera device of the range hood.

[0008] A further technical solution is that the historical cooking data includes the number of historical cooking times, the dates corresponding to different historical cooking times, and the cooking type.

[0009] A further technical solution is that the cooking types include braising, steaming, frying, stewing, and boiling.

[0010] A further technical solution is that the specific type of historical cooking data is decoction processing data.

[0011] A further technical solution involves determining if a user's health status is abnormal, specifically including: Based on historical cooking data of characteristic types within a preset time period, determine the user's decoction processing data within the preset time period; The date on which decoction data exists within the preset time period is determined based on the decoction processing data within the preset time period, and this date is used as the decoction processing date. Based on the percentage of decoction processing dates within a preset time period, it is determined whether the user's health status is abnormal.

[0012] A further technical solution is that when the proportion of decoction processing dates within the preset time period is greater than the preset proportion of decoction dates, it is determined that the user's health status is abnormal.

[0013] A further technical solution is that the switching processing conditions include the number of available cooking operation steps when the available cooking program is switched to the associated cooking program.

[0014] A further technical solution is that the method for determining the recommended cooking scheme among the available cooking schemes is as follows: The association weight value between the associated cooking program and the available cooking program is determined by the ratio of the number of available cooking operation steps when switching from the available cooking program to the associated cooking program to the number of cooking operation steps in the available cooking program. The switching availability value of the available cooking scheme is determined based on the sum of the association weight values ​​between different associated cooking schemes and the available cooking schemes. Based on the switching availability value, determine whether the available cooking program is a recommended cooking program.

[0015] A further technical solution involves automatically generating alternative cooking plans, specifically including: Using the real-time cooking images of the recommended cooking scheme during the cooking process as input, and the output of the large model, alternative cooking schemes are determined when the user switches between recommended cooking schemes.

[0016] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described cooking scheme recommendation processing method based on a large model when running the computer program.

[0017] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0018] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0020] Figure 1 This is a flowchart of a cooking scheme recommendation processing method based on a large model; Figure 2 This is a flowchart for determining if a user's health status is abnormal; Figure 3 This is a flowchart illustrating the method for determining the matching disease type for users; Figure 4 It is a flowchart of the method for determining the available cooking plans in the cooking plan; Figure 5 It is a framework diagram of a computer system. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0022] In this application, the camera device of the range hood is used to acquire the user's cooking operation data, and the cooking operation data is used to recommend personalized cooking plans for the user. When there is an abnormality in the cooking process, alternative cooking plans are automatically generated.

[0023] Example 1 like Figure 1 As shown, this application provides a cooking scheme recommendation processing method based on a large model, specifically including: S1 uses the range hood's monitoring device to determine the user's historical cooking data. If the user's health status is found to be abnormal based on specific types of historical cooking data within a preset time period, it proceeds to the next step. Specifically, the date containing decoction data within the preset time period is determined based on the decoction processing data within the preset time period, and this date is used as the decoction processing date. When the proportion of decoction processing dates within the preset time period is greater than the proportion of preset decoction dates, in one possible embodiment, if decoction processing is performed every day within the most recent week, it is determined that the user's health status is abnormal.

[0024] S2 determines the user's matched disease type based on the matching of specific types of historical cooking data with different disease types, and determines the available cooking schemes and scheme matching values ​​in the cooking schemes by matching different cooking schemes with different matched disease types and dishes; Specifically, based on the drug composition data corresponding to different decoction treatment times and the matching situation with different disease types, the disease types that have a matching relationship with different decoction treatment times are determined. When the number of decoction treatment times that have a matching relationship with a disease type is greater than the preset decoction treatment time threshold, the disease type is determined to be a matching disease type.

[0025] In one possible embodiment, for wind-cold type common cold: ephedra (to induce sweating and relieve exterior symptoms), cinnamon twig (to warm and invigorate yang qi), and saposhnikovia root (to dispel wind and cold); for wind-heat type common cold: honeysuckle (to clear heat and detoxify), isatis root (to fight viruses), and forsythia (to disperse wind-heat); for relieving cough and phlegm: apricot kernel (to moisten the lungs and relieve asthma), fritillaria bulb (to moisten the lungs and relieve cough), and mulberry leaf (to dispel wind and clear heat). Therefore, if a decoction of Chinese medicine containing ephedra or cinnamon twig is prepared every day for the past week, it indicates that the user may have wind-cold type common cold. If apricot kernel or mulberry leaf is also prepared every day, then the disease type of cough is determined to be wind-cold type common cold and cough.

[0026] It should be noted that the proportion of different cooking schemes and dishes matched in the total number of dishes is used to determine the dish matching value of the cooking scheme. The proportion of the number of disease types matched by the cooking scheme in the total number of disease types is used to determine the disease matching value of the cooking scheme. The product of the disease matching value and the dish matching value is used to determine the scheme matching value of the cooking scheme. When the scheme matching value is greater than 0.3, the cooking scheme is determined to be a usable cooking scheme.

[0027] Understandably, for pumpkin and red bean porridge, the pumpkin is suitable for users with colds and coughs caused by wind-cold. Therefore, its dish matching value is 0.5. At the same time, it is suitable for coughs and colds caused by wind-cold, so its scheme matching value is 0.5. At this time, it is considered an available cooking scheme.

[0028] S3, based on the user's processing data and processing deviation data under different cooking schemes, determines that the user's cooking proficiency does not meet the requirements, and then proceeds to the next step; Specifically, the user's cooking failure probability is determined based on the ratio of the total number of cooking failures to the total number of cooking attempts. When the cooking failure probability is greater than 0.2, the user's cooking proficiency is determined to be insufficient.

[0029] S4 takes other available cooking schemes that can be switched during the cooking process as associated cooking schemes, and determines the recommended cooking scheme among the available cooking schemes based on the number of associated cooking schemes and the switching processing conditions. When there is an anomaly when the user performs cooking processing with the recommended cooking scheme, an alternative cooking scheme is automatically generated based on the large model.

[0030] Specifically, the available cooking solutions and their associated cooking solutions are used as inputs to the large model, and the output of the large model is used as the recommended cooking solution among the available cooking solutions.

[0031] Furthermore, the monitoring device is the camera device of the range hood.

[0032] Specifically, the historical cooking data includes the number of historical cooking times, the dates corresponding to different historical cooking times, and the cooking type.

[0033] It should be noted that the cooking types include braising, steaming, deep-frying, stewing, and boiling.

[0034] Furthermore, the specific type of historical cooking data is decoction processing data.

[0035] Specifically, such as Figure 2 As shown, the user's health status has been determined to be abnormal, specifically including: Based on historical cooking data of characteristic types within a preset time period, determine the user's decoction processing data within the preset time period; The date on which decoction data exists within the preset time period is determined based on the decoction processing data within the preset time period, and this date is used as the decoction processing date. Based on the percentage of decoction processing dates within a preset time period, it is determined whether the user's health status is abnormal.

[0036] Optionally, if the proportion of decoction processing dates within the preset time period is greater than the preset proportion of decoction dates, then it is determined that the user's health status is abnormal.

[0037] It should be noted that when the user's health status is not abnormal, all cooking plans are considered as available cooking plans. The matching value of different available cooking plans is determined by multiplying the proportion of matching numbers of different available cooking plans with the dishes and the historical cooking success rate, and then the process proceeds to step S3.

[0038] In another possible embodiment, determining that a user's health status is abnormal specifically includes: Based on historical cooking data of characteristic types within a preset time period, determine the user's decoction processing data within the preset time period; The number of decoction processes within the preset time period is determined based on the decoction processing data within that preset time period. Based on the number of decoction processes within a preset time period, it is determined whether the user's health status is abnormal.

[0039] It should be noted that if the number of decoction processes within the preset time period does not meet the requirements, it is determined that the user's health status is abnormal.

[0040] In another possible embodiment, determining that a user's health status is abnormal specifically includes: S11 uses historical cooking data of characteristic types within a preset time period to determine the user's decoction processing data within the preset time period, determines the date in the preset time period where decoction processing data exists based on the decoction processing data within the preset time period, and uses it as the decoction processing date, and determines the basic abnormal value of the user's health status based on the proportion of the number of decoction processing dates within the preset time period. S12 obtains the number of decoction processes for different decoction processing dates, and combines the time interval between different decoction processing dates and the current date to determine the corrected outlier value of the user's health status; S13 determines the health status anomaly value based on the sum of the corrected anomaly value and the basic anomaly value, and uses the health status anomaly value to determine whether the user's health status is abnormal.

[0041] Furthermore, when the abnormal health status value is greater than a preset abnormal value threshold, it is determined that the user's health status is abnormal.

[0042] Optionally, step S11 above includes the following: S111 If the user does not have any decoction data within the preset time period based on historical cooking data of characteristic types, then the user's health status is determined to be normal. If the user has decoction data within the preset time period, proceed to step S112. S112 determines the number of decoction processes within the preset time period based on the decoction processing data within the preset time period. If the number of decoction processes within the preset time period does not meet the requirements, it is determined that the user's health status is abnormal. If the number of decoction processes within the preset time period meets the requirements, proceed to step S113. S113 When the number of decoction processes within a preset time period is less than the preset decoction process threshold, it is determined that the user's health status is not abnormal. When the number of decoction processes within a preset time period is not less than the preset decoction process threshold, proceed to step S114. S114 determines the date in the preset time period where decoction processing data exists based on the decoction processing data within the preset time period, and uses it as the decoction processing date. Based on the proportion of the number of decoction processing dates within the preset time period, the basic abnormal value of the user's health status is determined. When the basic abnormal value of the user's health status is greater than the preset abnormal value, it is determined that the user's health status is not abnormal. When the basic abnormal value of the user's health status is not greater than the preset abnormal value, proceed to step S12.

[0043] Optionally, step S12 above includes the following: S121 If, based on the number of decoctions for different decoction dates, there is a decoction date with a number of decoctions greater than a preset threshold, then proceed to step S122; if there is no decoction date with a number of decoctions greater than the preset threshold, then proceed to step S123. S122 When the number of decoction processing days with a number of decoction processing times greater than the preset decoction processing time threshold does not meet the requirements, it is determined that the user's health status is abnormal. When the number of decoction processing days with a number of decoction processing times greater than the preset decoction processing time threshold meets the requirements, proceed to step S123. S123 determines the abnormal correlation value of different decoction processing dates based on the number of decoction processing dates and the time interval with the current date. If there is a decoction processing date with an abnormal correlation value greater than the preset correlation value, proceed to step S124. If there is no decoction processing date with an abnormal correlation value greater than the preset correlation value, proceed to step S125. S124 When the number of decoction processing dates with abnormal correlation values ​​greater than the preset correlation value does not meet the requirements, it is determined that the user's health status is abnormal. When the number of decoction processing dates with abnormal correlation values ​​greater than the preset correlation value meets the requirements, proceed to step S125. S125 obtains the number of decoction processes for different decoction processing dates, and combines the time interval between different decoction processing dates and the current date to determine the corrected anomaly value of the user's health status. When the corrected anomaly value of the user's health status is greater than the preset corrected anomaly value threshold, it is determined that the user's health status is abnormal. When the corrected anomaly value of the user's health status is not greater than the preset corrected anomaly value threshold, proceed to step S13.

[0044] Furthermore, such as Figure 3 As shown, the method for determining the user's matched disease type is as follows: Using specific types of historical cooking data, determine the drug composition data corresponding to different decoction treatment times; Based on the drug composition data corresponding to different decoction treatment times and the matching with different disease types, the disease types that have a matching relationship with different decoction treatment times are determined. The number of decoction treatments that match different disease types is used to determine whether the disease type is a matching disease type.

[0045] Specifically, the disease types for which the number of decoction treatments is matched are determined based on a preset association between the drug composition data and the disease types.

[0046] It should be noted that when the number of decoction treatments that match the disease type is greater than the preset threshold for the number of decoction treatments, the disease type is determined to be a matching disease type.

[0047] It is understandable that, such as Figure 4 As shown, the method for determining the available cooking methods in the cooking plan is as follows: The dish matching value of a cooking method is determined by the proportion of different cooking methods and dishes in the total number of dishes. Based on the matching results of the cooking plan with different matching disease types, determine the number of matching disease types matched by the cooking plan, and use the proportion of the number of matching disease types matched by the cooking plan to the total number of matching disease types to determine the disease matching value of the cooking plan. The matching value of the cooking plan is determined by multiplying the disease matching value by the dish matching value, and the matching value is used to determine whether the cooking plan is an available cooking plan.

[0048] Furthermore, the matching disease type of the cooking plan is determined based on whether the cooking plan is suitable for patients with the matching disease type, specifically based on the preset correspondence between the cooking plan and different matching disease types.

[0049] Specifically, when the matching value of the scheme is greater than the preset matching value threshold, the cooking scheme is determined to be an available cooking scheme.

[0050] Furthermore, the processing data under the cooking scheme includes the historical number of cooking operations under the cooking scheme.

[0051] It is understood that the processing deviation data under the cooking program includes the number of processing failures under the cooking program.

[0052] Specifically, determining that the user's cooking skills do not meet the requirements includes: Based on the user's processing data under different cooking schemes, determine the sum of the user's historical cooking times under different cooking schemes, and use it as the total number of cooking processes; Based on the user's processing deviation data under different cooking schemes, the sum of the number of processing failures of the user under different cooking schemes is determined and used as the total number of cooking failures; Based on the ratio of the total number of cooking failures to the total number of cooking attempts, the user's cooking failure probability is determined, and the cooking failure probability is used to determine whether the user's cooking proficiency meets the requirements.

[0053] Furthermore, if the cooking failure probability is greater than a preset failure probability threshold, it is determined that the user's cooking proficiency does not meet the requirements.

[0054] It should be noted that when the user's cooking proficiency meets the requirements, the available cooking solution with the highest solution matching value will be used as the recommended cooking solution.

[0055] Optionally, determining that the user's cooking proficiency does not meet the requirements specifically includes: Based on the user's processing data under different cooking schemes, determine the user's historical cooking count under different cooking schemes; Based on the user's processing deviation data under different cooking schemes, determine the number of processing failures of the user under different cooking schemes, and determine the scheme failure probability under different cooking schemes based on the ratio of the number of processing failures under different cooking schemes to the historical number of cooking attempts. Based on the failure probability of different cooking methods, it is determined whether the user's cooking proficiency meets the requirements.

[0056] Furthermore, if there is no cooking solution with a failure probability less than a preset failure probability threshold, then it is determined that the user's cooking proficiency does not meet the requirements.

[0057] In another possible embodiment, determining that the user's cooking proficiency does not meet the requirements specifically includes: S31 uses the user's processing data under different cooking schemes to determine the sum of the user's historical cooking times under different cooking schemes, and uses it as the total number of cooking processes. Combined with the sum of the user's processing failure times under different cooking schemes, the user's cooking proficiency value is determined. S32 uses the user's processing deviation data under different cooking schemes to determine the number of processing failures under different cooking schemes, and determines the processing proficiency value under different cooking schemes based on the ratio of the number of processing failures under different cooking schemes to the historical number of cooking attempts, and in combination with the historical number of cooking attempts under different cooking schemes. S33 determines the user's cooking processing reliability value based on the processing proficiency value under different cooking schemes and the user's cooking processing proficiency value, and uses the cooking processing reliability value to determine whether the user's cooking processing proficiency meets the requirements.

[0058] Furthermore, when the cooking processing reliability value is greater than a preset reliability value threshold, it is determined that the user's cooking processing proficiency meets the requirements.

[0059] Optionally, step S31 above includes the following: S311 uses the user's processing data under different cooking schemes to determine the sum of the user's historical cooking times under different cooking schemes, and uses it as the total number of cooking times. When the total number of cooking times is less than a preset cooking times threshold, it is determined that the user's cooking proficiency does not meet the requirements. When the total number of cooking times is not less than the preset cooking times threshold, proceed to step S312. S312 determines the user's cooking failure probability by summing the number of times the user failed to cook under different cooking schemes and the total number of cooking attempts. If the cooking failure probability does not meet the requirements, it is determined that the user's cooking proficiency does not meet the requirements. If the cooking failure probability meets the requirements, proceed to step S313. S313 When the cooking failure probability is within the preset failure probability range, proceed to step S314; when the cooking failure probability is not within the preset failure probability range, proceed to step S315. S314 When the total number of cooking processes is within the preset cooking process range, it is determined that the user's cooking proficiency does not meet the requirements; when the total number of cooking processes is not within the preset cooking process range, proceed to step S315. S315 determines the user's cooking proficiency value based on the total number of cooking processes and the sum of the number of times the user failed to cook under different cooking schemes. When the user's cooking proficiency value is less than a preset proficiency value threshold, it is determined that the user's cooking proficiency does not meet the requirements. When the user's cooking proficiency value is not less than the preset proficiency value threshold, proceed to step S32.

[0060] Optionally, step S32 above includes the following: S321 uses the user's processing deviation data under different cooking schemes to determine the number of times the user failed to process under different cooking schemes. Based on the ratio of the number of processing failures under different cooking schemes to the historical number of cooking attempts, the failure probability of the scheme under different cooking schemes is determined. When there is no cooking scheme with a failure probability less than a preset failure probability threshold, it is determined that the user's cooking proficiency does not meet the requirements. When there is a cooking scheme with a failure probability less than a preset failure probability threshold, the process proceeds to step S322. S322 Obtain the number of cooking plans with a failure probability less than a preset failure probability threshold. When the number of cooking plans with a failure probability less than the preset failure probability threshold is greater than the preset number of cooking plans, proceed to step S323. When the number of cooking plans with a failure probability less than the preset failure probability threshold is not greater than the preset number of cooking plans, proceed to step S323. S323 When the total number of historical cooking attempts for a cooking scheme with a failure probability less than the preset failure probability threshold is greater than the preset number of cooking attempts, it is determined that the user's cooking proficiency meets the requirements. When the total number of historical cooking attempts for a cooking scheme with a failure probability less than the preset failure probability threshold is not greater than the preset number of cooking attempts, proceed to step S324. S324 determines the processing proficiency value for different cooking schemes based on the ratio of the number of processing failures to the number of historical cooking attempts under different cooking schemes, and in combination with the number of historical cooking attempts under different cooking schemes. When the average processing proficiency value under different cooking schemes meets the requirements, it is determined that the user's cooking proficiency meets the requirements. When the average processing proficiency value under different cooking schemes does not meet the requirements, the process proceeds to step S33.

[0061] Furthermore, the switching processing conditions include the number of available cooking operation steps when the available cooking program is switched to the associated cooking program.

[0062] Specifically, the method for determining the recommended cooking plan among the available cooking plans is as follows: The association weight value between the associated cooking program and the available cooking program is determined by the ratio of the number of available cooking operation steps when switching from the available cooking program to the associated cooking program to the number of cooking operation steps in the available cooking program. The switching availability value of the available cooking scheme is determined based on the sum of the association weight values ​​between different associated cooking schemes and the available cooking schemes. Based on the switching availability value, determine whether the available cooking program is a recommended cooking program.

[0063] Furthermore, the method for determining the recommended cooking scheme among the available cooking schemes is as follows: The available cooking schemes and their associated cooking schemes are used as inputs to a large model, and the outputs of the large model are used as recommended cooking schemes among the available cooking schemes.

[0064] It is understood that the recommended cooking scheme is the available cooking scheme with the highest available value.

[0065] Furthermore, determining that the user's cooking process using the recommended cooking plan is abnormal specifically includes: Using the cooking images of the recommended cooking scheme during cooking as input, and the output of the large model, it is determined whether there are any abnormalities in the user's cooking process of the recommended cooking scheme.

[0066] Specifically, it automatically generates alternative cooking plans, including: Using the real-time cooking images of the recommended cooking scheme during the cooking process as input, and the output of the large model, alternative cooking schemes are determined when the user switches between recommended cooking schemes.

[0067] Example 2 Secondly, such as Figure 5 As shown, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described cooking scheme recommendation processing method based on a large model when running the computer program.

[0068] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0069] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0070] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A cooking scheme recommendation processing method based on a large model, characterized in that, Specifically, it includes: The range hood's monitoring device determines the user's historical cooking data. If the user's health status is found to be abnormal based on specific types of historical cooking data within a preset time period, the process proceeds to the next step. Based on the matching of specific types of historical cooking data with different disease types, the matching disease type of the user is determined. Based on the matching of different cooking schemes with different matching disease types and dishes, the scheme matching value of the cooking scheme and the available cooking schemes in the cooking scheme are determined. Based on the user's processing data and processing deviation data under different cooking schemes, if it is determined that the user's cooking proficiency does not meet the requirements, proceed to the next step. One of the available cooking schemes will be selected as the target cooking scheme. Other available cooking schemes that can be switched to during the cooking process of the target cooking scheme will be used as associated cooking schemes. Based on the number of associated cooking schemes of the target cooking scheme and the switching conditions, a recommended cooking scheme will be determined from the target cooking scheme. When there is an anomaly when the user cooks using the recommended cooking scheme, an alternative cooking scheme will be automatically generated based on the large model. The specific type of historical cooking data refers to decoction processing data; The method for determining the available cooking plans in the cooking plan is as follows: The dish matching value of a cooking method is determined by the proportion of different cooking methods matched with the dishes in the total number of dishes. Based on the matching results of the cooking plan with different matching disease types, determine the number of matching disease types matched by the cooking plan, and use the proportion of the number of matching disease types matched by the cooking plan to the number of matching disease types to determine the disease matching value of the cooking plan. The matching value of the cooking plan is determined by multiplying the disease matching value and the dish matching value, and the matching value is used to determine whether the cooking plan is a usable cooking plan. When the matching value is greater than the preset matching value threshold, the cooking plan is determined to be a usable cooking plan. The switching processing conditions include the number of available cooking operation steps when the available cooking program is switched to the associated cooking program.

2. The cooking scheme recommendation processing method based on a large model as described in claim 1, characterized in that, The monitoring device is the camera device of the range hood.

3. The cooking scheme recommendation processing method based on a large model as described in claim 1, characterized in that, The historical cooking data includes the number of times the food was cooked, the dates corresponding to different historical cooking methods, and the cooking type.

4. The cooking scheme recommendation processing method based on a large model as described in claim 1, characterized in that, The user's health status is determined to be abnormal, specifically including: The user's decoction processing data within the preset time period is determined using specific types of historical cooking data within the preset time period. The date on which decoction data exists within the preset time period is determined based on the decoction processing data within the preset time period, and this date is used as the decoction processing date. Based on the percentage of decoction processing dates within a preset time period, it is determined whether the user's health status is abnormal.

5. The cooking scheme recommendation processing method based on a large model as described in claim 4, characterized in that, If the percentage of decoction processing dates within the preset time period is greater than the preset percentage of decoction dates, then it is determined that the user's health status is abnormal.

6. The cooking scheme recommendation processing method based on a large model as described in claim 1, characterized in that, The method for determining the recommended cooking scheme in the target cooking scheme is as follows: The association weight value between the associated cooking program and the target cooking program is determined by the ratio of the number of available cooking operation steps when the target cooking program is switched to the associated cooking program to the number of cooking operation steps in the target cooking program. The available switching value for the target cooking program is determined based on the sum of the association weight values ​​between different associated cooking programs and the target cooking program. Based on the available switching values, it is determined whether the target cooking program is a recommended cooking program.

7. The cooking scheme recommendation processing method based on a large model as described in claim 1, characterized in that, Automatically generate alternative cooking plans, including: Using the real-time cooking images of the recommended cooking scheme during the cooking process as input, and the output of the large model, alternative cooking schemes are determined when the user switches between recommended cooking schemes.

8. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a cooking scheme recommendation processing method based on any one of claims 1-7.

Images