Diabetes diet management method, system and equipment based on multi-modal data fusion

Abstract

The invention discloses a diabetes mellitus diet management method, system and device based on multi-modal data fusion, and the method comprises the steps: obtaining a diet analysis conclusion of a target user according to the physiological parameters and diet records of the target user; obtaining a diet target of the target user according to the diet analysis conclusion of the target user; obtaining a first diet plan of the target user according to the diet target of the target user; according to the first diet plan of the target user, obtaining an execution condition of executing the first diet plan by the target user; and obtaining a second diet plan of the target user through the generative artificial intelligence model according to the execution condition of executing the first diet plan by the target user and / or the diet target of the target user. The problems that current diabetes mellitus diet management depends on experts to make diet plans, but when the experts make the diet plans, the diet plans cannot be optimized for users, and the individuation degree is low are solved.

Description

Technical Field

[0001] This application relates to the field of dietary management technology, and in particular to a method, system and device for diabetes dietary management based on multimodal data fusion. Background Technology

[0002] Diabetes dietary management has become a significant health issue globally, especially against the backdrop of the prevalence of obesity and metabolic syndrome. With the increasing number of people with diabetes worldwide, dietary management is considered a core component of controlling diabetes and preventing its complications. The goal of diabetes dietary management is to control blood sugar levels through a reasonable diet, reduce the burden on insulin, improve metabolic indicators such as blood lipids and blood pressure, and prevent various complications caused by diabetes. Dietary management is not limited to controlling sugar intake; it also involves total energy intake, nutritional balance, food selection, and adjustments to dietary patterns. The core of dietary therapy lies in mastering the quantity and quality of carbohydrate intake, as carbohydrates are the main source of blood sugar fluctuations in diabetic patients.

[0003] In recent years, scientists have deepened their research on dietary management for diabetes, especially the effects of different dietary patterns. For example, the Mediterranean diet and the DASH diet have been proven to have positive effects on diabetes management. These dietary patterns emphasize a diverse diet, increasing the intake of fruits, vegetables, whole grains, nuts, and healthy fats, while reducing the intake of processed foods, red meat, and high-sugar foods. Furthermore, with technological advancements, dietary management for diabetic patients is beginning to utilize innovative methods, such as personalized diet plans, blood glucose monitoring devices, and smart dietary management applications, to provide more precise dietary advice and guidance. This allows diabetic patients to not only better control their blood sugar but also improve their quality of life.

[0004] Current diabetes dietary management mainly relies on experts to develop dietary plans. However, when developing dietary plans, experts can generally only create general plans and cannot optimize them based on the user's dynamic physiological characteristics, dynamic dietary preferences and needs, and dynamic health status, resulting in a low degree of personalization. Summary of the Invention

[0005] This invention provides a method, system, and device for diabetes dietary management based on multimodal data fusion, and offers a personalized dietary management solution. It addresses the current problem that diabetes dietary management mainly relies on experts to formulate dietary plans, but experts can generally only formulate general plans and cannot optimize the plans based on the user's dynamic physiological characteristics, dynamic dietary preferences, and dynamic health status, resulting in a low degree of personalization.

[0006] This application provides a diabetes dietary management method based on multimodal data fusion, including: Based on the target user's physiological parameters and dietary records, the dietary analysis conclusions of the target user are obtained; Based on the dietary analysis conclusions of the target users, the dietary goals of the target users are obtained; Based on the target user's dietary goals, a first dietary plan for the target user is obtained; The first dietary plan for the target user is obtained, along with the execution status of the target user's adherence to the first dietary plan. Based on the target user's execution of the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model.

[0007] Optionally, obtaining the dietary analysis conclusions of the target user based on the target user's physiological parameters and dietary records includes: Based on the target users' physiological parameters and dietary records, analyze the correlation between changes in physiological parameters and diet; Based on the correlation between changes in physiological parameters and diet, dietary analysis conclusions for the target user are obtained.

[0008] Optionally, obtaining the dietary goals of the target user based on the dietary analysis conclusions includes: Based on at least one physiological parameter of the target user, the target physiological parameter target is obtained; Based on the target user's physiological parameters and dietary analysis results, the target user's dietary goals are obtained.

[0009] Optional, also includes: The generative artificial intelligence model is configured to include at least one of the following two knowledge bases: A nutrient knowledge base, which includes nutrient data for different foods; A food pairing knowledge base, which includes data on the compatibility of different food pairings.

[0010] Optionally, obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan, the target user's dietary preferences are obtained; The target user's dietary preferences and dietary goals are input into the generative artificial intelligence model to obtain the target user's second dietary plan.

[0011] Optionally, obtaining the target user's dietary preferences based on the target user's execution of the first dietary plan includes: Based on the execution status of the first diet plan by the target user, the performance time series data of the target user when executing the first diet plan is analyzed by the pre-LSTM model to obtain user state time series data; Based on the user state time series data, obtain user state change time series data; The target user's dietary preferences are obtained by analyzing the time-series data of user status changes and the time-series data of the target user's execution of the first dietary plan.

[0012] Optionally, obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan and / or the target user's diet goals, obtain target diet prompts; The target dietary prompts are input into the artificial intelligence model to obtain a second dietary plan for the target user.

[0013] Optionally, obtaining target diet prompts based on the target user's execution of the first diet plan and / or the target user's diet goals includes: Based on the target user's execution of the first diet plan, obtain the target user's dietary preference weight data; Based on the dietary preference weight data, dietary preference prompts are obtained; Based on the dietary goals of the target users, obtain at least one key indicator of those goals; Based on at least one of the key indicators, obtain dietary goal cue words; Based on the dietary preference cue words and / or the dietary target cue words, obtain the target dietary cue words.

[0014] On the other hand, a diabetes diet management system based on multimodal data fusion includes a user analysis platform and a diet plan development platform; The user analytics platform is configured as follows: Based on the target user's physiological parameters and dietary records, the dietary analysis conclusions of the target user are obtained; Based on the dietary analysis conclusions of the target users, the dietary goals of the target users are obtained; The diet planning platform is configured as follows: Based on the target user's dietary goals, a first dietary plan for the target user is obtained; Based on the target user's first dietary plan, obtain the target user's execution status of the first dietary plan; Based on the target user's execution of the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model.

[0015] In another aspect, embodiments of this application also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0016] In another aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein a processor executes the computer program to implement the above-described method.

[0017] Compared with the prior art, the present invention has the following advantages and beneficial effects: This invention provides a method, system, and device for diabetes dietary management based on multimodal data fusion, comprising: obtaining a dietary analysis conclusion of a target user based on the target user's physiological parameters and dietary records; obtaining the target user's dietary goals based on the dietary analysis conclusion; obtaining a first dietary plan for the target user based on the target user's dietary goals; obtaining the target user's execution status of the first dietary plan based on the first dietary plan; and obtaining a second dietary plan for the target user through a generative artificial intelligence model based on the execution status of the first dietary plan and / or the target user's dietary goals. This provides a personalized dietary management solution, at least addressing the current problem that diabetes dietary management mainly relies on experts to formulate dietary plans, but experts can generally only formulate general plans and cannot optimize the plans for individual users, resulting in a low degree of personalization. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 This is a flowchart illustrating a diabetes dietary management method based on multimodal data fusion according to this application. Figure 2 This is a schematic diagram of the structure of a computer device according to this application.

[0020] The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory.

[0021] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present disclosure, the technical solutions of the present disclosure will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present disclosure, and not all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present disclosure.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Example 1 like Figure 1 As shown, a diabetes dietary management method based on multimodal data fusion includes: S1. Based on the target user's physiological parameters and dietary records, obtain the target user's dietary analysis conclusions.

[0025] Optionally, based on multimodal individual data such as the target user's physiological parameters and dietary records, a data dimensionality reduction model can be invoked. Based on AI or semi-human judgment, dietary analysis conclusions for the target user can be obtained. Different dimensionality reduction models can be selected to derive robust, core parameters. This step is generally completed by the data processing layer.

[0026] Optionally, obtaining dietary analysis conclusions for the target users based on their physiological parameters and dietary records includes sub-steps such as data collection, data preprocessing and fusion, and dietary analysis.

[0027] Optional, data collection includes: Physiological parameters of the target user, such as blood sugar levels, blood pressure, weight, BMI, activity level, and sleep quality, are collected through dedicated detection equipment or wearable smart devices; and / or Allow users to record their daily dietary information using an app or other methods, including the types and quantities of food; and / or Collect target users’ physiological parameters and dietary records through other methods.

[0028] Optional, data preprocessing and fusion include: Multimodal data from different sources are cleaned and standardized to ensure consistent data format; and / or By combining physiological parameters with dietary records using machine learning or data fusion methods, meaningful features such as blood glucose trends and postprandial blood glucose changes can be extracted, providing a basis for subsequent analysis.

[0029] Optional dietary analysis includes: Dietary analysis conclusions for the target user are obtained through pre-trained AI models and / or by experts or other personnel with expertise.

[0030] Specifically, dietary analysis conclusions may include: the target user's absorption of different nutrients.

[0031] Specifically, dietary analysis conclusions may also include: assessing whether the core dietary nutrients required by the target user are included; assessing whether the main food sources corresponding to the core dietary nutrients are of high quality, and whether there is a need for or a better alternative food option; and assessing whether it is necessary to increase or decrease the intake of a certain type of food.

[0032] S2. Based on the dietary analysis results of the target users, obtain the dietary goals of the target users.

[0033] Optionally, in practice, based on the dietary analysis results of the target users and combined with various clinical guidelines, diverse dietary recommendations can be compiled. Based on the users' acceptance of the recommendations, relevant popular science information can be provided to the users, ultimately obtaining the dietary goals of the target users.

[0034] Specifically, dietary goals are configured as personalized goals corresponding to the target user. These goals are set based on the user's health status, blood sugar control, and ability to absorb different foods. Dietary goals can include specific target values, such as daily carbohydrate intake targets and vitamin intake targets.

[0035] S3. Based on the target user's dietary goals, obtain the target user's initial dietary plan.

[0036] Optionally, dietary analysis can be performed using a pre-trained AI model, and / or an initial dietary plan for the target user can be obtained by experts or other personnel with expertise based on the target user's dietary goals.

[0037] Optionally, based on the target user's dietary goals, the data can be organized into structured parameters, such as the key feature vectors output by the dimensionality reduction model. Based on these structured parameters, the target user's initial dietary plan can be obtained.

[0038] Specifically, when generating a personalized first diet plan based on dietary goals, factors such as the user's individual basic information, gender, physical activity, food preferences, allergy history, budget, and daily habits can be considered.

[0039] Specifically, when generating a personalized first diet plan, food combinations can be optimized to ensure that users are within the target diet range while maintaining dietary diversity and meeting their daily nutritional needs.

[0040] S4. Based on the target user's first diet plan, obtain information on the target user's execution of the first diet plan.

[0041] Optionally, smart devices such as smart plates, cameras, and blood glucose monitors can be used to track users' dietary habits in real time. Alternatively, users can input their actual food intake into the app, providing feedback on discrepancies between their actual diet and the planned intake; the system will then process this information through text or voice recognition.

[0042] Optionally, the execution of the target user's first diet plan is configured to characterize the user's preferences for different foods.

[0043] S5. Based on the target user's execution of the first diet plan and / or the target user's dietary goals, obtain the target user's second diet plan through a generative artificial intelligence model.

[0044] Optionally, the execution status of the first diet plan by the target user can be obtained through multimodal individual data, such as diet records and physiological parameters of cyclic feedback; and the diet goal of the target user can be obtained through the key feature vector output by the optimized structured parameters: the dimensionality reduction model. Based on the execution status of the first diet plan and / or the diet goal of the target user, a second diet plan for the target user can be obtained through a generative artificial intelligence model.

[0045] Optionally, based on the target user's execution of the first dietary plan and / or the target user's dietary goals, the goal of obtaining the target user's second dietary plan through a generative artificial intelligence model is to make the target user's second dietary plan more able to meet the target user's preferences.

[0046] Optionally, after obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's diet goals, the target user's second diet plan is used as a new first diet plan and this step is repeated in a loop.

[0047] By implementing the methods described above, diabetic patients can receive personalized dietary plans. Combining physiological parameters, dietary records, feedback mechanisms, and generative artificial intelligence technology, dietary management becomes more precise and flexible. The entire system not only adjusts dietary plans in real time based on the target user's health data but also continuously optimizes them through intelligent technology, ensuring long-term effective dietary management for diabetes.

[0048] Example 2 This embodiment, based on Embodiment 1, presents a diabetes dietary management method based on multimodal data fusion, including: S1. Based on the target user's physiological parameters and dietary records, obtain the target user's dietary analysis conclusions.

[0049] Optionally, obtaining dietary analysis conclusions for the target users based on their physiological parameters and dietary records includes sub-steps such as data collection, data preprocessing and fusion, and dietary analysis.

[0050] Optional, data collection includes: Physiological parameters of the target user, such as blood sugar levels, blood pressure, weight, BMI, activity level, and sleep quality, are collected through dedicated detection equipment or wearable smart devices; and / or Allow users to record their daily dietary information using an app or other methods, including the types and quantities of food; and / or Collect target users’ physiological parameters and dietary records through other methods.

[0051] Optional, data preprocessing and fusion include: Multimodal data from different sources are cleaned and standardized to ensure consistent data format; and / or By combining physiological parameters with dietary records using machine learning or data fusion methods, meaningful features such as blood glucose trends and postprandial blood glucose changes can be extracted, providing a basis for subsequent analysis.

[0052] Optional dietary analysis includes: Dietary analysis conclusions for the target user are obtained through pre-trained AI models and / or by experts or other personnel with expertise.

[0053] Specifically, dietary analysis conclusions may include: the target user's absorption of different nutrients.

[0054] Specifically, dietary analysis conclusions may also include: assessing whether the core dietary nutrients required by the target user are included; assessing whether the main food sources corresponding to the core dietary nutrients are of high quality, and whether there is a need for or a better alternative food option; and assessing whether it is necessary to increase or decrease the intake of a certain type of food.

[0055] Optionally, based on the target user's physiological parameters and dietary records, dietary analysis conclusions for the target user can be obtained, including: Based on the target users' physiological parameters and dietary records, analyze the correlation between changes in physiological parameters and diet; Based on the correlation between changes in physiological parameters and diet, dietary analysis conclusions are obtained for the target users.

[0056] S2. Based on the dietary analysis results of the target users, obtain the dietary goals of the target users.

[0057] Specifically, dietary goals are configured as personalized goals corresponding to the target user. These goals are set based on the user's health status, blood sugar control, and ability to absorb different foods. Dietary goals can include specific target values, such as daily carbohydrate intake targets and vitamin intake targets.

[0058] Optionally, based on the dietary analysis results of the target users, the dietary goals of the target users can be obtained, including: Based on at least one physiological parameter of the target user, obtain the target physiological parameters of the target user; Based on the target users' physiological parameters and dietary analysis results, the target users' dietary goals are obtained.

[0059] S3. Based on the target user's dietary goals, obtain the target user's initial dietary plan.

[0060] Optionally, dietary analysis can be performed using a pre-trained AI model, and / or an initial dietary plan for the target user can be obtained by experts or other personnel with expertise based on the target user's dietary goals.

[0061] Specifically, when generating a personalized first diet plan based on dietary goals, factors such as the user's food preferences, allergy history, budget, and daily habits can be taken into account.

[0062] Specifically, when generating a personalized first diet plan, food combinations can be optimized to ensure that users are within the target diet range while maintaining dietary diversity and meeting their daily nutritional needs.

[0063] S4. Based on the target user's first diet plan, obtain information on the target user's execution of the first diet plan.

[0064] Optionally, smart devices such as smart plates, cameras, and blood glucose monitors can be used to track users' dietary habits in real time. Alternatively, users can input their actual food intake into the app, providing feedback on discrepancies between their actual diet and the planned intake; the system will then process this information through text or voice recognition.

[0065] Optionally, the execution of the target user's first diet plan is configured to characterize the user's preferences for different foods.

[0066] S5. Based on the target user's execution of the first diet plan and / or the target user's dietary goals, obtain the target user's second diet plan through a generative artificial intelligence model.

[0067] Optionally, based on the target user's execution of the first dietary plan and / or the target user's dietary goals, the goal of obtaining the target user's second dietary plan through a generative artificial intelligence model is to make the target user's second dietary plan more able to meet the target user's preferences.

[0068] Optionally, after obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's diet goals, the target user's second diet plan is used as a new first diet plan and this step is repeated in a loop.

[0069] Optional, also includes: The generative artificial intelligence model is configured to include at least one of the following two knowledge bases, which are used for the development and optimization of personalized diet plans in diabetes dietary management; Knowledge Base 1 is a nutrient knowledge base, which includes nutrient data for different foods; Knowledge Base 2 is a food pairing knowledge base, which includes data on the pairing degree of different foods.

[0070] Optionally, the generative artificial intelligence model is also configured to include a food attribute knowledge base, which includes information such as the production time, price, and place of origin of different foods.

[0071] Optionally, based on the target user's performance on the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model, including: Based on the target users' adherence to the first dietary plan, their dietary preferences are obtained; By inputting the target user's dietary preferences and dietary goals into a generative artificial intelligence model, a second dietary plan for the target user can be obtained.

[0072] Optionally, the execution status of the target user's first diet plan may also include feedback information from the target user when executing the first diet plan.

[0073] Optionally, based on the target users' adherence to the first dietary plan, their dietary preferences can be obtained, including: Based on the target user's execution of the first diet plan, the performance time series data of the target user when executing the first diet plan is analyzed by using a pre-built LSTM model to obtain user status time series data; Based on the user status time series data, obtain the user status change time series data; By analyzing the time-series data of user status changes and the time-series data of the target user's execution of the first diet plan, the target user's dietary preferences can be obtained.

[0074] Optionally, the LSTM model is configured to take user behavior time series data as input and user state time series data as output; Based on the target user's execution of the first dietary plan, the performance time-series data of the target user during the execution of the first dietary plan is analyzed using a pre-built LSTM model to obtain user state time-series data, including: Based on the target users' execution of the first dietary plan, obtain time-series data on user behavior; User behavior time series data is input into a trained LSTM model to obtain user state time series data.

[0075] Optionally, the LSTM model is configured to include: An LSTM layer used to extract time-dependent features from time-series data; Fully connected layer used to output the final user state feature values; An activation function used to represent probability or state strength.

[0076] Optionally, the user state feature value is a scalar value representing the user's current state. An activation function can be used to convert it into a value between 0 and 1, representing the probability of a certain state, such as the probability of a positive emotion. Finally, the user state feature values ​​at each time point are processed to obtain the user state time series data.

[0077] Optionally, based on the target user's performance on the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model, including: Based on the target user's execution of the first diet plan and / or the target user's diet goals, obtain target diet cue words; Input the target diet tips into the artificial intelligence model to obtain a second diet plan for the target user.

[0078] Optionally, the target dietary prompts can be optimized based on the user profile of the target users.

[0079] Optionally, based on the target user's adherence to the first diet plan and / or the target user's dietary goals, target diet cue words can be obtained, including: Based on the target users' execution of the first diet plan, obtain the target users' dietary preference weight data; Based on dietary preference weighting data, dietary preference prompts are obtained; Based on the dietary goals of the target users, obtain at least one key indicator of those goals. Obtain dietary goal cue words based on at least one key indicator; Obtain target dietary cue words based on dietary preference cue words and / or dietary goal cue words.

[0080] Optionally, the dietary preference weight data is configured as structured data, including food unique identifiers and food weights, with the food unique identifiers being the same as the unique identifiers in the nutrient knowledge base and food pairing knowledge base.

[0081] Specifically, dietary preference cues can be: the weight of a user's food preferences as shown in Table A; Table A contains dietary preference weight data.

[0082] Specifically, dietary goal prompts could be: the user's daily protein requirement range is the protein index in the dietary goal.

[0083] Example 3 A diabetes diet management system based on multimodal data fusion, including a user analysis platform and a diet plan development platform; The user analytics platform is configured as follows: Based on the target users' physiological parameters and dietary records, we obtain dietary analysis conclusions for the target users; Based on the dietary analysis results of the target users, obtain the dietary goals of the target users; The diet planning platform is configured as follows: Based on the target user's dietary goals, obtain the target user's initial dietary plan; The target user's first diet plan, and the status of the target user's adherence to the first diet plan; Based on the target user's performance in following the first dietary plan and / or the target user's dietary goals, a second dietary plan for the target user is obtained through a generative artificial intelligence model.

[0084] Optionally, obtaining the dietary analysis conclusions of the target user based on the target user's physiological parameters and dietary records includes: Based on the target users' physiological parameters and dietary records, analyze the correlation between changes in physiological parameters and diet; Based on the correlation between changes in physiological parameters and diet, dietary analysis conclusions for the target user are obtained.

[0085] Optionally, obtaining the dietary goals of the target user based on the dietary analysis conclusions includes: Based on at least one physiological parameter of the target user, the target physiological parameter target is obtained; Based on the target user's physiological parameters and dietary analysis results, the target user's dietary goals are obtained.

[0086] Optional, also includes: The generative artificial intelligence model is configured to include at least one of the following two knowledge bases; A nutrient knowledge base, which includes nutrient data for different foods; A food pairing knowledge base, which includes data on the compatibility of different food pairings.

[0087] Optionally, obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan, the target user's dietary preferences are obtained; The target user's dietary preferences and dietary goals are input into the generative artificial intelligence model to obtain the target user's second dietary plan.

[0088] Optionally, obtaining the target user's dietary preferences based on the target user's execution of the first dietary plan includes: Based on the execution status of the first diet plan by the target user, the performance time series data of the target user when executing the first diet plan is analyzed by the pre-LSTM model to obtain user state time series data; Based on the user state time series data, obtain user state change time series data; The target user's dietary preferences are obtained by analyzing the time-series data of user status changes and the time-series data of the target user's execution of the first dietary plan.

[0089] Optionally, obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan and / or the target user's diet goals, obtain target diet prompts; The target dietary prompts are input into the artificial intelligence model to obtain a second dietary plan for the target user.

[0090] Optionally, obtaining target diet prompts based on the target user's execution of the first diet plan and / or the target user's diet goals includes: Based on the target user's execution of the first diet plan, obtain the target user's dietary preference weight data; Based on the dietary preference weight data, dietary preference prompts are obtained; Based on the dietary goals of the target users, obtain at least one key indicator of those goals; Based on at least one of the key indicators, obtain dietary goal cue words; Based on the dietary preference cue words and / or the dietary target cue words, obtain the target dietary cue words.

[0091] Example 4 This embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the methods described above.

[0092] Specifically, such as Figure 2 As shown, Figure 2This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiments of this application. The computer device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface or a wireless interface. The network interface 103 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0093] Those skilled in the art will understand that Figure 2 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0094] like Figure 2 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and an application for implementing a diabetes dietary management method based on multimodal data fusion.

[0095] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device, and the electronic device can call the application stored in the memory 105 through the processor 101 to implement the above method.

[0096] Example 5 This embodiment provides a computer-readable storage medium on which a computer program is stored, and a processor executes the computer program to implement any of the methods described above.

[0097] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0098] In the above embodiments of this disclosure, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a non-volatile storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned non-volatile storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0103] The above are merely preferred embodiments of this disclosure. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this disclosure, and these improvements and modifications should also be considered within the scope of protection of this disclosure.

Claims

1. A method for diabetes dietary management based on multimodal data fusion, characterized in that, include: Based on the target user's physiological parameters and dietary records, the dietary analysis conclusions of the target user are obtained; Based on the dietary analysis conclusions of the target users, the dietary goals of the target users are obtained; Based on the target user's dietary goals, a first dietary plan for the target user is obtained; The first dietary plan for the target user is obtained, along with the execution status of the target user's adherence to the first dietary plan. Based on the target user's execution of the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model.

2. The method for diabetes dietary management based on multimodal data fusion according to claim 1, characterized in that, The step of obtaining dietary analysis conclusions for the target user based on the target user's physiological parameters and dietary records includes: Based on the target users' physiological parameters and dietary records, analyze the correlation between changes in physiological parameters and diet; Based on the correlation between changes in physiological parameters and diet, dietary analysis conclusions for the target user are obtained.

3. The method for diabetes dietary management based on multimodal data fusion according to claim 2, characterized in that, The step of obtaining the dietary goals of the target user based on the dietary analysis conclusions of the target user includes: Based on at least one physiological parameter of the target user, the target physiological parameter target is obtained; Based on the target user's physiological parameters and dietary analysis results, the target user's dietary goals are obtained.

4. The method for diabetes dietary management based on multimodal data fusion according to claim 1, characterized in that, Also includes: The generative artificial intelligence model is configured to include at least one of the following two knowledge bases: A nutrient knowledge base, which includes nutrient data for different foods; A food pairing knowledge base, which includes data on the compatibility of different food pairings.

5. A method for diabetes dietary management based on multimodal data fusion according to claim 1, characterized in that, The step of obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan, the target user's dietary preferences are obtained; The target user's dietary preferences and dietary goals are input into the generative artificial intelligence model to obtain the target user's second dietary plan.

6. A method for diabetes dietary management based on multimodal data fusion according to claim 5, characterized in that, The step of obtaining the target user's dietary preferences based on the target user's execution of the first dietary plan includes: Based on the execution status of the first diet plan by the target user, the performance time series data of the target user when executing the first diet plan is analyzed by the pre-LSTM model to obtain user state time series data; Based on the user state time series data, obtain user state change time series data; The target user's dietary preferences are obtained by analyzing the time-series data of user status changes and the time-series data of the target user's execution of the first dietary plan.

7. A method for diabetes dietary management based on multimodal data fusion according to claim 1, characterized in that, The step of obtaining a second diet plan for the target user through a generative artificial intelligence model based on the target user's execution of the first diet plan and / or the target user's dietary goals includes: Based on the target user's execution of the first diet plan and / or the target user's diet goals, obtain target diet prompts; The target dietary prompts are input into the artificial intelligence model to obtain a second dietary plan for the target user.

8. A method for diabetes dietary management based on multimodal data fusion according to claim 7, characterized in that, The step of obtaining target diet prompts based on the target user's execution of the first diet plan and / or the target user's diet goals includes: Based on the target user's execution of the first diet plan, obtain the target user's dietary preference weight data; Based on the dietary preference weight data, dietary preference prompts are obtained; Based on the dietary goals of the target users, obtain at least one key indicator of those goals; Based on at least one of the key indicators, obtain dietary goal cue words; Based on the dietary preference cue words and / or the dietary target cue words, obtain the target dietary cue words.

9. A diabetes diet management system based on multimodal data fusion, characterized in that, This includes user analytics platforms and diet planning platforms; The user analytics platform is configured as follows: Based on the target user's physiological parameters and dietary records, the dietary analysis conclusions of the target user are obtained; Based on the dietary analysis conclusions of the target users, the dietary goals of the target users are obtained; The diet planning platform is configured as follows: Based on the target user's dietary goals, a first dietary plan for the target user is obtained; Based on the target user's first dietary plan, obtain the target user's execution status of the first dietary plan; Based on the target user's execution of the first diet plan and / or the target user's dietary goals, a second diet plan for the target user is obtained through a generative artificial intelligence model.

10. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the computer program to implement the method according to any one of claims 1-8.

Images