Children obesity metabolism intelligent management system and method based on large model

Abstract

The invention discloses a child obesity metabolism intelligent management system and method based on a large model, and relates to the technical field of obesity intelligent management, and the system comprises a model training module and a personalized management suggestion generation module; the model training module is used for training a preset large language model based on the medical data and knowledge associated with the child obesity to obtain a child obesity intelligent management suggestion generation model; and the personalized management suggestion generation module is used for generating personalized management suggestions by using the child obesity intelligent management suggestion generation model when the child obesity related data input by the target user is received. According to the intelligent management suggestion generation model for children obesity, the management data and professional knowledge of obese patients are combined, the health requirements of different users are met, the users are helped to turn from passive treatment to active prevention, the health data of the patients can be rapidly analyzed, personalized management suggestions are generated, and the working efficiency of doctors and nutritionists is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent obesity management, and in particular to a large-scale model-based intelligent management system and method for childhood obesity metabolism. Background Art

[0002] With the continued rise in obesity rates, obesity has become a major public health issue affecting both physical and mental health. Existing childhood obesity interventions rely heavily on offline consultations and manual experience, lacking systematic, personalized, and intelligent intervention tools, and therefore cannot meet the growing demand for obesity health management. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to address the deficiencies of the existing technology and specifically provide a large-scale model-based intelligent management system and method for childhood obesity metabolism, as follows:

[0004] 1) In the first aspect, the present invention provides a large-scale model-based intelligent management system for childhood obesity metabolism. The specific technical solutions are as follows:

[0005] Includes model training module and personalized management suggestion generation module;

[0006] The model training module is used to train a preset large language model based on medical data and knowledge related to childhood obesity to generate a model for intelligent management recommendations for childhood obesity.

[0007] The personalized management suggestion generation module is used to: when receiving the child obesity-related data input by the target user, use the child obesity intelligent management suggestion generation model to generate personalized management suggestions.

[0008] The beneficial effects of the large-scale model-based intelligent management system for childhood obesity metabolism provided by the present invention are as follows:

[0009] On the one hand, by combining the management data and professional knowledge of obese patients, the model can provide personalized intervention plans of the "thousands of people, thousands of strategies" type to meet the health needs of different users and help users shift from "passive treatment" to "active prevention". On the other hand, the childhood obesity intelligent management recommendation generation model can quickly analyze the patient's health data, generate personalized health recommendations, and significantly improve the work efficiency of doctors and nutritionists.

[0010] On the basis of the above scheme, the large model-based intelligent management system for childhood obesity metabolism of the present invention can be further improved as follows.

[0011] Furthermore, an interactive module is included, which is used to guide the target user to input data related to childhood obesity in an interactive manner.

[0012] Furthermore, the optimization module is used to optimize personalized management suggestions.

[0013] Furthermore, the personalized management suggestions include at least one of dietary management suggestions, psychological management suggestions, and sleep management suggestions.

[0014] 2) In a second aspect, the present invention also provides a method for intelligent management of childhood obesity metabolism based on a large model. The specific technical solution is as follows:

[0015] Based on medical data and knowledge related to childhood obesity, a preset large language model is trained to generate a model for generating intelligent management recommendations for childhood obesity.

[0016] When receiving the child obesity-related data input by the target user, the child obesity intelligent management suggestion generation model is used to generate personalized management suggestions.

[0017] On the basis of the above scheme, the intelligent management method of childhood obesity metabolism based on a large model of the present invention can also be improved as follows.

[0018] Furthermore, the method also includes: guiding the target user to input data related to childhood obesity in an interactive manner.

[0019] Furthermore, it also includes: optimizing personalized management suggestions.

[0020] Furthermore, the personalized management suggestions include at least one of dietary management suggestions, psychological management suggestions, and sleep management suggestions.

[0021] 3) In a third aspect, the present invention further provides an electronic device, comprising a processor coupled to a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor, so that the electronic device implements any one of the above-mentioned methods for intelligent management of childhood obesity metabolism based on a large model.

[0022] 4) In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any one of the above-mentioned methods for intelligent management of childhood obesity metabolism based on a large model.

[0023] It should be noted that the beneficial effects achieved by the technical solutions of the second to fourth aspects of the present invention and the corresponding possible implementation methods can be found in the above-mentioned technical effects of the first aspect and its corresponding possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments of the present invention:

[0025] Figure 1 This is a schematic structural diagram of a large-scale model-based intelligent management system for childhood obesity metabolism according to an embodiment of the present invention;

[0026] Figure 2 Schematic diagram of a flow chart of a method for intelligent management of childhood obesity metabolism based on a large model according to an embodiment of the present invention;

[0027] Figure 3 The figure is a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The principles and features of the present invention are described below. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0029] The following describes in detail the technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems using specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following embodiments of the present invention are described in conjunction with the accompanying drawings.

[0030] like Figure 1 As shown, a large-model-based intelligent management system 200 for childhood obesity metabolism according to an embodiment of the present invention includes a model training module 201 and a personalized management suggestion generation module 202;

[0031] The model training module 201 is used to train a preset large language model based on medical data and knowledge related to childhood obesity to obtain a model for generating intelligent management suggestions for childhood obesity. Specifically:

[0032] 1) Integrate and obtain each user's structured health data, unstructured diet record text, and time-series physiological indicators based on structured electronic health records, wearable device time-series data, medical imaging feature vectors, unstructured medical literature knowledge base, and obesity-related medical data and knowledge. Among them, structured health data includes BMI and body fat percentage, and time-series physiological indicators include continuous blood glucose monitoring data and sleep cycle signals.

[0033] 2) Based on each user's structured health data, unstructured diet record text, and time-series physiological indicators, and based on a real-time feedback regulator and medical knowledge verification mechanism of reinforcement learning, the parameters of the preset large language model are updated through dual-channel backpropagation to complete the training of the preset large language model and obtain a model for generating intelligent management recommendations for childhood obesity.

[0034] The preset large language model includes a multimodal embedding layer, a temporal processing layer, a cross-modal fusion layer, a medical knowledge constraint layer, a cross-domain attention layer, a personalized adaptation layer, and a multi-target decoding layer. Specifically:

[0035] ① In the multimodal embedding layer, a fully connected embedding network is used to generate numerical feature vectors of structured health data. The BERT pre-trained model is used to extract semantic vectors from unstructured dietary record texts. A one-dimensional convolutional network is used to generate time-sensitive vectors of temporal physiological indicators. The numerical feature vectors, semantic vectors, and time-sensitive vectors are then concatenated to generate a multimodal joint embedding representation.

[0036] ② In the time series processing layer, the time series features of the time series components in the multimodal joint embedding representation are extracted through a bidirectional LSTM network. Based on the temporal attention mechanism, the key time points of the time series features are obtained. The time series features and the key time points are multiplied to obtain the enhanced time series features.

[0037] ③ In the cross-modal fusion layer, the non-temporal components in the multimodal joint embedding representation and the non-temporal components in the enhanced temporal features are concatenated to obtain the concatenated features. The concatenated features are processed based on the cross-attention mechanism to obtain the cross-modal joint representation.

[0038] ④ In the medical knowledge constraint layer, the childhood obesity medical knowledge graph is encoded into graph node vectors according to the disease-nutrition-drug relationship, and a cross-modal joint representation is used as the query vector to perform attention matching with the graph node vector to generate knowledge-constrained features.

[0039] ⑤ In the cross-domain attention layer, based on the gated multi-head attention mechanism, the knowledge-constrained features and cross-modal joint representation are processed to output cross-domain correlation features.

[0040] ⑥ In the personalized adaptation layer, the feature vector consisting of the user's age, gender, and medical history, as well as cross-domain correlation features, are input into the Softmax function to obtain a personalized weight matrix. The weights in the personalized weight matrix correspond to the three dimensions of diet, psychology, and sleep.

[0041] ⑦ In the multi-objective decoding layer, the weight of each dimension of the personalized weight matrix and the cross-modal joint representation are decoded separately to obtain a multi-dimensional suggestion text, namely personalized management suggestions. Personalized management suggestions include dietary management suggestions, psychological management suggestions, and sleep management suggestions.

[0042] The personalized management suggestion generation module 202 is used to: when receiving the child obesity related data input by the target user, generate personalized management suggestions by using the child obesity intelligent management suggestion generation model.

[0043] The target user may be the parent of the target child. The target user inputting the child obesity-related data refers to the target child's obesity-related data input by the parent of the target child.

[0044] Optionally, the above technical solution further includes an interactive module, which is used to interactively guide the target user to input data related to childhood obesity. The specific implementation process is as follows:

[0045] 1) Obtain the target child’s basic physiological parameters (including age, gender, height, initial weight, BMI, body fat percentage, and waist circumference) through the biometric interface to construct the target child’s initial user portrait vector; call the obesity risk factor library in the medical knowledge graph, and input the initial user portrait vector into the template matching algorithm based on the graph neural network to generate a personalized data collection requirement template.

[0046] Among them, based on the obesity-related terms and the correlation between symptoms contained in existing medical knowledge graphs (such as SNOMED CT, U-MLS), an initial obesity risk factor library was constructed, and the basic physiological parameters were matched and associated with the initial obesity risk factor library to construct an obesity risk factor library.

[0047] In the template matching algorithm based on graph neural networks, the initial user portrait vector of the target child is used as the query node, and relevant subgraphs are matched in the obesity risk factor library. Based on the relevant subgraphs, a personalized data collection requirement template is generated. Specifically:

[0048] The numerical data (age, height, initial weight, BMI, body fat percentage, waist circumference) of the target child's basic physiological parameters are normalized. The categorical data (gender) of the target child's basic physiological parameters are mapped into vectors. The normalized values ​​are feature concatenated with the vectors to generate an initial user profile vector. The initial user profile vector is dimensionally compressed using a fully connected layer to obtain a standardized user profile vector. The obesity risk factor library includes an obesity risk factor knowledge graph that expresses the association between obesity-related terms and complications. Nodes in the obesity risk factor knowledge graph represent obesity-related terms (also referred to as obesity risk factors), and edges between two nodes represent associations. The cosine similarity of each node in the standardized user profile vector is calculated. The nodes are sorted in descending order of cosine similarity to obtain a node sequence. The first k nodes in the node sequence are designated as key nodes. The minimum subgraph of the obesity risk factor knowledge graph that includes all key nodes is designated as a relevant subgraph. Alternatively, a cosine similarity threshold is set, and nodes with a cosine similarity greater than the cosine similarity threshold are designated as key nodes. A personalized data collection requirement template can be manually generated based on the nodes in the relevant subgraph and the relationships between the nodes, or the required and non-required items corresponding to the pre-set nodes can be screened based on the nodes in the relevant subgraph and the relationships between the nodes to generate a personalized data collection requirement template.

[0049] Among them, the personalized data collection requirement template includes required items, recommended items and associated collection modes. The associated collection mode refers to: data collected directly through other sensors, etc. For example, body fat percentage needs to be uploaded through a smart body fat scale, rather than directly input by the target user.

[0050] 2) Based on the personalized data collection requirement template and real-time interaction status, a multimodal guidance question set is generated through the improved GPT-4 architecture, and the guidance questions are presented through a mixed reality interface. When presenting guidance questions, text-based guidance questions are displayed through an adaptive font interface, voice-based guidance questions are optimized in output tone through a voiceprint adaptation module, and image-based guidance questions include interactive 3D human body model annotations.

[0051] Among them, the real-time interaction state refers to: the multidimensional state vector of the current interaction process, specifically including real-time dialogue coding and real-time emotional state, etc., among which the real-time dialogue coding is obtained by encoding the current interaction text, and the real-time emotional state is obtained by recognizing the current interaction text, audio or facial expression.

[0052] Among them, the voiceprint adaptation module extracts features such as the fundamental frequency and resonance peak of the voice, and then uses the WaveGlow vocoder to generate personalized voice, which can solve the "mechanical feel" problem of traditional voice interaction.

[0053] 3) Performing real-time structured processing on the multi-dimensional data of the target child input by the target user. Specifically, the text input data of the target child is converted into standard medical codes through the Clinical Terminology Normalization Model (CTN-Model), a medical ASR system is used to synchronously generate a text record and emotional feature vector of the target child's voice input data, and a deep learning segmentation network (e.g., U-Net++) is used to extract food portion estimation and body shape features from image input data and / or video input data.

[0054] Among them, body characteristics refer to: morphological indicators of target children, including waist-to-hip ratio and standing posture inclination angle.

[0055] Among them, the deep learning segmentation network can output a mask of the food area, and then calculate the food volume based on the mask area and reference objects (such as tableware size), thereby obtaining a food portion estimate.

[0056] 4) Detect whether there are missing or contradictory data in the multivariate data after temporal structured processing, and then trigger the dual-stream attention-based question generator. The dual-stream attention-based question generator constructs a missing dimension feature vector for characterizing different follow-up questions according to the missing or contradictory missing data, and calculates the question priority based on the missing dimension feature vector to obtain a follow-up question set. According to the priority relationship of the follow-up question set, corresponding follow-up questions are raised until all follow-up questions in the follow-up question set are completed or a personalized data collection requirement template is obtained after filling in the information. It should be noted that the follow-up question set can be updated in real time each time a follow-up question is issued.

[0057] The implementation process of detecting whether there is data missing or contradictory in the multivariate data after temporal structured processing is as follows:

[0058] ① Check whether the required items in the personalized data collection requirement template are filled in completely. If not, there is data missing.

[0059] ② Verify the consistency of multimodal descriptions of the same entity to identify any data discrepancies. For example, if the target user's voice description "the target child ate a small bowl of rice" is inconsistent with the calculated food portion estimate of 500g of rice, this indicates a data discrepancy. This can be determined by setting a deviation threshold.

[0060] Among them, the follow-up question generator is obtained by training models such as GPT-3. Each sample in the training set used includes: missing or contradictory data and corresponding follow-up questions.

[0061] Optionally, the above technical solution further includes an optimization module, which is used to optimize the personalized management suggestions, specifically:

[0062] Obtain obesity-related data from target children, including but not limited to circumference information, disease-related information, physical examination information, dietary records, and exercise data; pre-process the collected data, including data cleaning and normalization, to ensure data quality and availability; apply large-scale feature extraction techniques, such as using LLM to extract symptom features, and enhance knowledge retrieval through RAG, apply Llama Index scoring, and other methods to extract features related to obesity management from the processed data; based on the extracted features, use machine learning algorithms to train the preset large language model to obtain a model for generating intelligent management recommendations for children's obesity. During the training process, new obesity-related data is regularly injected to retrain the model to maintain its accuracy and timeliness. When receiving childhood obesity-related data input by the target child, use the trained model for generating intelligent management recommendations for children's obesity, combined with the support of professional doctors, to generate personalized management recommendations, including but not limited to dietary recommendations, exercise plans, and lifestyle adjustment recommendations.

[0063] Optionally, collect feedback from target users on personalized management suggestions, and continuously adjust and optimize the model and suggestion generation process based on the feedback and actual application effects to improve the accuracy and practicality of personalized management suggestions.

[0064] Optionally, in the above technical solution, the personalized management suggestions include at least one of dietary management suggestions, psychological management suggestions and sleep management suggestions.

[0065] The present invention is described by another embodiment, specifically:

[0066] In recent years, the development of artificial intelligence technology, especially large language models, has made it possible for the rapid processing and intelligent application of medical knowledge. However, how to deeply integrate the capabilities of large models with clinical practice knowledge to build a highly reliable and highly interactive intelligent intervention system is still facing challenges, especially in the field of children, which involves the intersection of multiple factors such as nutrition, psychology, exercise, and family environment, and requires more professional support. The present invention aims to provide a large-model-based intelligent management system for children's obesity metabolism that uses in-depth consultation as the main starting point, fully empowered by large models, and data-driven, to build a children's obesity metabolism intelligent body that integrates hospital expert knowledge, nutrition, sports medicine and clinical experience, and improve the scientificity, systematicness and personalization of intervention. Specifically:

[0067] 1) Construction of a disease-specific database: Collect medical data related to childhood obesity, such as hyperlipidemia, weight, and outpatient medical records, to form a structured obesity metabolism database.

[0068] 2) Multidisciplinary knowledge integration: Integrate expert knowledge on child nutrition, exercise intervention, psychological sleep, family environment, etc. to form a knowledge base, and combine it with clinical expert labeled data to train and optimize basic large language models (such as DeepSeek, etc.).

[0069] 3) Agent deployment and service role division:

[0070] ① Medical version: It connects to multimodal databases and knowledge bases, is suitable for use in hospital outpatient clinics, provides in-depth consulting services such as initial diagnosis, follow-up diagnosis, free Q&A, knowledge query, etc., and supports fine-grained consultation processes.

[0071] ② Parent version: For family users, it provides convenient mobile phone interaction, allowing users to upload children's exercise videos, identify the nutritional content of dishes, and generate personalized health recommendations covering psychological, sleep and other dimensions.

[0072] ③Teacher Edition: Serving the campus scene, focusing on curriculum design optimization and "nutrition kitchen" planning, and innovatively proposing that teachers participate in children's weight consultation every month to promote the construction of a healthy campus ecology.

[0073] 4) Question-and-answer system design: Based on a user-friendly process design and combined with a "step-by-step" interactive strategy, it guides users to complete the consultation and generates personalized recommendation reports supported by evidence-based medicine.

[0074] 5) Reporting and feedback mechanism: The generated forms cover medical, teaching and family scenarios, providing scientific, standardized and evidence-based consulting reports with good interpretability and enforceability.

[0075] Compared with the prior art, the present invention has the following beneficial effects:

[0076] Achieve regional-level deployment of child obesity metabolic intelligent entities, serving a wide range of targets; provide in-depth health consultation support for multiple roles and scenarios in a flexible manner; combine large-scale model reasoning capabilities with expert knowledge systems to improve the scientific nature and personalization of intervention recommendations; innovatively introduce teacher health service functions to expand new models of campus health intervention; highly scalable, with potential for industry implementation and iterative optimization.

[0077] Optionally, it also includes: establishing standardized data collection interfaces and structured storage methods; using fine-tuning technology to adapt large models to medical semantic understanding and consulting tasks; using graph neural networks or knowledge enhancement methods to enhance the logical reasoning ability of intelligent agents; combining actual hospital and school scenarios to develop multi-terminal client applications (APP, Web, etc.); supporting AI parsing capabilities for user-uploaded content, such as image recognition of dishes and video recognition of movement postures; and pushing consultation results to user terminals in the form of PDF or digital reports.

[0078] like Figure 2As shown, a method for intelligent management of childhood obesity metabolism based on a large model according to an embodiment of the present invention includes the following steps:

[0079] S1. Based on medical data and knowledge related to childhood obesity, a preset large language model is trained to obtain a model for generating intelligent management recommendations for childhood obesity.

[0080] S2. When receiving the child obesity-related data input by the target user, the child obesity intelligent management suggestion generation model is used to generate personalized management suggestions.

[0081] Optionally, the above technical solution further includes: guiding the target user to input data related to childhood obesity in an interactive manner.

[0082] Optionally, the above technical solution further includes: optimizing personalized management suggestions.

[0083] Optionally, in the above technical solution, the personalized management suggestions include at least one of dietary management suggestions, psychological management suggestions and sleep management suggestions.

[0084] It should be noted that the beneficial effects of the large-scale model-based intelligent management method for childhood obesity metabolism provided in the above embodiment are the same as those of the large-scale model-based intelligent management system for childhood obesity metabolism 200, and are not further elaborated here. The method and system embodiments provided in the above embodiment share the same concept, and their specific implementation process is detailed in the system embodiment and is not further elaborated here.

[0085] In the above embodiments, although the steps are numbered S1, S2, etc., these are only specific embodiments given by the present invention. Those skilled in the art may adjust the execution order of S1, S2, etc. according to actual conditions, which is also within the scope of protection of the present invention. It can be understood that in some embodiments, some or all of the above embodiments may be included.

[0086] Among them, the large-scale model-based intelligent management system for childhood obesity metabolism of the present invention can be a computer program (including program code) running in a computer device. For example, the large-scale model-based intelligent management system for childhood obesity metabolism of the present invention is an application software that can be used to execute the corresponding steps in the large-scale model-based intelligent management method for childhood obesity metabolism of the present invention.

[0087] In some embodiments, the large-scale model-based intelligent management system for childhood obesity metabolism of the present invention can be implemented by a combination of software and hardware. As an example, the large-scale model-based intelligent management system for childhood obesity metabolism of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the large-scale model-based intelligent management method for childhood obesity metabolism of the present invention. For example, the processor in the form of a hardware decoding processor can adopt one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0088] The modules described in the embodiments of the present invention may be implemented in software or hardware, and the name of a module does not necessarily limit the module itself.

[0089] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any of the aforementioned methods for intelligent management of childhood obesity metabolism based on a large model is implemented. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to, a processor and a memory; the memory is used to store the computer program; and the processor is used to execute the method for intelligent management of childhood obesity metabolism based on a large model as shown in any embodiment of the present invention by calling the computer program.

[0090] In an alternative embodiment, an electronic device is provided, such as Figure 3 As shown, Figure 3 The electronic device 4000 shown includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data exchange between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the number of transceivers 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0091] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0092] Bus 4002 may include a path for transmitting information between the above components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 4002 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 In the figure, only one thick line is used to represent the bus 4002, but this does not mean that there is only one bus or one type of bus.

[0093] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0094] The memory 4003 is used to store application code (computer program) for executing the solution of the present invention, and is controlled by the processor 4001. The processor 4001 is used to execute the application code stored in the memory 4003 to implement the content shown in the above method embodiment.

[0095] Among them, the electronic device can also be a terminal device, and the terminal device can be any device that can install applications, including at least one of a smartphone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart TV, and a smart car device.

[0096] It should be noted that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0097] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, which, when executed by a processor, implements any of the above-mentioned large-model-based intelligent management methods for childhood obesity metabolism.

[0098] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, or the like.

[0099] In an exemplary embodiment, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to implement any of the aforementioned large-scale model-based intelligent management methods for childhood obesity metabolism.

[0100] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0101] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0102] The computer-readable storage medium provided in the embodiment of the present invention may be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EEPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or component.

[0103] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0104] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present invention.

[0105] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and to define a specific order or precedence. Where appropriate, the order used for similar objects may be interchanged, such that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0106] Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the present invention may be implemented in the form of a computer program product embodied in one or more computer-readable media containing computer-readable program code.

[0107] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A large-scale model-based intelligent management system for childhood obesity metabolism, characterized by: Includes model training module and personalized management suggestion generation module; The model training module is used to train a preset large language model based on medical data and knowledge related to childhood obesity to obtain a model for generating intelligent management suggestions for childhood obesity; The personalized management suggestion generation module is used to: when receiving the child obesity related data input by the target user, use the child obesity intelligent management suggestion generation model to generate personalized management suggestions.

2. The large model-based intelligent management system for childhood obesity metabolism according to claim 1, characterized in that: The system also includes an interactive module, which is used to guide the target user to input data related to childhood obesity in an interactive manner.

3. The large model-based intelligent management system for childhood obesity metabolism according to claim 1, characterized in that: It also includes an optimization module, which is used to optimize the personalized management suggestions.

4. The large model-based intelligent management system for childhood obesity metabolism according to any one of claims 1 to 3, characterized in that: The personalized management suggestion includes at least one of a dietary management suggestion, a psychological management suggestion, and a sleep management suggestion.

5. A method for intelligent management of childhood obesity metabolism based on a large model, characterized in that: include: Based on medical data and knowledge related to childhood obesity, a preset large language model is trained to generate a model for generating intelligent management recommendations for childhood obesity. When receiving the child obesity related data input by the target user, the child obesity intelligent management suggestion generation model is used to generate personalized management suggestions.

6. The method for intelligent management of childhood obesity metabolism based on a large model according to claim 5, characterized in that: Also includes: Interactively guide target users to input data related to childhood obesity.

7. The method for intelligent management of childhood obesity metabolism based on a large model according to claim 6, characterized in that: Also includes: The personalized management suggestion is optimized.

8. A method for intelligent management of childhood obesity metabolism based on a large model according to any one of claims 5 to 7, characterized in that: The personalized management suggestion includes at least one of a dietary management suggestion, a psychological management suggestion, and a sleep management suggestion.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for intelligent management of childhood obesity metabolism based on a large model as claimed in any one of claims 5 to 8 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for intelligent management of childhood obesity metabolism based on a large model as described in any one of claims 5 to 8 is implemented.

Images