Auxiliary method and system for weight management of smoking quitters

Abstract

The invention specifically relates to a smoking cessation person weight management auxiliary method and system, and the method comprises the steps: obtaining a current multi-source weight data set of a user in response to a user data feedback signal of a smoking cessation person, the current multi-source weight data set at least comprises genotype data features of the user, current weight data features and various types of life behavior data features; the current multi-source weight data set of the user is substituted into the intelligent weight management model, a weight management scheme matched with the user is selectively updated or generated, and the weight management scheme at least comprises a diet suggestion parameter set, an exercise suggestion parameter set and a current target combination parameter set; and obtaining a feedback instruction of the user for the body weight management scheme matched with the user, and selectively adjusting the intelligent body weight management model based on the feedback instruction. When the change of any data of the smoking cessation person is monitored, the body weight management scheme is automatically adjusted, and it is ensured that the user is matched with the body weight management scheme.

Description

Technical Field

[0001] This invention relates to the field of weight management technology, specifically to the field of weight management technology for smokers quitting smoking, and specifically to an auxiliary method and system for weight management for smokers quitting smoking. Background Technology

[0002] With the advancement of genome-wide association studies (GWAS), scientists have discovered that specific single nucleotide polymorphisms (SNPs) of brain-derived neurotrophic factor (BDNF) on chromosome 11 are significantly associated with smoking behavior and body mass index (BMI). Particularly in former smokers, these SNP variations are associated with an increased risk of obesity.

[0003] Therefore, there is a need in this field for a new method to assist in weight management for smokers who are quitting smoking, so as to provide personalized weight management solutions for smokers who are quitting smoking. Summary of the Invention

[0004] Based on this, the present invention proposes an auxiliary method and system for weight management for smokers quitting smoking, which solves the technical problem that existing weight management methods cannot provide personalized weight management solutions for smokers quitting smoking.

[0005] According to a first aspect of the present invention, a method for assisting in weight management for smokers who are quitting smoking is provided, the method comprising the following steps:

[0006] In response to user data feedback signals from smokers who are quitting smoking, the user's current multi-source weight dataset is obtained. The current multi-source weight dataset includes at least the user's genotype data characteristics, current weight data characteristics, and various types of lifestyle behavior data characteristics.

[0007] By feeding the user's current multi-source weight dataset into the intelligent weight management model, the model can analyze and process various data in the user's current multi-source weight dataset, selectively update or generate a weight management plan that matches the user. The weight management plan includes at least a set of dietary recommendations, a set of exercise recommendations, and a set of current target combination parameters.

[0008] The system obtains user feedback on a weight management plan tailored to the user, and selectively adjusts the intelligent weight management model based on this feedback to enhance user engagement and satisfaction, thereby increasing the motivation and initiative of users quitting smoking to control their weight.

[0009] According to an embodiment of the present invention, obtaining the user's current multi-source weight dataset in response to the user data feedback signal from the smoker quitting includes:

[0010] In response to user data feedback signals from smokers quitting, the user's change data is determined, wherein the user data feedback signals include at least one of the user's genotype data, current weight data, and different types of lifestyle behavior data;

[0011] The user's change data is preprocessed to obtain preprocessed change data;

[0012] Based on the preprocessed change data, extract at least one feature from the change data;

[0013] Update the user's current multi-source weight dataset based on at least one feature from the changing data and record the update time.

[0014] According to an embodiment of the present invention, before substituting the user's current multi-source weight dataset into the intelligent weight management model, the method further trains the intelligent weight management model through the following steps:

[0015] Using different smoking cessation users as training samples, multiple training sample datasets are generated. The training sample datasets include at least the genotype data, personality data, and lifestyle behavior data corresponding to different weights of the training samples.

[0016] Based on multiple training sample datasets, determine the combined parameters of influence corresponding to different body weights for each training sample dataset.

[0017] Based on the combined influence parameters corresponding to each training sample dataset and each weight data, a weight management plan is generated for each training sample dataset at different weights.

[0018] Based on weight management schemes with different weights in each training sample dataset, the intelligent weight management model corresponding to each training sample is selectively optimized, and the optimized intelligent weight management model is retrained.

[0019] According to an embodiment of the present invention, generating multiple training sample datasets using users who have quit smoking as training samples includes:

[0020] Obtain multi-dimensional information on different users who have quit smoking at different weights, wherein the multi-dimensional information includes at least weight data, genotype data of users who have quit smoking, various types of lifestyle behavior data, and personality data of users who have quit smoking;

[0021] Using different smoking cessation users as training samples, and based on the multi-dimensional information of the different smoking cessation users at different weights, the different training samples are classified to obtain a training sample set of each type, wherein each type of training sample set includes at least one training sample.

[0022] Based on each type of training sample set and the multi-dimensional information of each training sample at different weights, a training sample dataset for each type is constructed to obtain multiple sets of training sample datasets.

[0023] According to an embodiment of the present invention, determining the combined influence parameters corresponding to different body weights for each training sample dataset based on multiple training sample datasets includes:

[0024] Obtain the initial combination parameters of the intelligent weight management model, wherein the initial combination parameters include at least the initial genotype data influence parameters, the initial personality data influence parameters, and the initial lifestyle behavior data influence parameters of different types;

[0025] Based on multiple training sample datasets and the latest version of the multi-source data influence comparison table, the influence ratio corresponding to each data item in each training sample dataset is determined.

[0026] Based on the influence ratios corresponding to each data point in each training sample dataset and the initial influence combination parameters of the intelligent weight management model, the influence combination parameters corresponding to different weights for each training sample are obtained.

[0027] This is to obtain the combined parameters of influence corresponding to different weights for each training sample dataset.

[0028] According to an embodiment of the present invention, generating a weight management plan for each training sample dataset at different weights based on the combined influence parameters corresponding to each weight data set includes:

[0029] Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, multiple weight management plans are generated for each training sample dataset at each weight.

[0030] Multiple weight management plans were simulated to obtain a weight goal completion dataset for each weight management plan. The weight goal completion dataset includes at least the completion rate of dietary goals, the completion rate of exercise goals, the total time to complete weight goals, and the user's psychological prediction change value.

[0031] Based on the weight goal completion dataset corresponding to each weight management plan, the completion score corresponding to each weight management plan is obtained;

[0032] Based on the completion score corresponding to each weight management plan, multiple weight management plans for each weight in each training sample dataset are filtered to obtain a weight management plan for each weight in each training sample dataset.

[0033] To obtain weight management plans for each training sample dataset at different weights.

[0034] According to an embodiment of the present invention, generating multiple weight management plans for each training sample dataset at each weight, based on various data in each training sample dataset and the combined influence parameters corresponding to different weights of each training sample dataset, includes:

[0035] Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, the influence parameter values ​​of each data in each training sample dataset on different weights are obtained.

[0036] Based on the data in each training sample dataset, determine the target weight value for each training sample at different weights.

[0037] Based on the target weight values ​​corresponding to different weights for each training sample and the influence parameters of various data in each training sample dataset on different weights, multiple weight management plans are generated for each training sample dataset at each weight.

[0038] According to an embodiment of the present invention, obtaining the completion score corresponding to each weight management plan based on the weight goal completion dataset corresponding to each weight management plan includes:

[0039] Based on the user's psychological prediction change value corresponding to the weight management plan, determine the psychological prediction score of the training sample after management of the weight management plan.

[0040] If the psychological prediction score of the training sample corresponding to the weight management plan is lower than the preset psychological prediction score threshold, or if the change value of the user's psychological prediction corresponding to the weight management plan exceeds the preset psychological prediction change threshold corresponding to the total time to complete the weight goal, then the completion score corresponding to the weight management plan will be set to "0".

[0041] Otherwise, the completion score corresponding to the weight management plan is obtained based on the weight target completion dataset corresponding to the weight management plan.

[0042] According to an embodiment of the present invention, obtaining user feedback instructions on a weight management plan matched to the user, and selectively adjusting the intelligent weight management model based on the feedback instructions, includes:

[0043] Obtain user feedback instructions on a weight management plan tailored to the user, wherein the feedback instructions include at least the user's questions or suggestions for adjustment;

[0044] If the feedback instruction is a proposed adjustment suggestion, then the intelligent weight management model is adjusted based on the adjustment suggestion to obtain the adjusted intelligent weight management model corresponding to the user.

[0045] The adjusted intelligent weight management model corresponding to the user is then retrained to optimize the intelligent weight management model for the user.

[0046] According to a second aspect of the present invention, a weight management assistance system for smokers is provided, the system comprising an interaction module, a processing module, a display module, and a control device;

[0047] The interaction module exchanges information with the user terminal to obtain input data and feedback data from the user terminal, and to obtain the user's current multi-source weight dataset and the user's feedback instructions on the weight management plan matched to the user.

[0048] The processing module and the interaction module interact with each other. The processing module includes a storage unit and an intelligent weight management model. The storage unit is used to store the data obtained by the interaction module and the data output by the intelligent weight management model. The intelligent weight management model is used to analyze and process various data in the user's current multi-source weight dataset, and selectively update or generate a weight management plan that matches the user.

[0049] The display module and the interaction module exchange information, and the display module is used to display a weight management plan that matches the user.

[0050] The control device interacts with the interaction module, processing module, and display module. The control device includes a processor and a memory. The memory is adapted to store multiple program codes. The program codes are adapted to be loaded and run by the processor to execute the weight management assistance method for smokers described in any of the above-mentioned technical solutions.

[0051] As can be seen from the above technical solutions, the weight management assistance method and system for smokers provided by the present invention have the following beneficial effects:

[0052] The weight management assistance method for smokers cessation provided by this invention obtains the user's current multi-source weight dataset in response to user data feedback signals. This allows for timely collection of multi-dimensional information about the user when changes in weight or any data point are detected. The current multi-source weight dataset is then fed into an intelligent weight management model, which analyzes and processes the data to selectively update or generate a weight management plan tailored to the user. This provides personalized weight management plans and suggestions, improving management effectiveness. The method dynamically adjusts the weight management plan based on user feedback signals, automatically adjusting the plan when changes in weight or any data point are detected, ensuring a match between the user and the plan. Furthermore, the method obtains user feedback instructions on the weight management plan and selectively adjusts the intelligent weight management model accordingly, enhancing user participation and satisfaction, and ultimately increasing the user's initiative and proactiveness in controlling their weight. Attached Figure Description

[0053] The disclosure of this invention will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0054] Figure 1 This is a schematic diagram of the main steps of a weight management assistance method for smokers according to an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of the main structure of a weight management assistance system for smokers according to an embodiment of the present invention;

[0056] List of reference numerals in the attached diagram:

[0057] 200: Weight management assistance system for smokers quitting smoking; 201: Interaction module; 202: Processing module; 2021: Storage unit; 2022: Intelligent weight management model; 203: Display module; 204: Control device; 2041: Processor; 2042: Memory; 2043: Program code. Detailed Implementation

[0058] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0059] In the description of this invention, "module" and "processor" can include hardware, software, or a combination of both. A module can include hardware circuitry, various suitable sensors, communication ports, memory, and may also include software components, such as program code, or a combination of software and hardware. A processor can be a central processing unit, microprocessor, image processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and can include only A, only B, or A and B. The singular terms "a" or "this" can also include plural forms.

[0060] See appendix Figure 1 , Figure 1 This is a schematic flowchart illustrating the main steps of a weight management assistance method for smokers according to an embodiment of the present invention. Figure 1 As shown, an auxiliary method for weight management for smokers in an embodiment of the present invention mainly includes the following steps S101-S103.

[0061] Step S101: In response to the user data feedback signal of the smoker quitter, obtain the user's current multi-source weight dataset, wherein the current multi-source weight dataset includes at least the user's genotype data features, current weight data features, and multiple types of lifestyle behavior data features;

[0062] In some embodiments, obtaining the user's current multi-source weight dataset in response to user data feedback signals from smokers includes:

[0063] In response to user data feedback signals from smokers quitting, the user's change data is determined, wherein the user data feedback signals include at least one of the user's genotype data, current weight data, and different types of lifestyle behavior data;

[0064] The user's change data is preprocessed to obtain preprocessed change data;

[0065] Based on the preprocessed change data, extract at least one feature from the change data;

[0066] Update the user's current multi-source weight dataset based on at least one feature from the changing data and record the update time.

[0067] Specifically, the various types of lifestyle data include at least dietary behavior and smoking history.

[0068] In some embodiments, preprocessing the user's change data to obtain preprocessed change data includes:

[0069] The user's change data is sequentially cleaned and integrated to obtain the initial processed change data.

[0070] The changed data after initial processing is preprocessed to obtain preprocessed changed data, wherein the preprocessing includes at least missing value handling, outlier detection and handling, and data standardization.

[0071] In some embodiments, extracting at least one feature from the preprocessed change data includes:

[0072] Feature selection is performed on the preprocessed change data to obtain labeled change data;

[0073] Feature extraction is performed on the labeled changing data to extract at least one feature from the changing data.

[0074] Specifically, data cleaning, data integration, and preprocessing can be performed using existing data cleaning, data integration, and preprocessing techniques, or by using a trained machine learning model. The choice of data cleaning, data integration, and preprocessing methods here is merely illustrative. In actual testing, those skilled in the art can choose according to actual needs, as long as it can achieve the sequential data cleaning and data integration of the user's change data to obtain the initially processed change data, and the preprocessed change data to obtain the preprocessed change data. Further details are omitted here.

[0075] Specifically, the method for feature selection and feature extraction of data can be a pre-trained neural network model or a pre-trained machine learning model. The choice of the method for feature selection and feature extraction of data here is only an example. In actual testing, those skilled in the art can choose according to actual needs. As long as it can achieve feature selection of pre-processed changed data, obtain labeled changed data, and perform feature extraction on labeled changed data, and achieve at least one feature of the changed data, it is acceptable. Further details will not be elaborated here.

[0076] In the above embodiments, genotypic data (especially SNP variants of BDNF), smoking history, dietary habits, exercise status, and other multi-dimensional information of smokers are collected from multiple data sources to ensure the accuracy and completeness of the data. The collected data undergoes data cleaning, integration, and preprocessing to improve data quality. Large-scale modeling techniques are used to perform in-depth analysis and mining of the preprocessed data to discover potential correlations between genotype and weight changes. Through feature selection and extraction methods, a feature set capable of effectively predicting weight changes is constructed to facilitate accurate processing of the feature set by the intelligent weight management model.

[0077] Step S102: Substitute the user's current multi-source weight dataset into the intelligent weight management model, so that the various data in the user's current multi-source weight dataset are analyzed and processed, and a weight management plan matching the user is selectively updated or generated. The weight management plan includes at least a set of dietary recommendations, a set of exercise recommendations, and a set of current target combination parameters.

[0078] In some embodiments, before incorporating the user's current multi-source weight dataset into the intelligent weight management model, the method further trains the intelligent weight management model through the following steps:

[0079] Using different smoking cessation users as training samples, multiple training sample datasets are generated. The training sample datasets include at least the genotype data, personality data, and lifestyle behavior data corresponding to different weights of the training samples.

[0080] Based on multiple training sample datasets, determine the combined parameters of influence corresponding to different body weights for each training sample dataset.

[0081] Based on the combined influence parameters corresponding to each training sample dataset and each weight data, a weight management plan is generated for each training sample dataset at different weights.

[0082] Based on weight management schemes with different weights in each training sample dataset, the intelligent weight management model corresponding to each training sample is selectively optimized, and the optimized intelligent weight management model is retrained.

[0083] In some embodiments, the intelligent weight management model can be constructed using large model techniques (here, Transformer or BERT) to obtain the intelligent weight management model;

[0084] The intelligent weight management model was trained using multiple training sample datasets, and the model parameters were optimized using gradient descent and backpropagation algorithms to improve the model's prediction and recommendation capabilities. The model was then validated and tuned using cross-validation and grid search methods to ensure its stability and accuracy.

[0085] Specifically, the predicted output of the intelligent weight management model based on the input features is obtained through the following formula:

[0086]

[0087] Here, X represents the input feature, and satisfies X = {x1, x2, ..., x} n}, where x1 represents the genotypic data characteristics of users who have quit smoking, x2, ..., x n These represent various types of lifestyle behavior data features, h θ (X) represents the predicted output of the intelligent weight management model for the input feature X, and θ represents the model parameters, satisfying θ={θ0,θ1,…,θ n};

[0088] Specifically, the loss function of the intelligent weight management model is obtained through the following formula:

[0089]

[0090] Where L(θ) represents the loss function of the intelligent weight management model, m represents the number of users quitting smoking, and X (i) and y (i) These represent the input features of the i-th user quitting smoking and the corresponding weight management plan for that user, respectively.

[0091] Specifically, in gradient descent, the gradient of the model parameters is obtained using the following formula:

[0092]

[0093] in, The gradient represents the model parameters, i.e., the partial derivative of the loss function with respect to the model parameters θ;

[0094] Specifically, the parameters are updated using the gradient descent formula using the following formula:

[0095]

[0096] This section focuses on neural networks. The backpropagation algorithm calculates gradients layer by layer based on the chain rule and uses these gradients to update the weights and biases in the network.

[0097] In some embodiments, generating multiple training sample datasets using users who have quit smoking as training samples includes:

[0098] Obtain multi-dimensional information on different users who have quit smoking at different weights, wherein the multi-dimensional information includes at least weight data, genotype data of users who have quit smoking, various types of lifestyle behavior data, and personality data of users who have quit smoking;

[0099] Using different smoking cessation users as training samples, and based on the multi-dimensional information of the different smoking cessation users at different weights, the different training samples are classified to obtain a training sample set of each type, wherein each type of training sample set includes at least one training sample.

[0100] Based on each type of training sample set and the multi-dimensional information of each training sample at different weights, a training sample dataset for each type is constructed to obtain multiple sets of training sample datasets.

[0101] In some embodiments, different smoking cessation users are used as training samples, and based on multi-dimensional information about the different smoking cessation users at different weights, the different training samples are classified to obtain a training sample set for each type, including:

[0102] If the overall similarity of multiple types of life behavior data from different training samples reaches a preset overall similarity threshold, then the different training samples are determined to be of the same type, and the type is marked with the name "life behavior type + number".

[0103] If the gene similarity of the genotype data of different training samples reaches a preset gene similarity threshold, then the different training samples are determined to be of the same type, and the type is marked with the label name "genotype + number".

[0104] If the personality similarity of personality data from different training samples reaches a preset personality similarity threshold, then the different training samples are determined to be of the same type, and the type is marked with the name "personality type + number".

[0105] If the similarity of all data of different training samples to all data of other training samples is lower than the preset similarity threshold, then the different training samples will be classified separately and the type of each training sample will be labeled with the label name "independent type + number".

[0106] To obtain training sample sets for each type;

[0107] Among them, "genotype" has higher priority than "lifestyle behavior type", and "lifestyle behavior type" has higher priority than "personality type". That is, when both "genotype" and "lifestyle behavior type" appear at the same time, only the type is marked as "genotype + number". This ensures that different training samples have corresponding classifications, thereby improving the training ability of the intelligent weight management model on training samples of different classifications. This, in turn, improves the intelligent weight management model's ability to analyze and process the data corresponding to various training samples, enabling the intelligent weight management model to implement intelligent weight management.

[0108] In some embodiments, determining the combined influence parameters corresponding to different body weights for each training sample dataset based on multiple training sample datasets includes:

[0109] Obtain the initial combination parameters of the intelligent weight management model, wherein the initial combination parameters include at least the initial genotype data influence parameters, the initial personality data influence parameters, and the initial lifestyle behavior data influence parameters of different types;

[0110] Based on multiple training sample datasets and the latest version of the multi-source data influence comparison table, the influence ratio corresponding to each data item in each training sample dataset is determined.

[0111] Based on the influence ratios corresponding to each data point in each training sample dataset and the initial influence combination parameters of the intelligent weight management model, the influence combination parameters corresponding to different weights for each training sample are obtained.

[0112] This is to obtain the combined parameters of influence corresponding to different weights for each training sample dataset.

[0113] In some embodiments, the latest version of the pre-defined multi-source data influence control table includes at least the influence ratios corresponding to different genotype data, the influence ratios corresponding to different weights in different personality data, and the influence ratios corresponding to different weights in different types of lifestyle behavior data.

[0114] Furthermore, the method of updating the multi-source data affecting the data in the control table can be a trained neural network model or a trained machine learning model. The choice of method for updating the multi-source data affecting the data in the control table here is only an example. In actual testing, those skilled in the art can choose according to actual needs, as long as the updated multi-source data affecting the data in the control table is more consistent with the analysis results of the impact of each data point on the weight of the smoking cessation user compared to the data in the control table before the update. This will not be elaborated further here.

[0115] In some embodiments, based on the influence ratios corresponding to various data points in each training sample dataset and the initial influence combination parameters of the intelligent weight management model, the influence combination parameters corresponding to different weights for each training sample are obtained, including:

[0116] The combined influence parameters of any training sample at different weights can be obtained by the following formula: The influence parameter of genotype data of any training sample at any weight in the combined influence parameters = the influence parameter of the initial genotype data * the influence ratio of the genotype data;

[0117] The influence parameter of personality data for any training sample in any combination of influence parameters corresponding to any weight = the influence parameter of initial personality data * the influence ratio of the weight in the personality data;

[0118] The influence parameter of any training sample on any type of lifestyle data in the influence combination parameters corresponding to any weight is equal to the influence parameter of the initial lifestyle data of that type multiplied by the influence ratio of the weight on each type of lifestyle data.

[0119] In some embodiments, generating a weight management plan for each training sample dataset at different weights, based on the combined influence parameters corresponding to each set of training sample datasets and each weight data, includes:

[0120] Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, multiple weight management plans are generated for each training sample dataset at each weight.

[0121] Multiple weight management plans were simulated to obtain a weight goal completion dataset for each weight management plan. The weight goal completion dataset includes at least the completion rate of dietary goals, the completion rate of exercise goals, the total time to complete weight goals, and the user's psychological prediction change value.

[0122] Based on the weight goal completion dataset corresponding to each weight management plan, the completion score corresponding to each weight management plan is obtained;

[0123] Based on the completion score corresponding to each weight management plan, multiple weight management plans for each weight in each training sample dataset are filtered to obtain a weight management plan for each weight in each training sample dataset.

[0124] To obtain weight management plans for each training sample dataset at different weights.

[0125] In some embodiments, generating multiple weight management plans for each training sample dataset at each weight, based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights for each training sample dataset, includes:

[0126] Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, the influence parameter values ​​of each data in each training sample dataset on different weights are obtained.

[0127] Based on the data in each training sample dataset, determine the target weight value for each training sample at different weights.

[0128] Based on the target weight values ​​corresponding to different weights for each training sample and the parameter values ​​of the various data in each training sample dataset on different weights, multiple weight management plans are generated for each weight in each training sample dataset. Among them, there are differences in the set of dietary recommendations or exercise recommendations among the multiple weight management plans.

[0129] In some embodiments, obtaining the completion score for each weight management plan based on the weight goal completion dataset corresponding to each weight management plan includes:

[0130] Based on the user's psychological prediction change value corresponding to the weight management plan, determine the psychological prediction score of the training sample after management of the weight management plan.

[0131] If the psychological prediction score of the training sample corresponding to the weight management plan is lower than the preset psychological prediction score threshold, or if the change value of the user's psychological prediction corresponding to the weight management plan exceeds the preset psychological prediction change threshold corresponding to the total time to complete the weight goal, then the completion score corresponding to the weight management plan will be set to "0".

[0132] Otherwise, the completion score corresponding to the weight management plan is obtained based on the weight target completion dataset corresponding to the weight management plan.

[0133] In some embodiments, the preset psychological prediction score threshold and the preset psychological prediction change threshold can be set by the administrator or obtained through a trained machine learning model. The setting of the preset psychological prediction score threshold and the preset psychological prediction change threshold here is only an illustrative example. In actual testing, those skilled in the art can set them according to actual needs, as long as the preset psychological prediction score threshold and the preset psychological prediction change threshold can match the weight of the training sample, and the preset psychological prediction score threshold and the preset psychological prediction change threshold can ensure the mental health of the training sample. Further details are omitted here.

[0134] In some embodiments, the completion score corresponding to the weight management program is obtained using the following formula:

[0135] The completion score corresponding to the weight management plan = (the completion rate of the dietary goals corresponding to the weight management plan * the preset weight value of the dietary behavior type of the training sample in the lifestyle behavior data corresponding to the weight + the completion rate of the exercise goals corresponding to the weight management plan * the preset weight value of the training sample in the exercise suggestions corresponding to the weight + the total time to complete the weight goals corresponding to the weight management plan * the preset weight value of the total time to complete the weight goals) * the preset influence coefficient corresponding to the psychological prediction score of the training sample after management of the weight management plan.

[0136] In some embodiments, based on the completion score corresponding to each weight management plan, multiple weight management plans for each weight in each training sample dataset are filtered to obtain a set of weight management plans for each weight in each training sample dataset, including:

[0137] Based on the completion score corresponding to each weight management plan, the top 3 weight management plans with the highest completion scores in the multiple weight management plans for each weight in each training sample dataset are selected.

[0138] Based on the top three weight management plans with the highest completion scores in each weight management plan set for each training sample dataset, the weight management plan with the highest psychological prediction score after management of the corresponding training sample dataset is selected as the weight management plan set for that weight. This results in a weight management plan set for each weight of each training sample dataset, enabling smokers to effectively control their weight while ensuring their mental health, increasing their motivation to control their weight, and ensuring the effectiveness and sustainability of weight management.

[0139] In some embodiments, based on weight management schemes at different weights and in each training sample dataset, selectively optimizing the intelligent weight management model corresponding to each training sample, and retraining the optimized intelligent weight management model includes:

[0140] Based on the weight target completion dataset corresponding to weight management plans at different weights in each training sample dataset, determine the comprehensive evaluation score of multiple weight management plans corresponding to each training sample.

[0141] If the comprehensive evaluation score of the multiple weight management schemes corresponding to the training sample is lower than the preset comprehensive evaluation score threshold, it is determined that the training sample does not match the intelligent weight management model. Then, the intelligent weight management model corresponding to the training sample is optimized, and the "training of the optimized intelligent weight management model based on the multiple training sample datasets corresponding to the training sample" is re-executed.

[0142] If the overall evaluation score of the multiple weight management plans corresponding to the training sample is higher than the preset overall evaluation score threshold, and the difference between the overall evaluation score of the multiple weight management plans corresponding to the training sample and the preset overall evaluation score threshold is higher than the preset difference threshold, then the training sample is determined to be a match for the intelligent weight management model, and the smoking cessation user of the training sample is bound to the influence combination parameters of the training sample at different weights in the intelligent weight management model;

[0143] If the overall evaluation score of the multiple weight management schemes corresponding to the training sample is higher than the preset overall evaluation score threshold, and the difference between the overall evaluation score of the multiple weight management schemes corresponding to the training sample and the preset overall evaluation score threshold is lower than the preset difference threshold, then it is determined that the training sample matches the intelligent weight management model. Furthermore, the intelligent weight management model corresponding to the training sample is optimized, and the steps of "training the optimized intelligent weight management model based on the multiple training sample datasets corresponding to the training sample" and subsequent steps are re-executed.

[0144] In some embodiments, based on the weight target completion dataset corresponding to weight management plans at different weights in each training sample dataset, the comprehensive evaluation score of multiple weight management plans corresponding to each training sample is determined, including:

[0145] The comprehensive evaluation score of the multiple weight management plans corresponding to the training sample is the average of (the completion score of any weight management plan in the training sample * the preset weight management coefficient value corresponding to the weight of the weight in the weight management plan).

[0146] In some embodiments, the preset comprehensive evaluation score threshold and the preset difference threshold can be set by the administrator or obtained through a trained machine learning model. The setting of the preset comprehensive evaluation score threshold and the preset difference threshold here is only an illustrative example. In actual testing, those skilled in the art can set them according to actual needs, as long as the preset comprehensive evaluation score threshold and the preset difference threshold can match the training samples. Further details are omitted here.

[0147] In some embodiments, the user's current multi-source weight dataset is substituted into the intelligent weight management model, enabling the analysis and processing of various data points in the user's current multi-source weight dataset, and selectively updating or generating a weight management plan that matches the user, including:

[0148] Based on the user's current multi-source weight dataset, determine the influence combination parameters corresponding to the user's current multi-source weight dataset;

[0149] Based on the user's current multi-source weight dataset and the combined influencing parameters, generate multiple weight management plans corresponding to the user's current multi-source weight dataset;

[0150] Multiple weight management plans were simulated to obtain the weight target achievement dataset for each weight management plan.

[0151] Based on the weight goal completion dataset corresponding to each weight management plan, the completion score corresponding to each weight management plan is obtained;

[0152] Based on the completion score corresponding to each weight management plan, multiple weight management plans are filtered to obtain and output the weight management plan corresponding to the user's current multi-source weight dataset.

[0153] In the above embodiments, based on the user's genotype, lifestyle habits, and other information, the intelligent weight management model automatically generates a personalized weight management plan, which may include multiple aspects such as dietary adjustments, exercise plans, and psychological support, to help the user effectively control their weight.

[0154] Step S103: Obtain user feedback instructions on the weight management plan that matches the user, and selectively adjust the intelligent weight management model based on the feedback instructions to enhance user participation and satisfaction, thereby increasing the user's enthusiasm and initiative in controlling weight.

[0155] In some embodiments, obtaining user feedback instructions on a weight management plan tailored to the user, and selectively adjusting the intelligent weight management model based on the feedback instructions, includes:

[0156] Obtain user feedback instructions on a weight management plan tailored to the user, wherein the feedback instructions include at least the user's questions or suggestions for adjustment;

[0157] If the feedback instruction is a question raised by the user, then based on the question raised by the user, the answer to the question is given to the user.

[0158] If the feedback instruction is a proposed adjustment suggestion, then the intelligent weight management model is adjusted based on the adjustment suggestion to obtain the adjusted intelligent weight management model corresponding to the user.

[0159] The adjusted intelligent weight management model corresponding to the user is then retrained to optimize the model, thereby improving the matching degree between the model and the user and enhancing the relevance and effectiveness of the weight management plan output by the model.

[0160] According to embodiments of this disclosure, the following technical effects are achieved: By responding to user data feedback signals from smokers trying to quit, the current multi-source weight dataset of the user is obtained. This enables timely collection of multi-dimensional information about the smoker when changes in their weight or any data point are detected. Furthermore, by inputting the user's current multi-source weight dataset into the intelligent weight management model, the various data points in the dataset are analyzed and processed. A weight management plan tailored to the user is selectively updated or generated, providing personalized weight management plans and suggestions to smokers trying to quit, thus improving management effectiveness. The weight management plan is dynamically adjusted based on user feedback signals, automatically adjusting the plan when changes in the smoker's weight or any data point are detected, ensuring a match between the user and the weight management plan. Additionally, user feedback instructions regarding the weight management plan are obtained, and the intelligent weight management model is selectively adjusted based on these instructions to enhance user participation and satisfaction, thereby increasing the smoker's enthusiasm and initiative in controlling their weight.

[0161] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of the present invention.

[0162] Furthermore, the present invention also provides a weight management assistance system for smokers quitting smoking.

[0163] Figure 2A schematic diagram of the main structure of a weight management assistance system for smokers according to an embodiment of the present invention is shown; as follows: Figure 2 As shown, the smoking cessation weight management assistance system 200 in this embodiment mainly includes an interaction module 201, a processing module 202, a display module 203, and a control device 204.

[0164] The interaction module 201 interacts with the user terminal to obtain input data and feedback data from the user terminal, and to obtain the user's current multi-source weight dataset and the user's feedback instructions on the weight management plan that matches the user.

[0165] The processing module 202 and the interaction module 201 interact with each other. The processing module 202 includes a storage unit 2021 and an intelligent weight management model 2022. The storage unit 2021 is used to store the data obtained by the interaction module and the data output by the intelligent weight management model 2022. The intelligent weight management model 2022 is used to analyze and process various data in the user's current multi-source weight dataset, and selectively update or generate a weight management plan that matches the user.

[0166] The display module 203 interacts with the interaction module 201, and the display module 203 is used to display a weight management plan that matches the user.

[0167] The control device 204 interacts with the interaction module 201, processing module 202, and display module 203. The control device 204 includes a processor 2041 and a memory 2042. The memory 2042 can be configured to store program code 2043 for executing the weight management assistance method for smokers in the above-described method embodiments. The processor 2041 can be configured to execute the program code 2043 in the memory 2042. This program code 2043 includes, but is not limited to, the program code 2043 for executing the weight management assistance method for smokers in the above-described method embodiments. For ease of explanation, only the parts related to the embodiments of the present invention are shown. For specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The control device 204 can be a control device 204 device comprising various electronic devices. In the embodiments, the specific functional descriptions can be found in steps S101 to S103.

[0168] In the above embodiments, the system provides interactive functions for users, allowing those quitting smoking to record information such as weight changes, dietary habits, and exercise through an interactive module. Through a simple user interface, users can conveniently and promptly input and update their data. The system supports real-time communication between users and the system, allowing users to ask questions or make suggestions at any time, and the system will adjust and optimize accordingly based on feedback. The system can continuously optimize its weight management plan based on user feedback and actual needs. By analyzing and learning from user feedback data through machine learning algorithms, the system can gradually improve the targeting and effectiveness of its plans.

[0169] The aforementioned weight management assistance system 200 for smokers is used for implementation Figure 1 The illustrated embodiments of the smoking cessation weight management assistance method are similar in technical principle, the technical problems solved, and the technical effects produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the smoking cessation weight management assistance system 200 can be found in the embodiments of the smoking cessation weight management assistance method, and will not be repeated here.

[0170] Those skilled in the art will understand that all or part of the processes in the method of the above embodiment of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 2041, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0171] Furthermore, the weight management assistance system 200 for smokers quitting smoking according to the present invention also includes a computer-readable storage medium. In one embodiment of the present invention, the computer-readable storage medium may be configured to store program code 2043 for executing the weight management assistance method for smokers quitting smoking according to the above-described method embodiments. This program code 2043 may be loaded and executed by a processor 2041 to implement the above-described weight management assistance method for smokers quitting smoking. For ease of explanation, only the parts related to the embodiments of the present invention are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of the present invention. The computer-readable storage medium may be a memory device comprising various electronic devices. Optionally, in the embodiments of the present invention, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0172] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules may be the processor 2041 itself, or a part of the software, a part of the hardware, or a combination of software and hardware in the processor 2041. Therefore, the number of each module in the figure is merely illustrative.

[0173] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of the present invention; therefore, the technical solutions after splitting or combining will fall within the protection scope of the present invention.

[0174] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

[0175] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for assisting in weight management for smokers quitting smoking, characterized in that, The method includes the following steps: In response to user data feedback signals from smokers who are quitting smoking, the user's current multi-source weight dataset is obtained. The current multi-source weight dataset includes at least the user's genotype data characteristics, current weight data characteristics, and various types of lifestyle behavior data characteristics. By feeding the user's current multi-source weight dataset into the intelligent weight management model, the model can analyze and process various data in the user's current multi-source weight dataset, selectively update or generate a weight management plan that matches the user. The weight management plan includes at least a set of dietary recommendations, a set of exercise recommendations, and a set of current target combination parameters. The system obtains user feedback on a weight management plan tailored to the user, and selectively adjusts the intelligent weight management model based on this feedback to enhance user engagement and satisfaction, thereby increasing the motivation and initiative of users quitting smoking to control their weight.

2. The method for assisting in weight management for smokers according to claim 1, characterized in that, The process of obtaining the user's current multi-source weight dataset in response to user data feedback signals from those quitting smoking includes: In response to user data feedback signals from smokers quitting, the user's change data is determined, wherein the user data feedback signals include at least one of the user's genotype data, current weight data, and different types of lifestyle behavior data; The user's change data is preprocessed to obtain preprocessed change data; Based on the preprocessed change data, extract at least one feature from the change data; Update the user's current multi-source weight dataset based on at least one feature from the changing data and record the update time.

3. The method for assisting in weight management for smokers according to claim 2, characterized in that, Before incorporating the user's current multi-source weight dataset into the intelligent weight management model, the method further trains the intelligent weight management model through the following steps: Using different smoking cessation users as training samples, multiple training sample datasets are generated. The training sample datasets include at least the genotype data, personality data, and lifestyle behavior data corresponding to different weights of the training samples. Based on multiple training sample datasets, determine the combined parameters of influence corresponding to different body weights for each training sample dataset. Based on the combined influence parameters corresponding to each training sample dataset and each weight data, a weight management plan is generated for each training sample dataset at different weights. Based on weight management schemes with different weights in each training sample dataset, the intelligent weight management model corresponding to each training sample is selectively optimized, and the optimized intelligent weight management model is retrained.

4. The method for assisting in weight management for smokers according to claim 3, characterized in that, The dataset of multiple training samples generated using users who have quit smoking as training samples includes: Obtain multi-dimensional information on different users who have quit smoking at different weights, wherein the multi-dimensional information includes at least weight data, genotype data of users who have quit smoking, various types of lifestyle behavior data, and personality data of users who have quit smoking; Using different smoking cessation users as training samples, and based on the multi-dimensional information of the different smoking cessation users at different weights, the different training samples are classified to obtain a training sample set of each type, wherein each type of training sample set includes at least one training sample. Based on each type of training sample set and the multi-dimensional information of each training sample at different weights, a training sample dataset for each type is constructed to obtain multiple sets of training sample datasets.

5. The method for assisting in weight management for smokers according to claim 4, characterized in that, The method for determining the combined influence parameters corresponding to different body weights for each training sample dataset based on multiple training sample datasets includes: Obtain the initial combination parameters of the intelligent weight management model, wherein the initial combination parameters include at least the initial genotype data influence parameters, the initial personality data influence parameters, and the initial lifestyle behavior data influence parameters of different types; Based on multiple training sample datasets and the latest version of the multi-source data influence comparison table, the influence ratio corresponding to each data item in each training sample dataset is determined. Based on the influence ratios corresponding to each data point in each training sample dataset and the initial influence combination parameters of the intelligent weight management model, the influence combination parameters corresponding to different weights for each training sample are obtained. This is to obtain the combined parameters of influence corresponding to different weights for each training sample dataset.

6. The method for assisting in weight management for smokers according to claim 5, characterized in that, The process of generating a weight management plan for each training sample dataset at different weights, based on the combined influence parameters corresponding to each set of training sample datasets and each type of weight data, includes: Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, multiple weight management plans are generated for each training sample dataset at each weight. Multiple weight management plans were simulated to obtain a weight goal completion dataset for each weight management plan. The weight goal completion dataset includes at least the completion rate of dietary goals, the completion rate of exercise goals, the total time to complete weight goals, and the user's psychological prediction change value. Based on the weight goal completion dataset corresponding to each weight management plan, the completion score corresponding to each weight management plan is obtained; Based on the completion score corresponding to each weight management plan, multiple weight management plans for each weight in each training sample dataset are filtered to obtain a weight management plan for each weight in each training sample dataset. To obtain weight management plans for each training sample dataset at different weights.

7. The method for assisting in weight management for smokers according to claim 6, characterized in that, The process of generating multiple weight management plans for each training sample dataset at each weight, based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, includes: Based on the data in each training sample dataset and the combined parameters of influence corresponding to different weights in each training sample dataset, the parameter values ​​of the influence of each data in each training sample dataset on different weights are obtained. Based on the data in each training sample dataset, determine the target weight value for each training sample at different weights. Based on the target weight values ​​corresponding to different weights for each training sample and the influence parameters of various data in each training sample dataset on different weights, multiple weight management plans are generated for each training sample dataset at each weight.

8. The method for assisting in weight management for smokers according to claim 7, characterized in that, The completion score for each weight management plan, obtained from the weight goal completion dataset corresponding to each weight management plan, includes: Based on the user's psychological prediction change value corresponding to the weight management plan, determine the psychological prediction score of the training sample after management of the weight management plan. If the psychological prediction score of the training sample corresponding to the weight management plan is lower than the preset psychological prediction score threshold, or if the change value of the user's psychological prediction corresponding to the weight management plan exceeds the preset psychological prediction change threshold corresponding to the total time to complete the weight goal, then the completion score corresponding to the weight management plan will be set to "0". Otherwise, the completion score corresponding to the weight management plan is obtained based on the weight target completion dataset corresponding to the weight management plan.

9. The method for assisting in weight management for smokers according to claim 8, characterized in that, The step of obtaining user feedback instructions on a weight management plan tailored to the user, and selectively adjusting the intelligent weight management model based on these instructions, includes: Obtain user feedback instructions on a weight management plan tailored to the user, wherein the feedback instructions include at least the user's questions or suggestions for adjustment; If the feedback instruction is a proposed adjustment suggestion, then the intelligent weight management model is adjusted based on the adjustment suggestion to obtain the adjusted intelligent weight management model corresponding to the user. The adjusted intelligent weight management model corresponding to the user is then retrained to optimize the intelligent weight management model for the user.

10. A weight management assistance system for smokers quitting smoking, characterized in that, The system includes an interaction module, a processing module, a display module, and a control device; The interaction module exchanges information with the user terminal to obtain input data and feedback data from the user terminal, and to obtain the user's current multi-source weight dataset and the user's feedback instructions on the weight management plan matched to the user. The processing module and the interaction module interact with each other. The processing module includes a storage unit and an intelligent weight management model. The storage unit is used to store the data obtained by the interaction module and the data output by the intelligent weight management model. The intelligent weight management model is used to analyze and process various data in the user's current multi-source weight dataset, and selectively update or generate a weight management plan that matches the user. The display module and the interaction module exchange information, and the display module is used to display a weight management plan that matches the user. The control device interacts with the interaction module, processing module, and display module. The control device includes a processor and a memory. The memory is adapted to store multiple program codes, which are adapted to be loaded and run by the processor to execute the weight management assistance method for smokers as described in any one of claims 1 to 9.

Images