Intelligent nutrition recommendation method, device and equipment based on physical fitness data

Abstract

The present application relates to the technical field of nutrition recommendation, and discloses a method, device and equipment for intelligently recommending nutrition based on physical data, which performs matching analysis on nutrition data and physical data of training personnel in a past period of time, analyzes missing and over-intake nutrition parameters when the analysis shows that the nutrition data and the physical data do not match, and combines current physical conditions of the user to adjust the nutrition of the training personnel and recommend required nutrition data, thereby improving the recommendation accuracy of required nutrition intake data of the training personnel, which is conducive to improving the accuracy of nutrition required by the training personnel, and further conducive to improving the effect of physical training of the training personnel and reducing the risk of sports injury.

Description

Technical Field

[0001] This invention relates to the field of nutrition recommendation technology, and in particular to a method, apparatus, and equipment for intelligent nutrition recommendation based on physical fitness data. Background Technology

[0002] In special scenarios such as military and sports training, the physical condition of trainees (especially military personnel) directly affects the effectiveness of physical training, mission execution, and even their overall health. Scientific and reasonable nutritional intake is key to maintaining and improving physical fitness. Therefore, it is necessary to recommend accurate nutritional data for each trainee.

[0003] Currently, nutritional recommendations for trainees mainly involve providing corresponding nutrition to each trainee based on unified nutritional supply standards, such as the "Standards for Daily Dietary Energy and Nutrient Supply for Military Personnel," or optimizing the required nutrition based on the unified nutritional supply standards and the current training program. However, practice has shown that the current nutritional supply method, which provides a uniform supply to all trainees, cannot provide accurate nutritional intake data and therefore cannot meet their nutritional needs for training and physical development. Therefore, proposing a new nutritional recommendation method to improve the accuracy of recommended nutritional intake data for trainees, thereby enhancing training effectiveness and reducing the risk of sports injuries, is particularly important. Summary of the Invention

[0004] This invention provides a method, device, and equipment for intelligent nutrition recommendation based on physical fitness data, which can improve the accuracy of the recommended nutritional intake data for trainees, thereby improving the training effect and reducing the risk of sports injuries.

[0005] The first aspect of this invention discloses a method for intelligent nutrition recommendation based on physical fitness data, the method comprising: Obtain nutritional intake and physical fitness data of the target trainees during a target duration period in the past, wherein the physical fitness data is used to characterize the physical fitness status of the target trainees during the target duration period; Determine whether the nutritional intake data matches the physical fitness data; When it is determined that the nutritional intake data does not match the physical fitness data, the nutritional intake data and the physical fitness data are analyzed to obtain target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include a first nutritional parameter that the target trainee lacks and / or a second nutritional parameter that is excessively ingested. Based on the target nutritional parameters and the physical condition of the target trainee, nutritional recommendations are performed for the target trainee.

[0006] As an optional implementation, in a first aspect of the present invention, the method further includes: Obtain the type and training data of the physical training program that the target trainee will undergo next; Based on the type of the physical training program, the target nutritional parameters are adjusted to obtain the first target nutritional parameters. Based on the training data of the physical training program, the first target nutritional parameter is adjusted to obtain the second target nutritional parameter. The step of performing nutritional recommendations for the target trainee based on the target nutritional parameters and the target trainee's physical condition includes: Based on the second target nutritional parameters and the physical condition of the target trainee, nutritional recommendations are performed for the target trainee.

[0007] As an optional implementation, in a first aspect of the present invention, the training data of the physical training program includes training duration, training intensity level and training environment parameters, wherein a higher training intensity level indicates a greater training intensity. The process of adjusting the first target nutritional parameter based on the training data from the physical training program to obtain the second target nutritional parameter includes: Based on the training duration, an adjustment operation is performed on the first target nutrient parameter to obtain the duration nutrient parameter; Based on the training intensity level, an adjustment operation is performed on the first target nutrient parameter to obtain the intensity nutrient parameter; Based on the training environment parameters, an adjustment operation is performed on the first target nutrient parameters to obtain the environmental nutrient parameters. Set corresponding training weights for the training duration, the training intensity level, and the training environment parameters; The second target nutritional parameters are generated based on the duration nutritional parameters and training weights corresponding to the training duration, the intensity nutritional parameters and training weights corresponding to the training intensity level, and the environmental nutritional parameters and training weights corresponding to the training environment parameters.

[0008] As an optional implementation, in a first aspect of the present invention, the nutrient intake data includes multiple sub-nutrient data. The determination of whether the nutrient intake data matches the physical fitness data includes: Based on the pre-trained nutrition-physical fitness matching model, the nutritional matching degree between each of the sub-nutrition intake data and the physical fitness data is obtained by analyzing the nutritional matching data between each of the sub-nutrition intake data and the physical fitness data. Based on the physical fitness data, a corresponding nutritional weight is set for each of the sub-nutrition data points; Based on the nutritional matching degree and nutritional weight corresponding to each of the sub-nutrition data, a target nutritional matching degree between the nutritional intake data and the physical fitness data is generated. Determine whether the target nutritional matching degree is greater than or equal to a preset nutritional matching degree. If it is determined to be greater than or equal to the preset nutritional matching degree, it is determined that the nutritional intake data matches the physical fitness data. If it is determined to be less than the preset nutritional matching degree, it is determined that the nutritional intake data does not match the physical fitness data.

[0009] As an optional implementation, in a first aspect of the present invention, the physical fitness data includes physical training data and physical test data within the target duration period; The aforementioned analysis of each sub-nutrient intake data and physical fitness data based on a pre-trained nutrition-fitting model to obtain the nutrition matching degree between each sub-nutrient intake data and the physical fitness data includes: Based on the pre-trained nutrition-training matching model, the sub-nutrition intake data and the physical training data are analyzed to obtain the physical training matching degree between each sub-nutrition intake data and the physical training data. Based on the pre-trained nutrition-physical test matching model, the sub-nutrition intake data and the physical test data are analyzed to obtain the physical test matching degree between each sub-nutrition intake data and the physical test data. Set corresponding matching weights for the physical training data and the physical test data; For any of the sub-nutrition data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is calculated based on the physical fitness training matching degree and the matching weight corresponding to the physical fitness training data, the physical fitness test matching degree and the matching weight corresponding to the physical fitness test data.

[0010] As an optional implementation, in a first aspect of the present invention, setting a corresponding nutritional weight for each sub-nutritional data based on the physical fitness data includes: Based on the physical training data and the preset training goals of the target trainees, analyze the target trainees' needs for each of the sub-nutrition data. Based on the demand degree corresponding to each of the sub-nutrient data, analyze the initial nutrient weight corresponding to each of the sub-nutrient data; Based on the physical test data and the preset training objectives, analyze all abnormal physical test parameters of the target trainees and the abnormality of these abnormal physical test parameters; Based on all the abnormal body measurement parameters, select all target sub-nutrient data that match the abnormal body measurement parameters from all the sub-nutrient data; Based on the abnormality of all the abnormal body measurement parameters, an adjustment operation is performed on the initial nutrient weight corresponding to each of the target sub-nutrient data to obtain the nutrient weight set for each of the sub-nutrient data.

[0011] As an optional implementation, in the first aspect of the present invention, after performing a nutrition recommendation operation for the target trainee based on the target nutritional parameters and the physical condition of the target trainee, the method further includes: Determine the target nutritional data after nutritional adjustment, and obtain multiple first ingredients that match the target nutritional data; Obtain the caloric parameters of each of the first ingredients and all the sub-nutrient parameters contained in each of the first ingredients for the target trainees; Analyze the heat parameters of each of the first ingredients to obtain the heat value of the target trainee for each of the first ingredients; Based on the heat value corresponding to each of the first ingredients, select all second ingredients whose heat value is greater than or equal to a preset heat value from all the first ingredients; Based on the pre-determined correlation between physical and nutritional needs and all sub-nutritional parameters of each second ingredient, the proportion parameters of all second ingredients are analyzed.

[0012] A second aspect of this invention discloses a device for intelligent nutrition recommendation based on physical fitness data, the device comprising: The acquisition module is used to acquire the nutritional intake data and physical fitness data of the target trainee during a past target duration period. The physical fitness data is used to characterize the physical fitness status of the target trainee during the target duration period. The judgment module is used to determine whether the nutrient intake data matches the physical fitness data; The analysis module is used to analyze the nutritional intake data and the physical fitness data when it is determined that the nutritional intake data and the physical fitness data do not match, and to obtain the target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include a first nutritional parameter that the target trainee lacks and / or a second nutritional parameter that is excessively ingested. The recommendation module is used to perform nutritional recommendation operations for the target trainee based on the target nutritional parameters and the target trainee's physical condition.

[0013] As an optional implementation, in a second aspect of the present invention, the acquisition module is further configured to acquire the type and training data of the physical training program that the target trainee will undergo next; The device further includes: An adjustment module is used to perform an adjustment operation on the target nutritional parameters based on the type of the physical training program to obtain the first target nutritional parameters; The adjustment module is also used to perform an adjustment operation on the first target nutritional parameter based on the training data of the physical training program to obtain the second target nutritional parameter; The specific method by which the recommendation module performs nutritional recommendations for the target trainee based on the target nutritional parameters and the target trainee's physical condition includes: Based on the second target nutritional parameters and the physical condition of the target trainee, nutritional recommendations are performed for the target trainee.

[0014] As an optional implementation, in a second aspect of the present invention, the training data of the physical training program includes training duration, training intensity level, and training environment parameters, wherein a higher training intensity level indicates a greater training intensity. The specific method by which the adjustment module adjusts the first target nutritional parameter based on the training data of the physical training program to obtain the second target nutritional parameter includes: Based on the training duration, an adjustment operation is performed on the first target nutrient parameter to obtain the duration nutrient parameter; Based on the training intensity level, an adjustment operation is performed on the first target nutrient parameter to obtain the intensity nutrient parameter; Based on the training environment parameters, an adjustment operation is performed on the first target nutrient parameters to obtain the environmental nutrient parameters. Set corresponding training weights for the training duration, the training intensity level, and the training environment parameters; The second target nutritional parameters are generated based on the duration nutritional parameters and training weights corresponding to the training duration, the intensity nutritional parameters and training weights corresponding to the training intensity level, and the environmental nutritional parameters and training weights corresponding to the training environment parameters.

[0015] As an optional implementation, in a second aspect of the present invention, the nutrient intake data includes multiple sub-nutrient data. The specific method by which the judgment module determines whether the nutrient intake data matches the physical fitness data includes: Based on the pre-trained nutrition-physical fitness matching model, the nutritional matching degree between each of the sub-nutrition intake data and the physical fitness data is obtained by analyzing the nutritional matching data between each of the sub-nutrition intake data and the physical fitness data. Based on the physical fitness data, a corresponding nutritional weight is set for each of the sub-nutrition data points; Based on the nutritional matching degree and nutritional weight corresponding to each of the sub-nutrition data, a target nutritional matching degree between the nutritional intake data and the physical fitness data is generated. Determine whether the target nutritional matching degree is greater than or equal to a preset nutritional matching degree. If it is determined to be greater than or equal to the preset nutritional matching degree, it is determined that the nutritional intake data matches the physical fitness data. If it is determined to be less than the preset nutritional matching degree, it is determined that the nutritional intake data does not match the physical fitness data.

[0016] As an optional implementation, in a second aspect of the present invention, the physical fitness data includes physical training data and physical test data within the target duration period; The judgment module, based on a pre-trained nutrition-fitness matching model, analyzes each sub-nutrient intake data and the fitness data to obtain the specific method for determining the nutrition matching degree between each sub-nutrient intake data and the fitness data, including: Based on the pre-trained nutrition-training matching model, the sub-nutrition intake data and the physical training data are analyzed to obtain the physical training matching degree between each sub-nutrition intake data and the physical training data. Based on the pre-trained nutrition-physical test matching model, the sub-nutrition intake data and the physical test data are analyzed to obtain the physical test matching degree between each sub-nutrition intake data and the physical test data. Set corresponding matching weights for the physical training data and the physical test data; For any of the sub-nutrition data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is calculated based on the physical fitness training matching degree and the matching weight corresponding to the physical fitness training data, the physical fitness test matching degree and the matching weight corresponding to the physical fitness test data.

[0017] As an optional implementation, in a second aspect of the present invention, the specific method by which the determining module sets a corresponding nutritional weight for each of the sub-nutritional data based on the physical fitness data includes: Based on the physical training data and the preset training goals of the target trainees, analyze the target trainees' needs for each of the sub-nutrition data. Based on the demand degree corresponding to each of the sub-nutrient data, analyze the initial nutrient weight corresponding to each of the sub-nutrient data; Based on the physical test data and the preset training objectives, analyze all abnormal physical test parameters of the target trainees and the abnormality of these abnormal physical test parameters; Based on all the abnormal body measurement parameters, select all target sub-nutrient data that match the abnormal body measurement parameters from all the sub-nutrient data; Based on the abnormality of all the abnormal body measurement parameters, an adjustment operation is performed on the initial nutrient weight corresponding to each of the target sub-nutrient data to obtain the nutrient weight set for each of the sub-nutrient data.

[0018] As an optional implementation, in a second aspect of the present invention, the recommendation module is further configured to determine the target nutritional data after performing a nutritional recommendation operation for the target trainee based on the target nutritional parameters and the physical condition of the target trainee; The acquisition module is also used to acquire a plurality of first ingredients that match the target nutritional data; The acquisition module is also used to acquire the heat parameters of each first ingredient and all sub-nutrient parameters contained in each first ingredient for the target trainee; The analysis module is also used to analyze the heat parameters of each of the first ingredients to obtain the heat value of the target trainee for each of the first ingredients; The device further includes: The filtering module is used to filter all second ingredients whose heat values ​​are greater than or equal to a preset heat value from all the first ingredients based on the heat value corresponding to each first ingredient. The analysis module is also used to analyze the proportion parameters of all the second ingredients based on the pre-determined physical-nutritional requirement relationship and all sub-nutritional parameters of each second ingredient.

[0019] A third aspect of the present invention discloses a nutrition recommendation device, the nutrition recommendation device comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in any of the methods described in the first aspect of the present invention.

[0020] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in any of the methods described in the first aspect of the present invention.

[0021] Compared with the prior art, the present invention has the following beneficial effects: In this embodiment of the invention, nutritional intake data and physical fitness data of the target trainee over a target duration period are obtained. Physical fitness data characterizes the trainee's physical condition during the target duration period. The system determines whether the nutritional intake data matches the physical fitness data. When a mismatch is found, the system analyzes the nutritional intake and physical fitness data to obtain target nutritional parameters that do not match the trainee's physical condition. These target nutritional parameters include a first nutritional parameter that the trainee lacks and / or a second nutritional parameter that is excessively ingested. Based on the target nutritional parameters and the trainee's physical condition, nutritional recommendations are performed. Therefore, by matching and analyzing the trainee's nutritional and physical fitness data over a past period, and analyzing the missing or excessive nutritional parameters when a mismatch is found, combined with the user's current physical condition, the system adjusts the trainee's nutrition and recommends the necessary nutritional data. This improves the accuracy of the recommended nutritional intake data, thereby improving the trainee's ability to consume the necessary nutrients for their body and training, ultimately enhancing the effectiveness of physical training and reducing the risk of sports injuries. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention. Figure 2 This is a flowchart illustrating another method for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of a device for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another device for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of a nutrition recommendation device disclosed in an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will understand, explicitly and implicitly, that the embodiments described herein can be combined with other embodiments.

[0027] This invention discloses a method, device, and equipment for intelligent nutrition recommendation based on physical fitness data. By matching and analyzing the nutritional intake data and physical fitness data of trainees over a past period, and identifying any mismatches, the method analyzes the missing or excessive nutritional parameters and, combined with the user's current physical condition, adjusts the trainee's nutrition and recommends the necessary nutritional data. This improves the accuracy of the recommended nutritional intake data, thereby enhancing the accuracy of trainees consuming the nutrients required for their bodies and training, ultimately improving the effectiveness of physical training and reducing the risk of sports injuries. Detailed descriptions follow.

[0028] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for intelligent nutrition recommendation based on physical fitness data, as disclosed in an embodiment of the present invention. Figure 1 The described method can be applied to any scenario requiring nutritional data analysis, such as military training or sports training. Figure 1 As shown, the method may include the following operations: 101. Obtain nutritional intake and physical fitness data of the target trainees during a past target duration. The physical fitness data is used to characterize the physical fitness of the target trainees during the target duration.

[0029] In this embodiment of the invention, optionally, the target duration can be any duration, such as 7 days or 15 days, without limitation. The nutritional intake data includes, but is not limited to, the type of food consumed, the category and amount of nutrients consumed, and the time of nutrient intake. The type of food consumed includes, but is not limited to, the type of ingredients consumed and the type of staple food consumed. The type of ingredients consumed includes multiple commonly seen ingredients such as scrambled eggs with tomatoes, stewed beef with potatoes, and stir-fried lettuce. The type of staple food consumed includes one or more commonly seen ingredients such as rice, steamed buns, noodles, and rice noodles. Nutritional intake categories and amounts include, but are not limited to, protein (e.g., 65g), carbohydrates (e.g., 220g), fat (e.g., 58g), vitamin C (e.g., 80mg), and calcium (e.g., 350mg); physical fitness data includes physical training data and physical test data, as well as the corresponding training / test times. Physical training data includes, but is not limited to, physical training items, performance data for each item (e.g., 3km run in 14 minutes daily, 30 squats / set x 3 sets, 12 pull-ups / set x 2 sets, etc.), and body indicators (height, weight, body fat); physical test data includes, but is not limited to, physical test items, performance data, and body indicators, such as standing long jump 2.3m, vital capacity 4200ml; physical fitness status includes, but is not limited to, body shape, physiological function, and athletic ability.

[0030] 102. Determine whether the nutritional intake data matches the physical fitness data.

[0031] 103. When it is determined that the nutritional intake data and physical fitness data do not match, analyze the nutritional intake data and physical fitness data to obtain the target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include the first nutritional parameter that the target trainee lacks and / or the second nutritional parameter that is excessively ingested.

[0032] In this embodiment of the invention, optionally, when it is determined that the nutritional intake data matches the physical fitness data, the current process is terminated, or step 101 is continued after a preset interval (such as 3 days).

[0033] 104. Based on the target nutritional parameters and the physical condition of the target trainees, perform the recommended nutritional procedures for the target trainees.

[0034] In this embodiment of the invention, the types of target nutrient data recommended are detailed in the foregoing description of nutrient intake data, and will not be repeated here.

[0035] It is evident that implementation Figure 1The described method matches and analyzes the nutritional and physical data of trainees over a past period. When mismatches are found, it analyzes the missing or excessive nutritional parameters and, combined with the user's current physical condition, makes nutritional adjustments for trainees, recommending the necessary nutritional data. This improves the accuracy of the recommended nutritional intake data for trainees, thereby improving the accuracy of trainees consuming the nutrients required for their bodies and training, which in turn helps to improve the effectiveness of physical training and reduce the risk of sports injuries.

[0036] In this embodiment of the invention, optionally, the nutrient intake data includes multiple sub-nutrient data; wherein, determining whether the nutrient intake data matches the physical fitness data includes: Based on the pre-trained nutrition-physical fitness matching model, the nutritional intake data and physical fitness data of each sub-nutrition data are analyzed to obtain the nutritional matching degree between each sub-nutrition intake data and physical fitness data. Based on physical fitness data, set corresponding nutritional weights for each sub-nutrition data; Based on the nutritional matching degree and nutritional weight corresponding to each sub-nutrition data, a target nutritional matching degree between nutritional intake data and physical fitness data is generated. Determine whether the target nutritional matching degree is greater than or equal to the preset nutritional matching degree. If it is determined to be greater than or equal to the preset nutritional matching degree, it is determined that the nutritional intake data and physical fitness data match. If it is determined to be less than the preset nutritional matching degree, it is determined that the nutritional intake data and physical fitness data do not match.

[0037] In this embodiment of the invention, optionally, for cases of mismatch, the degree of mismatch is also included, such as mild mismatch, moderate mismatch, or severe mismatch, and each degree of mismatch has a corresponding degree of mismatch range.

[0038] As can be seen, implementing the embodiments of the present invention can also analyze the sub-nutrition data and physical fitness data through the nutrition-physical fitness matching model, accurately quantify the matching degree of individual sub-nutrition, improve the accuracy and efficiency of the comparison between nutrition intake and physical fitness needs, and dynamically allocate nutritional weights to each sub-nutrition based on physical fitness data, so as to take into account the key nutritional needs under different training intensities and different physical qualities, making the matching judgment between nutrition and physical fitness more consistent with the actual training situation. Finally, the final nutrition matching degree is calculated based on the sub-nutrition matching degree and the corresponding nutritional weight, and then compared with the preset nutrition matching degree, which improves the accuracy and reliability of the judgment between the nutrition data ingested by the trainee in the past period and physical fitness, thereby helping to further improve the accuracy and reliability of nutrition data recommendations for trainees.

[0039] In this embodiment of the invention, the physical fitness data may further optionally include physical training data and physical test data within the target duration period; Specifically, based on a pre-trained nutrition-fitness matching model, the nutrition intake data and fitness data for each sub-category are analyzed to obtain the nutrition matching degree between each sub-category of nutrition intake data and fitness data, including: Based on the pre-trained nutrition-training matching model, the nutritional intake data and physical training data of each sub-nutrition data are analyzed to obtain the physical training matching degree between the nutritional intake data and physical training data of each sub-nutrition data. Based on the pre-trained nutrition-physical test matching model, the nutritional intake data and physical test data of each sub-nutrition data are analyzed to obtain the physical test matching degree between each sub-nutrition intake data and physical test data. Set corresponding matching weights for physical training data and physical test data, and the sum of the matching weights for the two is equal to 1; For any sub-nutrition data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is calculated based on the matching degree of physical fitness training corresponding to the sub-nutrition data and the matching weight of physical fitness training data, the matching degree of physical fitness test corresponding to the sub-nutrition data and the matching weight of physical fitness test data.

[0040] In this embodiment of the invention, the nutrition-fitness matching model includes a nutrition-training matching model and a nutrition-fitness test matching model. Optionally, both the nutrition-training matching model and the nutrition-fitness test matching model can be constructed based on a basic multilayer perceptron (MLP) model to fit the matching relationship between sub-nutrition intake data and fitness data. The basic MLP model includes an input layer → embedding layer → batch normalization layer → first fully connected layer → second fully connected layer → dropout layer → output layer, where the output of the previous layer is the output of the next layer. Taking the nutrition-training matching model as an example, a physical fitness training sample is defined as a sample of physical fitness training data, its corresponding sample sub-nutrition data, and the nutritional matching between the two. Multiple physical fitness training samples form a physical fitness training set. The network is initialized based on an MLP structure, with the learning rate, batch size, and optimizer set. The physical fitness training samples are input, and forward propagation is performed according to the aforementioned network layers. The predicted nutritional matching degree is output, and the predicted nutritional matching degree is analyzed against the corresponding sample nutritional matching degree to obtain the nutritional matching degree loss. Then, backpropagation is performed based on the nutritional matching degree loss to update the parameters until the loss of the trained MLP is less than or equal to the preset loss, indicating that training is complete and the desired nutrition-training matching model is obtained. For the training process of the nutrition-physical fitness test matching model, please refer to the training process of the nutrition-training matching model, except that the input sample data is different. Specifically, the input sample data for the training process of the nutrition-physical fitness test matching model consists of sample physical fitness training data, its corresponding sample sub-nutrition data, and the nutritional matching between the two.

[0041] In this embodiment of the invention, corresponding matching weights are set for physical training data and physical fitness test data based on the current stage of the target trainees. For example, in the regular training stage, which emphasizes balance, the matching weight between the two can be 1:1; in the high-intensity field training stage, which emphasizes training, the matching weight between physical training data and physical fitness test data is 7:3; and in the new recruit adaptation period, which emphasizes physical fitness tests, the matching weight between physical training data and physical fitness test data is 2:8.

[0042] As can be seen, implementing the embodiments of the present invention can further divide physical fitness data into two dimensions: physical fitness training data and physical fitness test data. The sub-nutrition data and their respective physical fitness data are then analyzed independently using corresponding nutrition-training matching models and nutrition-physical fitness test matching models to obtain their respective matching degrees. By combining the matching weights corresponding to the physical fitness training data and physical fitness test data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is comprehensively analyzed. This approach takes into account both dynamic training load and static physical condition, while reducing the one-sidedness of matching nutrition and physical fitness solely based on physical fitness training data or physical fitness test data. This improves the comprehensiveness, accuracy, and reliability of the matching judgment between sub-nutrition data and physical fitness data, thereby further enhancing the accuracy and reliability of nutritional data recommendations for trainees.

[0043] In this embodiment of the invention, optionally, a corresponding nutritional weight is set for each sub-nutritional data based on physical fitness data, including: Based on physical training data and the preset training goals of the target trainees, the needs of the target trainees for each sub-nutrient data are analyzed. The higher the need, the higher the demand for that sub-nutrient data. Based on the demand level corresponding to each sub-nutrient data, analyze the initial nutrient weight corresponding to each sub-nutrient data. The greater the demand level, the greater the corresponding initial nutrient weight. The sum of the initial nutrient weights corresponding to all sub-nutrient data equals 1. Based on the physical test data and the preset training objectives, analyze all abnormal physical test parameters of the target trainees and the abnormality of these abnormal physical test parameters; Based on all abnormal body test parameters, select all target sub-nutrient data that match the abnormal body test parameters from all sub-nutrient data; Based on the abnormalities of all abnormal body measurement parameters, the initial nutrient weights corresponding to each target sub-nutrient data are adjusted to obtain the nutrient weights set for each sub-nutrient data.

[0044] In this embodiment of the invention, different preset training goals require different levels of sub-nutrient data. For example, to improve endurance, enhance muscle strength, and improve overall physical fitness, the required levels of carbohydrates, protein, fat, calcium, iron, and vitamin C can be 0.35, 0.3, 0.1, 0.08, 0.09, and 0.08, respectively. Different abnormal physical test parameters correspond to different sub-nutrient data; for example, low hemoglobin corresponds to iron, low muscle mass corresponds to protein, and slightly high body fat corresponds to fat.

[0045] As can be seen, implementing the embodiments of the present invention can first combine the physical training data of trainees with preset training goals to analyze the nutritional requirements of each sub-nutrient and determine the corresponding initial nutritional weights, so that the allocation of nutritional weights fits the training load and the needs of the stage of training, thereby ensuring the rationality of the direction of basic nutritional supply. Then, through physical test data and preset training goals, abnormal physical test parameters and their abnormalities are identified, and the corresponding sub-nutrient data are accurately associated. Based on this, the previously determined initial weights are dynamically adjusted, which improves the accuracy and reliability of determining the weight of each sub-nutrient data, makes up for the nutritional supply deviation caused by physical fitness deficiencies, takes into account both the conventional nutritional needs oriented towards training tasks and specifically strengthens the nutritional supplementation required for abnormal physical conditions, thereby helping to further improve the accuracy and reliability of recommending the required nutritional data for trainees.

[0046] In an optional embodiment, after performing nutritional recommendations for the target trainee based on the target nutritional parameters and the target trainee's physical condition, the method may further include the following steps: Determine the target nutritional data after nutritional adjustment, and obtain multiple primary ingredients that match the target nutritional data; Obtain the caloric parameters of each primary ingredient and all sub-nutrient parameters contained in each primary ingredient for the target trainees; Analyze the heat parameters of each primary ingredient to obtain the heat value of the target trainee for each primary ingredient; Based on the heat value corresponding to each first ingredient, select all second ingredients whose heat value is greater than or equal to a preset heat value (e.g., 0.6) from all first ingredients; Based on the pre-determined relationship between physical and nutritional needs and all sub-nutrient parameters of each second ingredient, the proportion parameters of all second ingredients are analyzed.

[0047] In this optional embodiment, the popularity parameters of the first ingredient include, but are not limited to, one or more of the following: number of votes, number of orders, number of positive reviews, and number of reposts. Different physical fitness data correspond to different ingredient ratio parameters. For example, according to the physical fitness requirements of high carbohydrate, high iron, high protein, low fat, and high calcium, the weight ratio and time ratio of the second ingredient are used. The weight ratio is used to indicate the number of grams to be consumed per meal, and the time ratio is used to indicate the time of consumption per meal, such as whether it is eaten in the morning, at noon, or in the evening.

[0048] As can be seen, implementing this optional embodiment, after completing nutritional recommendations and adjusting nutritional data, further combines the recommended nutritional data with matching ingredients, and takes into account the trainees' understanding of the heat content and sub-nutrient parameters of each ingredient to adjust the ingredient ratio. This transforms abstract nutritional indicators into specific edible ingredient matching schemes, which helps to ensure that the overall nutritional structure accurately meets the training and physical needs of trainees, while also taking into account dietary preferences. The final recommended ingredient matching scheme is more in line with the actual training situation and taste preferences of trainees, thereby improving the accuracy of trainees obtaining the required nutrition and enhancing their food consumption experience.

[0049] Example 2 Please see Figure 2 , Figure 2 This is a flowchart illustrating another method for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention. Figure 2 The described method can be applied to any scenario requiring nutritional data analysis, such as military training or sports training. Figure 2 As shown, the method may include the following operations: 201. Obtain nutritional intake and physical fitness data of the target trainees during a target duration period in the past. The physical fitness data is used to characterize the physical fitness of the target trainees during the target duration period.

[0050] 202. Determine whether the nutritional intake data matches the physical fitness data.

[0051] 203. When it is determined that the nutritional intake data and physical fitness data do not match, analyze the nutritional intake data and physical fitness data to obtain the target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include the first nutritional parameter that the target trainee lacks and / or the second nutritional parameter that is excessively ingested.

[0052] 204. Obtain the type of physical training program and training data that the target trainees will undergo next.

[0053] In this embodiment of the invention, the type of physical training program includes one of all programs offered by the trainee's work unit. The work unit includes, but is not limited to, military units or sports units.

[0054] 205. Based on the type of physical training program, adjust the target nutritional parameters to obtain the first target nutritional parameters.

[0055] In this embodiment of the invention, the types of physical training programs include, but are not limited to, one or more of the following: endurance training, strength training, speed training, flexibility training, and agility and coordination training. Endurance training includes, but is not limited to, one of the following: middle-distance running, cross-country running, long-distance swimming, and continuous aerobic training. Strength training includes, but is not limited to, one of the following: weighted squats, bench presses, pull-ups, weighted marches, and weightlifting exercises. Speed ​​training includes, but is not limited to, one of the following: sprinting, endurance running, explosive jumping, and quick reaction training. Flexibility training includes, but is not limited to, one of the following: stretching, joint mobilization, yoga, and flexibility-specific training. Agility and coordination training includes, but is not limited to, one of the following: change-of-direction running, obstacle running, tactical movement, balance training, and coordination exercises.

[0056] 206. Based on the training data from the physical training program, adjust the first target nutritional parameters to obtain the second target nutritional parameters.

[0057] 207. Based on the second target nutritional parameters and the physical condition of the target trainees, perform the recommended nutritional procedures for the target trainees.

[0058] In this embodiment of the invention, steps 201-203 and 207 are described in detail. Please refer to the other descriptions of steps 101-104 in Embodiment 1. This embodiment of the invention will not repeat them.

[0059] It should be noted that steps 205 and 206 can also occur after step 203 and before step 204, that is, the order in which they occur is not limited.

[0060] It is evident that implementation Figure 2The described method analyzes and matches trainees' nutritional and physical fitness data over a past period. When mismatches are identified, it analyzes missing or excessive nutrient parameters and, combined with the user's current physical condition, adjusts the trainee's nutrition accordingly, recommending necessary nutritional data. This improves the accuracy of recommended nutrient intake, ensuring trainees receive the necessary nutrients for their training, thus enhancing training effectiveness and reducing the risk of sports injuries. Furthermore, by combining the type of subsequent training program with training data, it allows for step-by-step adjustments to target nutrient parameters, improving the match between nutritional supply and upcoming training tasks. Initial adjustments are made based on the type of training program to clarify the core nutritional needs of different training subjects. Then, a refined secondary adjustment is made based on specific training data to further match training intensity, load, and duration differences. This accurately predicts and supports the trainee's subsequent training expenditure, reducing the disconnect between nutritional supply and training tasks, and ultimately ensuring better training results and physical recovery.

[0061] In this embodiment of the invention, optionally, the training data for the physical training program includes training duration, training intensity level, and training environment parameters, wherein a higher training intensity level indicates greater training intensity. Specifically, based on training data from physical training programs, adjustments are made to the first target nutritional parameters to obtain the second target nutritional parameters, including: Based on the training duration, the first target nutrient parameter is adjusted to obtain the duration nutrient parameter. Based on the training intensity level, the first target nutrient parameter is adjusted to obtain the intensity nutrient parameter. Based on the training environment parameters, the first target nutrient parameters are adjusted to obtain the environmental nutrient parameters. Set corresponding training weights for training duration, training intensity level, and training environment parameters, such as 0.3, 0.5, and 0.2 respectively. The second target nutrient parameters are generated based on the duration nutrient parameters and training weights corresponding to the training duration, the intensity nutrient parameters and training weights corresponding to the training intensity level, and the environmental nutrient parameters and training weights corresponding to the training environment parameters.

[0062] In this embodiment of the invention, the training environment parameters include ambient temperature, ambient humidity, and ambient oxygen content. Specifically, the longer the training time, the more carbohydrates are needed; the higher the training intensity, the more protein is needed; and the lower the oxygen level in the training environment, the greater the need for iron and carbohydrates.

[0063] In this embodiment of the invention, optionally, a physical training program consists of at least one sub-physical training program, and the training data of the physical training program is composed of training data from multiple sub-physical training programs. (Missing or excessive) As can be seen, implementing the embodiments of the present invention can further refine the training data of physical training projects into training duration, training intensity level, and training environment parameters. The nutritional parameters that have been initially determined according to the type of training project to be carried out can be adjusted independently. The nutritional needs brought about by training load and external environment are accurately analyzed from different dimensions, and the corresponding training weights are reasonably allocated according to the task focus. Finally, the nutritional parameters required by the trainees are generated, so that the nutritional supply can not only adapt to the energy consumption brought about by the training duration and the recovery needs brought about by the training intensity, but also take into account the needs brought about by the training environment, further improving the accuracy and reliability of determining the nutritional parameters required by the trainees.

[0064] In an optional embodiment, when multiple sub-physical training programs are included, the training data for each sub-physical training program also includes the training order and interval duration between all sub-physical training programs (e.g., after completing one physical training program, wait 15 or 30 minutes before starting the next). The aforementioned duration nutritional parameters, intensity nutritional parameters, environmental nutritional parameters, and second target nutritional parameters are parameters for each individual sub-physical training program. Specifically, based on the second target nutritional parameters and the physical condition of the target trainee, a nutritional recommendation process is performed for the target trainee, including: For any sub-physical training program, based on the physical fitness of the target trainee, the second target nutritional parameter is adjusted to obtain the adjusted third target nutritional parameter; wherein the third target nutritional parameter includes at least one first sub-nutritional parameter; For any sub-physical training program, based on the type of the sub-physical training program and the training data, as well as the physical fitness of the target trainee, determine the other basic physical nutrition parameters required by the target trainee, excluding the third target nutritional parameter; among which, the other basic physical nutrition parameters include multiple second sub-nutritional parameters. For any target sub-nutrition parameter, a nutritional requirement path for that target sub-nutrition parameter is generated based on the training order among all sub-physical training programs, wherein all target sub-nutrition parameters include all first sub-nutrition parameters and all second sub-nutrition parameters. Based on the nutritional requirement path of each target sub-nutrition parameter, generate the nutritional parameter ratio for each target sub-nutrition parameter when the target trainee performs each sub-physical training program. Based on the training duration of each sub-physical training program and the interval duration between all sub-physical training programs, generate the nutrient intake time for each target sub-nutrient parameter, including at least one sub-nutrient intake time. Nutritional data for the target trainees is generated based on the nutritional parameter ratios corresponding to all target sub-nutritional parameters and the intake times of all target sub-nutritional parameters. The nutritional data includes the nutritional parameter ratios corresponding to each target sub-nutritional parameter and the intake times of all sub-nutrients. The nutritional parameter ratios corresponding to all target sub-nutritional parameters include the aforementioned target nutritional data.

[0065] In this embodiment of the invention, different sub-physical training programs have different requirements for the target sub-nutrient parameters. For example, for carbohydrates, the nutritional requirement path is high requirement for sprint running → medium requirement for squats → relatively high requirement for obstacle training; for protein, the nutritional requirement path is low requirement for sprint running → high requirement for squats → medium requirement for obstacle training; for iron, the nutritional requirement path is continuous requirement throughout the entire process, with slightly higher requirement during the sprint running phase.

[0066] As can be seen, the embodiments of the present invention can first adjust the nutritional parameters that are determined to be excessive or insufficient based on the physical condition of the trainees, and then analyze the other required nutritional parameters according to the type of physical training program they will be engaged in, training data, and physical condition, so as to fully meet the training characteristics and nutritional needs of different programs. Then, combined with the training sequence between programs, a demand path for each nutritional parameter is generated to meet the demand change pattern of each nutrient throughout the entire training program, thereby improving the scientificity and accuracy of the nutritional parameter ratio. Finally, the nutritional parameter ratio required for each training program and the optimal nutritional intake time for each nutrient parameter are generated and recommended to the trainees, which improves the accuracy and scientificity of the nutritional recommendations for the trainees, thereby improving the timeliness and accuracy of the trainees' physical energy supply and the accuracy of the body's rapid recovery, and thus improving the training effect of continuous multi-program training.

[0067] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a device for intelligent nutrition recommendation based on physical fitness data disclosed in an embodiment of the present invention. Figure 3 The described device can be applied to any scenario requiring nutritional data analysis, such as military training or sports training. Figure 3 As shown, the device may include: The acquisition module 301 is used to acquire the nutritional intake data and physical fitness data of the target trainees during a past target duration period. The physical fitness data is used to characterize the physical fitness status of the target trainees during the target duration period. The judgment module 302 is used to determine whether the nutritional intake data matches the physical fitness data. Analysis module 303 is used to analyze the nutritional intake data and physical fitness data when it is determined that the nutritional intake data and physical fitness data do not match, and obtain the target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include the first nutritional parameter that the target trainee lacks and / or the second nutritional parameter that is excessively ingested. The recommendation module 304 is used to perform nutritional recommendation operations for the target trainees based on the target nutritional parameters and the physical condition of the target trainees.

[0068] It is evident that implementation Figure 3 The described device analyzes and matches the nutritional and physical data of trainees over a period of time. When mismatches are found, it analyzes the missing or excessive nutritional parameters and, combined with the user's current physical condition, adjusts the trainee's nutrition and recommends the necessary nutritional data. This improves the accuracy of the recommended nutritional intake data, thereby improving the accuracy of trainees consuming the nutrients required for their bodies and training. Ultimately, this helps to improve the effectiveness of physical training and reduce the risk of sports injuries.

[0069] In this embodiment of the invention, optionally, the nutrient intake data includes multiple sub-nutrient data; wherein, the specific method by which the judgment module 302 judges whether the nutrient intake data matches the physical fitness data includes: Based on the pre-trained nutrition-physical fitness matching model, the nutritional intake data and physical fitness data of each sub-nutrition data are analyzed to obtain the nutritional matching degree between each sub-nutrition intake data and physical fitness data. Based on physical fitness data, set corresponding nutritional weights for each sub-nutrition data; Based on the nutritional matching degree and nutritional weight corresponding to each sub-nutrition data, a target nutritional matching degree between nutritional intake data and physical fitness data is generated. Determine whether the target nutritional matching degree is greater than or equal to the preset nutritional matching degree. If it is determined to be greater than or equal to the preset nutritional matching degree, it is determined that the nutritional intake data and physical fitness data match. If it is determined to be less than the preset nutritional matching degree, it is determined that the nutritional intake data and physical fitness data do not match.

[0070] It is evident that implementation Figure 3The described device can also analyze sub-nutrient data and physical fitness data through a nutrition-fitness matching model. It can accurately quantify the matching degree of individual sub-nutrients, improving the accuracy and efficiency of comparing nutrient intake with physical fitness needs. It also dynamically assigns nutrient weights to each sub-nutrient based on physical fitness data to take into account the key nutrient needs under different training intensities and physical conditions. This makes the matching judgment between nutrition and physical fitness more consistent with the actual training situation. Finally, it calculates the final nutrient matching degree based on the sub-nutrient matching degree and the corresponding nutrient weight, and compares it with the preset nutrient matching degree. This improves the accuracy and reliability of judging the nutrient data and physical fitness of trainees over a period of time, thereby helping to further improve the accuracy and reliability of nutrient data recommendations for trainees.

[0071] In this embodiment of the invention, the physical fitness data may further optionally include physical training data and physical test data within the target duration period; Specifically, the judgment module 302, based on a pre-trained nutrition-fitness matching model, analyzes the nutrition intake data and fitness data for each sub-category to determine the specific method for achieving the nutrition matching degree between each sub-category and fitness data, including: Based on the pre-trained nutrition-training matching model, the nutritional intake data and physical training data of each sub-nutrition data are analyzed to obtain the physical training matching degree between the nutritional intake data and physical training data of each sub-nutrition data. Based on the pre-trained nutrition-physical test matching model, the nutritional intake data and physical test data of each sub-nutrition data are analyzed to obtain the physical test matching degree between each sub-nutrition intake data and physical test data. Set corresponding matching weights for physical training data and physical test data; For any sub-nutrition data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is calculated based on the matching degree of physical fitness training corresponding to the sub-nutrition data and the matching weight of physical fitness training data, the matching degree of physical fitness test corresponding to the sub-nutrition data and the matching weight of physical fitness test data.

[0072] It is evident that implementation Figure 3The described device can also split physical fitness data into two dimensions: physical fitness training data and physical fitness test data. It can then independently analyze the sub-nutrition data and their respective physical fitness data using corresponding nutrition-training matching models and nutrition-physical fitness test matching models to obtain their respective matching degrees. By combining the matching weights corresponding to the physical fitness training data and physical fitness test data, the device can comprehensively analyze the nutritional matching degree between the sub-nutrition data and the physical fitness data. This approach takes into account both dynamic training load and static physical condition, while reducing the one-sidedness of matching nutrition and physical fitness solely based on physical fitness training data or physical fitness test data. This improves the comprehensiveness, accuracy, and reliability of the matching judgment between sub-nutrition data and physical fitness data, thereby further enhancing the accuracy and reliability of nutritional data recommendations for trainees.

[0073] In this embodiment of the invention, optionally, the specific method by which the judging module 302 sets corresponding nutritional weights for each sub-nutritional data based on physical fitness data includes: Based on physical training data and the preset training goals of the target trainees, analyze the needs of the target trainees for each sub-nutrient data. Based on the demand level corresponding to each sub-nutrient data, analyze the initial nutrient weight corresponding to each sub-nutrient data. Based on the physical test data and the preset training objectives, analyze all abnormal physical test parameters of the target trainees and the abnormality of these abnormal physical test parameters; Based on all abnormal body test parameters, select all target sub-nutrient data that match the abnormal body test parameters from all sub-nutrient data; Based on the abnormalities of all abnormal body measurement parameters, the initial nutrient weights corresponding to each target sub-nutrient data are adjusted to obtain the nutrient weights set for each sub-nutrient data.

[0074] It is evident that implementation Figure 3 The described device can first combine the trainee's physical training data and preset training goals to analyze the nutritional requirements of each sub-nutrient and determine the corresponding initial nutritional weights. This ensures that the nutritional weight allocation is aligned with the training load and the needs of each stage of training, guaranteeing the rationality of the basic nutritional supply direction. Then, through physical test data and preset training goals, it identifies abnormal physical test parameters and their abnormalities, accurately correlates them with the corresponding sub-nutrient data, and dynamically adjusts the previously determined initial weights accordingly. This improves the accuracy and reliability of determining the weights of each sub-nutrient data, compensates for nutritional supply deviations caused by physical deficiencies, and takes into account both the conventional nutritional needs oriented towards training tasks and the targeted strengthening of nutritional supplementation required for abnormal physical conditions. This further helps to improve the accuracy and reliability of recommending the required nutritional data for trainees.

[0075] In an optional embodiment, such as Figure 3As shown, the acquisition module 301 is also used to acquire the type of physical training program and training data that the target trainee will be carrying out next. And such as Figure 4 As shown, the device may further include: The adjustment module 305 is used to perform adjustment operations on the target nutritional parameters based on the type of physical training program to obtain the first target nutritional parameters. The adjustment module 305 is also used to perform adjustment operations on the first target nutritional parameter based on the training data of the physical training program to obtain the second target nutritional parameter; The recommendation module 304, based on the target nutritional parameters and the physical condition of the target trainees, specifies the details of how to perform nutritional recommendations for them, including: Based on the second target nutritional parameters and the physical condition of the target trainees, nutritional recommendations are implemented for them.

[0076] It is evident that implementation Figure 4 The described device adjusts target nutritional parameters in a step-by-step manner by combining the type of subsequent physical training program with training data. This improves the matching degree between nutritional supply and the upcoming training task. First, an initial adjustment is made based on the type of training program to clarify the core nutritional needs of different training subjects. Then, a refined secondary adjustment is made based on specific training data to further match the differences in training intensity, load, and duration. This accurately predicts and supports the consumption of trainees in subsequent training, reduces the disconnect between nutritional supply and training tasks, and thus helps to better ensure the training effect and physical recovery of trainees.

[0077] In this optional embodiment, the physical training program may include at least one sub-physical training program. The training data for each sub-physical training program includes training duration, training intensity level, and training environment parameters. The higher the training intensity level, the greater the training intensity. The adjustment module 305, based on training data from a physical training program, performs adjustments to the first target nutritional parameter to obtain the second target nutritional parameter. The specific methods include: Based on the training duration, the first target nutrient parameter is adjusted to obtain the duration nutrient parameter. Based on the training intensity level, the first target nutrient parameter is adjusted to obtain the intensity nutrient parameter. Based on the training environment parameters, the first target nutrient parameters are adjusted to obtain the environmental nutrient parameters. Set corresponding training weights for training duration, training intensity level, and training environment parameters; The second target nutrient parameters are generated based on the duration nutrient parameters and training weights corresponding to the training duration, the intensity nutrient parameters and training weights corresponding to the training intensity level, and the environmental nutrient parameters and training weights corresponding to the training environment parameters.

[0078] It is evident that implementation Figure 4 The described device can also refine training data for physical training programs into training duration, training intensity level, and training environment parameters. It can independently adjust the nutritional parameters that have been initially determined based on the type of training program to be conducted. It can accurately analyze the nutritional needs brought about by training load and external environment from different dimensions, and reasonably allocate corresponding training weights according to the task focus. Finally, it generates the nutritional parameters required by the trainees, so that the nutritional supply can not only adapt to the energy consumption brought about by training duration and the recovery needs brought about by training intensity, but also take into account the needs brought about by the training environment, further improving the accuracy and reliability of determining the nutritional parameters required by the trainees.

[0079] In another alternative embodiment, such as Figure 4 As shown, the recommendation module 304 is also used to determine the target nutritional data after performing nutritional recommendation operations for the target trainees based on the target nutritional parameters and the physical condition of the target trainees. The acquisition module 301 is also used to acquire multiple first ingredients that match the target nutritional data; The acquisition module 301 is also used to acquire the heat parameters of each first ingredient and all the sub-nutrient parameters contained in each first ingredient for the target trainee; The analysis module 303 is also used to analyze the heat parameters of each first ingredient to obtain the heat value of the target trainee for each first ingredient; And such as Figure 4 As shown, the device may further include: The filtering module 306 is used to filter all second ingredients whose heat values ​​are greater than or equal to a preset heat value from all first ingredients based on the heat value corresponding to each first ingredient. The analysis module 303 is also used to analyze the proportion parameters of all second ingredients based on the predetermined physical-nutritional demand relationship and all sub-nutritional parameters of each second ingredient.

[0080] It is evident that implementation Figure 4The described device can further combine the recommended nutritional data with the ingredients matched to the nutritional data after completing the nutritional recommendations and adjustments. It also takes into account the trainees' understanding of the heat content and sub-nutrient parameters of each ingredient to adjust the ingredient ratio. This transforms abstract nutritional indicators into specific edible ingredient matching schemes, which helps to accurately meet the trainees' training and physical needs while taking into account their dietary preferences. The final recommended ingredient matching scheme is more in line with the trainees' actual training situation and taste preferences, thereby improving the accuracy of the nutrition trainees receive and enhancing their food consumption experience.

[0081] Example 4 Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of a nutrition recommendation device disclosed in an embodiment of the present invention. Figure 5 The described nutrition recommendation device can be applied to any scenario requiring nutritional data analysis, such as military training or sports training. Figure 5 As shown, the nutrition recommendation device may include: Memory 401 storing executable program code; Processor 402 coupled to memory 401; The processor 402 calls the executable program code stored in the memory 401 to execute some or all of the steps in the method for intelligent nutrition recommendation based on physical fitness data as described in either Embodiment 1 or Embodiment 2 of the present invention.

[0082] Example 5 This invention discloses a computer storage medium storing computer instructions. When these computer instructions are invoked, they are used to execute some or all of the steps in any of the methods for intelligent nutrition recommendation based on physical fitness data disclosed in Embodiment 1 or Embodiment 2 of this invention.

[0083] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0084] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0085] Finally, it should be noted that the above embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent nutrition recommendation based on physical fitness data, characterized in that, The method includes: Obtain nutritional intake and physical fitness data of the target trainees during a target duration period in the past, wherein the physical fitness data is used to characterize the physical fitness status of the target trainees during the target duration period; Determine whether the nutritional intake data matches the physical fitness data; When it is determined that the nutritional intake data does not match the physical fitness data, the nutritional intake data and the physical fitness data are analyzed to obtain target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include a first nutritional parameter that the target trainee lacks and / or a second nutritional parameter that is excessively ingested. Based on the target nutritional parameters and the physical condition of the target trainee, nutritional recommendations are performed for the target trainee.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the type and training data of the physical training program that the target trainee will undergo next; Based on the type of the physical training program, the target nutritional parameters are adjusted to obtain the first target nutritional parameters. Based on the training data of the physical training program, the first target nutritional parameter is adjusted to obtain the second target nutritional parameter. The step of performing nutritional recommendations for the target trainee based on the target nutritional parameters and the target trainee's physical condition includes: Based on the second target nutritional parameters and the physical condition of the target trainee, nutritional recommendations are performed for the target trainee.

3. The method according to claim 2, characterized in that, The training data for the physical training program includes training duration, training intensity level, and training environment parameters, wherein a higher training intensity level indicates greater training intensity. The process of adjusting the first target nutritional parameter based on the training data from the physical training program to obtain the second target nutritional parameter includes: Based on the training duration, an adjustment operation is performed on the first target nutrient parameter to obtain the duration nutrient parameter; Based on the training intensity level, an adjustment operation is performed on the first target nutrient parameter to obtain the intensity nutrient parameter; Based on the training environment parameters, an adjustment operation is performed on the first target nutrient parameters to obtain the environmental nutrient parameters. Set corresponding training weights for the training duration, the training intensity level, and the training environment parameters; The second target nutritional parameters are generated based on the duration nutritional parameters and training weights corresponding to the training duration, the intensity nutritional parameters and training weights corresponding to the training intensity level, and the environmental nutritional parameters and training weights corresponding to the training environment parameters.

4. The method according to any one of claims 1-3, characterized in that, The nutrient intake data includes multiple sub-nutrient data; The determination of whether the nutrient intake data matches the physical fitness data includes: Based on the pre-trained nutrition-physical fitness matching model, the nutritional matching degree between each of the sub-nutrition intake data and the physical fitness data is obtained by analyzing the nutritional matching data between each of the sub-nutrition intake data and the physical fitness data. Based on the physical fitness data, a corresponding nutritional weight is set for each of the sub-nutrition data points; Based on the nutritional matching degree and nutritional weight corresponding to each of the sub-nutrition data, a target nutritional matching degree between the nutritional intake data and the physical fitness data is generated. Determine whether the target nutritional matching degree is greater than or equal to a preset nutritional matching degree. If it is determined to be greater than or equal to the preset nutritional matching degree, it is determined that the nutritional intake data matches the physical fitness data. If it is determined to be less than the preset nutritional matching degree, it is determined that the nutritional intake data does not match the physical fitness data.

5. The method according to claim 4, characterized in that, The physical fitness data includes physical training data and physical test data within the target duration period; The aforementioned analysis of each sub-nutrient intake data and physical fitness data based on a pre-trained nutrition-fitting model to obtain the nutrition matching degree between each sub-nutrient intake data and the physical fitness data includes: Based on the pre-trained nutrition-training matching model, the sub-nutrition intake data and the physical training data are analyzed to obtain the physical training matching degree between each sub-nutrition intake data and the physical training data. Based on the pre-trained nutrition-physical test matching model, the sub-nutrition intake data and the physical test data are analyzed to obtain the physical test matching degree between each sub-nutrition intake data and the physical test data. Set corresponding matching weights for the physical training data and the physical test data; For any of the sub-nutrition data, the nutritional matching degree between the sub-nutrition data and the physical fitness data is calculated based on the physical fitness training matching degree and the matching weight corresponding to the physical fitness training data, the physical fitness test matching degree and the matching weight corresponding to the physical fitness test data.

6. The method according to claim 5, characterized in that, The step of setting corresponding nutritional weights for each sub-nutritional data based on the physical fitness data includes: Based on the physical training data and the preset training goals of the target trainees, analyze the target trainees' needs for each of the sub-nutrition data. Based on the demand degree corresponding to each of the sub-nutrient data, analyze the initial nutrient weight corresponding to each of the sub-nutrient data; Based on the physical test data and the preset training objectives, analyze all abnormal physical test parameters of the target trainees and the abnormality of these abnormal physical test parameters; Based on all the abnormal body measurement parameters, select all target sub-nutrient data that match the abnormal body measurement parameters from all the sub-nutrient data; Based on the abnormality of all the abnormal body measurement parameters, an adjustment operation is performed on the initial nutrient weight corresponding to each of the target sub-nutrient data to obtain the nutrient weight set for each of the sub-nutrient data.

7. The method according to any one of claims 1-3, 5 and 6, characterized in that, After performing nutritional recommendations for the target trainee based on the target nutritional parameters and the target trainee's physical condition, the method further includes: Determine the target nutritional data after nutritional adjustment, and obtain multiple first ingredients that match the target nutritional data; Obtain the caloric parameters of each of the first ingredients and all the sub-nutrient parameters contained in each of the first ingredients for the target trainees; Analyze the heat parameters of each of the first ingredients to obtain the heat value of the target trainee for each of the first ingredients; Based on the heat value corresponding to each of the first ingredients, select all second ingredients whose heat value is greater than or equal to a preset heat value from all the first ingredients; Based on the pre-determined correlation between physical and nutritional needs and all sub-nutritional parameters of each second ingredient, the proportion parameters of all second ingredients are analyzed.

8. A device for intelligent nutrition recommendation based on physical fitness data, characterized in that, The device includes: The acquisition module is used to acquire the nutritional intake data and physical fitness data of the target trainee during a past target duration period. The physical fitness data is used to characterize the physical fitness status of the target trainee during the target duration period. The judgment module is used to determine whether the nutrient intake data matches the physical fitness data; The analysis module is used to analyze the nutritional intake data and the physical fitness data when it is determined that the nutritional intake data and the physical fitness data do not match, and to obtain the target nutritional parameters that do not match the physical fitness of the target trainee. The target nutritional parameters include a first nutritional parameter that the target trainee lacks and / or a second nutritional parameter that is excessively ingested. The recommendation module is used to perform nutritional recommendation operations for the target trainee based on the target nutritional parameters and the target trainee's physical condition.

9. A nutritional recommendation device, characterized by The nutrition recommendation device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for intelligent nutrition recommendation based on physical fitness data as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the method for intelligent nutrition recommendation based on physical fitness data as described in any one of claims 1-7.

Images