Training teaching intelligent question and answer management system and method based on large model

Abstract

The invention discloses a training teaching intelligent question and answer management system and method based on a large model, relates to the field of training management, solves the problem of low adaptability of a training plan and a target user, and comprises a data acquisition module, a user analysis module, a training plan optimization module and an effectiveness judgment module. The data acquisition module is used for acquiring body characteristic data and historical training item types of a target user; the user analysis module is used for analyzing the physical condition of the target user to obtain a pre-selected training plan of the target user; the training plan optimization module is used for optimizing a pre-selected training plan according to the question and answer text with the target user to obtain an optimized training plan of the target user; the effectiveness judgment module is used for judging the effectiveness of the optimization training plan on the target personnel, continuing training if the optimization training plan is effective, and making corresponding adjustment if the optimization training plan is ineffective; according to the invention, the training plan of the target user is dynamically adjusted.

Description

Technical Field

[0001] The present invention belongs to the technical field of training management, and specifically is a training teaching intelligent question-answering management system and method based on a large model. Background Art

[0002] A big model refers to a deep learning model with a very large number of parameters and a very large amount of data. The construction of the big model is based on a deep neural network. The training and teaching intelligent question and answer management system uses natural language processing, machine learning and other technologies to simulate the coach's answering method and optimize the training plan for the target personnel. Its purpose is to improve the training efficiency of the target personnel, reduce the burden on the coach, and provide the target personnel with a more personalized and convenient training experience.

[0003] However, the traditional training plan recommendation method relies on manual experience and static templates, and cannot be dynamically adjusted according to the user's real-time physical condition, resulting in poor adaptability between the target user and the training plan, and unable to ensure that the user achieves his or her training goals; To this end, the present invention proposes a training and teaching intelligent question-answering management system and method based on a large model. Summary of the invention

[0004] The purpose of the present invention is to propose a large-model-based training and teaching intelligent question-answering management system and method to solve the problems raised in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A training and teaching intelligent question-answering management system based on a large model, comprising a data acquisition module, a user analysis module, a training plan optimization module, an effectiveness judgment module, a user terminal and a display terminal; The data collection module is used to collect the target user's physical feature data and historical training project types, and then send the target user's physical feature data to the user analysis module, and send the target user's historical training project types to the training plan optimization module; The user analysis module is used to analyze the physical condition of the target user, obtain the pre-selected training plan of the target user and send it to the training plan optimization module; The training plan optimization module is used to optimize the pre-selected training plan based on the question and answer text with the target user, obtain the optimized training plan for the target user and send it to the user terminal; The user terminal is held by the user, and the user views the optimization training plan and performs training through the user terminal; The effectiveness judgment module is used to judge the effectiveness of the optimized training plan for the target user. If the optimized training plan is effective for the target user, it will continue to be executed. If the optimized training plan is not effective for the target user, the optimized training plan will be adjusted in real time. After the target user reaches the training goal, a training completion signal is generated and sent to the display terminal, and the adjusted training plan is sent to the database for storage; The display terminal is used to receive a training completion signal of a target user and display the training results of the target user.

[0006] Furthermore, the physical characteristic data includes the target user's real-time height, real-time weight, real-time body fat percentage, and resting heart rate.

[0007] Furthermore, the analysis process of the user analysis module is as follows: Obtain the target user's physical characteristic data, and obtain the target user's real-time height SSG, real-time weight STZ, real-time body fat rate TZL, and resting heart rate JXL; The target user's physical health index SJK is calculated using the formula, which is as follows: ; In the formula, a1 and a2 are weight coefficients with fixed values, and TBZ is the standard body fat percentage; Comparing the target user's physical health index with the health index threshold; If the target user's physical health index is less than the first health index threshold, the target user's physical health level is recorded as first-level health; If the target user's physical health index is greater than or equal to the first health index threshold and less than the second health level threshold, the target user's physical health level is recorded as level 2 health; If the physical health index of the target user is greater than or equal to the third health index threshold, the physical health level of the target user is recorded as level three health.

[0008] Furthermore, the analysis process of the user analysis module also includes: The physical condition of the target users corresponding to the third level of health is better than that of the target users corresponding to the second level of health, and the physical condition of the target users corresponding to the second level of health is better than that of the target users corresponding to the first level of health; the third health index threshold> the second health index threshold> the first health index threshold; According to the physical fitness level of the target user, a plurality of pre-selected training plans of people with the same physical fitness level are screened in the database, and the resting heart rates of the people corresponding to each pre-selected training plan are read; The resting heart rate of the personnel is compared with the resting heart rate of the target personnel, and the pre-selected training plan corresponding to the group with the smallest difference is selected as the pre-selected training plan for the target personnel.

[0009] Furthermore, the optimization process of the training plan optimization module includes the following: Obtain the historical training project types of the target user, obtain the training project categories of the corresponding historical training projects according to the historical training project types, and use the training project categories with the highest proportion as the reference training project categories of the target user; specifically, the reference training project categories include: strength training, aerobic training, flexibility training, agility training, and endurance training; If there is no historical training data for the target user, a first question text is generated and sent to the user terminal; The first question text is a text for confirming the training project category of the target user; The target user receives the first question text through the user terminal and makes a reply, and the user terminal feeds back the first reply text to the training plan optimization module; the training plan optimization module obtains and identifies the content of the first reply text, and confirms the training project category of the target user; Obtaining a pre-selected training plan for a target user, reading a pre-selected training item category for each training item in the pre-selected training plan, and if the pre-selected training item category is different from a reference training item category for the target user, generating a second question text and sending the second question text to a user terminal; The second question text is a text that confirms the target user's demand for replacement of the pre-selected training items; The target user makes a reply and feeds back the corresponding second reply text to the training plan optimization module, which obtains and recognizes the content of the second reply text and then makes corresponding operations; If the pre-selected training item category is the same as the reference training item category of the target user, a third question text is generated and sent to the user terminal; the target user makes a reply and feeds back the corresponding third reply text to the training plan optimization module; The third question text is a text to confirm the target user's tendency to adjust the training intensity of different pre-selected training items; The training plan optimization module identifies the content of the third reply text of the target user, and then adjusts and optimizes the training amount of the pre-selected training items to obtain an optimized training plan corresponding to the target user.

[0010] Furthermore, the process of the training plan optimization module identifying the corresponding contents of different reply texts is specifically as follows: Treat the reply text as a collection of words, ignore the grammar and word order in the reply text, and divide the reply text into multiple reply participles; match each reply participle with the word library, identify the part of speech of each reply participle and perform part of speech tagging; discard reply participles whose part of speech is auxiliary words, conjunctions, prepositions and stop words; Count the word frequencies of different reply words and calculate the importance index of different reply words. The calculation formula is: Importance index = weight coefficient × word frequency; where the weight coefficient has different values ​​for different reply texts, and the greater the relevance of the reply word to the corresponding question text, the greater the weight coefficient; The response participles whose importance index is greater than the importance threshold are retained and recorded as important participles; If there are no important participles, the answer text is deemed meaningless and the target user is prompted to answer again; If the number of important participles is greater than or equal to one, the meanings of the important participles are identified, and the pre-selected training plan is optimized according to the meanings of the important participles.

[0011] Furthermore, the determination process of the validity determination module includes the following: Obtaining the physical health index of the target user as the first physical health index; Acquire the second physical characteristic data of the target user, and obtain the second real-time height DEG, the second real-time weight DEZ, and the second real-time body fat percentage ETZ corresponding to the target user; The second physical health index of the target user is calculated by the formula, and the calculation formula is as follows: ; Where b1 and b2 are weight coefficients with fixed values; A first deviation value is obtained by subtracting the standard physical health index from the first physical health index of the target user and taking the absolute value, and a second deviation value is obtained by subtracting the standard physical health index from the second physical health index and taking the absolute value; The standard physical health index is the physical health value of the target user under ideal conditions; the larger the first deviation value and the second deviation value, the worse the physical health of the target user.

[0012] Furthermore, the determination process of the validity determination module further includes: The first deviation value of the target user is compared with the second deviation value, and if the first deviation value of the target user is greater than or equal to the second deviation value, the target user continues to be trained using the optimized training plan; If the first deviation value of the target user is less than the second deviation value, the real-time training result of the target user is compared with the expected training result. When the real-time training result is greater than or equal to the expected training result, no operation is performed; when the real-time training result is less than the expected training result, it is determined that the optimized training plan is invalid for the target user, and the optimized training plan is adjusted through questions and answers to obtain an adjusted training plan; Among them, the real-time training results are the actual improvement of the target user after setting the training goal, and the expected training results are the expected improvement after setting the training goal; During the adjustment, the reasons for failure of the optimized training plan are obtained based on the data monitoring indicators, and corresponding adjustment directions are made accordingly; wherein, the data monitoring indicators are obtained by interacting with the target users and extracting the texts replied by the target users.

[0013] Furthermore, the reasons for failure include: unreasonable goal setting, insufficient training intensity, insufficient recovery, deviation in movement execution and mismatched nutritional intake; adjustment directions include: renegotiating training goals, increasing training intensity or changing training mode, reducing training frequency or adding rest days, replacing training movements or adding corrective training, and adjusting nutritional plans or supplementation strategies.

[0014] A training and teaching intelligent question-answering management method based on a large model, the method comprising: Step S101, collecting the target user's physical characteristic data and historical training items, analyzing the target user's physical condition, and obtaining a pre-selected training plan for the target user; Step S102, optimizing the pre-selected training plan according to the question-and-answer text with the target user to obtain an optimized training plan for the target user; Step S103, collecting and analyzing the physical characteristic data of the target user for a period of time after the optimized training plan is executed, and determining the effectiveness of the optimized training plan; Step S104: If the optimized training plan is effective for the target user, the optimized training plan continues to be executed; if the optimized training plan is not effective for the target user, the optimized training plan is adjusted in real time.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention first collects the physical characteristic data and historical training project types of the target user through the data collection module and sends the physical characteristic data of the target user to the user analysis module, and sends the historical training project types of the target user to the training plan optimization module; then uses the user analysis module to analyze the physical condition of the target user, obtains the pre-selected training plan of the target user and sends it to the training plan optimization module; then uses the training plan optimization module to optimize the pre-selected training plan in combination with the question and answer text between the target user and the target user, and obtains the optimized training plan corresponding to the target user; the present invention realizes the formulation of the corresponding training plan for the target user.

[0016] 2. The present invention first collects the physical condition data of the target user after a period of training and sends it to the effectiveness judgment module, so as to use the effectiveness judgment module to judge the effectiveness of the preferred training plan for the target person. If it is effective, the training will continue; if it is not effective, the preferred training plan will be adjusted until the target user achieves the training goal; the present invention realizes real-time adjustment of the training plan of the target user. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 is the overall system block diagram of the present invention; Figure 2 It is a schematic diagram of the optimization process of pre-selecting a training plan in the present invention; Figure 3 The figure is a flowchart of the method of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Example 1, please refer to Figure 1 and Figure 2 As shown, the technical solution provided by the present invention is: a training and teaching intelligent question-answering management system based on a large model, including a data acquisition module, a user analysis module, a training plan optimization module, an effectiveness judgment module, a database, a user terminal and a display terminal; The data collection module is used to collect the target user's physical characteristic data and historical training program types, and then send the target user's physical characteristic data to the user analysis module, and send the target user's historical training program types to the training plan optimization module; wherein the physical characteristic data are the target user's real-time height, real-time weight, real-time body fat percentage and resting heart rate.

[0021] The user analysis module is used to analyze the physical condition of the target user. The analysis process is as follows: Obtain the target user's physical characteristic data, and obtain the target user's real-time height SSG, real-time weight STZ, real-time body fat rate TZL, and resting heart rate JXL; The target user's physical health index SJK is calculated using the formula, which is as follows: ; In the formula, a1 and a2 are weight coefficients with fixed values, TBZ is the standard body fat percentage, and the standard body fat percentage can be obtained by comparing the real-time height and real-time weight; Comparing the target user's physical health index with the health index threshold; If the target user's physical health index is less than the first health index threshold, the target user's physical health level is recorded as first-level health; If the target user's physical health index is greater than or equal to the first health index threshold and less than the second health level threshold, the target user's physical health level is recorded as level 2 health; If the target user's physical health index is greater than or equal to the third health index threshold, the target user's physical health level is recorded as level three health; Among them, the physical condition of the target user corresponding to the third level of health is better than that of the target user corresponding to the second level of health, and the physical condition of the target user corresponding to the second level of health is better than that of the target user corresponding to the first level of health; the third health index threshold> the second health index threshold> the first health index threshold; According to the physical fitness level of the target user, a plurality of pre-selected training plans of people with the same physical fitness level are screened in the database, and the resting heart rates of the people corresponding to each pre-selected training plan are read; Compare the resting heart rate of the personnel with the resting heart rate of the target personnel, and select the pre-selected training plan corresponding to the group with the smallest difference as the pre-selected training plan for the target personnel; The user analysis module sends the pre-selected training plan of the target user to the training plan optimization module.

[0022] The training plan optimization module is used to optimize the pre-selected training plan based on the question and answer text between the target user. The optimization process is as follows: Obtain the historical training project types of the target user, obtain the training project categories of the corresponding historical training projects according to the historical training project types, and use the training project categories with the highest proportion as the reference training project categories of the target user; specifically, the reference training project categories include: strength training, aerobic training, flexibility training, agility training, and endurance training; If there is no historical training data for the target user, a first question text is generated and sent to the user terminal; The first question text is a text for confirming the training program category of the target user; for example, the first question text may be: "Do you prefer strength training, aerobic training, flexibility training, agility training or endurance training?"; The target user receives the first question text through the user terminal and makes a reply, and the user terminal feeds back the first reply text to the training plan optimization module; the training plan optimization module obtains and identifies the content of the first reply text, and confirms the training project category of the target user; Obtaining a pre-selected training plan for a target user, reading a pre-selected training item category for each training item in the pre-selected training plan, and if the pre-selected training item category is different from a reference training item category for the target user, generating a second question text and sending the second question text to a user terminal; The second question text is a text confirming the target user's need to replace the pre-selected training items; for example, the second question text is: "Would you like to replace the pre-selected training items?"; The target user makes a reply and feeds back the corresponding second reply text to the training plan optimization module, which obtains and recognizes the content of the second reply text and then makes corresponding operations; If the pre-selected training item category is the same as the reference training item category of the target user, a third question text is generated and sent to the user terminal; the target user makes a reply and feeds back the corresponding third reply text to the training plan optimization module; The third question text is a text for confirming the target user's tendency to adjust the training intensity of different pre-selected training items; for example, the third question text may be: "Would you like to increase or decrease the training intensity? What is the specific range?"; The training plan optimization module identifies the content of the third reply text of the target user, and then adjusts and optimizes the training amount of the pre-selected training items to obtain an optimized training plan corresponding to the target user; Specifically, the process of the training plan optimization module identifying the corresponding content of the reply text is as follows: Treat the reply text as a collection of words, ignore the grammar and word order in the reply text, and divide the reply text into multiple reply participles; match each reply participle with the word library, identify the part of speech of each reply participle and perform part of speech tagging; discard reply participles whose part of speech is auxiliary words, conjunctions, prepositions and stop words; Among them, parts of speech include: nouns, verbs, adjectives, numerals, quantifiers, pronouns, adverbs, prepositions, conjunctions, and auxiliary words; Count the word frequencies of different reply words and calculate the importance index of different reply words. The calculation formula is: Importance index = weight coefficient × word frequency; where the weight coefficient has different values ​​for different reply texts, and the greater the relevance of the reply word to the corresponding question text, the greater the weight coefficient; The response participles whose importance index is greater than the importance threshold are retained and recorded as important participles; If there are no important participles, the answer text is deemed meaningless and the target user is prompted to answer again; If the number of important participles is greater than or equal to one, the meanings of the important participles are identified, and the pre-selected training plan is optimized according to the meanings of the important participles; The training plan optimization module sends the optimized training plan of the target user to the user terminal.

[0023] The user terminal is held by the user, and the user views the optimization training plan and performs training through the user terminal; After the target user performs training for a certain period of time, the data collection module will collect the target user's physical characteristic data again, record it as second physical characteristic data, and send it to the validity determination module; The effectiveness judgment module is used to judge the effectiveness of the optimization training plan for the target personnel. The judgment process is as follows: Obtaining the physical health index of the target user as the first physical health index; Acquire the second physical characteristic data of the target user, and obtain the second real-time height DEG, the second real-time weight DEZ, and the second real-time body fat percentage ETZ corresponding to the target user; The second physical health index of the target user is calculated by the formula, and the calculation formula is as follows: ; Where b1 and b2 are weight coefficients with fixed values; A first deviation value is obtained by subtracting the standard physical health index from the first physical health index of the target user and taking the absolute value, and a second deviation value is obtained by subtracting the standard physical health index from the second physical health index and taking the absolute value; It should be specifically noted that the standard physical health index is the physical health value of the target user in an ideal state (the healthiest state); the larger the first deviation value and the second deviation value, the worse the physical health condition of the target user; The first deviation value of the target user is compared with the second deviation value, and if the first deviation value of the target user is greater than or equal to the second deviation value, the target user continues to be trained using the optimized training plan; If the first deviation value of the target user is less than the second deviation value, the real-time training result of the target user is compared with the expected training result. When the real-time training result is greater than or equal to the expected training result, no operation is performed; when the real-time training result is less than the expected training result, it is determined that the optimized training plan is invalid for the target user, and the optimized training plan is adjusted through questions and answers to obtain an adjusted training plan; Among them, the real-time training results are the actual improvement of the target user after setting the training goal, and the expected training results are the expected improvement after setting the training goal; For example, the target user's training goal is to gain 5 kg of muscle in 5 months. After the target user has trained for one month using the optimized training plan, the actual muscle gain weight at this time is the actual training result, and the expected muscle gain weight at this time is the expected training result. During the adjustment, the failure reason of the optimized training plan is obtained based on the data monitoring indicators, and corresponding adjustments are made accordingly; wherein the data monitoring indicators are obtained by interacting with the target user and extracting the text replied by the target user; Specifically, refer to the adjustment strategy reference table for adjustment. The adjustment strategy reference table is as follows:

[0024] Among them: unreasonable goal setting, such as the target user has poor physical fitness but chooses high-intensity training. It is recommended that the target user recover to a healthy state before training; insufficient training intensity, such as heart rate is lower than 60% of the maximum heart rate for a long time, change steady-state aerobics to HIIT, or increase the weight by 5% to 10%; insufficient recovery, such as sleep duration <6 hours / day, or persistently low heart rate variability, appropriately reduce the training frequency, for example, from 5 training sessions per week to 3 training sessions; deviation in action execution, such as posture analysis shows that the deformation rate of the action is >30%, use equipment assistance instead of free weights, and increase core stability exercises; mismatched nutritional intake, such as dietary records show that protein intake is <1.2g / kg body weight, formulate a high-protein diet, and it is recommended to supplement fast-absorbing carbohydrates within 30 minutes after training; The target user executes the adjusted training plan, and compares the target user's current real-time training results with the expected training results to verify the effect; if the current real-time training results are greater than or equal to the expected training results, the adjusted training plan is deemed effective, and the training continues until the target user is reached; If the current real-time training result is still less than the expected training result, a reformulation signal is generated and sent to the user analysis module. The user analysis module receives the reformulation signal, reformulates the training plan for the target user, and runs the subsequent process again. After the target user achieves the training goal, a training completion signal is generated and sent to the display terminal, and the adjusted training plan is sent to the database for storage.

[0025] The display terminal is used to receive a training completion signal of a target user and display the training results of the target user.

[0026] In this application, if corresponding calculation formulas appear, the above calculation formulas are all dimensionless and take their numerical calculations. The weight coefficients, proportional coefficients and other coefficients in the formulas are set to a result value obtained by quantifying each parameter. The size of the weight coefficient and the proportional coefficient can be determined as long as it does not affect the proportional relationship between the parameter and the result value.

[0027] Embodiment 2, as Figure 3 As shown, based on another concept of the same invention, a training teaching intelligent question and answer management method based on a large model is now proposed, comprising the following steps: Step S101, collecting the target user's physical characteristic data and historical training item types, analyzing the target user's physical condition, and obtaining a pre-selected training plan for the target user; Step S102, optimizing the pre-selected training plan based on the question-and-answer text with the target user to obtain an optimized training plan for the target user; Step S103, collecting and analyzing the physical characteristic data of the target user for a period of time after the optimized training plan is executed, and determining the effectiveness of the optimized training plan; Step S104: If the optimized training plan is effective for the target user, the optimized training plan continues to be executed; if the optimized training plan is not effective for the target user, the optimized training plan is dynamically adjusted in real time.

[0028] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A training and teaching intelligent question-answering management system based on a large model, characterized in that: It includes a data collection module, a user analysis module, a training plan optimization module, an effectiveness judgment module, a user terminal and a display terminal. The data collection module is used to collect the physical feature data and historical training project types of the target user, and then send the physical feature data of the target user to the user analysis module, and send the historical training project types of the target user to the training plan optimization module; The user analysis module is used to analyze the physical condition of the target user, obtain the pre-selected training plan of the target user and send it to the training plan optimization module; The training plan optimization module is used to optimize the pre-selected training plan based on the question and answer text with the target user, obtain the optimized training plan for the target user and send it to the user terminal; the user terminal is held by the user, and the user views the optimized training plan and performs training through the user terminal; The effectiveness judgment module is used to judge the effectiveness of the optimized training plan for the target user. If the optimized training plan is effective for the target user, it will continue to be executed. If the optimized training plan is not effective for the target user, the optimized training plan will be adjusted in real time. After the target user reaches the training goal, a training completion signal is generated and sent to the display terminal, and the adjusted training plan is sent to the database for storage; The display terminal is used to receive a training completion signal of a target user and display the training results of the target user.

2. According to the large model-based intelligent question-answering management system for training and teaching according to claim 1, it is characterized in that: The physical characteristic data include the target user's real-time height, real-time weight, real-time body fat percentage, and resting heart rate.

3. According to the large model-based intelligent question-answering management system for training and teaching according to claim 1, it is characterized in that: The analysis process of the user analysis module is as follows: Obtain the target user's physical characteristic data, and obtain the target user's real-time height SSG, real-time weight STZ, real-time body fat rate TZL, and resting heart rate JXL; The target user's physical health index SJK is calculated using the formula, which is as follows: ; ; In the formula, a1 and a2 are weight coefficients with fixed values, and TBZ is the standard body fat percentage; Comparing the target user's physical health index with the health index threshold; If the target user's physical health index is less than the first health index threshold, the target user's physical health level is recorded as first-level health; If the target user's physical health index is greater than or equal to the first health index threshold and less than the second health level threshold, the target user's physical health level is recorded as level 2 health; If the physical health index of the target user is greater than or equal to the third health index threshold, the physical health level of the target user is recorded as level three health.

4. According to claim 3, a large model-based intelligent question-answering management system for training and teaching, characterized in that: The analysis process of the user analysis module also includes: The physical condition of the target users corresponding to the third level of health is better than that of the target users corresponding to the second level of health, and the physical condition of the target users corresponding to the second level of health is better than that of the target users corresponding to the first level of health; the third health index threshold> the second health index threshold> the first health index threshold; According to the physical fitness level of the target user, a plurality of pre-selected training plans of people with the same physical fitness level are screened in the database, and the resting heart rates of the people corresponding to each pre-selected training plan are read; The resting heart rate of the personnel is compared with the resting heart rate of the target personnel, and the pre-selected training plan corresponding to the group with the smallest difference is selected as the pre-selected training plan for the target personnel.

5. According to the large model-based intelligent question-answering management system for training and teaching according to claim 1, it is characterized in that: The optimization process of the training plan optimization module includes the following: Obtain the historical training project types of the target user, obtain the training project categories of the corresponding historical training projects according to the historical training project types, and use the training project category with the highest proportion as the reference training project category for the target user; Reference training program categories include: strength training, aerobic training, flexibility training, agility training and endurance training; If the target user does not have historical training data, a first question text is generated and sent to the user terminal; wherein the first question text is used to confirm that the category of the training project of the target user is the target text; The target user receives the first question text through the user terminal and makes a reply, and the user terminal feeds back the first reply text to the training plan optimization module; the training plan optimization module obtains and identifies the content of the first reply text, and confirms the training project category of the target user; Obtaining a pre-selected training plan for a target user, reading a pre-selected training item category for each training item in the pre-selected training plan, and if the pre-selected training item category is different from a reference training item category for the target user, generating a second question text and sending the second question text to a user terminal; wherein the second question text is a text for confirming the target user's demand for replacing the pre-selected training item; The target user makes a reply and feeds back the corresponding second reply text to the training plan optimization module, which obtains and recognizes the content of the second reply text and then makes corresponding operations; If the pre-selected training item category is the same as the reference training item category of the target user, a third question text is generated and sent to the user terminal; the target user makes a reply and feeds back the corresponding third reply text to the training plan optimization module; wherein the third question text is a text used to confirm the target user's tendency to adjust the training intensity of different pre-selected training items; The training plan optimization module identifies the content of the third reply text of the target user, and then adjusts and optimizes the training amount of the pre-selected training items to obtain an optimized training plan corresponding to the target user.

6. According to claim 5, a large model-based intelligent question-answering management system for training and teaching, characterized in that: The process of training the plan optimization module to identify the corresponding content of different reply texts is as follows: The reply text is regarded as a set of words, the grammar and word order in the reply text are ignored, and the reply text is divided into multiple reply participles; Match each reply word with the word library, identify the part of speech of each reply word and perform part of speech tagging; Discard the reply participles whose parts of speech are particles, conjunctions, prepositions and stop words; Count the word frequencies of different reply words and calculate the importance index of different reply words. The calculation formula is: Importance index = weight coefficient × word frequency; The response participles whose importance index is greater than the importance threshold are retained and recorded as important participles; If there are no important participles, the answer text is deemed meaningless and the target user is prompted to answer again; If the number of important participles is greater than or equal to one, the meanings of the important participles are identified, and the pre-selected training plan is optimized according to the meanings of the important participles.

7. According to the large model-based intelligent question-answering management system for training and teaching according to claim 1, it is characterized in that: The determination process of the validity determination module includes the following: Obtaining the physical health index of the target user as the first physical health index; Acquire the second physical characteristic data of the target user, and obtain the second real-time height DEG, the second real-time weight DEZ, and the second real-time body fat percentage ETZ corresponding to the target user; The second physical health index of the target user is calculated by the formula, and the calculation formula is as follows: ; Where b1 and b2 are weight coefficients with fixed values; A first deviation value is obtained by subtracting the standard physical health index from the first physical health index of the target user and taking the absolute value, and a second deviation value is obtained by subtracting the standard physical health index from the second physical health index and taking the absolute value; The standard physical health index is the physical health value of the target user under ideal conditions; the larger the first deviation value and the second deviation value, the worse the physical health of the target user.

8. The intelligent question-answering management system for training and teaching based on a large model according to claim 7 is characterized in that: The determination process of the validity determination module also includes: The first deviation value of the target user is compared with the second deviation value, and if the first deviation value of the target user is greater than or equal to the second deviation value, the target user continues to be trained using the optimized training plan; If the first deviation value of the target user is less than the second deviation value, the real-time training result of the target user is compared with the expected training result. When the real-time training result is greater than or equal to the expected training result, no operation is performed; when the real-time training result is less than the expected training result, it is determined that the optimized training plan is invalid for the target user, and the optimized training plan is adjusted through questions and answers to obtain an adjusted training plan; Among them, the real-time training results are the actual improvement of the target user after setting the training goal, and the expected training results are the expected improvement after setting the training goal; When making adjustments, the reasons for failure of the optimized training plan can be obtained based on data monitoring indicators, and corresponding adjustments can be made accordingly.

9. The large model-based intelligent question-answering management system for training and teaching according to claim 8, characterized in that: The reasons for failure include: unreasonable goal setting, insufficient training intensity, insufficient recovery, deviation in action execution, and mismatched nutritional intake; Adjustments include: renegotiating training goals, increasing training intensity or changing training mode, reducing training frequency or adding rest days, replacing training movements or adding corrective training, and adjusting nutrition plans or supplementation strategies.

10. A training and teaching intelligent question-answering management method based on a large model, characterized in that: In combination with a large model-based intelligent question-answering management system for training and teaching as described in any one of claims 1 to 9, the method comprises: Step S101, collecting the target user's physical characteristic data and historical training items, analyzing the target user's physical condition, and obtaining a pre-selected training plan for the target user; Step S102, optimizing the pre-selected training plan according to the question-and-answer text with the target user to obtain an optimized training plan for the target user; Step S103, collecting and analyzing the physical characteristic data of the target user for a period of time after the optimized training plan is executed, and determining the effectiveness of the optimized training plan; Step S104: If the optimized training plan is effective for the target user, the optimized training plan continues to be executed; if the optimized training plan is not effective for the target user, the optimized training plan is dynamically adjusted in real time.

Images