Cooking professional skill training progress management and individualized guidance method and system

Abstract

The present application relates to the technical field of cooking management, in particular to a cooking professional skill training progress management and individualized guidance method and system, operation behavior data of trainees in the cooking professional skill training process is acquired and training behavior time sequence data is formed, an operation rhythm-performance fluctuation mapping model is constructed, tolerance ability state parameters, current training rhythm parameters and training progress parameters are calculated; on this basis, training rhythm suitability matching is performed, rhythm disturbance response data is acquired; the tolerance ability state parameters are dynamically calibrated using the rhythm disturbance response curve, and individualized training guidance instructions are generated. The present application can objectively depict the adaptability of trainees to training rhythm changes while maintaining the stability of training targets, accurately distinguish different abnormal reasons, realize the adaptive regulation of training rhythm and training progress, and thus improve the scientificity, pertinence and training efficiency of cooking professional skill training.

Description

Technical Field

[0001] This invention relates to the field of culinary management, specifically to a method and system for managing the progress of culinary professional skills training and providing personalized guidance. Background Technology

[0002] As culinary training increasingly incorporates intelligent and data-driven methods, trainees' operational behaviors, training progress, and skill mastery can be recorded and analyzed through computer systems. Modern culinary training systems can collect behavioral data such as operational sequences, operational rhythms, and error recovery times, and automatically evaluate training progress. In this technological environment, training systems not only focus on the final operational results but also attempt to analyze trainees' skill development trends and training efficiency through behavioral data analysis, in order to achieve intelligent management and personalized guidance throughout the training process.

[0003] Existing cooking training systems typically employ a fixed pace or uniform training schedule, primarily assessing trainees' progress by evaluating the final dish or skill score. Additionally, some systems incorporate basic data analysis or statistical methods, evaluating trainee progress based on the number of operations, time taken, or error frequency.

[0004] The inventors of this application have discovered the following technical problems with existing cooking training systems: different trainees have very different tolerances to training intensity and operating rhythm, and a uniform training rhythm can easily lead to accumulated fatigue, decreased efficiency, and even skill stagnation; at the same time, existing systems cannot determine whether a trainee's performance decline is due to fatigue or insufficient skills, nor can they dynamically adjust the training rhythm to match the trainee's current state; in addition, when trainees change cuisines, ingredients, or equipment, their skill performance may suddenly decline, but the system cannot distinguish whether this is due to skill degradation or skill transfer distortion caused by changes in the training context, resulting in inaccurate assessment of training progress. Summary of the Invention

[0005] This application provides a method and system for managing the progress and providing personalized guidance in culinary skills training, which solves the problems of existing culinary skills training where the training rhythm setting relies on experience, adjustments are delayed, and it is difficult to distinguish the causes of abnormalities.

[0006] To achieve the above objectives, the embodiments of this application disclose the following technical solutions:

[0007] On the one hand, this plan discloses methods for managing the progress of culinary skills training and providing personalized guidance, including the following steps:

[0008] The data collection and synchronization steps involve acquiring operational behavior data of trainees during culinary skills training. This operational behavior data includes at least operational rhythm data, operational continuity data, error distribution data, error correction behavior data, training interruption data, and operational sequence change data. The operational behavior data is then uniformly time-stamped to form training behavior time-series data.

[0009] The aforementioned operational behavior data characterizes the trainees' actual operational state during training from multiple dimensions, including operational rhythm, operational continuity, error distribution, and error correction behavior. This type of data directly reflects the stability, proficiency, and state fluctuations of trainees' skill execution. Using a unified time stamp to form training behavior time-series data helps maintain consistency across various operational behaviors over time, providing an aligned data foundation for subsequent state modeling and change analysis, and avoiding judgment biases caused by different sampling frequencies and operational granularities.

[0010] The state modeling and evaluation steps involve performing a correlation analysis between operational rhythm and operational performance fluctuations based on training behavior time-series data, constructing an operational rhythm-performance fluctuation mapping model, and calculating the tolerance state parameter representing the trainee's current training state. Simultaneously, the operational rhythm data is statistically processed to calculate the current training rhythm parameter representing the trainee's current training rhythm state. Based on training behavior time-series data and preset training plan information, the training progress parameter representing the trainee's current training progress state is calculated.

[0011] As an external manifestation of skill execution, the rhythm of operation often precedes or accompanies fluctuations in performance such as operational errors and a decline in continuity. By establishing a mapping relationship between the rhythm of operation and fluctuations in operational performance, complex changes in operational behavior can be transformed into quantifiable state parameters, thereby avoiding coarse-grained evaluation based solely on the number of single errors or completion status.

[0012] By introducing endurance status parameters, current training rhythm parameters, and training progress parameters respectively, a layered characterization of trainees' training status, training load, and training progress can be achieved, so that subsequent rhythm control and progress adjustment have clear parameter basis, rather than adjustments based on experience or fixed rules.

[0013] The rhythm suitability matching step matches and calculates the tolerance state parameters with the current training rhythm parameters to generate training rhythm matching results.

[0014] By matching the current training pace parameters with the appropriate range corresponding to the endurance state parameters, it is possible to dynamically determine whether the current training pace matches the trainee's actual state, thus avoiding fatigue caused by an excessively fast pace or a decrease in training efficiency caused by an excessively slow pace.

[0015] The controlled perturbation test procedure involves applying controlled rhythm perturbations to the current training rhythm parameters without changing the preset training objective constraints, and collecting operational behavior data generated by trainees under the rhythm perturbation conditions to form rhythm perturbation response data.

[0016] Applying rhythmic perturbations without changing the pre-set training objectives and constraints allows for observation of trainees' true response characteristics to rhythmic changes while maintaining the consistency of the training task. This process is equivalent to an online test of trainees' training tolerance and helps distinguish between occasional errors and state changes.

[0017] The parameter dynamic calibration step generates a training rhythm perturbation response curve based on the rhythm perturbation response data, and uses the training rhythm perturbation response curve to dynamically calibrate the endurance state parameters to obtain the updated endurance state parameters.

[0018] By dynamically calibrating the endurance state parameters through the training rhythm perturbation response curve, the state assessment results can be updated in real time as the trainee trains, thereby improving the accuracy and timeliness of the state assessment.

[0019] The multi-state anomaly diagnosis step, based on the updated tolerance state parameters and training behavior time series data, performs anomaly cause determination processing to obtain the anomaly cause determination result;

[0020] By distinguishing between fatigue, skill deficiency, and changes in training context, we can avoid mixing operational anomalies from different sources, thereby preventing incorrect adjustments to training pace or progress and improving the targeted nature of training management.

[0021] The personalized control instruction generation step adaptively adjusts the training progress parameters and the current training rhythm parameters based on the abnormality cause determination results and the training rhythm matching results, and generates corresponding personalized training guidance instructions.

[0022] Based on the comprehensive abnormality cause determination results and training rhythm matching results, personalized training guidance instructions are generated, so that the adjustment of training rhythm and training progress has a clear logical basis, and differentiated intervention is achieved for different trainees' training status.

[0023] Furthermore, rhythm stability features, rhythm mutation frequency features, and operational result fluctuation features characterize the relationship between operational rhythm and operational performance from three aspects: long-term stability, short-term variability, and result feedback, respectively. This combination can avoid the problem that a single feature cannot fully reflect the training state. By establishing a functional relationship between operational rhythm changes and operational performance fluctuations, multidimensional behavioral features can be uniformly mapped to tolerance state parameters, thereby forming interpretable state assessment results.

[0024] Furthermore, by determining the appropriate training rhythm range and judging the relationship between the ranges, the continuously changing training rhythm parameters can be transformed into clear state indicators, thereby providing a clear decision-making basis for subsequent adjustments and avoiding the problem of overly rigid judgments caused by using a single threshold.

[0025] Furthermore, by applying controlled amplitude and duration rhythm variations to the training rhythm parameters, observable operational responses can be guided from trainees without interfering with the completion of training objectives, thus providing the necessary experimental conditions for endurance assessment and parameter calibration. Applying perturbations in stages helps to obtain response characteristics at different intensities, enhancing the reliability of the assessment results.

[0026] Furthermore, by constructing training rhythm perturbation response curves and extracting rhythm perturbation response features, the overall response pattern of operational performance to rhythm changes can be characterized. This pattern reflects the trainee's true adaptability under different rhythm loads. Using these response features to correct the tolerance state parameters can prevent the state assessment results from remaining at the initial estimate for a long time, thereby improving the model's adaptability to changes in the training process.

[0027] Furthermore, by analyzing the overall response trend of operational performance to rhythm disturbances and combining the local change characteristics of operational performance in each skill dimension, it is possible to identify whether the abnormality presents an overall decline or a local shift, thereby distinguishing between fatigue state and skill deficiency state and avoiding misjudging short-term state fluctuations as skill problems.

[0028] Furthermore, changes in training cuisine, ingredient types, or equipment conditions can alter the skill application environment, potentially causing temporary fluctuations in operational performance. By introducing a skill transfer distortion assessment mechanism, factors leading to decreased tolerance due to situational changes can be excluded during anomaly diagnosis, thereby improving the accuracy of anomaly assessment results.

[0029] Furthermore, the operation frequency distribution model can reflect the actual level of trainees' engagement across different skill dimensions. By inferring the attention distribution state, it can identify trainees' attentional biases towards different skill dimensions during training. Based on this attention distribution state, training rhythm adjustment parameters and training content allocation parameters are generated, so that training regulation no longer depends solely on the overall state, but also takes into account the differences at the skill structure level.

[0030] Furthermore, by generating descriptions of rhythm adjustment criteria and creating training adjustment records, the traceability of the training rhythm and progress adjustment process can be achieved, enabling subsequent training adjustments to refer to historical state changes and control results, thereby forming a continuously optimized training management closed loop.

[0031] On the other hand, this solution discloses a culinary skills training progress management and personalized guidance system, including:

[0032] The data acquisition module is used to acquire operational behavior data of trainees during the culinary skills training process and generate training behavior time-series data;

[0033] The tolerance modeling module is used to construct an operation rhythm-performance fluctuation mapping model based on the training behavior time series data and to calculate the tolerance state parameters.

[0034] The rhythm matching and perturbation module is used to perform training rhythm matching calculations and apply controlled rhythm perturbations to generate rhythm perturbation response data.

[0035] The dynamic calibration module is used to generate a training rhythm perturbation response curve based on the rhythm perturbation response data and to dynamically calibrate the tolerance state parameters.

[0036] The anomaly detection and guidance module is used to perform anomaly cause detection and processing, and adaptively generate training progress parameters, current training rhythm parameters, and personalized training guidance instructions based on the anomaly cause detection results.

[0037] This invention effectively solves the problems of existing cooking skills training, such as reliance on experience in setting training rhythm, delayed adjustments, and difficulty in distinguishing the causes of anomalies, by collecting and analyzing trainee operational behavior data in a time-series manner and through multi-dimensional modeling and analysis. It introduces a collaborative evaluation mechanism of operational rhythm, performance, and training progress. By constructing an operational rhythm-performance fluctuation mapping model and introducing tolerance state parameters, the training system can quantitatively characterize trainees' adaptability to rhythm changes under different training conditions, thereby achieving precise matching and dynamic control of the training rhythm. Furthermore, by implementing controlled rhythm perturbation tests without changing the constraints of the training objectives, and dynamically calibrating the tolerance state parameters based on the perturbation response curve, the training evaluation results are no longer limited to static historical performance but can reflect the trainees' true response characteristics and potential changes in ability. Combined with a multi-state anomaly diagnosis mechanism, it can effectively distinguish different sources of anomalies such as fatigue, skill deficiencies, and changes in training context, avoiding unreasonable training adjustments due to misjudgments. In addition, this invention, through attention distribution state modeling, links and optimizes training rhythm adjustments with training content allocation, achieving more targeted and personalized training guidance, which helps improve training efficiency, reduce ineffective training burden, and promote the stable improvement and transfer application of trainees' professional skills. Attached Figure Description

[0038] Figure 1 This is a general flowchart of Embodiment 1 of the present invention;

[0039] Figure 2This is a flowchart of the state modeling and evaluation steps in Embodiment 1 of the present invention;

[0040] Figure 3 This is a flowchart illustrating the training rhythm suitability matching process in Embodiment 1 of the present invention.

[0041] Figure 4 This is a flowchart of the controlled disturbance test steps according to Embodiment 1 of the present invention.

[0042] Figure 5 This is a flowchart of the parameter dynamic calibration steps in Embodiment 1 of the present invention.

[0043] Figure 6 This is a flowchart of the multi-state anomaly diagnosis process according to Embodiment 1 of the present invention.

[0044] Figure 7 This is a flowchart illustrating the attention distribution and personalized control process in Embodiment 1 of the present invention.

[0045] Figure 8 This is a system structure block diagram of Embodiment 2 of the present invention. Detailed Implementation

[0046] Specific embodiments of the invention will now be described in detail. Although the invention is described in conjunction with these specific embodiments, it should be understood that the invention is not intended to be limited to these specific embodiments. Rather, these embodiments are intended to cover alternative, modified, or equivalent embodiments that may be included within the spirit and scope of the invention as defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. The invention may be practiced without some or all of these specific details. In other instances, well-known processes have not been described in detail so as not to unnecessarily obscure the invention.

[0047] When used in conjunction with the terms "comprising," "method comprising," or similar language in this specification and appended claims, the singular forms "a," "some," and "the" include plural references unless the context clearly indicates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0048] Example 1

[0049] This plan discloses methods for managing the progress of culinary skills training and providing personalized guidance, including the following steps:

[0050] The data collection and synchronization steps involve acquiring operational behavior data of trainees during culinary skills training. This operational behavior data includes at least operational rhythm data, operational continuity data, error distribution data, error correction behavior data, training interruption data, and operational sequence change data. The operational behavior data is then uniformly time-stamped to form training behavior time-series data.

[0051] In practice, operational behavior data can be acquired through various mature technologies. For example, operational trigger signals can be collected through smart kitchen equipment, the sequence of operational actions can be identified through video analysis modules, and error prompts and correction interactions can be recorded through training systems. The above technologies can be replaced or combined according to the training scenario, but all must ensure the consistency of the data over time.

[0052] This step aims to provide a unified, continuous, and traceable data foundation for subsequent operational rhythm analysis, endurance modeling, and dynamic adjustment of training rhythm. By collecting data on trainees' operational rhythm, operational continuity, error distribution, error correction behavior, training interruption, and operational sequence changes during culinary skills training, and by uniformly time-stamping these data, training behavior time-series data is formed. This allows trainees' operational behaviors during training to be accurately characterized in time-series form.

[0053] On the one hand, it avoids the problem of traditional training that only focuses on result scoring and ignores process behavior; on the other hand, it provides continuous and complete input data conditions for subsequent rhythm stability analysis, rhythm change analysis, and abnormal cause determination. For example, in a "cutting and matching training" scenario, the system can distinguish whether the student's mistake is due to unstable operation rhythm or a decrease in operation continuity due to training interruption.

[0054] Based on training behavior time-series data, a correlation analysis of operational rhythm and operational performance fluctuations is performed to construct an operational rhythm-performance fluctuation mapping model and calculate the tolerance state parameter representing the trainee's current training state. At the same time, time window division and statistical modeling processing are performed on the operational rhythm data to calculate the current training rhythm parameter representing the trainee's current training rhythm state. Based on training behavior time-series data and preset training plan information, the completion status of training tasks by trainees is statistically analyzed to calculate the training progress parameter representing the trainee's current training progress state.

[0055] Based on the time-series data of the training behavior, extract rhythm stability features, rhythm mutation frequency features, and operation result fluctuation features;

[0056] Establish a functional relationship between the changes in operational rhythm and the fluctuations in operational performance by combining the rhythm stability characteristics, the frequency characteristics of rhythm mutations, and the fluctuation characteristics of operational results.

[0057] Endurance state parameters are calculated based on functional relationships. These parameters include at least rhythm carrying threshold parameters and rhythm sensitivity parameters, which are used to quantitatively characterize the trainee's ability to adapt to changes in training rhythm under current training conditions.

[0058] In this embodiment, to quantitatively characterize the comprehensive impact of operational rhythm changes on operational performance fluctuations, the operational rhythm parameters and their variation characteristics are used as independent variables, and operational performance fluctuations are used as dependent variables to construct an operational rhythm-performance fluctuation mapping model. Specifically, based on the operational rhythm data extracted from the training behavior time-series data, the current operational rhythm parameter r(t), the operational rhythm change Δr(t), and the rhythm stability feature σr(t) of the trainee at time t are obtained. The operational rhythm change Δr(t) is calculated from the difference in operational rhythm parameters within adjacent time windows, and the rhythm stability feature σr(t) is calculated from the statistical fluctuation degree of the operational rhythm parameters within a preset time window.

[0059] Based on the above parameters, a functional relationship is established between changes in operational rhythm and fluctuations in operational performance, resulting in the operational rhythm-performance fluctuation mapping function, as shown in the following equation:

[0060] P(t) = f(r(t), Δr(t), σr(t));

[0061] Wherein, P(t) represents the fluctuation value of the trainee's operation performance at time t, which is used to comprehensively characterize the distribution data of operation errors, the change in operation continuity, and the degree of change in training interruption at that time; the function f(·) is a mapping function adaptively established by the parameterized modeling unit based on the time series data of training behavior, and its specific form can be any one of linear function, piecewise function, or nonlinear fitting function according to the training scenario.

[0062] r(t) is calculated from the number of operations completed per unit time or the operation interval;

[0063] Δr(t) represents the change in the operation rhythm parameter within adjacent time windows;

[0064] σr(t) is a stability index obtained by statistically calculating the operation rhythm parameters within a preset time window.

[0065] The tolerance state parameters are calculated based on the functional relationship. The tolerance state parameters include at least the rhythm carrying threshold parameter and the rhythm sensitivity parameter, which are used to quantitatively characterize the trainee's ability to adapt to changes in training rhythm under the current training conditions.

[0066] In this embodiment, to further transform the operational rhythm-performance fluctuation mapping result into state parameters that can be used for subsequent training rhythm matching and adjustment, a tolerance state parameter is calculated based on the operational rhythm-performance fluctuation mapping model. The tolerance state parameter is composed of a rhythm carrying threshold parameter and a rhythm sensitivity parameter, used to comprehensively characterize the trainee's tolerance and response characteristics to changes in training rhythm under current training conditions, specifically as follows:

[0067] T = α⋅θc + β⋅θs;

[0068] Where T represents the tolerance state parameter; θc represents the rhythm carrying threshold parameter, which characterizes the maximum training rhythm level that trainees can withstand before their performance fluctuations increase significantly; and θs represents the rhythm sensitivity parameter, which characterizes the degree to which performance fluctuations respond to changes in the operating rhythm.

[0069] The rhythm carrying threshold parameter θc can be calculated by analyzing the rhythm level when the fluctuation of the operation performance first exceeds the preset threshold during the gradual increase of the operation rhythm; the rhythm sensitivity parameter θs can be calculated by the ratio between the change in operation rhythm and the corresponding change in operation performance fluctuation.

[0070] Here, α and β are weighting coefficients used to adjust the relative influence of the rhythm carrying threshold parameter θc and the rhythm sensitivity parameter θs on the endurance state parameter T. The weighting coefficients α and β are not fixed parameters, but are set or dynamically adjusted according to the training stage, training objectives, and trainee training status.

[0071] In one feasible implementation, during the basic skill development stage or the training stage mainly focused on skill stability training, the influence weight of the rhythm carrying threshold parameter θc on the tolerance state parameter T can be appropriately increased, so that the value of α is greater than β, in order to highlight the trainee's ability to maintain operational stability under a higher training rhythm; during the skill refinement training stage or the training stage mainly focused on rhythm change adaptability training, the influence weight of the rhythm sensitivity parameter θs can be appropriately increased, so that the value of β is greater than α, in order to enhance the sensitive representation of the fluctuation of the trainee's operational performance with rhythm changes.

[0072] In another feasible implementation, the weighting coefficients α and β can be adaptively determined based on the trainee's historical training data. For example, based on the statistical results of the trainee's performance fluctuations under different training rhythm conditions, the importance of rhythm carrying capacity and rhythm sensitivity can be weighted so that the endurance state parameter T can more realistically reflect the trainee's comprehensive adaptability to changes in training rhythm.

[0073] The weighting coefficients α and β can be positive parameters, and their values ​​can be set to 0-1. In one embodiment, α+β=1 is satisfied to achieve weight normalization. In another embodiment, α and β can also be set independently without normalization constraints. This invention is not limited to the specific values ​​or ranges of α and β.

[0074] By introducing weighting coefficients α and β, the endurance state parameter can be flexibly adjusted to emphasize rhythm carrying capacity and rhythm change sensitivity under different training conditions and training objectives. This avoids the one-sidedness of a single rhythm indicator in assessing trainees' training adaptability and improves the accuracy and robustness of training rhythm assessment and control.

[0075] The core of this step lies in establishing the intrinsic relationship between changes in operational rhythm and fluctuations in operational performance, and based on this, forming tolerance state parameters that can be used for training and regulation. This is one of the important innovations of this scheme.

[0076] In practical operation, the system extracts rhythm stability features, rhythm mutation frequency features, and operation result fluctuation features from the training behavior time-series data formed in step 1, and inputs these features into the parametric modeling unit. This parametric modeling unit is not a simple statistical model, but a modeling module used to characterize the causal relationship between "rhythm change - performance change". It can adopt rule-driven modeling, regression modeling, or adaptive modeling based on training samples as alternative solutions.

[0077] By constructing an operational rhythm-performance fluctuation mapping model, the system can identify under what rhythmic change conditions trainees' operational performance begins to fluctuate significantly. Based on this mapping relationship, tolerance state parameters are further calculated, enabling the training system to no longer rely on experience to set the rhythm, but to dynamically quantify the trainee's rhythm tolerance and rhythm sensitivity based on their own performance.

[0078] This step transforms the previously difficult-to-observe "trainee's adaptability to the training rhythm" into a calculable and updatable state parameter, providing a basis for subsequent rhythm matching and dynamic adjustments. For example, in continuous stir-frying training, the system can identify a trainee whose operational errors increase sharply after the rhythm speeds up, thus determining that their rhythm sensitivity is high.

[0079] The tolerance state parameter is matched and calculated with the current training rhythm parameter to generate a training rhythm matching result, which is used to characterize whether the current training rhythm is in the appropriate range corresponding to the tolerance state parameter.

[0080] Based on the tolerance status parameters, determine the appropriate training rhythm range for the trainees;

[0081] Determine the interval relationship between the current training rhythm parameter and the suitable training rhythm interval, and generate a rhythm matching identifier;

[0082] In this embodiment, a suitable training rhythm interval is generated for each trainee based on the endurance state parameter, and the current training rhythm is matched using an interval determination method. Specifically, the lower limit rmin(T) and upper limit rmax(T) of the suitable training rhythm interval are calculated based on the endurance state parameter T, and the current training rhythm parameter r is compared with the suitable training rhythm interval to obtain the training rhythm matching result. The determination relationship can be expressed as follows:

[0083] M=I(r∈[rmin(T),rmax(T)])

[0084] Where M represents the rhythm matching identifier; I(·) is the indicator function. When the current training rhythm parameter r falls into the suitable training rhythm range, the rhythm matching identifier indicates that the current training rhythm is in the suitable range. When the current training rhythm parameter is higher than the upper limit of the suitable training rhythm range or lower than the lower limit of the suitable training rhythm range, the rhythm matching identifier indicates that the current training rhythm is in the state of exceeding the upper limit of the suitable range or lower than the lower limit of the suitable range, respectively.

[0085] The rhythm matching identifier is used to indicate any of the following states: the current training rhythm is in the appropriate range, exceeds the upper limit of the appropriate range, or is below the lower limit of the appropriate range.

[0086] The purpose of this step is to apply endurance status parameters to the rationality of the actual training rhythm, thereby avoiding the problems of decreased efficiency or fatigue accumulation caused by uniform rhythm training.

[0087] In its implementation, the system determines the appropriate training rhythm range for each trainee based on their tolerance status parameters, and then compares the current training rhythm parameters with this range to determine the interval relationship, generating a rhythm matching identifier. This rhythm matching identifier is not a simple binary judgment, but clearly distinguishes between states such as "within the appropriate range," "exceeding the upper limit of the appropriate range," and "below the lower limit of the appropriate range," providing a clear basis for subsequent adjustments.

[0088] The technical advantage of this step is that it enables the training system to identify in real time whether the current training pace is suitable for the trainee's current state, rather than passively adjusting after a large number of errors occur. For example, in knife skills training, when the system determines that the current pace exceeds the upper limit of the appropriate range, it can trigger the pace adjustment logic in advance to prevent a rapid decline in the quality of operation.

[0089] Without changing the constraints of the training objectives, a controlled rhythm perturbation is applied to the current training rhythm parameters, and operational behavior data generated by trainees under the rhythm perturbation conditions are collected to form rhythm perturbation response data; the constraints of the training objectives include at least the training task content, the training completion judgment criteria, and the target skill dimension requirements.

[0090] While keeping the training objective constraints unchanged, apply rhythmic changes with limited amplitude and controlled duration to the current training rhythm parameters;

[0091] The rhythm changes are applied in stages according to a preset perturbation strategy to create multiple different rhythm perturbation conditions;

[0092] The corresponding operational behavior data are collected under each rhythm disturbance condition to form the rhythm disturbance response data.

[0093] The innovation of this step lies in introducing controlled rhythm perturbation as an active testing mechanism to verify and calibrate the trainees' endurance state parameters.

[0094] During implementation, the system applies rhythmic changes with limited amplitude and controlled duration to the current training rhythm parameters without altering the training task content and objective constraints, and implements these changes in stages according to a preset perturbation strategy. This perturbation is not a random change of rhythm, but a controlled and traceable rhythmic change used to observe the immediate responses of the trainees' operational behavior.

[0095] The technical advantage of this step is that it improves the accuracy and stability of endurance assessment by actively perturbing rather than passively observing. Alternative approaches include using strategies with different perturbation amplitudes or durations, but all must adhere to the principle of "not altering the training objective constraints." For example, in stir-fry training, briefly and slightly increasing the tempo can be used to verify whether the trainee is at the tempo tolerance boundary.

[0096] Based on the rhythm perturbation response data, a training rhythm perturbation response curve is generated, and the tolerance state parameters are dynamically calibrated using the training rhythm perturbation response curve to obtain the updated tolerance state parameters.

[0097] Based on the rhythm disturbance response data, the correspondence between the rhythm change amplitude and the change in operational performance is extracted;

[0098] By fitting the corresponding relationships, a curve model representing the degree of operational response to rhythm changes is obtained;

[0099] Based on the curve model, rhythmic perturbation response features are extracted to characterize the operational performance in response to rhythmic perturbation.

[0100] The tolerance state parameters are corrected using a curve model to reflect the actual response characteristics of trainees to different rhythmic disturbance conditions.

[0101] In this embodiment, to quantitatively describe the response characteristics of trainees' operational performance to different rhythmic perturbation conditions, a training rhythmic perturbation response curve is constructed based on the rhythmic perturbation response data. Specifically, a response relationship is established between the change in operational rhythm Δr caused by the rhythmic perturbation and the corresponding change in operational performance Δp, thereby obtaining the training rhythmic perturbation response function, the expression of which is as follows:

[0102] R(Δr) = ΔrΔp;

[0103] Where R(Δr) represents the training rhythm perturbation response value, used to characterize the sensitivity of operational performance to rhythm perturbations; Δr is used to characterize the degree of change of the training rhythm relative to the baseline rhythm under controlled rhythm perturbation conditions. In one feasible implementation, the change in operational rhythm Δr can be calculated by comparing the current training rhythm parameters before and after the rhythm perturbation is applied, specifically expressed as the difference or change ratio between the training rhythm parameters after the perturbation and the training rhythm parameters before the perturbation.

[0104] The current training rhythm parameter can be characterized by the number of operations per unit time, the time interval of key operations, or the statistical characteristic parameters of the operation rhythm; therefore, the change in operation rhythm Δr can also be expressed as the change in the above-mentioned rhythm statistical characteristics under different rhythm conditions. This invention is not limited to the specific calculation method of the change in operation rhythm Δr; as long as it can objectively reflect the amplitude of training rhythm disturbance, it can be used as an effective source of Δr value.

[0105] Δp represents the change in operational performance fluctuation under corresponding rhythm disturbance conditions. In one feasible implementation, the change in operational performance Δp can be calculated by comparing operational performance evaluation indicators under rhythm disturbance conditions and under no-disturbance conditions. The operational performance evaluation indicators include at least one or more of the following: operational success rate, operational error amplitude, error occurrence frequency, operational stability, or operational continuity indicators.

[0106] By calculating the difference, rate of change, or normalizing the above-mentioned performance evaluation indicators before and after rhythm perturbation, the corresponding change in performance Δp can be obtained. Δp reflects the intensity and direction of the performance response to changes in training rhythm, thus characterizing the degree of impact of rhythm perturbation on performance.

[0107] The tolerance state parameters are corrected using a curve model to reflect the actual response characteristics of trainees to different rhythmic disturbance conditions.

[0108] This step is used to convert the rhythm disturbance response data collected in step 4 into a response curve that can be used for parameter correction, and is a key component of the "self-calibration mechanism" in this scheme.

[0109] The system performs fitting based on the correspondence between the amplitude of rhythm changes and changes in operational performance to obtain the training rhythm perturbation response curve, and then dynamically calibrates the tolerance state parameters accordingly. This process does not rely on a fixed model, but continuously corrects itself based on actual training behavior, thereby preventing the model from becoming ineffective as the training phase changes.

[0110] The technical effect of this step is to enable the tolerance state parameters to evolve with the training process, thereby improving stability and accuracy during long-term training. For example, when a trainee's response to rhythm changes weakens after multiple training sessions, the system can automatically increase their rhythm tolerance threshold parameter.

[0111] Based on the updated tolerance state parameters and the training behavior time series data, an abnormal cause determination process is performed to obtain an abnormal cause determination result, so as to distinguish whether the abnormal operation of the trainee is caused by fatigue, insufficient skills or changes in the training situation.

[0112] Based on the updated tolerance state parameters, analyze the overall response trend of operational performance to rhythmic disturbances.

[0113] By combining the changes in operational performance across different skill dimensions in the time-series training behavior data, it can be determined whether operational anomalies exhibit global consistency or local concentration.

[0114] Based on the overall response trend and the local change characteristics of the operational performance of each skill dimension in the training behavior time series data, the operational anomaly is determined to be one of the following: fatigue state, skill deficiency state, or training situation change state.

[0115] When a change in the training context is detected, the corresponding change in the training context is marked; the training context includes the training cuisine, ingredient type, or equipment conditions.

[0116] Based on the changes in the training context, the operational performance changes are analyzed in conjunction with the training rhythm perturbation response curve to determine whether they are consistent with the rhythm perturbation response characteristics.

[0117] When changes in operational performance are inconsistent with rhythmic disturbance response characteristics, the corresponding changes in operational performance are identified as skill transfer distortion, and excluded from the abnormal cause determination process as a basis for decreased tolerance.

[0118] In this embodiment, to further improve the accuracy of anomaly cause determination, the observed rhythm perturbation response features are compared and analyzed with the response features predicted based on the training rhythm perturbation response curve. Specifically, the degree of difference between the observed rhythm perturbation response value Robserved and the predicted rhythm perturbation response value Rexpected based on the current tolerance state parameters is calculated, thereby obtaining the skill transfer distortion determination index, the expression of which is as follows:

[0119] D=∣Robserved−Rexpected∣

[0120] Wherein, D represents the skill transfer distortion judgment index; when the skill transfer distortion judgment index exceeds the preset threshold, it is determined that the corresponding change in operation performance does not conform to the rhythm disturbance response characteristics, and thus the change in operation performance is identified as skill transfer distortion, and it is excluded as the basis for the decline in tolerance in the abnormal cause judgment and processing.

[0121] In one feasible implementation, Robserved can be calculated based on the rhythm perturbation response data collected during the rhythm perturbation test step.

[0122] Specifically, after applying controlled rhythm perturbation to the current training rhythm parameters, the corresponding change in rhythm Δr and change in performance Δp are calculated by collecting operational behavior data generated by trainees under the corresponding rhythm perturbation conditions, and the actual observed rhythm perturbation response value Robserved is calculated based on the relationship R(Δr)=Δr·Δp.

[0123] Robserved can objectively reflect the trainee's actual response to rhythm changes under actual rhythm disturbance conditions. Its value is directly derived from the measured operational behavior data during the training process.

[0124] In one feasible implementation, Rexpected can be calculated based on the tolerance state parameters determined before the update or during the historical training phase, and in combination with the corresponding rhythm perturbation amplitude, through an operational rhythm-performance fluctuation mapping model or a rhythm perturbation response curve.

[0125] Specifically, given the known rhythm disturbance amplitude Δr, the expected range of change in operational performance can be inferred based on the rhythm carrying threshold parameter and rhythm sensitivity parameter in the tolerance state parameters, and the corresponding expected rhythm disturbance response value Rexpected can be calculated accordingly.

[0126] Rexpected is used to characterize the level of response that a trainee should produce to rhythmic disturbances under normal training conditions, without considering the interference of immediate abnormal factors.

[0127] The purpose of this step is to avoid simply attributing all operational abnormalities to fatigue or lack of ability, which is a key innovation that distinguishes it from existing training systems.

[0128] The system analyzes the overall response trend of operational performance to rhythmic perturbations based on updated tolerance state parameters, and combines changes in operational performance across different skill dimensions to determine whether anomalies are globally consistent or locally concentrated. Simultaneously, a training context change labeling mechanism is introduced to avoid misjudging a decline in tolerance when changes in cuisine, ingredients, or equipment conditions are detected.

[0129] By comparing the actual observed rhythmic perturbation response with the predicted response, the system can identify skill transfer distortions and exclude them in the anomaly detection process. The technical benefits of this step are: significantly reduced false positive rate and improved targeting of training adjustments. For example, when switching from Chinese-style cutting training to Western-style cutting training, the system can identify that operational anomalies originate from contextual changes rather than fatigue.

[0130] Based on the results of the anomaly cause determination and the training rhythm matching results, the training progress parameters and the current training rhythm parameters are adaptively adjusted, and corresponding personalized training guidance instructions are generated.

[0131] Based on the training behavior time-series data, a model of the operation frequency distribution of trainees in different skill dimensions is constructed.

[0132] Based on the operation frequency distribution model, the attention distribution of trainees in each skill dimension is inferred;

[0133] In this embodiment, the student's attention distribution is quantitatively inferred based on the distribution of operation frequency across different skill dimensions. Specifically, the operation frequency corresponding to each skill dimension is normalized to obtain the student's attention distribution parameters across each skill dimension, calculated as follows:

[0134] Ak=fkj=1Kfj;

[0135] Where Ak represents the attention distribution parameter of the trainee in the k-th skill dimension; fk represents the operation frequency of the trainee in the k-th skill dimension; K represents the total number of skill dimensions, which at least include dimensions related to culinary professional skills training such as knife skills, heat control, seasoning order, and operational standardization. j=1Kfj represents the sum of the operation frequency characteristic values ​​of the trainee in all skill dimensions within the same statistical time window, used to normalize the operation frequency of each skill dimension; the attention distribution parameter is used to characterize the trainee's attention to different skill dimensions during training and serves as an important basis for adjusting the training rhythm and emphasizing the training content when generating personalized training guidance instructions.

[0136] Based on the attention distribution state, generate corresponding training rhythm adjustment parameters and training content allocation parameters;

[0137] When generating the personalized training guidance instructions, the training rhythm adjustment focus and training content emphasis corresponding to the training rhythm adjustment parameters and training content allocation parameters are adjusted synchronously in combination with the attention distribution state.

[0138] Based on the abnormality cause determination result, the training rhythm matching result, and the tolerance state parameter, corresponding rhythm adjustment basis description information is generated;

[0139] The rhythm adjustment is associated with the description information and the current training rhythm parameters and training progress parameters to form a traceable training adjustment record.

[0140] The training adjustment records are used as reference inputs for training guidance and parameter updates in subsequent training processes.

[0141] This step is a comprehensive application of the preceding steps, and its purpose is to transform the analysis results into actionable training guidelines.

[0142] Based on the anomaly cause determination results and training rhythm matching results, the system adaptively adjusts the training progress and training rhythm parameters, and simultaneously optimizes the focus of training rhythm adjustment and training content emphasis by combining the attention distribution status. The attention distribution status is inferred through an operation frequency distribution model to identify which skill dimensions the learner is under-engaged in.

[0143] In the dynamic adjustment logic, the rhythm matching identifier and tolerance state parameter serve as the threshold judgment criteria, directly affecting whether to trigger subsequent operations such as rhythm reduction, maintenance, or increase. The final generated training adjustment record is traceable and can serve as an important reference for subsequent training.

[0144] The technical benefits of this step are: enabling truly personalized training pace control, improving training efficiency, and reducing the risk of fatigue. For example, for trainees whose attention is focused on a single skill dimension for extended periods, the system can adjust the allocation of training content without increasing the overall pace.

[0145] Example 2

[0146] A culinary skills training progress management and personalized guidance system includes:

[0147] The data acquisition module is used to acquire operational behavior data of trainees during the culinary skills training process and generate training behavior time-series data;

[0148] The tolerance modeling module is used to construct an operation rhythm-performance fluctuation mapping model based on the training behavior time series data and to calculate the tolerance state parameters.

[0149] The rhythm matching and perturbation module is used to perform training rhythm matching calculations and apply controlled rhythm perturbations to generate rhythm perturbation response data.

[0150] The dynamic calibration module is used to generate a training rhythm perturbation response curve based on the rhythm perturbation response data and to dynamically calibrate the tolerance state parameters.

[0151] The anomaly detection and guidance module is used to perform anomaly cause detection and processing, and adaptively generate training progress parameters, current training rhythm parameters, and personalized training guidance instructions based on the anomaly cause detection results.

[0152] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation methods of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A method for managing the progress and providing personalized guidance in culinary skills training, characterized by: Includes the following steps: The data collection and synchronization steps involve acquiring operational behavior data of trainees during culinary skills training. This operational behavior data includes at least operational rhythm data, operational continuity data, error distribution data, error correction behavior data, training interruption data, and operational sequence change data. The operational behavior data is then uniformly time-stamped to form training behavior time-series data. The state modeling and evaluation steps involve performing a correlation analysis between operational rhythm and operational performance fluctuations based on training behavior time-series data, constructing an operational rhythm-performance fluctuation mapping model, and calculating the tolerance state parameters that characterize the trainee's current training state. Simultaneously, the operational rhythm data is statistically processed to obtain the current training rhythm parameters that characterize the trainee's current training rhythm state. Based on training behavior time-series data and preset training plan information, training progress parameters that characterize the current training progress status of trainees are calculated. The rhythm suitability matching step matches and calculates the tolerance state parameters with the current training rhythm parameters to generate training rhythm matching results. The controlled perturbation test procedure involves applying controlled rhythm perturbations to the current training rhythm parameters without changing the preset training objective constraints, and collecting operational behavior data generated by trainees under the rhythm perturbation conditions to form rhythm perturbation response data. The parameter dynamic calibration step generates a training rhythm perturbation response curve based on the rhythm perturbation response data, and uses the training rhythm perturbation response curve to dynamically calibrate the endurance state parameters to obtain the updated endurance state parameters. The multi-state anomaly diagnosis step, based on the updated tolerance state parameters and training behavior time series data, performs anomaly cause determination processing to obtain the anomaly cause determination result; The personalized control instruction generation step adaptively adjusts the training progress parameters and the current training rhythm parameters based on the abnormality cause determination results and the training rhythm matching results, and generates corresponding personalized training guidance instructions.

2. The method according to claim 1, characterized in that, In the state modeling and evaluation step, the construction of the operation rhythm-performance fluctuation mapping model includes: Based on the time-series data of the training behavior, extract rhythm stability features, rhythm mutation frequency features, and operation result fluctuation features; Based on the rhythm stability characteristics, rhythm mutation frequency characteristics, and operation result fluctuation characteristics, a functional relationship is established between operation rhythm changes and operation performance fluctuations. Endurance state parameters are calculated based on functional relationships. These parameters include at least rhythm carrying threshold parameters and rhythm sensitivity parameters, which are used to quantitatively characterize the trainee's ability to adapt to changes in training rhythm under current training conditions.

3. The method according to claim 1, characterized in that, In the rhythm suitability matching step, the generation of the training rhythm matching results includes: Based on the tolerance status parameters, determine the appropriate training rhythm range for the trainees; Determine the interval relationship between the current training rhythm parameter and the suitable training rhythm interval, and generate a rhythm matching identifier; The rhythm matching identifier is used to indicate any of the following states: the current training rhythm is in the appropriate range, exceeds the upper limit of the appropriate range, or is below the lower limit of the appropriate range.

4. The method according to claim 1, characterized in that, In the controlled perturbation test procedure, the controlled rhythm perturbations include: While keeping the training objective constraints unchanged, apply rhythmic changes with limited amplitude and controlled duration to the current training rhythm parameters; The rhythm changes are applied in stages according to the preset perturbation strategy to create multiple different rhythm perturbation conditions; Operational behavior data were collected under different rhythmic disturbance conditions to form rhythmic disturbance response data.

5. The method according to claim 1, characterized in that, The parameter dynamic calibration step, including the generation of the training rhythm perturbation response curve, comprises: Based on the rhythm disturbance response data, the correspondence between the rhythm change amplitude and the change in operational performance is extracted; By fitting the corresponding relationships, a curve model representing the degree of operational response to rhythm changes is obtained; Based on the curve model, rhythmic perturbation response features are extracted to characterize the operational performance in response to rhythmic perturbation. The tolerance state parameters are corrected using a curve model to reflect the actual response characteristics of trainees to different rhythmic disturbance conditions.

6. The method according to claim 1, characterized in that, In the multi-state anomaly diagnosis process, the anomaly cause determination process includes: Analysis of the overall response trend of operational performance to rhythmic perturbations based on updated tolerance state parameters; By combining the changes in operational performance across different skill dimensions in the time-series training behavior data, it can be determined whether operational anomalies exhibit global consistency or local concentration. Based on the overall response trend and the local change characteristics of the operational performance of each skill dimension in the training behavior time series data, the operational anomaly is determined to be one of the following: fatigue state, skill deficiency state, or training situation change state.

7. The method according to claim 1, characterized in that, The multi-state anomaly diagnosis process also includes: When a change in the training context is detected, the corresponding change in the training context is marked. Based on the changes in the training context, and combined with the training rhythm perturbation response curve, we analyze whether the changes in operational performance are consistent with the rhythm perturbation response characteristics. When changes in operational performance are inconsistent with rhythmic disturbance response characteristics, the corresponding changes in operational performance are identified as skill transfer distortion, and excluded from the abnormal cause determination process as a basis for decreased tolerance.

8. The method according to claim 1, characterized in that, The method further includes: Based on the training behavior time-series data, a model of the operation frequency distribution of trainees in different skill dimensions is constructed. Based on the operation frequency distribution model, the attention distribution of trainees in each skill dimension is inferred; Based on the attention distribution state, generate corresponding training rhythm adjustment parameters and training content allocation parameters; When generating the personalized training guidance instructions, the training rhythm adjustment focus and training content emphasis corresponding to the training rhythm adjustment parameters and training content allocation parameters are adjusted synchronously based on the attention distribution state.

9. The method according to claim 8, characterized in that, In the personalized control instruction generation step, the generation of the personalized training guidance instruction includes: Based on the abnormality cause determination result, the training rhythm matching result, and the tolerance state parameter, corresponding rhythm adjustment basis description information is generated; The rhythm adjustment is associated with the description information and the current training rhythm parameters and training progress parameters to form a traceable training adjustment record. The training adjustment records are used as reference inputs for training guidance and parameter updates in subsequent training processes.

10. A system for managing the progress of culinary skills training and providing personalized guidance, characterized in that: include: The data acquisition module is used to acquire operational behavior data of trainees during the culinary skills training process and generate training behavior time-series data; The tolerance modeling module is used to construct an operation rhythm-performance fluctuation mapping model based on the training behavior time series data and to calculate the tolerance state parameters. The rhythm matching and perturbation module is used to perform training rhythm matching calculations and apply controlled rhythm perturbations to generate rhythm perturbation response data. The dynamic calibration module is used to generate a training rhythm perturbation response curve based on the rhythm perturbation response data and to dynamically calibrate the tolerance state parameters. The anomaly detection and guidance module is used to perform anomaly cause detection and processing, and adaptively generate training progress parameters, current training rhythm parameters, and personalized training guidance instructions based on the anomaly cause detection results.

Images