Case-based reasoning method for human-machine collaborative personalized exercise training driven by causal knowledge

Abstract

The application relates to the technical field of intelligent sports training, and particularly discloses a case reasoning method for personalized sports training driven by cause-effect knowledge and based on man-machine cooperation, which comprises the following steps: constructing a case library containing multiple cases and reconstructing cause-effect knowledge at different levels; retrieving a case most similar to a target case from the case library based on the weight of each description variable; identifying the difference between the training scheme variables of the target case and the retrieved similar case, performing counterfactual intervention and inference on any training scheme variable of the target case, and screening one or more new cases; when the actual result generated after the execution of the new case does not meet the expectation, executing an attribution process and generating different processing suggestions according to the attribution type; and storing the new case that does not meet the expectation in the case library and periodically reconstructing the cause-effect knowledge. The application can deeply integrate cause-effect science and man-machine interaction to perform personalized training scheme reasoning.

Description

Technical Field

[0001] This invention relates to the field of intelligent sports training technology, and more specifically to a causal knowledge-driven human-computer collaborative personalized sports training case reasoning method. Background Technology

[0002] Case-based reasoning technology generates causal knowledge from a case database using structural equation modeling, and then integrates this causal knowledge throughout the reasoning process to arrive at a training plan. However, current case-based reasoning technologies often fail to meet the personalized needs of sports training, especially competitive sports training, mainly due to a lack of supporting causal knowledge and insufficient collaboration between coaches and athletes.

[0003] Therefore, how to deeply integrate causal science with human-computer interaction to conduct personalized training scheme reasoning is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of the above problems, this invention proposes a causal knowledge-driven human-computer collaborative personalized sports training case reasoning method to overcome or at least partially solve the above problems.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A causal knowledge-driven human-computer collaborative personalized exercise training case reasoning method includes the following steps:

[0007] S1. Construct a case library containing multiple cases, where the observation data for each case consists of descriptive variables, training scheme variables, and athletic performance variables; based on all the observation data in the case library, perform causal knowledge reconstruction at different levels.

[0008] S2. On the inverse causal graph of descriptive variables and sports performance variables, the weight of each descriptive variable is calculated using the PageRank algorithm, and the case most similar to the target case is retrieved from the case library based on the weight of each descriptive variable.

[0009] S3. Identify the differences in training scheme variables between the target case and the retrieved similar cases, perform counterfactual intervention and inference on the target case using arbitrary training scheme variables, and select one or more new cases;

[0010] S4. Compare the actual athletic performance generated after the new case is executed with the original athletic performance. When the two do not match, receive feedback from the coach, execute the attribution process, and generate different handling suggestions based on the attribution type.

[0011] S5. When the execution result of a new case does not match the original motion performance, the new case is stored in the case library and causal knowledge is reconstructed periodically.

[0012] Furthermore, in S1, each case is defined as a triple (X, T, Y), where X is a set containing m descriptive variables, denoted as X = {x1, x2, ..., x...}. m These descriptive variables describe the case background, environment, or the state of the subject.

[0013] T is a set containing n training scheme variables, denoted as T = {t1, t2, ..., t}. n These training program variables are the interventions or actions implemented;

[0014] Y is a set containing k athletic performance variables, represented as Y = {y1, y2, ..., y...} k These scalar metrics of athletic performance are the results or outputs that need to be observed;

[0015] Case Library CB For a containing p A set of cases, denoted as CB = {( X 1, T 1, Y 1), ( X 2, T 2, Y 2), ..., ( X p , T p , Y p )}.

[0016] Furthermore, in S1, the process of reconstructing causal knowledge at different levels includes:

[0017] Determine the set of variables V XY = X∪Y, in the variable set V XY The causal discovery algorithm is executed to construct a description-representation causal graph;

[0018] Determine the set of variables V TY = T ∪ Y In the variable set V TY The causal discovery algorithm is executed to construct the training-performance causal graph;

[0019] Determine the set of variables V XTY = X ∪ T ∪ Y In the variable setV XTY The causal discovery algorithm is executed to construct a description-training-performance causal graph.

[0020] Furthermore, S2 includes:

[0021] Reverse the direction of all directed edges in the description-representation causal graph to obtain the reverse causal graph;

[0022] In the reverse causal graph, the PageRank algorithm is used to generate a PageRank score for each descriptive variable node, which serves as the weight of the descriptive variable node.

[0023] The distance between the target case and any case in the case library is calculated based on the weights of each descriptive variable node.

[0024] Sort all cases in the case library in ascending order of their distance from the target case, and select the top k cases as the search results.

[0025] Furthermore, the formula for calculating the distance between the target case and any case in the case library is as follows:

[0026]

[0027] in, d w ( Q C j ) represents the target case Q and the j-th case C in the case library. j The weighted distance between them; i represents the i-th description vector node, m represents the total number of description vector nodes in a case, w i q represents the weight of the i-th description vector node. i Let C represent the feature value of the i-th descriptive vector in the target case. ji This represents the feature value of the i-th descriptive vector of the j-th case in the case library.

[0028] Furthermore, the calculation process for the weights of each descriptive variable node using the PageRank algorithm is as follows:

[0029] Initialize the weights of all descriptive variable nodes to equal values, and update the weights of each descriptive variable node according to the following iterative formula until the weight values ​​of all descriptive variable nodes converge.

[0030] The formula for weight iteration update is as follows:

[0031]

[0032] in, To describe variable nodes x iIn the k Weights for +1 iteration; To describe variable nodes x i In the k The weights for the next iteration; d It is the damping factor; G R This is a reverse cause-effect graph; | V | represents the total number of nodes in the reverse causal graph; In( x i , G R (in the reverse causal graph) G R Middle pointer node x i The set of nodes; Out( x i , G R ) is a node x i In the reverse causality diagram G R The degree of exit in.

[0033] Furthermore, S3 includes:

[0034] S31. Compare the training scheme variables of the target case and any similar case, identify the training scheme variables with different values, and construct a set of difference variables Δ. T j ;

[0035] S32. Calculate the set of differential variables Δ T j power set P (Δ T j ), power set P (Δ T j Each element S in ) is a subset of one or more differential training scheme variables, representing a potential modification scheme;

[0036] S33. For each element S in the power set, construct a counterfactual intervention, which is to modify the training scheme variable that belongs to element S in the target case to the value of the corresponding training scheme variable in the similar case, while keeping the values ​​of other training scheme variables that do not belong to element S in the target case unchanged.

[0037] S34. Perform S31-S33 on all similar cases to generate a set of counterfactual interventions;

[0038] S35. Apply each counterfactual intervention in the counterfactual intervention set to the individual causal model corresponding to the target case, perform counterfactual inference, and calculate the latent values ​​of the motion performance variables under different counterfactual interventions;

[0039] S36. Compile all potential performances under counterfactual interventions into a list, with each entry containing: a complete candidate training program, the potential value of the performance variable, and the improvement relative to the original performance variable value; sort the list in descending order based on the improvement and select one or more new cases from it.

[0040] Furthermore, S4 includes:

[0041] S41. The actual values ​​of the athlete's performance variables after implementing the new case. Y actual Compared with original movement performance Y Q Compare, if Y actual Inferior Y Q If no failure occurs, it is considered a failure; if no failure occurs, the causal unexpectedness is calculated.

[0042] S42. When a failure or causal unexpectedness exceeds the threshold, a structured interface or guided question is provided, and error attribution is performed based on the feedback received from the coach. The attribution type is divided into incidental situational factors or structural model defects.

[0043] S43. Based on the attribution type, generate different treatment suggestions. For incidental situational factors, mark new cases as situational anomalous cases. For structural model defects, transform the received expert knowledge from the coach into one or more specific modification hypotheses for the structural causal model.

[0044] Furthermore, in S41, the calculation process for causal unexpectedness includes:

[0045] Reverse all directed edges in the description-training-representation causal graph to obtain the corresponding total variable reverse causal graph;

[0046] Run the PageRank algorithm on the total variable inverse causal graph for all variables ( X , T , Y Calculate a global causal weight vector. W XTY ;

[0047] The actual value of the motion performance vector is calculated using the causal weights corresponding to the motion performance variable Y. Y actual With potential valueY’ Q The weighted distance between them, as the causal unexpectedness, is calculated using the following formula:

[0048]

[0049] Among them, y i Let Y represent the i-th athletic performance variable, and let Y represent the set of athletic performance variables. This represents the i-th performance variable in the global causal weight vector. W XTY Normalized weights in This represents the latent value of the i-th athletic performance variable. This represents the actual value of the i-th performance variable.

[0050] Furthermore, in S5, after enhancing the structural causal model, it is stored in the case library as a new model, while the original old model is archived. When the new model performs poorly, it is rolled back to the previous old model.

[0051] As can be seen from the above technical solution, compared with the prior art, the present invention has the following beneficial effects:

[0052] This invention presents an intelligent closed-loop process that learns from experience, co-evolves with experts, and continuously improves its causal model through causal modification and retention. From knowledge discovery in causal reconstruction to precise matching in causal retrieval, and then to the generation of quantitative schemes for causal reuse, this framework integrates causal inference with case-based reasoning techniques, using causal knowledge generated from case sets to drive each stage of case-based reasoning. Furthermore, the closed loop of causal-case reasoning incorporates multiple reasoning processes collaborative with coaches, not only overcoming the limitations of traditional CBR but also pioneering a new paradigm of personalized decision support that deeply integrates causal science and human-computer interaction. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0054] Figure 1 This is a flowchart of the causal knowledge-driven human-computer collaborative personalized sports training case reasoning method provided in this embodiment of the invention;

[0055] Figure 2 This is a diagram illustrating the causal case reasoning framework provided in an embodiment of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] like Figures 1-2 As shown in the figure, this invention discloses a causal knowledge-driven human-computer collaborative personalized sports training case reasoning method, including the following steps:

[0058] S1. Causal Reconstruction: Construct a case library containing multiple cases, where the observation data of each case consists of descriptive variables, training scheme variables, and athletic performance variables; based on all the observation data in the case library, perform causal knowledge reconstruction at different levels.

[0059] S2. Causal Retrieval: On the inverse causal graph of descriptive variables and sports performance variables, the weight of each descriptive variable is calculated using the PageRank algorithm, and the case most similar to the target case is retrieved from the case library based on the weight of each descriptive variable.

[0060] S3. Causal reuse: Identify the differences in training scheme variables between the target case and the retrieved similar cases, perform counterfactual intervention and inference on the target case using arbitrary training scheme variables, and select one or more new cases;

[0061] S4. Causal Modification: Compare the actual athletic performance after the new case is executed with the original athletic performance. When the two do not match, receive feedback from the coach, execute the attribution process, and generate different handling suggestions based on the attribution type.

[0062] S5. Causal Preservation: When the execution result of a new case does not match the original motion performance, the new case is stored in the case library, and causal knowledge is reconstructed periodically.

[0063] The following is a further explanation of each of the above steps.

[0064] S1 Causal Reconstruction: The task of the causal reconstruction step is to generate causal knowledge from the case library.

[0065] Specifically, each case is defined as a triple (X, T, Y), where X is a set containing m descriptive variables, denoted as X = {x1, x2, ..., x...}. m These descriptive variables describe the background, environment, or state of the subject, such as the athlete's age, fatigue level, and weather conditions.

[0066] T is a set containing n training scheme variables, denoted as T = {t1, t2, ..., t}. n These training program variables are the interventions or actions implemented, such as training duration, number of strength training sets, and type of tactical drills. In causal inference, this is usually referred to as treatment.

[0067] Y is a set containing k athletic performance variables, represented as Y = {y1, y2, ..., y...} k These athletic performance scalars are the results or outputs that need to be observed, such as shooting percentage, 100-meter sprint time, and game points. In causal inference, this is usually referred to as the outcome.

[0068] Case Library CB For a containing p A set of cases, denoted as CB = {( X 1, T 1, Y 1), ( X 2, T 2, Y 2), ..., ( X p , T p , Y p Let V = X∪T∪Y be the set of all variables.

[0069] The overall goal of causal reconstruction is to reconstruct a three-level causal graph from the observational data of the case library CB, in order to obtain causal path knowledge at different levels. The specific process includes:

[0070] Determine the set of variables V XY = X∪Y, in the variable set V XY The causal discovery algorithm is executed to construct a description-representation causal graph. G XY = ( V XY , E XY This causal diagram focuses on the relationship between intrinsic states and outcomes, revealing descriptive variables. X With athletic performance Y The causal path between them, ignoring the training scheme for now. T The impact provides knowledge about "how the system operates in the absence of specific interventions?". For example, it might reveal "fatigue levels (...)". x iThis will directly affect shooting percentage. y j )decline".

[0071] Causal discovery algorithms can be PC or FCI, and the process includes: based on CB The data underwent a series of conditional independence tests. A ⊥ B | S ),in A , B ∈ V XY , S V XY \ { A , B Construct a causal framework and orient edges to produce a directed graph. G XY = ( V XY , E XY ).

[0072] Determine the set of variables V TY = T ∪ Y In the variable set V TY The causal discovery algorithm is executed to construct the training-performance causal graph. G TY = ( V TY , E TY This causal diagram focuses on the correlation between interventions and outcomes, revealing the training program. T With athletic performance Y The causal path between them, temporarily ignoring the athlete's initial state. X The differences provide a preliminary answer to the question, "Are different training programs effective?" For example, it might show that "increasing the duration of tactical drills ( t i ) and game score ( y k "Positive correlation." But this relationship may be spurious.

[0073] Determine the set of variables V XTY = X ∪ T ∪ Y In the variable set V XTYThe causal discovery algorithm is executed to construct a description-training-representation causal graph. G XTY = ( V XTY , E XTY This cause-effect graph is a global, comprehensive view that includes all variables. X , T , Y A unified causal model is proposed to reveal the complex interaction pathways among these factors, including confounding and mediation effects. This diagram can verify or revise [the model / model]. G XY and G TY The findings. For example, if in G TY There are edges in t i → y j But G XTY The edge in the middle disappeared, and it was replaced by a path. t i ← x k → y j Then a confounding variable was identified. x k Discovering mediating effects: for example, graphs G XTY May reveal the path x i → t j → y k This means describing variables x i By influencing the choice of training program t j This, in turn, affects the final performance. y k .

[0074] S2. Causal Retrieval: The task of the causal retrieval stage is to retrieve the most similar case to the input target case from the case library based on causal knowledge. Unlike the association-based similarity measure of traditional CBR, "causal retrieval" uses the causal knowledge learned in the causal reconstruction stage to determine the weights of descriptive feature variables on the "reverse causal graph" using the PageRank algorithm. This results in root features that influence athletic performance through multiple mediating paths having higher weights in the similarity measure, while the case similarity is independent of variables that have no impact on athletic performance. For example, sprinting ability may have a greater impact on a soccer striker's goal tally, but a smaller impact on a goalkeeper's save percentage.

[0075] Specifically, this invention provides a method for determining feature weights based on a reverse causal graph and PageRank. In the original causal graph, edges point from cause to effect; in the reverse graph, edges point from effect back to cause. Therefore, a feature node that serves as a common cause for multiple performance indicators becomes an authoritative node in the reverse graph, attracting multiple incoming chains. By calculating the centrality score of this node using the PageRank algorithm, its causal importance can be quantified, thereby generating objective feature weights that contain causal knowledge. The specific implementation steps are as follows:

[0076] 1) Obtain or construct a directed acyclic graph (DAG) representing the causal relationships between multiple feature variables, denoted as a causal graph. G =( V , E In this invention, this diagram is the description-representation causal graph constructed earlier. G XY ,in V Descriptive features X and performance characteristics Y The set of nodes, E Let be the set of directed edges representing direct causal relationships.

[0077] Reversing the direction of all directed edges in the description-representation causal graph yields a reverse causal graph, in which the original root cause node becomes the terminal node where influence converges.

[0078] 2) On the reverse cause-effect graph, the PageRank algorithm is used to generate a PageRank score for each descriptive variable node, which serves as the weight of the descriptive variable node; specifically, the weights of all descriptive variable nodes are initialized to equal values, and the weights of each descriptive variable node are updated according to the following iterative formula until the weights of all descriptive variable nodes converge.

[0079] The formula for weight iteration update is as follows:

[0080]

[0081] in, To describe variable nodes x i In the k Weights for +1 iteration; To describe variable nodes x i In the k The weights for the next iteration; d It is the damping factor; G R This is a reverse cause-effect graph; | V | represents the total number of nodes in the reverse causal graph; In( x i , G R (in the reverse causal graph) G R Middle pointer node x i The set of nodes; Out( x i , G R ) is a node x i In the reverse causality diagram G R The degree of exit in.

[0082] 3) Combine the converged descriptive feature nodes X = { x 1, x 2, ..., x n The PageRank score of the feature is used as the final weight for the corresponding feature, forming an n-dimensional feature weight vector. W = ( w 1, w 2, ..., w n This vector can be normalized.

[0083] 4) Calculate the distance between the target case and any case in the case library based on the weights of each descriptive variable node. The specific calculation formula is as follows:

[0084]

[0085] in, d w ( Q C j ) represents the target case Q and the j-th case C in the case library. jThe weighted distance between them; i represents the i-th description vector node, m represents the total number of description vector nodes in a case, w i q represents the weight of the i-th description vector node. i Let C represent the feature value of the i-th descriptive vector in the target case. ji This represents the feature value of the i-th descriptive vector of the j-th case in the case library.

[0086] 5) Sort all cases in the case library in ascending order of their distance from the target case, and select the top k cases as the search results. k can be specified by the coach, and the default value is 1.

[0087] S3. Causal Reuse: The core task of the causal reuse step is to diagnose and optimize the current athlete's training program. This embodiment of the invention introduces an innovative method based on Granular Counterfactual Inference in this step, aiming to answer the core question: "For the current athlete, to what extent would their athletic performance improve if different training programs were adopted?"

[0088] This method utilizes a constructed training-representation causal graph G TY It uses the corresponding Structural Causal Model (SCM) as the computational basis. Unlike traditional CBR which directly reuses the entire solution, this invention uses the retrieved similar cases C j Training scheme T Cj Consider it a collection of inspirations for improvement. By identifying the target case T Q Similar case T Cj By analyzing the differences in training variables, counterfactual interventions can be constructed and evaluated for any subset of variables. This means the system can explore various refined "hybrid schemes," such as "changing only training intensity," "changing only training frequency," or "changing both intensity and frequency," and predict the improvement of each scheme relative to current known performance. The implementation steps of this process are as follows:

[0089] S30. Obtain the target cases for current diagnosis and optimization. Q =( X Q , T Q , Y Q ),in X Q For the athlete's condition, T Q For the current training scheme, Y QThis represents the observed motion performance under this scheme. Simultaneously, it retrieves the k most similar cases output from the "causal retrieval" step. C 1, ..., C k Loading the trained-performance causal model already learned in the causal reconstruction phase. M .

[0090] For each retrieved similar case C j (j=1, ..., k) Perform the following S31-S33 operations:

[0091] S31. Identify discrepancy variables: Compare the training scheme variables of the target case and any similar case, identify the training scheme variables with different values, and construct a set of discrepancy variables Δ. T j = { t i | t i ∈ T and t i,Q ≠ t i,Cj};

[0092] S32. Generate intervention subsets: Calculate the set of differential variables Δ T j power set P (Δ T j (excluding the empty set), power set P (Δ T j Each element S in ) is a subset of one or more differential training scheme variables, representing a potential modification scheme;

[0093] S33. Constructing Counterfactual Interventions: Targeting Power Sets P (Δ T j For each element S in the equation, construct a counterfactual intervention: modify the training scheme variables belonging to element S in the target case to similar cases. C j The values ​​of the corresponding training scheme variables are kept constant, and the values ​​of other training scheme variables that are not part of element S in the target case remain unchanged. For example, if T Q ={ t 1=A, t 2=B, t 3=C}, T Cj ={ t 1=X,t 2=Y, t If 3 = C}, then Δ T j ={ t 1, t 2}. The generated interventions include: ① Modification t 1(do( t 1=X); ② Modify t 2(do( t 2=Y)); ③ Simultaneously modify t 1 and t 2(do( t (t1=X, t2=Y). By performing this operation on all k similar cases, the system will generate a large and diverse set of counterfactual interventions.

[0094] S34. Perform S31-S33 on all similar cases to generate a set of counterfactual interventions.

[0095] S35. Apply each counterfactual intervention from the counterfactual intervention set to the individual causal model corresponding to the target case, perform counterfactual inference, and calculate the latent values ​​of the sports performance variables under different counterfactual interventions; the counterfactual inference process is a standard three-step process:

[0096] (a) Abduction: This step only needs to be performed once for the target case Q, using all the observed facts of the target case Q. X Q , T Q , Y Q ), through structural causal model M Inverse inference of exogenous noise variables representing inherent athlete traits U Q The posterior distribution or expected value. This step utilizes the most complete information to complete an accurate model of the individual athlete, explaining why this athlete, under these conditions, received this training, and achieved this result.

[0097] (b) Action: For the original model M Apply the counterfactual intervention currently being evaluated. For example, for the intervention do( t 1=X, t If 2=Y), then the model will determine t 1 and t The equations in equation 2 are replaced with the following: t 1 = X and t 2 = Y, resulting in a modified model. M' .

[0098] (c) Prediction: In the modified model M' In this process, the individual traits obtained in step (a) are used. U Q Descriptive variables of the target case X Q The new athletic performance is calculated in a positive direction. Y The expected value. This expected value is the potential value under this specific intervention. Y' Q .

[0099] S36. Summarize all potential performances under counterfactual interventions into a list, each entry containing: a complete candidate training scheme (i.e. T Q The modified version after a subset), the latent value of the athletic performance variable, and the improvement Δ relative to the original athletic performance variable value. Y = Y' Q - Y Q According to the lifting amount Δ Y Sort the list in descending order (e.g., shorter time, improved score rate, etc.).

[0100] Next, the ranked list of candidate solutions is presented to the coaches. This list clearly shows the various possible fine-tuning options and their quantifiable expected effects, and is presented in comparison with the current performance, making it more valuable for decision-making.

[0101] For example, assuming the current 100-meter sprint time is 10.5 seconds, the system might output: "Current performance: 10.5 seconds." Based on this, the following optimization suggestions are proposed:

[0102] 1. Option A (increasing the weight only from 80kg to 100kg): Expected time 10.4 seconds (improvement of 0.1 seconds);

[0103] 2. Option B (increasing flexibility training duration by 30 minutes only): Expected time 10.45 seconds (improvement of 0.05 seconds);

[0104] 3. Option C (simultaneously adjust strength and flexibility training): Expected time 10.42 seconds (improvement of 0.08 seconds)...

[0105] Coaches can use this information, combined with their professional knowledge and competition goals, to select one or more optimal solutions as new cases for adoption, thus completing human-machine collaborative decision-making.

[0106] S4. Causal Modification: The causal modification stage is the core of this invention's human-machine collaborative knowledge evolution. Its task is to attribute the discrepancy between the system's prediction and the actual result after the new solution is implemented and produces results, and to collaborate with the coach to correct the underlying causal knowledge. This stage transforms "failures" or "unexpected" cases into valuable opportunities for system learning and evolution, rather than simply viewing them as errors. Its core idea is that when predictions do not match reality, there must be a reason that has not been captured by the model. Specifically, this includes:

[0107] S41. After executing the new case generated in S3, obtain new complete case data. C new = ( X actual , T final , Y actual ).in Y actual It represents the athlete's actual athletic performance after implementing the new case; it represents the actual value of the athlete's athletic performance variable after implementing the new case. Y actual Compared with original movement performance Y Q Compare, if Y actual Inferior Y Q If a failure occurs, it is considered a failure; if no failure occurs, the causal unexpectedness is calculated.

[0108] This step aims to quantify the degree of "abnormality" of the new case execution result, categorizing it into two cases: "failure" and "unexpected".

[0109] (a) Failure judgment: First, assess the actual performance of the new solution. Y actual Original performance before adoption of the solution Y Q Compare. If Y actual Inferior Y Q (For example, if the sprint time increases or the score rate decreases), it is judged as a failure. Failure cases are high-value learning signals, and the system will directly mark this case and proceed to S42 for attribution.

[0110] (b) Causality contingency calculation: If no failure occurs (i.e., Y actual ≥ Y QThe accuracy of the predictions will be further evaluated by calculating the "Causal Surprise Degree," a metric that utilizes a full-variable causal graph. G XTY The specific calculation process is as follows:

[0111] Reverse all directed edges in the description-training-representation causal graph to obtain the corresponding total variable reverse causal graph;

[0112] Run the PageRank algorithm on the total variable inverse causal graph for all variables ( X , T , Y Calculate a global causal weight vector. W XTY The reason for calculating the global causal weight vector for all variables is to evaluate the causal similarity between the potential and actual values ​​globally. The specific calculation process is the same as the feature weight determination method based on the reverse causal graph and PageRank proposed in the S2 causal retrieval section. Each variable in X, T, and Y has a weight value, which together constitute W. XTY Weight vector.

[0113] The actual value of the motion performance vector is calculated using the causal weights corresponding to the motion performance variable Y. Y actual With potential value Y’ Q The weighted distance between them, as the causal unexpectedness, is calculated using the following formula:

[0114]

[0115] Among them, y i Let Y represent the i-th athletic performance variable, and let Y represent the set of athletic performance variables. This represents the i-th performance variable in the global causal weight vector. W XTY The normalized weights in the formula are all normalized. Y Variable weights w yi The sum is 1. This represents the latent value of the i-th athletic performance variable. This represents the actual value of the i-th performance variable. Y has more than one variable; for example, in a 20km race walk, performance Y might include two variables: the first half time and the second half time. The first half time influences the second half time. When there are multiple Y variables, the sum of the weights of all performance variables in Y is normalized to 1. In other words, if there is only one Y variable, no weighting is needed.

[0116] The calculated SD With the preset threshold θ surprise Compare. If S D >θ surprise If the result is unexpected, it means that the existing causal structure model failed to accurately predict the outcome and attribution is required.

[0117] S42. When a failure or causal unexpectedness exceeds the threshold, a structured interface or guided question is provided, and error attribution is performed based on the received coach feedback; the attribution type is divided into incidental situational factors or structural model defects.

[0118] Among them, incidental situational factors refer to the coach's observation of a temporary, unmodeled variable. X The factors included (such as "poor sleep") suggest that this bias was caused by randomness or a specific situation, and the structural causal model itself may not be flawed.

[0119] The structural model flaw refers to the coach's decision to exclude all incidental factors and the assumption that the model may underestimate the negative impact of short-term neural fatigue following high-intensity strength training on explosive power. This directly points to the shortcomings of the current causal diagram. G XTY Or the structural equation parameters may be defective.

[0120] Below is an example of a human-computer collaborative attribution dialogue:

[0121] The system outputs: "Warning: A significant unexpected event has been detected. For the plan 'increasing the strength load to 100kg,' the system predicted that the 100-meter time would increase to 10.4 seconds, but the actual observed time was 10.48 seconds. The unexpectedness exceeds the threshold. Please assist in attributing the cause."

[0122] The system outputs: "During training or testing, were there any of the following unrecorded special circumstances? 1. Athlete's physical discomfort (such as a cold, muscle soreness)? 2. Abnormal venue or weather conditions? 3. Fluctuations in mental state? 4. Other special events?"

[0123] The coach typed: "The athlete reported poor sleep quality last night."

[0124] S43. Based on the attribution type, generate different treatment suggestions, and for incidental situational factors, apply them to new cases. C new Cases marked as contextually anomalous will be stored in the case library during subsequent causal retention, but may be assigned a lower weight or excluded during model retraining to avoid noise interference with the model. To address structural model deficiencies, the received expert knowledge from the coach is transformed into one or more specific modification hypotheses for the structural causal model, such as: "It is recommended to modify the causal graph..."G XTY "Add a negative causal edge from t_strength_load to y_start_reaction, or introduce a new mediator variable 'neural fatigue'", the system presents this hypothesis to the coach and requests confirmation.

[0125] S5. Causal Preservation: The causal preservation stage is responsible for solidifying new knowledge and experience, enabling the long-term evolution of the system. This stage ensures that each reasoning cycle provides a richer and more accurate foundation for the next. It not only preserves cases, but more importantly, it dynamically updates the causal graph of the entire system based on the conclusions of the "causal modification" stage. Specifically, it includes:

[0126] S51. Case Enhancement and Conditional Storage:

[0127] Case enhancement and conditional storage: This step is conditional. First, the evaluation results of the causal modification step are checked: the new solution is judged to have failed if and only if its causal unexpectedness exceeds a preset threshold θ. surprise This step is performed only when the time is right.

[0128] Execute the action: If the conditions are met, the new case will be... C new = ( X actual , T final , Y actual The case is then enhanced by attaching metadata (annotations) obtained during the collaborative attribution process. Finally, this enhanced case is stored in the case library. CB .

[0129] Skip Operation: If the new solution does not lead to failure and the causal unexpectedness does not reach the threshold, it indicates that the existing structural causal model is sufficient to explain the outcome of this intervention. The system will not perform case storage to avoid case library redundancy and maintain model simplicity, and subsequent steps S52, S53, and S54 will also be skipped.

[0130] S52, Structural Causal Model Update: This step is triggered only after case storage was performed in S51. The operation is executed based on the conclusion of the causal modification step:

[0131] If the cause is attributed to incidental situational factors, the existing cause-and-effect diagram will not be modified. G XTY and structural causal model M To maintain the stability of current knowledge.

[0132] If the attribution is due to a structural model flaw, and the coach has confirmed the need to modify the assumptions, a model update operation will be performed. This may include: Structural update: based on the assumptions confirmed by the coach, modifying the causal graph... G XTY Add or remove edges, and then re-estimate the structural causal model based on the updated graph structure and a case library containing new cases. M The parameters.

[0133] Parameter Update: If the cause-effect graph structure remains unchanged, but the parameter estimation is inaccurate, a new case study can be used. C new For the model M The relevant parameters are updated online (e.g., using Bayesian updates or gradient descent).

[0134] S53. Model Version Control and Archiving: To ensure system robustness and traceability, any structural modifications to the structural causal model will not directly overwrite the old model. Instead, it will archive the old model and save the new model as... G XTY_v1.1 This version control mechanism offers the following advantages: it allows tracking the evolution of system knowledge; it enables rapid rollback to a previous stable version if the updated model performs poorly; and it allows for comparative analysis of different model versions to evaluate learning effectiveness.

[0135] S54. Periodic Causal Reconstruction: In addition to immediate updates triggered by "failure" or "accident" cases, the system should also have a built-in periodic or case library-based trigger. For example, whenever 100 new cases are added to the case library, the system can automatically re-execute a complete causal reconstruction process to discover more macroscopic and fundamental structural changes that may occur in the data distribution.

[0136] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0137] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A causal knowledge-driven human-computer collaborative personalized exercise training case reasoning method, characterized in that, Includes the following steps: S1. Construct a case library containing multiple cases. The observation data for each case consists of descriptive variables, training scheme variables, and performance variables. Based on all the observation data in the case library, perform causal knowledge reconstruction at different levels. Each case is defined as a triple (X, T, Y), where X is a set containing m descriptive variables, represented as X = {x1, x2, ..., x...}. m These descriptive variables are variables that describe the case background, environment, or subject state; T is a set containing n training scheme variables, denoted as T = {t1, t2, ..., t}. n The training program variables are the applied interventions or actions; Y is a set containing k athletic performance variables, denoted as Y = {y1, y2, ..., y}. k These performance scalars represent the results or outputs that need to be observed; case library. CB For a containing p A set of cases, denoted as CB = {( X 1, T 1, Y 1), ( X 2, T 2, Y 2), ..., ( X p , T p , Y p )}; The process of reconstructing causal knowledge at different levels includes: Determine the set of variables V XY = X∪Y, in the variable set V XY The causal discovery algorithm is executed to construct a description-representation causal graph; Determine the set of variables V TY = T ∪ Y In the variable set V TY The causal discovery algorithm is executed to construct the training-performance causal graph; Determine the set of variables V XTY = X ∪ T ∪ Y In the variable set V XTY The causal discovery algorithm is executed to construct a description-training-representation causal graph; S2. On the inverse causal graph of descriptive variables and athletic performance variables, the weights of each descriptive variable are calculated using the PageRank algorithm, and based on the weights of each descriptive variable, the case most similar to the target case is retrieved from the case library; S2 includes: Reverse the direction of all directed edges in the description-representation causal graph to obtain the reverse causal graph; In the reverse causal graph, the PageRank algorithm is used to generate a PageRank score for each descriptive variable node, which serves as the weight of the descriptive variable node. The distance between the target case and any case in the case library is calculated based on the weights of each descriptive variable node. Sort all cases in the case library in ascending order of their distance from the target case, and select the top k cases as the search results; The calculation process for the weights of each descriptive variable node using the PageRank algorithm is as follows: Initialize the weights of all descriptive variable nodes to equal values, and update the weights of each descriptive variable node according to the following iterative formula until the weight values ​​of all descriptive variable nodes converge. The formula for weight iteration update is as follows: in, To describe variable nodes x i In the k Weights for +1 iteration; To describe variable nodes x i In the k The weights for the next iteration; d It is the damping factor; G R This is a reverse cause-effect graph; | V | represents the total number of nodes in the reverse causal graph; In( x i , G R (in the reverse causal graph) G R Middle pointer node x i The set of nodes; Out( x i , G R ) is a node x i In the reverse causality diagram G R Out of range; S3. Identify the differences in training scheme variables between the target case and the retrieved similar cases, perform counterfactual intervention and inference on the target case using arbitrary training scheme variables, and select one or more new cases; S4. Compare the actual athletic performance generated after the new case is executed with the original athletic performance. When the two do not match, receive feedback from the coach, execute the attribution process, and generate different handling suggestions based on the attribution type. S5. When the execution result of a new case does not match the original motion performance, the new case is stored in the case library and causal knowledge is reconstructed periodically.

2. The causal knowledge-driven human-machine collaborative personalized sports training case reasoning method as described in claim 1, characterized in that, The formula for calculating the distance between the target case and any case in the case library is: in, d w ( Q C j ) represents the target case Q and the j-th case C in the case library. j The weighted distance between them; i represents the i-th description vector node, m represents the total number of description vector nodes in a case, w i q represents the weight of the i-th description vector node. i Let C represent the feature value of the i-th descriptive vector in the target case. ji This represents the feature value of the i-th descriptive vector of the j-th case in the case library.

3. The causal knowledge-driven human-computer collaborative personalized sports training case reasoning method as described in claim 1, characterized in that, S3 include: S31. Compare the training scheme variables of the target case and any similar case, identify the training scheme variables with different values, and construct a set of difference variables Δ. T j ; S32. Calculate the set of differential variables Δ T j power set P (Δ T j ), power set P (Δ T j Each element S in ) is a subset of one or more differential training scheme variables, representing a potential modification scheme; S33. For each element S in the power set, construct a counterfactual intervention, which is to modify the training scheme variable that belongs to element S in the target case to the value of the corresponding training scheme variable in the similar case, while keeping the values ​​of other training scheme variables that do not belong to element S in the target case unchanged. S34. Perform S31-S33 on all similar cases to generate a set of counterfactual interventions; S35. Apply each counterfactual intervention in the counterfactual intervention set to the individual causal model corresponding to the target case, perform counterfactual inference, and calculate the latent values ​​of the motion performance variables under different counterfactual interventions; S36. Compile all potential performances under counterfactual interventions into a list, with each entry containing: a complete candidate training program, the potential value of the performance variable, and the improvement relative to the original performance variable value; sort the list in descending order based on the improvement and select one or more new cases from it.

4. The causal knowledge-driven human-computer collaborative personalized sports training case reasoning method as described in claim 1, characterized in that, S4 include: S41. The actual values ​​of the athlete's performance variables after implementing the new case. Y actual Compared with original movement performance Y Q Compare, if Y actual Inferior Y Q If no failure occurs, it is considered a failure; if no failure occurs, the causal unexpectedness is calculated. S42. When a failure or causal unexpectedness exceeds the threshold, a structured interface or guided question is provided, and error attribution is performed based on the feedback received from the coach. The attribution type is divided into incidental situational factors or structural model defects. S43. Based on the attribution type, generate different treatment suggestions. For incidental situational factors, mark new cases as situational anomalous cases. For structural model defects, transform the received expert knowledge from the coach into one or more specific modification hypotheses for the structural causal model.

5. The causal knowledge-driven human-computer collaborative personalized sports training case reasoning method as described in claim 4, characterized in that, In S41, the calculation process for the degree of causal unexpectedness includes: Reverse all directed edges in the description-training-representation causal graph to obtain the corresponding total variable reverse causal graph; Run the PageRank algorithm on the total variable inverse causal graph for all variables ( X , T , Y Calculate a global causal weight vector. W XTY ; The actual value of the motion performance vector is calculated using the causal weights corresponding to the motion performance variable Y. Y actual With potential value Y’ Q The weighted distance between them, as the causal unexpectedness, is calculated using the following formula: Among them, y i Let Y represent the i-th athletic performance variable, and let Y represent the set of athletic performance variables. This represents the i-th performance variable in the global causal weight vector. W XTY Normalized weights in This represents the latent value of the i-th athletic performance variable. This represents the actual value of the i-th performance variable.

6. The causal knowledge-driven human-machine collaborative personalized sports training case reasoning method as described in claim 4, characterized in that, In S5, after the structural causal model is enhanced, it is stored as a new model in the case library, while the original old model is archived. When the new model performs poorly, it is rolled back to the previous old model.

Images