Bone joint rehabilitation training optimization method

Abstract

The invention belongs to the field of rehabilitation training, and particularly relates to a bone joint rehabilitation training optimization method which comprises the steps of information extraction, model generation and memory replacement. According to the scheme, a skeleton model generation method is adopted, a plurality of depth cameras are adopted to obtain limb data of a patient from different angles, the 3D human body skeleton model is generated and continuously updated, continuous tracking of human body postures is achieved, and the stability and flexibility of the 3D human body skeleton model are improved; a memory replacement method is adopted, video data are continuously learned when a patient carries out bone joint rehabilitation training through a long-short-term memory network, and on the premise that past knowledge is not forgotten, the structure of the long-short-term memory network is dynamically adjusted, a new node path is constructed, and unimportant nodes are removed, so that new joint movement knowledge is learned; and the continuous learning ability of the long-short-term memory network is improved.

Description

Technical Field

[0001] The invention relates to the field of rehabilitation training, and in particular to a bone and joint rehabilitation training optimization method. Background Art

[0002] The bone and joint rehabilitation training optimization method refers to the method of optimizing patient rehabilitation training through a 3D human skeleton model.

[0003] The existing patient posture capture technology has certain errors and occlusion problems in the 3D joint position data generated by the depth camera; in addition, the traditional long short-term memory network has the fatal disadvantage of catastrophic forgetting, and there is a technical problem that it is not suitable for analyzing and learning rehabilitation training videos with large data volumes, high real-time requirements, and fast update speeds. Summary of the invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a method for optimizing bone and joint rehabilitation training. In view of the fact that the existing patient posture capture technology has certain errors and occlusions in the 3D joint position data generated by the depth camera, this scheme adopts a skeleton model generation method, adopts multiple depth cameras to obtain the patient's limb data from different angles, generates and continuously updates the 3D human skeleton model, realizes the continuous tracking of the human posture, and improves the stability and flexibility of the 3D human skeleton model; in view of the technical problems that the traditional long and short-term memory network has the disadvantage of catastrophic forgetting and is not suitable for analyzing and learning rehabilitation training videos with large data volume, high real-time requirements and fast update speed, this scheme adopts a memory replacement method to realize the long and short-term memory network to continuously learn the video data when the patient is undergoing bone and joint rehabilitation training, and dynamically adjusts the long and short-term memory network structure without forgetting the past knowledge, constructs new node pathways and removes unimportant nodes to learn new joint movement knowledge, so as to improve the continuous learning ability of the long and short-term memory network.

[0005] The technical solution adopted by the present invention is as follows: The present invention provides a bone and joint rehabilitation training optimization method, the method comprising the following steps:

[0006] Step S1: information extraction, using M depth cameras to obtain depth information of the patient's limbs from different angles;

[0007] Step S2: Model generation, using a skeleton model generation method to generate and update a 3D human skeleton model;

[0008] Step S3: Memory replacement, using the memory replacement method to optimize the long short-term memory network, using the long short-term memory network to infer the similarity between the activities of body parts and the standard human posture of medical rehabilitation training, and detecting the patient's execution of the doctor's instructions for joint rehabilitation training.

[0009] Furthermore, in step S2, the skeleton model generation method specifically includes the following steps:

[0010] Step S21: using a pre-trained CNN network to process the depth information, generate 2D joint positions, and convert the 2D joint position data into 3D coordinates according to camera parameters to obtain a 3D human skeleton model;

[0011] Step S22: using all 3D human skeleton models, calculating joint positions, obtaining joint position vectors, and classifying the joints in the 3D human skeleton models according to anatomical structure functions to form joint groups;

[0012] Step S23: Continuous tracking of human body posture.

[0013] Further, in step S23, the human body posture continuous tracking specifically includes the following steps:

[0014] Step S231: Calculate the projection angle of the joint using the following formula: ;

[0015] In the formula, represents the projection angle of the joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, Represents the unit direction vector from the joint to the depth camera, Represents the direction vector from the joint to the depth camera;

[0016] Step S232: Calculate the occlusion degree of the joint, specifically, pre-set the reference threshold , if the projection angle is less than the reference threshold , then the joint is considered not to be blocked, and the blocking degree is set to 1, recorded as , if the projection angle is greater than or equal to the reference threshold , then it is considered that the joint is blocked, and the occlusion degree calculation formula is as follows: ;

[0017] In the formula, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, represents the projection angle of the current joint, represents the baseline threshold;

[0018] Step S233: Evaluate the reliability of the joint group, specifically, traverse and calculate the confidence of the joints in all joint groups, and calculate the confidence of the joint group according to the confidence of the joint and the occlusion degree. The formula used is as follows: ;

[0019] In the formula, Indicates that at time step At that time, 3D human skeleton model The confidence of each joint group, Represents the index of the 3D human skeleton model, represents the index of the joint group, Indicates 3D human skeleton model The number of detected joints in a joint group, represents the index of the joint, Indicates 3D human skeleton model The joint group The confidence of each joint, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint;

[0020] Step S234: calculating the comprehensive confidence, which is used to calculate the comprehensive confidence of all 3D human skeleton models according to the confidence of the joint group. Specifically, firstly calculating the ratio of the confidence of each joint group in each 3D human skeleton model to the cumulative sum of the confidence of all joint groups to obtain the average confidence, and then calculating the cumulative sum of the average confidence of all 3D human skeleton models to obtain the comprehensive confidence;

[0021] Step S235: updating the joint position vector of the current time step, specifically, obtaining the joint position vector of the current time step by adding the joint position vector of the previous time step and the comprehensive confidence of the current time step;

[0022] Step S236: Update the comprehensive confidence of the current time step, specifically, repeat steps S231 to S234 to obtain the comprehensive confidence, integrate the 3D human skeleton models generated by the depth camera according to their respective comprehensive confidences, and obtain the final 3D human skeleton model.

[0023] Furthermore, in step S3, the memory replacement method specifically includes the following steps:

[0024] Step S31: extracting activity features, specifically, using a 3DCNN network as a feature extractor, using the feature extractor to extract new long-term features and short-term features related to human activities from the 3D human skeleton model in real time, and recording the new long-term features and short-term features as input data;

[0025] Step S32: Network replacement.

[0026] Furthermore, in step S32, the network replacement specifically includes the following steps:

[0027] Step S321: Update the long-term memory weight vector. The formula used is as follows: ; ;

[0028] In the formula, represents the maximum value of the long-term memory weight vector, express The updated value of represents the minimum value of the long-term memory weight vector, express The updated value of represents the learning rate, represents the input data, Indicates the current time step hour In the The value of the dimension, and Respectively and No. Dimensions, Represents the global maximum value and outputs a and The largest scalar value across all dimensions of Represents the maximum value of each element, outputting a vectors of the same dimension, where each dimension represents the and The larger value of

[0029] The long-term memory weight vector is used to store the boundary value of the long-term feature in the long short-term memory network learning iteration process;

[0030] Step S322: Calculate the The matching error between a node and the current input data is calculated using the following formula: ;

[0031] In the formula, Indicates that at the current time step t, the first The matching error of the nodes to the input data is represents the square of the Euclidean distance, Indicates The weight vector of each node;

[0032] Step S323: Matching nodes, specifically, selecting the best matching node corresponding to the current input data. The best matching node is the node that is most similar to the input data, that is, the node with the smallest matching error. The formula used is as follows: ;

[0033] In the formula, Represents the best matching node for the current input data, Indicates The index of the smallest node;

[0034] Step S324: Calculate the activation value of the best matching node. The activation value is used to measure the response strength of the node to the input data. The formula used is as follows: ;

[0035] In the formula, represents the activation value of the best matching node, Represents the matching error of the best matching node to the input data;

[0036] Step S325: pre-set an activation threshold. Specifically, if the activation value is less than the preset threshold, it means that the current best matching node is not good enough to represent the input data, and a new node needs to be generated. Step S326 is executed. If the activation value is greater than or equal to the preset threshold, it means that the current best matching node can represent the input data, and there is no need to generate a new node.

[0037] Step S326: generating a new node, specifically, constructing a new node, wherein the initial weight of the generated new node is the mean of the sum of the input data and the best matching node weight vector;

[0038] Step S327: Update the regularization degree, the formula used is as follows: ;

[0039] In the formula, represents the regularization degree of the node, represents the degree of regularization after the node is updated, Representation Node The time decay factor, represents the regularization control parameter;

[0040] Step S328: Update the weight vector of the node. The formula used is as follows: ;

[0041] In the formula, Representation Node The weight vector of Indicates the updated node The weight vector of Representation Node The learning rate;

[0042] Step S329: node removal, specifically, calculating the removal threshold. If the regularization degree of any node is greater than or equal to the removal threshold, the node is retained. If the regularization degree of any node is less than the removal threshold, the node is considered unimportant and is removed. The calculation formula for the removal threshold is as follows: ;

[0043] In the formula, represents the removal threshold, represents the average regularization degree of all nodes, Represents the standard deviation of the normal distribution.

[0044] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0045] (1) In view of the fact that the 3D joint position data generated by the depth camera in the existing patient posture capture technology has certain errors and occlusion problems, this solution adopts a skeleton model generation method, uses multiple depth cameras to obtain patient limb data from different angles, generates and continuously updates the 3D human skeleton model, realizes continuous tracking of human posture, and improves the stability and flexibility of the 3D human skeleton model;

[0046] (2) In view of the shortcomings of catastrophic forgetting in traditional long-short-term memory networks, which are not suitable for analyzing and learning rehabilitation training videos with large data volumes, high real-time requirements, and fast update speeds, this scheme adopts a memory replacement method to enable the long-short-term memory network to continuously learn video data when patients undergo bone and joint rehabilitation training. Without forgetting past knowledge, the long-short-term memory network structure is dynamically adjusted to construct new node pathways and remove unimportant nodes to learn new joint movement knowledge, thereby improving the continuous learning ability of the long-short-term memory network. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of a flow chart of a bone and joint rehabilitation training optimization method provided by the present invention;

[0048] Figure 2 Schematic diagram of the process of step S2;

[0049] Figure 3 Schematic diagram of the process of step S23;

[0050] Figure 4 Schematic diagram of the process of step S3;

[0051] Figure 5 Schematic diagram of the process of step S32;

[0052] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0054] Example 1, see Figure 1 The present invention provides a bone and joint rehabilitation training optimization method, which comprises the following steps:

[0055] Step S1: information extraction, using M depth cameras to obtain depth information of the patient's limbs from different angles;

[0056] Step S2: Model generation, using a skeleton model generation method to generate and update a 3D human skeleton model;

[0057] Step S3: Memory replacement, using the memory replacement method to optimize the long short-term memory network, using the long short-term memory network to infer the similarity between the activities of body parts and the standard human posture of medical rehabilitation training, and detecting the patient's execution of the doctor's instructions for joint rehabilitation training.

[0058] Example 2, see Figure 1 to Figure 2 This embodiment is based on the above embodiment. In step S2, the skeleton model generation method specifically includes the following steps:

[0059] Step S21: using a pre-trained CNN network to process the depth information, generate 2D joint positions, and convert the 2D joint position data into 3D coordinates according to camera parameters to obtain a 3D human skeleton model;

[0060] Step S22: using all 3D human skeleton models, calculating joint positions, obtaining joint position vectors, and classifying the joints in the 3D human skeleton models according to anatomical structure functions to form joint groups;

[0061] Step S23: Continuous tracking of human body posture.

[0062] Further, in step S23, the human body posture continuous tracking specifically includes the following steps:

[0063] Step S231: Calculate the projection angle of the joint using the following formula: ;

[0064] In the formula, represents the projection angle of the joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, Represents the unit direction vector from the joint to the depth camera, Represents the direction vector from the joint to the depth camera;

[0065] Step S232: Calculate the occlusion degree of the joint, specifically, pre-set the reference threshold , if the projection angle is less than the reference threshold , then the joint is considered not to be blocked, and the blocking degree is set to 1, recorded as , if the projection angle is greater than or equal to the reference threshold , then it is considered that the joint is blocked, and the occlusion degree calculation formula is as follows: ;

[0066] In the formula, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, represents the projection angle of the current joint, represents the baseline threshold;

[0067] Step S233: Evaluate the reliability of the joint group, specifically, traverse and calculate the confidence of the joints in all joint groups, and calculate the confidence of the joint group according to the confidence of the joint and the occlusion degree. The formula used is as follows: ;

[0068] In the formula, Indicates that at time step At that time, 3D human skeleton model The confidence of each joint group, Represents the index of the 3D human skeleton model, represents the index of the joint group, Indicates 3D human skeleton model The number of detected joints in a joint group, represents the index of the joint, Indicates 3D human skeleton model The joint group The confidence of each joint, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint;

[0069] Step S234: calculating the comprehensive confidence, which is used to calculate the comprehensive confidence of all 3D human skeleton models according to the confidence of the joint group. Specifically, firstly calculating the ratio of the confidence of each joint group in each 3D human skeleton model to the cumulative sum of the confidence of all joint groups to obtain the average confidence, and then calculating the cumulative sum of the average confidence of all 3D human skeleton models to obtain the comprehensive confidence;

[0070] Step S235: updating the joint position vector of the current time step, specifically, obtaining the joint position vector of the current time step by adding the joint position vector of the previous time step and the comprehensive confidence of the current time step;

[0071] Step S236: Update the comprehensive confidence of the current time step, specifically, repeat steps S231 to S234 to obtain the comprehensive confidence, integrate the 3D human skeleton models generated by the depth camera according to their respective comprehensive confidences, and obtain the final 3D human skeleton model.

[0072] Example 4, see Figures 1 to 4 This embodiment is based on the above embodiment. In step S3, the memory replacement method specifically includes the following steps:

[0073] Step S31: extracting activity features, specifically, using a 3DCNN network as a feature extractor, using the feature extractor to extract new long-term features and short-term features related to human activities from the 3D human skeleton model in real time, and recording the new long-term features and short-term features as input data;

[0074] Step S32: Network replacement.

[0075] Example 5, see Figures 1 to 5This embodiment is based on the above embodiment. In step S32, the network replacement specifically includes the following steps:

[0076] Step S321: Update the long-term memory weight vector. The formula used is as follows: ; ;

[0077] In the formula, represents the maximum value of the long-term memory weight vector, express The updated value of represents the minimum value of the long-term memory weight vector, express The updated value of represents the learning rate, represents the input data, Indicates the current time step hour In the The value of the dimension, and Respectively and No. Dimensions, Represents the global maximum value and outputs a and The largest scalar value across all dimensions of Represents the maximum value of each element, outputting a vectors of the same dimension, where each dimension represents the and The larger value of

[0078] The long-term memory weight vector is used to store the boundary value of the long-term feature in the long short-term memory network learning iteration process;

[0079] Step S322: Calculate the The matching error between a node and the current input data is calculated using the following formula: ;

[0080] In the formula, Indicates that at the current time step t, the first The matching error of the nodes to the input data is represents the square of the Euclidean distance, Indicates The weight vector of each node;

[0081] Step S323: Matching nodes, specifically, selecting the best matching node corresponding to the current input data. The best matching node is the node that is most similar to the input data, that is, the node with the smallest matching error. The formula used is as follows: ;

[0082] In the formula, Represents the best matching node for the current input data, Indicates The index of the smallest node;

[0083] Step S324: Calculate the activation value of the best matching node. The activation value is used to measure the response strength of the node to the input data. The formula used is as follows: ;

[0084] In the formula, represents the activation value of the best matching node, Represents the matching error of the best matching node to the input data;

[0085] Step S325: pre-set an activation threshold. Specifically, if the activation value is less than the preset threshold, it means that the current best matching node is not good enough to represent the input data, and a new node needs to be generated. Step S326 is executed. If the activation value is greater than or equal to the preset threshold, it means that the current best matching node can represent the input data, and there is no need to generate a new node.

[0086] Step S326: generating a new node, specifically, constructing a new node, wherein the initial weight of the generated new node is the mean of the sum of the input data and the best matching node weight vector;

[0087] Step S327: Update the regularization degree, the formula used is as follows: ;

[0088] In the formula, represents the regularization degree of the node, represents the degree of regularization after the node is updated, Representation Node The time decay factor, represents the regularization control parameter;

[0089] Step S328: Update the weight vector of the node. The formula used is as follows: ;

[0090] In the formula, Representation Node The weight vector of Indicates the updated node The weight vector of Representation Node The learning rate;

[0091] Step S329: node removal, specifically, calculating the removal threshold. If the regularization degree of any node is greater than or equal to the removal threshold, the node is retained. If the regularization degree of any node is less than the removal threshold, the node is considered unimportant and is removed. The calculation formula for the removal threshold is as follows: ;

[0092] In the formula, represents the removal threshold, represents the average regularization degree of all nodes, Represents the standard deviation of the normal distribution.

[0093] Example 6, see Figures 1 to 5 This embodiment is based on the above embodiment. In step S22, the joint group specifically includes a trunk group, a head group, a left upper limb group, a right upper limb group, a left lower limb group and a right lower limb group. The trunk group includes the joints of the neck, chest and waist; the head group includes the head joints; the left upper limb group includes the joints of the left upper limb; the right upper limb group includes the joints of the right upper limb; the left lower limb group includes the joints of the left lower limb; and the right lower limb group includes the joints of the right lower limb.

[0094] Embodiment 7, see Figures 1 to 5 This embodiment is based on the above embodiment. In step S233, .

[0095] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0096] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0097] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A bone and joint rehabilitation training optimization method, characterized in that: The method comprises the following steps: Step S1: information extraction, using M depth cameras to obtain depth information of the patient's limbs from different angles; Step S2: Model generation, using a skeleton model generation method to generate and update a 3D human skeleton model; Step S3: Memory replacement, using the memory replacement method to optimize the long short-term memory network, using the long short-term memory network to infer the similarity between the activities of body parts and the standard human posture of medical rehabilitation training, and detecting the patient's execution of the doctor's instructions for joint rehabilitation training.

2. A bone and joint rehabilitation training optimization method according to claim 1, characterized in that: In step S2, the skeleton model generation method specifically includes the following steps: Step S21: using a pre-trained CNN network to process the depth information, generate 2D joint positions, and convert the 2D joint position data into 3D coordinates according to camera parameters to obtain a 3D human skeleton model; Step S22: using all 3D human skeleton models, calculating joint positions, obtaining joint position vectors, and classifying the joints in the 3D human skeleton models according to anatomical structure functions to form joint groups; Step S23: Continuous tracking of human body posture.

3. A bone and joint rehabilitation training optimization method according to claim 2, characterized in that: In step S23, the human body posture is continuously tracked, specifically comprising the following steps: Step S231: Calculate the projection angle of the joint using the following formula: ； In the formula, represents the projection angle of the joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, Represents the unit direction vector from the joint to the depth camera, Represents the direction vector from the joint to the depth camera; Step S232: Calculate the occlusion degree of the joint, specifically, pre-set the reference threshold , if the projection angle is less than the reference threshold , then the joint is considered not to be blocked, and the blocking degree is set to 1, recorded as , if the projection angle is greater than or equal to the reference threshold , then it is considered that the joint is blocked, and the occlusion degree calculation formula is as follows: ； In the formula, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint, represents the joint position vector, Indicates The joint position vectors of the depth cameras, represents the projection angle of the current joint, represents the baseline threshold; Step S233: Evaluate the reliability of the joint group, specifically, traverse and calculate the confidence of the joints in all joint groups, and calculate the confidence of the joint group according to the confidence of the joint and the occlusion degree. The formula used is as follows: ； In the formula, Indicates that at time step At that time, 3D human skeleton model The confidence of each joint group, Represents the index of the 3D human skeleton model, represents the index of the joint group, Indicates 3D human skeleton model The number of detected joints in a joint group, represents the index of the joint, Indicates 3D human skeleton model The joint group The confidence of each joint, Indicates 3D human skeleton model The joint group The degree of occlusion of each joint; Step S234: calculating the comprehensive confidence, which is used to calculate the comprehensive confidence of all 3D human skeleton models according to the confidence of the joint group. Specifically, firstly calculating the ratio of the confidence of each joint group in each 3D human skeleton model to the cumulative sum of the confidence of all joint groups to obtain the average confidence, and then calculating the cumulative sum of the average confidence of all 3D human skeleton models to obtain the comprehensive confidence; Step S235: updating the joint position vector of the current time step, specifically, obtaining the joint position vector of the current time step by adding the joint position vector of the previous time step and the comprehensive confidence of the current time step; Step S236: Update the comprehensive confidence of the current time step, specifically, repeat steps S231 to S234 to obtain the comprehensive confidence, integrate the 3D human skeleton models generated by the depth camera according to their respective comprehensive confidences, and obtain the final 3D human skeleton model.

4. The method for optimizing bone and joint rehabilitation training according to claim 3, characterized in that: In step S3, the memory replacement method specifically includes the following steps: Step S31: extracting activity features, specifically, using a 3DCNN network as a feature extractor, using the feature extractor to extract new long-term features and short-term features related to human activities from the 3D human skeleton model in real time, and recording the new long-term features and short-term features as input data; Step S32: Network replacement.

5. A bone and joint rehabilitation training optimization method according to claim 4, characterized in that: Furthermore, in step S32, the network replacement specifically includes the following steps: Step S321: Update the long-term memory weight vector. The formula used is as follows: ； ； In the formula, represents the maximum value of the long-term memory weight vector, express The updated value of represents the minimum value of the long-term memory weight vector, express The updated value of represents the learning rate, represents the input data, Indicates the current time step hour In the The value of the dimension, and Respectively and No. Dimensions, Represents the global maximum value and outputs a and The largest scalar value across all dimensions of Represents the maximum value of each element, outputting a vectors of the same dimension, where each dimension represents the and The larger value of The long-term memory weight vector is used to store the boundary value of the long-term feature in the long short-term memory network learning iteration process; Step S322: Calculate the The matching error between a node and the current input data is calculated using the following formula: ； In the formula, Indicates that at the current time step t, the first The matching error of the nodes to the input data is represents the square of the Euclidean distance, Indicates The weight vector of each node; Step S323: Matching nodes, specifically, selecting the best matching node corresponding to the current input data. The best matching node is the node that is most similar to the input data, that is, the node with the smallest matching error. The formula used is as follows: ； In the formula, Represents the best matching node for the current input data, Indicates The index of the smallest node; Step S324: Calculate the activation value of the best matching node. The activation value is used to measure the response strength of the node to the input data. The formula used is as follows: ； In the formula, represents the activation value of the best matching node, Represents the matching error of the best matching node to the input data; Step S325: pre-set an activation threshold. Specifically, if the activation value is less than the preset threshold, it means that the current best matching node is not good enough to represent the input data, and a new node needs to be generated. Step S326 is executed. If the activation value is greater than or equal to the preset threshold, it means that the current best matching node can represent the input data, and there is no need to generate a new node. Step S326: generating a new node, specifically, constructing a new node, wherein the initial weight of the generated new node is the mean of the sum of the input data and the best matching node weight vector; Step S327: Update the regularization degree, the formula used is as follows: ； In the formula, represents the regularization degree of the node, represents the degree of regularization after the node is updated, Representation Node The time decay factor, represents the regularization control parameter; Step S328: Update the weight vector of the node. The formula used is as follows: ； In the formula, Representation Node The weight vector of Indicates the updated node The weight vector of Representation Node The learning rate; Step S329: node removal, specifically, calculating the removal threshold. If the regularization degree of any node is greater than or equal to the removal threshold, the node is retained. If the regularization degree of any node is less than the removal threshold, the node is considered unimportant and is removed. The calculation formula for the removal threshold is as follows: ； In the formula, represents the removal threshold, represents the average regularization degree of all nodes, Represents the standard deviation of the normal distribution.

Images