Performance evaluation method and device for automatically and rapidly unfolding and folding tent

Abstract

The invention discloses a method and a device for evaluating the performance of an automatic and rapid unfolding and folding tent. The method comprises the following steps: acquiring a performance index test data set of the automatic and rapid unfolding and folding tent; the performance index test data set comprises an unfolding and folding type index test data set, an efficiency type index test data set and an environment adaptation type index test data set; each type of index test data set comprises a plurality of types of index test data sequences; preprocessing the performance index test data set to obtain a preprocessed data set; performing classification evaluation processing on each type of index test data set in the preprocessed data set to obtain a sub-index test value set; and performing fusion evaluation processing on the sub-index test value set to obtain a performance evaluation result value of the automatic rapid unfolding and folding tent.

Description

Technical Field

[0001] The present invention relates to the fields of performance evaluation and artificial intelligence, and particularly to a method and device for evaluating the performance of an automatically rapid unfolding and folding tent. Background Art

[0002] With the increasing demand for tents in fields such as outdoor activities and emergency rescue, automatically rapid unfolding and folding tents have received extensive attention due to their high efficiency and convenience. However, there are still many problems in the performance evaluation of automatically rapid unfolding and folding tents at present. Traditional evaluation methods mainly focus on the testing of single performance indicators, such as unfolding and folding time or wind resistance, lacking comprehensive consideration of multiple performance indicators. In addition, existing methods have deficiencies in data processing, without fully considering the integrity and time consistency of data, resulting in inaccurate and unreliable evaluation results. At the same time, there are no effective technical means for the classification evaluation and comprehensive evaluation of different categories of performance indicators, making it difficult to comprehensively reflect the comprehensive performance of the tent in actual use. These problems limit the scientificity and practicality of the performance evaluation of automatically rapid unfolding and folding tents, unable to provide strong technical support for product improvement and optimization, and also unable to meet the needs of users for high-quality tent products. Summary of the Invention

[0003] The present invention mainly solves the problem that there are no effective technical means for the classification evaluation and comprehensive evaluation of different categories of performance indicators in the prior art, making it difficult to comprehensively reflect the comprehensive performance of an automatically rapid unfolding and folding tent in actual use. The present invention discloses a method and device for evaluating the performance of an automatically rapid unfolding and folding tent.

[0004] In the first aspect of the embodiment of the present invention, a method for evaluating the performance of an automatically rapid unfolding and folding tent is disclosed, including:

[0005] S1, collecting a set of performance index test data of the automatically rapid unfolding and folding tent; the set of performance index test data includes a set of unfolding and folding type index test data, a set of efficiency type index test data, and a set of environmental adaptability type index test data; each set of index test data includes several types of index test data sequences;

[0006] S2, preprocessing the set of performance index test data to obtain a set of preprocessed data;

[0007] S3, performing classification evaluation processing on each set of index test data in the set of preprocessed data to obtain a set of sub-index test values;

[0008] S4, performing fusion evaluation processing on the set of sub-index test values to obtain a performance evaluation result value of the automatically rapid unfolding and folding tent.

[0009] Preprocessing the performance index test data set to obtain a preprocessed data set, including:

[0010] S21. Perform data cleaning on the performance index test data set to obtain a first data set;

[0011] S22. Perform time alignment on the first data set to obtain a second data set;

[0012] S23. Perform pattern discrimination on the second data set to obtain a third data set.

[0013] Classifying and evaluating each type of index test data set in the preprocessed data set to obtain a set of sub-index test values, including:

[0014] For each type of index test data set in the preprocessed data set, obtain the corresponding standard test data set; the standard test data set includes the standard values of the index test data of each type;

[0015] For each index test data sequence of each type in each type of index test data set, subtract the standard value of the index test data of the corresponding type to obtain a difference data sequence of the corresponding type;

[0016] For each type of index test data set, construct a difference data matrix using all types of difference data sequences;

[0017] Perform principal component analysis on the difference data matrix to obtain a coefficient matrix and a principal component matrix; each row vector of the principal component matrix is the difference value of the extracted principal component index at each test moment;

[0018] Perform sub-index calculation on the principal component matrix to obtain a sub-index vector corresponding to the index test data set of the category;

[0019] Use the sub-index vectors corresponding to all index test data sets to construct a set of sub-index test values.

[0020] The sub-index calculation process is expressed as:

[0021] t=(P T V + aI) -1 P T y,

[0022] V = QR -1 ,

[0023] Among them, t is the calculated sub-index vector, Q and R are the Q matrix and R matrix obtained by performing QR decomposition on the principal component matrix P respectively, V is the intermediate matrix, a is the largest eigenvalue of the principal component matrix P, y is the eigenvector of the principal component matrix P, and I is the identity matrix.

[0024] Performing a fusion evaluation process on the set of sub-index test values to obtain a performance evaluation result value of the automatic quick-opening and closing tent, including:

[0025] Using the set of sub-index test values to construct a test matrix; the row vectors of the test matrix are the sub-index vectors corresponding to the index test data sets of each category;

[0026] Constructing a pattern matching model for the test matrix and the intermediate matrix;

[0027] Solving the pattern matching model to obtain a coefficient matrix;

[0028] Performing a decomposition transformation process on the coefficient matrix to obtain an evaluation factor vector;

[0029] Performing a fusion evaluation calculation process on the evaluation factor vector to obtain a performance evaluation result value of the automatic quick-opening and closing tent.

[0030] The process of performing a decomposition transformation process on the coefficient matrix to obtain an evaluation factor vector includes:

[0031] Performing a decomposition process on the coefficient matrix to obtain a left decomposition matrix, a characteristic matrix, and a right decomposition matrix of the coefficient matrix;

[0032] The calculation expression of the decomposition process is:

[0033] Y = UAV, where U is the left decomposition matrix, Y is the coefficient matrix, A is the characteristic matrix, V is the right decomposition matrix, both U and V are orthogonal matrices, and A is a diagonal matrix;

[0034] Extracting the diagonal elements of the characteristic matrix to obtain an eigenvector;

[0035] Performing a linear fitting process on the elements and element serial number values of the eigenvector to obtain a factor polynomial;

[0036] Using the factor polynomial to calculate the mean value of each row vector of the coefficient matrix to obtain a corresponding calculated value;

[0037] Using the calculated values of all row vectors of the coefficient matrix to construct an evaluation factor vector.

[0038] The pattern matching model, its expression is:

[0039] min|vA - R|,

[0040] subject to AA T = I A ,

[0041] wherein, I A represents an identity matrix with the row dimension of the coefficient matrix A as the dimension, the coefficient matrix A represents the matrix to be solved, v represents an intermediate matrix, and R represents a test matrix.

[0042] In a second aspect of the embodiments of the present invention, a performance evaluation device for an automatically quickly deployable and retractable tent is disclosed. The device includes:

[0043] a memory storing executable program code;

[0044] a processor coupled to the memory;

[0045] The processor calls the executable program code stored in the memory to execute the performance evaluation method for the automatically quickly deployable and retractable tent.

[0046] In a third aspect of the embodiments of the present invention, a computer-storable medium is disclosed. The computer-storable medium stores computer instructions, which are used to execute the performance evaluation method for the automatically quickly deployable and retractable tent when called by a computer.

[0047] In a fourth aspect of the embodiments of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the performance evaluation method for the automatically quickly deployable and retractable tent.

[0048] The beneficial effects of the present invention are as follows:

[0049] The present invention provides a performance evaluation method for an automatically quickly deployable and retractable tent. By collecting multi-class performance index test data and combining technical means such as preprocessing, classification evaluation, and fusion evaluation, a comprehensive and accurate evaluation of the performance of the automatically quickly deployable and retractable tent is achieved.

[0050] The present invention comprehensively considers various performance indexes such as deployment and retraction type, efficiency type, and environmental adaptability type, and can comprehensively reflect the performance of the automatically quickly deployable and retractable tent in different usage scenarios, overcoming the limitation of traditional methods that only focus on a single index.

[0051] The present invention respectively conducts classification evaluation on different categories of index test data sets, and uses principal component analysis to extract key features, which can highlight the influence of main performance indexes, reduce the data dimension at the same time, and improve the evaluation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flowchart of the implementation of the method of the present invention. DETAILED DESCRIPTION

[0053] To better understand the content of the present invention, an embodiment is given here.

[0054] Figure 1 It is the implementation flowchart of the method of the present invention.

[0055] In the first aspect of the embodiment of the present invention, a performance evaluation method for an automatic quick unfolding and folding tent is disclosed, including:

[0056] S1, collecting a set of performance index test data of the automatic quick unfolding and folding tent; the set of performance index test data includes a set of unfolding and folding type index test data, a set of efficiency type index test data, and a set of environmental adaptability type index test data; each set of index test data includes several types of index test data sequences;

[0057] S2, preprocessing the set of performance index test data to obtain a set of preprocessed data;

[0058] S3, performing classification evaluation processing on each set of index test data in the set of preprocessed data to obtain a set of sub-index test values;

[0059] S4, performing fusion evaluation processing on the set of sub-index test values to obtain a performance evaluation result value of the automatic quick unfolding and folding tent.

[0060] The preprocessing of the set of performance index test data to obtain a set of preprocessed data includes:

[0061] S21, performing data cleaning processing on the set of performance index test data to obtain a first set of data;

[0062] S22, performing time alignment processing on the first set of data to obtain a second set of data;

[0063] S23, performing pattern discrimination processing on the second set of data to obtain a third set of data;

[0064] The data cleaning processing includes filling missing values, smoothing noisy data, and smoothing or deleting outliers;

[0065] The time alignment processing can adopt interpolation / extrapolation method, Lagrange three-point interpolation method, etc.;

[0066] The pattern discrimination processing includes:

[0067] For the data of each data attribute in the second data set, taking the data acquisition information of the data as the independent variable and the data value of the data as the dependent variable, performing autoregressive-moving average modeling to respectively obtain the regression models of the data attributes of the class;

[0068] Using the regression model, perform calculation processing on the independent variable to obtain a regression data value; determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the second data set, and if it is less than or equal to the first regression discrimination threshold, do not process the data;

[0069] Perform fusion processing on all the data after the execution mode discrimination processing of the second data set to obtain a third data set;

[0070] Through preprocessing steps such as data cleaning, time alignment, and mode discrimination, the present invention can effectively solve problems such as noise, missing values, and time deviation in test data, ensure the integrity and consistency of the data, and thus improve the reliability of the evaluation results.

[0071] Performing classification evaluation processing on each type of index test data set in the preprocessing data set to obtain a sub-index test value set, including:

[0072] For each type of index test data set in the preprocessing data set, obtain the corresponding standard test data set; the standard test data set includes the standard values of the index test data of each type;

[0073] For each type of index test data sequence in each type of index test data set, subtract the standard value of the index test data of the corresponding type respectively to obtain a difference data sequence of the corresponding type;

[0074] For each type of index test data set, use all types of difference data sequences to construct a difference data matrix;

[0075] Perform principal component analysis processing on the difference data matrix to obtain a coefficient matrix and a principal component matrix; each row vector of the principal component matrix is the difference value of the extracted principal component index at each test moment;

[0076] Perform sub-index calculation processing on the principal component matrix to obtain a sub-index vector corresponding to the index test data set of the category.

[0077] Use the sub-index vectors corresponding to all the index test data sets to construct a sub-index test value set;

[0078] The sub-index calculation processing has the following expression:

[0079] t=(P T V+aI) -1 P T y,

[0080] V = QR-1 ,

[0081] Among them, t is the calculated sub-index vector, Q and R are the Q matrix and R matrix obtained by performing QR decomposition on the principal component matrix P respectively, V is the intermediate matrix, a is the largest eigenvalue of the principal component matrix P, and y is the eigenvector of the principal component matrix P.

[0082] The data acquisition information may be acquisition time information;

[0083] Performing fusion evaluation processing on the set of sub-index test values to obtain the performance evaluation result value of the automatic quick-opening and closing tent, including:

[0084] Using the set of sub-index test values to construct a test matrix; the row vectors of the test matrix are the sub-index vectors corresponding to the index test data sets of each category;

[0085] Constructing a pattern matching model for the test matrix and the intermediate matrix;

[0086] Solving the pattern matching model to obtain a coefficient matrix;

[0087] Performing decomposition transformation processing on the coefficient matrix to obtain an evaluation factor vector;

[0088] Performing fusion evaluation calculation processing on the evaluation factor vector to obtain the performance evaluation result value of the automatic quick-opening and closing tent;

[0089] Performing decomposition transformation processing on the coefficient matrix to obtain an evaluation factor vector, including:

[0090] Performing decomposition processing on the coefficient matrix to obtain the left decomposition matrix, eigenmatrix, and right decomposition matrix of the coefficient matrix;

[0091] The calculation expression of the decomposition processing is:

[0092] Y = UAV,

[0093] Among them, U is the left decomposition matrix, Y is the coefficient matrix, A is the eigenmatrix, V is the right decomposition matrix, both U and V are orthogonal matrices, and A is a diagonal matrix;

[0094] Extracting the diagonal elements of the eigenmatrix to obtain an eigenvector;

[0095] Performing linear fitting processing on the elements and element serial number values of the eigenvector to obtain a factor polynomial;

[0096] The decomposition processing can be implemented by using the matrix singular value decomposition algorithm.

[0097] For the linear fitting process, the serial number value Ix of the characteristic vector element is used as the known independent variable, and the value of the characteristic vector element is used as the known dependent variable. A curve to be approximated is constructed using the known independent variable and the known dependent variable, and the curve fitting of the curve to be approximated is performed using the function approximation method to obtain a factor polynomial.

[0098] The characteristic vector is expressed as I a , I a =[λ1,λ2,…,λ N1 , where N1 is the number of elements included in the characteristic vector; for the curve fitting of the curve to be approximated using the function approximation method, the best uniform linear approximation method can be adopted. The factor polynomial f(Ix) has the following expression:

[0099] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0100] where P1 is the order of the factor polynomial f(Ix), and α0,α1,α2,…,α P1 are the coefficients of the factor polynomial f(Ix);

[0101] Using the factor polynomial, the mean value of each row vector of the coefficient matrix is calculated to obtain the corresponding calculated value;

[0102] Using the calculated values of all row vectors of the coefficient matrix, an evaluation factor vector is constructed.

[0103] The fusion evaluation calculation process includes:

[0104]

[0105] where F 1-α (m - 1,i) represents the 1 - α quantile of the F - distribution according to m - 1 and i, α is a preset proportionality factor, and its value can be 0.6, m is the length of the evaluation factor vector, θ i is the i - th element of the evaluation factor vector, and rs is the performance evaluation result value of the automatic fast - expanding and contracting tent;

[0106] The value distribution of the evaluation factor vector conforms to the F - distribution. Therefore, the quantiles of the F - distribution are used to weight it to make up for the differences in the values of each evaluation factor vector and obtain an accurate performance evaluation result value.

[0107] The expression of the pattern matching model is:

[0108] min|vA - R|,

[0109] subject to AA T = I A ,

[0110] wherein, I A represents an identity matrix with the row dimension of the coefficient matrix A as the dimension. The coefficient matrix A represents the matrix to be solved, v represents the intermediate matrix, and R represents the test matrix;

[0111] The pattern matching model can adopt numerical optimization algorithms such as genetic algorithms.

[0112] The expression for the principal component analysis process is:

[0113] P = CX,

[0114] wherein, P is the principal component matrix, C is the coefficient matrix, and X is the difference data matrix. The principal component analysis process can be implemented by the PCA algorithm. The principal component matrix and the coefficient matrix are both determined through the principal component analysis process;

[0115] The principal component matrix P is a square matrix;

[0116] In the second aspect of the present invention, a performance evaluation device for an automatic quick - deploying and retracting tent is disclosed. The device includes:

[0117] A memory storing executable program code;

[0118] A processor coupled to the memory;

[0119] The processor calls the executable program code stored in the memory to execute the performance evaluation method of the automatic quick - deploying and retracting tent.

[0120] In the third aspect of the present invention, a computer - storable medium is disclosed. The computer - storable medium stores computer instructions, and when the computer instructions are called by the computer, they are used to execute the performance evaluation method of the automatic quick - deploying and retracting tent.

[0121] In the fourth aspect of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the performance evaluation method of the automatic quick - deploying and retracting tent.

[0122] By constructing a pattern matching model and fusing evaluation calculations, the present invention can effectively fuse the classification evaluation results to obtain a comprehensive performance evaluation result value. This comprehensive evaluation method can comprehensively reflect the overall performance level of the tent, providing a scientific basis for the optimal design of the product and user selection.

[0123] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A performance evaluation method for automatically and quickly deploying and retracting a tent, characterized in that: include: S1, collecting a set of performance index test data for automatic rapid deployment and folding of tents; The performance index test data set includes a collection index test data set, an efficiency index test data set, and an environmental adaptability index test data set; each type of index test data set includes several types of index test data sequences; S2, preprocessing the performance indicator test data set to obtain a preprocessed data set; S3, performing classification evaluation processing on each type of indicator test data set in the preprocessed data set to obtain a sub-indicator test value set; S4, performing fusion evaluation processing on the sub-index test value set to obtain a performance evaluation result value of automatically and quickly deploying and retracting the tent.

2. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 1, characterized in that: include: The preprocessing of the performance indicator test data set to obtain a preprocessed data set includes: S21, performing data cleaning processing on the performance indicator test data set to obtain a first data set; S22, performing time alignment processing on the first data set to obtain a second data set; S23, performing pattern discrimination processing on the second data set to obtain a third data set.

3. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 1, characterized in that: The step of performing classification evaluation on each type of indicator test data set in the preprocessed data set to obtain a sub-indicator test value set includes: For each type of indicator test data set in the preprocessed data set, a corresponding standard test data set is obtained; the standard test data set includes a standard value of each type of indicator test data; Subtract each type of indicator test data sequence in each type of indicator test data set from the standard value of the corresponding type of indicator test data to obtain the corresponding type of difference data sequence; For each type of indicator test data set, all types of difference data sequences are used to construct a difference data matrix; Performing principal component analysis on the difference data matrix to obtain a coefficient matrix and a principal component matrix; each row vector of the principal component matrix is ​​the difference value of the extracted principal component index at each test time; Performing sub-index calculation processing on the principal component matrix to obtain a sub-index vector corresponding to the index test data set of the category; Using the sub-indicator vectors corresponding to all indicator test data sets, a sub-indicator test value set is constructed.

4. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 3, characterized in that: The sub-index calculation process is expressed as follows: t=(P T V+aI) -1 P T yes, V=QR -1 , Among them, t is the calculated index vector, Q and R are the Q matrix and R matrix obtained by QR decomposition of the principal component matrix P, V is the intermediate matrix, a is the maximum eigenvalue of the principal component matrix P, y is the eigenvector of the principal component matrix P, and I is the unit matrix.

5. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 4, characterized in that: The fusion evaluation process is performed on the sub-index test value set to obtain the performance evaluation result value of the automatic rapid tent deployment, including: Using the sub-indicator test value set, a test matrix is ​​constructed; the row vector of the test matrix is ​​the sub-indicator vector corresponding to each category of the indicator test data set; For the test matrix and the intermediate matrix, a pattern matching model is constructed; Solving the pattern matching model to obtain a coefficient matrix; Decompose and transform the coefficient matrix to obtain the evaluation factor vector; The evaluation factor vector is subjected to fusion evaluation calculation processing to obtain a performance evaluation result value of automatically and quickly deploying and retracting the tent.

6. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 5, characterized in that: The decomposition and transformation of the coefficient matrix to obtain the evaluation factor vector includes: Decomposing the coefficient matrix to obtain a left decomposition matrix, a characteristic matrix and a right decomposition matrix of the coefficient matrix; The decomposition process is calculated as follows: Y=UAV, Among them, U is the left decomposition matrix, Y is the coefficient matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix; Extracting the diagonal elements of the feature matrix to obtain a feature vector; Performing linear fitting processing on the elements and element sequence values ​​of the eigenvector to obtain a factor polynomial; Using the factor polynomial, the mean of each row vector of the coefficient matrix is ​​calculated to obtain a corresponding calculated value; An evaluation factor vector is constructed using the calculated values ​​of all row vectors of the coefficient matrix.

7. The performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in claim 5, characterized in that: The pattern matching model is expressed as follows: min|vA-R|, subject to AA T =I A , Among them, I A represents the identity matrix with the row dimension of the coefficient matrix A as its dimension, the coefficient matrix A represents the matrix to be solved, v represents the intermediate matrix, and R represents the test matrix.

8. A performance evaluation device for automatically and quickly deploying and retracting a tent, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the performance evaluation method for automatically and quickly deploying and retracting a tent according to any one of claims 1 to 7.

9. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the performance evaluation method for automatically and quickly deploying and retracting a tent according to any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the performance evaluation method for automatically and quickly deploying and retracting a tent as claimed in any one of claims 1 to 7.

Images