CN115329673A - Gathering performance optimization design system and method of sports bra - Google Patents
Gathering performance optimization design system and method of sports bra Download PDFInfo
- Publication number
- CN115329673A CN115329673A CN202210985823.9A CN202210985823A CN115329673A CN 115329673 A CN115329673 A CN 115329673A CN 202210985823 A CN202210985823 A CN 202210985823A CN 115329673 A CN115329673 A CN 115329673A
- Authority
- CN
- China
- Prior art keywords
- tension
- vector
- scale
- neighborhood
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/12—Cloth
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Professional, Industrial, Or Sporting Protective Garments (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of intelligent clothing design and manufacture, and particularly discloses a gathering performance optimization design system and a gathering performance optimization design method for a sports bra. Therefore, an intelligent design scheme of gathering performance of the sports bra is constructed based on an artificial intelligence technology.
Description
Technical Field
The application relates to the field of intelligent garment design and manufacture, and more particularly to a gathering performance optimization design system and method for a sports bra.
Background
It has been found that when a person runs for 1 mile, the breasts are shaken for 135 meters, and the intense motion of the female breasts can injure the elastic fibrous tissue in the breasts, causing them to be permanently injured, resulting in loose, sagging and deformed breasts. The invention discloses a sports bra, which is invented for avoiding the injury of female breasts during sports and fitness.
In the design of a sports bra, the gathering performance is the core performance index. If the gathering performance of the sports bra is too strong, a larger binding feeling can be generated, and the user experience is influenced; and if the gathering performance of the sports bra is too poor, the bra cannot play a better supporting effect on the chest, so that the chest expands, sags and the like.
Therefore, in the preparation process of the sports bra, the gathering performance of the sports bra needs to be evaluated so as to optimize the gathering performance of the sports bra.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a gathering performance optimization design system and a gathering performance optimization design method for a sports bra, which are characterized in that tension values at a plurality of test points of the sports bra to be detected are measured, a deep neural network model is used as a feature extractor to extract correlation features of the tension values of the plurality of test points in different neighborhood scales, spatial topological features of the plurality of test points are introduced into the correlation features of the tension values to obtain classification feature representation containing spatial topology and multi-scale neighborhood correlation of the tension values, and then the classification feature representation is processed by a classifier to obtain a classification result used for representing whether the gathering performance of the sports bra to be detected meets a preset standard. Therefore, an intelligent design scheme of gathering performance of the sports bra is constructed based on an artificial intelligence technology.
Accordingly, according to an aspect of the present application, there is provided a gathering performance optimization design system for a sports bra, comprising:
the test data acquisition module is used for acquiring tension values of a plurality of test points of the bra to be tested;
the test data coding module is used for arranging the tension values of a plurality of test points of the to-be-detected motion bra into a tension input vector and then obtaining a multi-scale tension characteristic vector through the multi-scale neighborhood characteristic extraction module;
the test point spatial correlation module is used for constructing a topological matrix of the test points, wherein the characteristic value of each position on a non-diagonal position in the topological matrix is the distance between two corresponding test points, and the characteristic value of each position on a diagonal position in the topological matrix is zero;
the test point space pattern coding module is used for enabling the topological matrix to pass through a convolutional neural network model serving as a feature extractor to obtain a topological feature matrix;
the fusion module is used for multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classified characteristic vector;
the correction module is used for correcting the characteristic value of each position in the classification characteristic vector to obtain a corrected classification characteristic vector; and
and the optimization result generation module is used for enabling the corrected classification characteristic vectors to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the gathering performance of the bra to be detected meets a preset standard or not.
In the gathering performance optimization design system of the sports bra, the test data encoding module comprises: the tension value vectorization unit is used for arranging the tension values of a plurality of test points of the to-be-detected motion bra into the tension input vector; the first scale convolution coding unit is used for inputting the tension input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension correlation feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length; a second scale convolution coding unit, configured to input the tension input vector into a second convolution layer of the multi-scale neighborhood region feature extraction module to obtain a second neighborhood scale tension associated feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and the cascading unit is used for cascading the first neighborhood scale tension correlation characteristic vector and the second neighborhood scale tension correlation characteristic vector to obtain the multi-scale tension characteristic vector.
In the gathering performance optimization design system of the sports bra, the first scale convolution coding unit is further configured to perform one-dimensional convolution coding on the tension input vector by using a first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a first neighborhood scale tension associated feature vector; wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
In the gathering performance optimization design system of the sports bra, the second scale convolution coding unit is further configured to perform one-dimensional convolution coding on the tension input vector by using a second convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain a second neighborhood scale tension associated feature vector; wherein the formula is:
wherein b is the width of the second convolution kernel in the X direction, F is a parameter vector of the second convolution kernel, G is a local vector matrix operated with the convolution kernel function, m is the size of the second convolution kernel, and X represents a tension input vector.
In the gathering performance optimization design system of the sports bra, the test point spatial pattern coding module is further configured to perform convolution processing, pooling processing along channel dimensions, and nonlinear activation processing on input data respectively in forward transmission of layers by using each layer of the convolutional neural network model serving as the feature extractor, so that the last layer of the convolutional neural network model serving as the feature extractor outputs the topological feature matrix.
In the gathering performance optimization design system of the sports bra, the correction module is further configured to correct the feature values of the positions in the classification feature vector according to the following formula to obtain a corrected classification feature vector; wherein the formula is:
where μ and σ are the mean and variance, respectively, of the set of eigenvalues of the classification eigenvector, and α is a bias hyperparameter, v i Is the feature value of each position in the classified feature vector, N is the number of the feature values in the classified feature vector, v' i And classifying the characteristic value of each position in the characteristic vector after correction.
In the gathering performance optimization design system for the sports bra, the optimization result generation module is further configured to process the corrected classification feature vectors by using the classifier according to the following formula to obtain the classification result;
wherein the formula is: o = softmax { (W) n ,B n ):…:(W 1 ,B 1 ) I X }, wherein W 1 To W n As a weight matrix, B 1 To B n Is the offset vector and X is the corrected classification feature vector.
According to another aspect of the present application, there is also provided a gathering performance optimization design method for a sports bra, including:
acquiring tension values of a plurality of test points of the motion bra to be detected;
arranging tension values of a plurality of test points of the to-be-detected motion bra into a tension input vector, and then obtaining a multi-scale tension characteristic vector through a multi-scale neighborhood characteristic extraction module;
constructing a topological matrix of the plurality of test points, wherein the characteristic value of each position on the non-diagonal position in the topological matrix is the distance between the corresponding two test points, and the characteristic value of each position on the diagonal position in the topological matrix is zero;
enabling the topological matrix to pass through a convolutional neural network model serving as a feature extractor to obtain a topological feature matrix;
multiplying the multi-scale tension characteristic vector by the topological characteristic matrix to obtain a classification characteristic vector;
correcting the characteristic value of each position in the classified characteristic vector to obtain a corrected classified characteristic vector; and
and passing the corrected classification characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the gathering performance of the bra to be detected meets a preset standard or not.
In the gathering performance optimization design method for the sports bra, after arranging the tension values of a plurality of test points of the sports bra to be detected as a tension input vector, obtaining a multi-scale tension characteristic vector through a multi-scale neighborhood characteristic extraction module, the method includes: arranging the tension values of a plurality of test points of the to-be-detected motion bra into the tension input vector; inputting the tension input vector into a first convolution layer of the multi-scale neighborhood region feature extraction module to obtain a first neighborhood region scale tension correlation feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; inputting the tension input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale tension associated feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and cascading the first neighborhood scale tension correlation feature vector and the second neighborhood scale tension correlation feature vector to obtain the multi-scale tension feature vector.
In the gathering performance optimization design method of the sports bra, the tension input vector is input into the first convolution layer of the multi-scale neighborhood characteristic extraction module to obtain a first neighborhood scale tension related characteristic vector, and the first convolution layer of the multi-scale neighborhood characteristic extraction module is used for carrying out one-dimensional convolution coding on the tension input vector according to the following formula to obtain the first neighborhood scale tension related characteristic vector; wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory, in which computer program instructions are stored, and when the computer program instructions are executed by the processor, the processor executes the gathering performance optimization design method of the sports bra.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions, which when executed by a processor, cause the processor to execute the gathering performance optimization design method of a sports bra as described above.
Compared with the prior art, the gathering performance optimization design system and method for the sports bra are characterized in that tension values of a plurality of test points of the sports bra to be detected are measured, a deep neural network model is used as a feature extractor to extract association features of the tension values of the plurality of test points in different neighborhood scales, spatial topological features of the plurality of test points are introduced into the tension value association features to obtain classification feature representations including spatial topology and multi-scale neighborhood association of the tension values, and then the classification feature representations are processed by a classifier to obtain a classification result used for representing whether the gathering performance of the sports bra to be detected meets a preset standard. Therefore, an intelligent design scheme of gathering performance of the sports bra is constructed based on an artificial intelligence technology.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally indicate like parts or steps.
Fig. 1 illustrates a scene schematic diagram of a convergence performance optimization design system of a sports bra according to an embodiment of the present application.
FIG. 2 illustrates a block diagram of a gathering performance optimization design system for a sports bra in accordance with an embodiment of the present application.
Fig. 3 illustrates an architectural diagram of a gathering performance optimization design system of a sports bra according to an embodiment of the present application.
Fig. 4 illustrates a block diagram of a test data encoding module in a convergence performance optimization design system of a sports bra according to an embodiment of the present application.
Fig. 5 illustrates a flowchart of a gathering performance optimization design method for a sports bra according to an embodiment of the present application.
Fig. 6 illustrates a flowchart of obtaining multi-scale tension feature vectors in a gathering performance optimization design method of a sports bra according to an embodiment of the present application.
FIG. 7 illustrates a block diagram of an electronic device in accordance with an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only a few embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
In the design of a sports bra, the gathering performance is the core performance index. If the gathering performance of the sports bra is too strong, a larger binding feeling can be generated, and the user experience is influenced; and if the gathering performance of the sports bra is too poor, the bra cannot play a better supporting effect on the chest, so that the chest expands, sags and the like. Therefore, in the preparation process of the sports bra, the gathering performance of the sports bra needs to be evaluated so as to carry out the optimization design of the gathering performance of the sports bra.
Correspondingly, in the technical scheme of this application, the strain value that gathers together performance accessible preparation of motion brassiere is accomplished and is detected a plurality of test points of motion brassiere characterizes. It will be appreciated that if the gathering of the sports bra is strong at a test point, it will have a relatively large tension value at that test point. In addition, considering that the sports bra is an organic whole, the tension values of the test points are related, and the relationship is also presented in a certain space topological characteristic, namely, the sports bra is an organic whole, which not only needs to meet the preset requirement of the tension values of the test points, but also possibly meets the preset requirement on a related mode using the sports bra as a space carrier, so that whether the gathering performance of the sports bra is reasonable or whether the gathering performance needs to be optimized can be judged more accurately. From a simple and intuitive experience, when a female user wears the sports bra to do sports, the sports bra as a whole provides a function of supporting the chest (namely, the tension values of all test points need to meet the preset requirements), and the support provided by the sports bra as a whole needs to be adaptively adjusted based on all parts of the body, so that the function of supporting the chest can be provided, and the binding feeling and the injury to the user can be reduced as much as possible.
Specifically, in the technical scheme of this application, at first acquire the tension value of a plurality of test points of motion brassiere to be detected. Then, after arranging the tension values of the plurality of test points of the bra to be detected into a tension input vector, obtaining a multi-scale tension characteristic vector through a multi-scale neighborhood characteristic extraction module, namely, after constructing the tension value sequence of the plurality of test points into the tension input vector, extracting the association mode characteristics among the tension values in neighborhoods of different spans in the tension input vector through the multi-scale neighborhood characteristic extraction module. It should be understood that in the technical solution of the present application, a plurality of test points are provided on the sports bra, and different test points correspond to different body parts, so that the tension values of different test points need to extract the associated features in different neighborhood scales according to the difference of the body parts.
In the technical solution of the present application, the multi-scale neighborhood feature extraction module includes two one-dimensional convolutional layers (i.e., a first convolutional layer and a second convolutional layer). In the encoding process, the tension input vector is firstly input into a first convolution layer of the multi-scale neighborhood region feature extraction module to obtain a first neighborhood region scale tension related feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length. Then, the tension input vector is input into a second convolution layer of the multi-scale neighborhood region feature extraction module to obtain a second neighborhood region scale tension related feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length. And then, cascading the first neighborhood scale tension correlation characteristic vector and the second neighborhood scale tension correlation characteristic vector to obtain the multi-scale tension characteristic vector. In other examples of the present application, the multi-scale neighborhood feature extraction module may further include a greater number of one-dimensional convolution layers, which perform neighborhood-related feature extraction of different scales using one-dimensional convolution kernels of different lengths, which is not limited in this application.
And then, constructing a topology matrix of the test points, wherein the characteristic value of each position on the non-diagonal position in the topology matrix is the distance between the corresponding two test points, and the characteristic value of each position on the diagonal position in the topology matrix is zero. Then, the topological matrix is encoded by taking the convolutional neural network model as a feature extractor to obtain a topological feature matrix, that is, the convolutional neural network model is taken as a feature extractor to extract spatial topological features among the test points.
And then multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classification characteristic vector containing the correlation characteristic information of the tension values of different neighborhood scales and the space topological information among the plurality of test points. And then, the classification characteristic vector is processed by a classifier to obtain a classification result which is used for indicating whether the gathering performance of the bra to be detected meets the preset standard or not. Based on the classification result, whether the performance of gathering the sports bra needs to be optimized can be judged.
Particularly, in the technical solution of the present application, since the multi-scale tension eigenvector includes multi-scale associated features of tension parameters, that is, tension associated eigenvalues between sample scales of multiple test points, and the topological eigen matrix has more balanced scale features, when the multi-scale tension eigenvector and the topological eigen matrix are multiplied, there may be a disturbance of a special instance of the eigenvalue of the classified eigenvector.
Therefore, the information statistics normalization of the adaptive instance is performed on the classification feature vector, which is expressed as:
μ and σ are the mean and variance, respectively, of the set of eigenvalues of the classification eigenvector, and α is a bias hyperparameter.
The information statistical normalization of the self-adaptive example is implemented by taking a feature set as intrinsic prior information of statistical features of the self-adaptive example to perform dynamic generation type information normalization on a single feature value, and normalization mode length information of the feature set is used as bias and is used as invariance description in a set distribution domain, so that feature optimization for shielding disturbance distribution of a special example as far as possible is realized, and the classification effect of the classification feature vector is improved. That is, the accuracy of whether the gathering performance of the sports bra meets the predetermined standard is improved.
Based on this, this application provides a performance optimal design system is gathered together to motion brassiere, and it includes: the intelligent electric meter electric quantity obtaining unit is used for obtaining electric quantity information from each intelligent electric meter corresponding to each electric equipment to be monitored through wireless communication; the electric equipment state monitoring unit is used for acquiring the running state information of each electric equipment to be monitored, and the running state information is represented by binary data; an input data matrix generating unit, configured to generate an input data matrix from the power consumption amount information of each smart meter and the operating state information of each electrical device, where a value at each position of the input data matrix represents a relationship between one of the smart meters and one of the user devices; the neural network feature extraction unit is used for inputting the input data matrix into a convolutional neural network to obtain a first feature map; the signal space information calculation unit is used for calculating a weight value for compensating the wireless communication crosstalk of the intelligent electric meters based on the wireless transmitting power of each intelligent electric meter; the characteristic information weighting correction unit is used for weighting the first characteristic diagram according to the incidence relation corresponding to each characteristic value based on the weight value so as to obtain a second characteristic diagram; and the power utilization and electricity quantity information classification unit is used for enabling the second characteristic diagram to pass through a classifier so as to obtain a classification result for indicating whether the power utilization state of each piece of power utilization equipment is normal or not.
Fig. 1 illustrates a schematic view of a gathering performance optimization design system of a sports bra according to an embodiment of the present application. As shown in fig. 1, in an application scenario of the gathering performance optimization design system of the sports bra, first, tension values of the sports bra to be detected at a plurality of test points (e.g., T1 to Tn as illustrated in fig. 1) are obtained through a load cell (e.g., F as illustrated in fig. 1), and the test points are distributed on the sports bra to be detected in a predetermined topological pattern. And then, inputting the tension values and the topological data of the test points into a server (for example, S shown in fig. 1) deployed with a gathering performance optimization design algorithm of the brassiere, where the server can process the tension values by using the gathering performance optimization design algorithm of the brassiere to obtain an optimization result indicating whether the gathering performance of the brassiere to be detected meets a predetermined standard.
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary System
Fig. 2 illustrates a block diagram of a gathering performance optimization design system for a sports bra in accordance with an embodiment of the present application. As shown in fig. 2, a gathering performance optimization design system 100 for a sports bra according to an embodiment of the present application includes: the test data acquisition module 110 is used for acquiring tension values of a plurality of test points of the bra to be tested; the test data encoding module 120 is configured to arrange tension values of a plurality of test points of the to-be-detected sports bra into a tension input vector and then obtain a multi-scale tension feature vector through the multi-scale neighborhood feature extraction module; a test point spatial association module 130, configured to construct a topology matrix of the plurality of test points, where a characteristic value of each position at a non-diagonal position in the topology matrix is a distance between two corresponding test points, and a characteristic value of each position at a diagonal position in the topology matrix is zero; the test point space pattern coding module 140 is configured to pass the topology matrix through a convolutional neural network model serving as a feature extractor to obtain a topology feature matrix; the fusion module 150 is configured to multiply the multi-scale tension feature vector and the topological feature matrix to obtain a classification feature vector; a correction module 160, configured to correct the feature values at each position in the classification feature vector to obtain a corrected classification feature vector; and an optimization result generating module 170, configured to pass the corrected classification feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the gathering performance of the to-be-detected sports bra meets a predetermined standard.
Fig. 3 illustrates an architectural diagram of a convergence performance optimization design system of a sports bra according to an embodiment of the present application. As shown in fig. 3, first, tension values and distance information are obtained from a plurality of test points of the brassiere to be detected. Then, arranging the tension values of a plurality of test points of the brassiere to be detected into a tension input vector, then obtaining a multi-scale tension characteristic vector through a multi-scale neighborhood characteristic extraction module, and constructing a topological matrix of the plurality of test points by using distance information. And then, passing the topological matrix through a convolutional neural network model serving as a feature extractor to obtain a topological feature matrix. And then multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classification characteristic vector. And then, correcting the characteristic value of each position in the classification characteristic vector to obtain a corrected classification characteristic vector, and enabling the corrected classification characteristic vector to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the gathering performance of the to-be-detected motion bra meets a preset standard or not.
In the gathering performance optimization design system 100 for the sports bra, the test data acquisition module 110 is configured to acquire tension values of a plurality of test points of the sports bra to be detected. In the design of a sports bra, the gathering performance is the core performance index. If the gathering performance of the sports bra is too strong, a larger binding feeling can be generated, and the user experience is influenced; and if the gathering performance of the sports bra is too poor, the bra cannot play a better supporting effect on the chest, so that the chest expands, sags and the like. Therefore, in the preparation process of the sports bra, the gathering performance of the sports bra needs to be evaluated so as to carry out the optimization design of the gathering performance of the sports bra. Correspondingly, in the technical scheme of this application, gathering together performance accessible preparation of motion brassiere is accomplished and is detected the tension value representation of a plurality of test points of motion brassiere.
In the gathering performance optimization design system 100 for the sports bra, the test data encoding module 120 is configured to arrange tension values of a plurality of test points of the sports bra to be detected as a tension input vector and then obtain a multi-scale tension feature vector through a multi-scale neighborhood feature extraction module. That is, after the tension value sequence of the test points is constructed into a tension input vector, the multi-scale neighborhood feature extraction module is used for extracting the association mode features among the tension values in neighborhoods of different spans in the tension input vector. It should be understood that in the technical solution of the present application, a plurality of test points are provided on the sports bra, and different test points correspond to different body parts, so that the tension values of different test points need to extract the associated features in different neighborhood scales according to the difference of the body parts.
Fig. 4 illustrates a block diagram of a test data encoding module in a convergence performance optimization design system of a sports bra according to an embodiment of the present application. In an example, as shown in fig. 4, in the gathering performance optimization design system 100 of the sports bra, the test data encoding module 120 includes a tension value vectorization unit 121, configured to arrange tension values of a plurality of test points of the sports bra to be detected as the tension input vector; a first scale convolution coding unit 122, configured to input the tension input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension associated feature vector, where the first convolution layer has a first one-dimensional convolution kernel with a first length; a second scale convolution coding unit 123, configured to input the tension input vector into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale tension associated feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and a cascading unit 124, configured to cascade the first neighborhood scale tension related feature vector and the second neighborhood scale tension related feature vector to obtain the multi-scale tension feature vector. In the technical solution of the present application, the multi-scale neighborhood feature extraction module includes two one-dimensional convolutional layers (i.e., a first convolutional layer and a second convolutional layer).
In the encoding process, the tension input vector is firstly input into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension correlation feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length. Then, the tension input vector is input into a second convolution layer of the multi-scale neighborhood feature extraction module to obtain a second neighborhood scale tension correlation feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length. And then, cascading the first neighborhood scale tension correlation characteristic vector and the second neighborhood scale tension correlation characteristic vector to obtain the multi-scale tension characteristic vector. In other examples of the present application, the multi-scale neighborhood feature extraction module may further include a greater number of one-dimensional convolution layers, which perform neighborhood-related feature extraction of different scales using one-dimensional convolution kernels of different lengths, which is not limited in this application.
In an example, in the gathering performance optimization design system 100 of the sports bra, in the test data encoding module 120, the first scale convolution encoding unit 122 is further configured to perform one-dimensional convolution encoding on the tension input vector by using the first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain the first neighborhood scale tension associated feature vector; wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
In an example, in the gathering performance optimization design system 100 of the sports bra, in the test data encoding module 120, the second scale convolutional encoding unit 123 is further configured to perform one-dimensional convolutional encoding on the tension input vector by using a second convolutional layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain the second neighborhood scale tension related feature vector;
wherein the formula is:
wherein b is the width of the second convolution kernel in the X direction, F is a parameter vector of the second convolution kernel, G is a local vector matrix operated with the convolution kernel function, m is the size of the second convolution kernel, and X represents a tension input vector.
In the gathering performance optimization design system 100 for the sports bra, the test point spatial association module 130 is configured to construct a topology matrix of the plurality of test points, where a characteristic value of each position on a non-diagonal position in the topology matrix is a distance between two corresponding test points, and a characteristic value of each position on a diagonal position in the topology matrix is zero. Considering that the sports bra is an organic whole, the tension values of the test points are related, and the relationship is also presented in a certain spatial topological characteristic, namely, the sports bra is an organic whole, which not only needs to meet the preset requirement of the tension values of the test points, but also possibly meets the preset requirement on a related mode using the sports bra as a spatial carrier, so that whether the gathering performance of the sports bra is reasonable or whether the gathering performance needs to be optimized can be judged more accurately. From a simple and intuitive experience, when a female user wears the sports bra to do sports, the sports bra as a whole provides a function of supporting the chest (namely, the tension values of all test points need to meet the preset requirements), and the support provided by the sports bra as a whole needs to be adaptively adjusted based on all parts of the body, so that the function of supporting the chest can be provided, and the binding feeling and the injury to the user can be reduced as much as possible.
In the gathering performance optimization design system 100 of the sports bra, the test point spatial pattern coding module 140 is configured to obtain a topological feature matrix by passing the topological matrix through a convolutional neural network model serving as a feature extractor. That is, the convolutional neural network model is used as a feature extractor to extract spatial topological features between the test points.
In an example, in the gathering performance optimization design system 100 of the sports bra, the test point spatial pattern coding module 140 is further configured to perform convolution processing, pooling processing along channel dimensions, and nonlinear activation processing on input data in layer forward pass using each layer of the convolutional neural network model as the feature extractor, respectively, so as to output the topological feature matrix by a last layer of the convolutional neural network model as the feature extractor.
In the gathering performance optimization design system 100 for the sports bra, the fusion module 150 is configured to multiply the multi-scale tension feature vector and the topological feature matrix to obtain a classification feature vector. That is, the multi-scale tension feature vector contains multi-scale correlation features of tension parameters, i.e., tension correlation feature values between multiple test point sample scales, and the topological feature matrix has more balanced scale features.
And multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classification characteristic vector, namely mapping topological characteristic information in the topological characteristic matrix to the multi-scale tension characteristic vector, so that the classification characteristic vector comprises associated characteristic information and spatial topological information of the tension values of the plurality of test points in different neighborhood scales.
In the gathering performance optimization design system 100 for a sports bra, the correction module 160 is configured to correct the feature values of each position in the classification feature vector to obtain a corrected classification feature vector. In particular, in the technical solution of the present application, since the multi-scale tension feature vector includes multi-scale associated features of tension parameters, that is, tension associated feature values between sample scales of multiple test points, and the topological feature matrix has more balanced scale features, when the multi-scale tension feature vector and the topological feature matrix are multiplied, there may be a disturbance of a special instance of feature values in the classified feature vector.
Therefore, the information statistics normalization of the adaptive instance is performed on the classification feature vector, and is expressed as:
μ and σ are the mean and variance, respectively, of the set of eigenvalues of the classification eigenvector, and α is a bias hyperparameter.
The information statistical normalization of the self-adaptive example is implemented by taking a feature set as intrinsic prior information of statistical features of the self-adaptive example to perform dynamic generation type information normalization on a single feature value, and normalization mode length information of the feature set is used as bias and is used as invariance description in a set distribution domain, so that feature optimization for shielding disturbance distribution of a special example as far as possible is realized, and the classification effect of the classification feature vector is improved. That is, improve the precision of gathering together the performance to the motion brassiere and whether satisfying predetermined standard.
In an example, in the gathering performance optimization design system 100 for a sports bra, the correction module 160 is further configured to correct feature values of each position in the classification feature vector by using the following formula to obtain a corrected classification feature vector;
wherein the formula is:
where μ and σ are the mean and variance, respectively, of the set of eigenvalues of the classification eigenvector, and α is a bias hyperparameter, v i Is the eigenvalue of each position in the classified eigenvector, N is the number of eigenvalues in the classified eigenvector, v' i And classifying the feature value of each position in the feature vector after correction.
In the gathering performance optimization design system 100 for the sports bra, the optimization result generation module 170 is configured to pass the corrected classification feature vectors through a classifier to obtain a classification result, where the classification result is used to indicate whether the gathering performance of the sports bra to be detected meets a predetermined standard. Based on the classification result, whether the performance of gathering the sports bra needs to be optimized can be judged.
In an example, in the gathering performance optimization design system 100 for a sports bra, the optimization result generating module 170 is further configured to process the corrected classification feature vector by using the classifier according to the following formula to obtain the classification result;
wherein the formula is: o = softmax { (W) n ,B n ):…:(W 1 ,B 1 ) | X }, wherein W 1 To W n As a weight matrix, B 1 To B n Is the offset vector and X is the corrected classification feature vector.
In summary, the gathering performance optimization design system 100 for a sports bra according to the embodiment of the present application is illustrated, which extracts association features of tension values of a plurality of test points in different neighborhood scales by measuring the tension values at the plurality of test points of the sports bra to be detected, using a deep neural network model as a feature extractor, introduces spatial topology features of the plurality of test points into the tension value association features to obtain a classification feature representation including spatial topology and multi-scale neighborhood associations of the tension values, and then processes the classification feature representation by using a classifier to obtain a classification result used for representing whether the gathering performance of the sports bra to be detected meets a predetermined standard. Therefore, an intelligent design scheme of gathering performance of the sports bra is constructed based on an artificial intelligence technology.
As described above, the gathering performance optimization design system 100 for a sports bra according to the embodiment of the present application may be implemented in various terminal devices, for example, an intelligent evaluation instrument for gathering performance optimization design of a sports bra, and the like. In one example, the gathering performance optimization design system 100 of the sports bra according to the embodiment of the present application may be integrated into a terminal device as a software module and/or a hardware module. For example, the gathering performance optimization design system 100 of the sports bra may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the gathering performance optimization design system 100 of the sports bra may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the gathering performance optimization design system 100 of the sports bra and the terminal device may also be separate devices, and the gathering performance optimization design system 100 of the sports bra may be connected to the terminal device through a wired and/or wireless network and transmit the interaction information according to the agreed data format.
Exemplary method
Fig. 5 is a flowchart of a gathering performance optimization design method of a sports bra according to an embodiment of the present application. As shown in fig. 5, the method for optimally designing the gathering performance of a sports bra according to the embodiment of the present application includes: s110, acquiring tension values of a plurality of test points of the bra to be detected; s120, arranging the tension values of a plurality of test points of the to-be-detected motion bra into a tension input vector, and then obtaining a multi-scale tension feature vector through a multi-scale neighborhood feature extraction module; s130, constructing a topological matrix of the plurality of test points, wherein the characteristic value of each position on the non-diagonal position in the topological matrix is the distance between two corresponding test points, and the characteristic value of each position on the diagonal position in the topological matrix is zero; s140, obtaining a topological characteristic matrix by using the topological matrix through a convolutional neural network model as a characteristic extractor; s150, multiplying the multi-scale tension characteristic vector by the topological characteristic matrix to obtain a classified characteristic vector; s160, correcting the characteristic value of each position in the classification characteristic vector to obtain a corrected classification characteristic vector; and S170, passing the corrected classification characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the gathering performance of the bra to be detected meets a preset standard or not.
In an example, in the gathering performance optimization design method for a sports bra, as shown in fig. 6, the step of arranging the tension values of the plurality of test points of the sports bra to be detected as a tension input vector and then obtaining a multi-scale tension feature vector through a multi-scale neighborhood feature extraction module includes: s210, arranging tension values of a plurality of test points of the to-be-detected motion bra into the tension input vector; s220, inputting the tension input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension correlation feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length; s230, inputting the tension input vector into a second convolution layer of the multi-scale neighborhood region feature extraction module to obtain a second neighborhood region scale tension related feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and S240, cascading the first neighborhood scale tension related feature vector and the second neighborhood scale tension related feature vector to obtain the multi-scale tension feature vector.
In an example, in the gathering performance optimization design method for a sports bra, the tension input vector is input into the first convolution layer of the multi-scale neighborhood region feature extraction module to obtain a first neighborhood region scale tension related feature vector, and the first convolution layer of the multi-scale neighborhood region feature extraction module is used to perform one-dimensional convolution coding on the tension input vector according to the following formula to obtain the first neighborhood region scale tension related feature vector; wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
In summary, the gathering performance optimization design method of the sports bra according to the embodiment of the application is clarified, the method comprises the steps of measuring tension values of a plurality of test points of the sports bra to be detected, extracting association features of the tension values of the plurality of test points in different neighborhood scales by taking a deep neural network model as a feature extractor, introducing spatial topological features of the plurality of test points into the tension value association features to obtain classification feature representations including spatial topology and multi-scale neighborhood association of the tension values, and processing the classification feature representations by a classifier to obtain a classification result used for representing whether the gathering performance of the sports bra to be detected meets a preset standard. Therefore, an intelligent design scheme of gathering performance of the sports bra is constructed based on an artificial intelligence technology.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 7. FIG. 7 illustrates a block diagram of an electronic device in accordance with an embodiment of the application.
As shown in fig. 7, the electronic device 10 includes one or more processors 11 and memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input device 13 may include, for example, a keyboard, a mouse, and the like.
The output device 14 can output various information including the optimization results to the outside. The output devices 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 7, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer-readable storage Medium
In addition to the above-described methods and apparatus, embodiments of the present application may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions of the method for gathering performance optimization design of athletic brassieres according to various embodiments of the present application described in the "exemplary methods" section above of this specification.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages, for carrying out operations according to embodiments of the present application. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions of the gathering performance optimization design method for a sports bra according to various embodiments of the present application described in the "exemplary methods" section above in this specification.
The computer readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The foregoing describes the general principles of the present application in conjunction with specific embodiments, however, it is noted that the advantages, effects, etc. mentioned in the present application are merely examples and are not limiting, and they should not be considered essential to the various embodiments of the present application. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the foregoing disclosure is not intended to be exhaustive or to limit the disclosure to the precise details disclosed.
The block diagrams of devices, apparatuses, systems referred to in this application are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," "comprising," "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably herein. As used herein, the words "or" and "refer to, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that in the devices, apparatuses, and methods of the present application, each component or step can be decomposed and/or re-combined. These decompositions and/or recombinations are to be considered as equivalents of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the application to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (10)
1. The utility model provides a performance optimal design system is gathered together of motion brassiere which characterized in that includes:
the test data acquisition module is used for acquiring tension values of a plurality of test points of the bra to be tested;
the test data coding module is used for arranging tension values of a plurality of test points of the to-be-detected sports bra into a tension input vector and then obtaining a multi-scale tension characteristic vector through the multi-scale neighborhood characteristic extraction module;
the test point spatial association module is used for constructing a topological matrix of the plurality of test points, wherein the characteristic value of each position at a non-diagonal position in the topological matrix is the distance between two corresponding test points, and the characteristic value of each position at a diagonal position in the topological matrix is zero;
the test point space pattern coding module is used for enabling the topological matrix to pass through a convolutional neural network model serving as a feature extractor to obtain a topological feature matrix;
the fusion module is used for multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classified characteristic vector;
the correction module is used for correcting the characteristic value of each position in the classification characteristic vector to obtain a corrected classification characteristic vector; and
and the optimization result generation module is used for enabling the corrected classification characteristic vectors to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the gathering performance of the bra to be detected meets a preset standard or not.
2. The gathering performance optimization design system of a sports bra of claim 1, wherein the test data encoding module comprises:
the tension value vectorization unit is used for arranging the tension values of a plurality of test points of the to-be-detected motion bra into the tension input vector;
the first scale convolution coding unit is used for inputting the tension input vector into a first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension correlation feature vector, wherein the first convolution layer is provided with a first one-dimensional convolution kernel with a first length;
a second scale convolution coding unit, configured to input the tension input vector into a second convolution layer of the multi-scale neighborhood region feature extraction module to obtain a second neighborhood scale tension associated feature vector, where the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and
the cascade unit is used for cascading the first neighborhood scale tension correlation feature vector and the second neighborhood scale tension correlation feature vector to obtain the multi-scale tension feature vector.
3. The gathering performance optimization design system of a sports bra according to claim 2, wherein the first scale convolution encoding unit is further configured to perform one-dimensional convolution encoding on the tension input vector using the first convolution layer of the multi-scale neighborhood feature extraction module in the following formula to obtain the first neighborhood scale tension associated feature vector;
wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
4. The gathering performance optimization design system of a sports bra according to claim 2, wherein the second scale convolution encoding unit is further configured to perform one-dimensional convolution encoding on the tension input vector using a second convolution layer of the multi-scale neighborhood feature extraction module in the following formula to obtain the second neighborhood scale tension associated feature vector;
wherein the formula is:
wherein b is the width of the second convolution kernel in the X direction, F is a parameter vector of the second convolution kernel, G is a local vector matrix operated with the convolution kernel function, m is the size of the second convolution kernel, and X represents a tension input vector.
5. The gathering performance optimization design system of a sports bra as claimed in claim 4, wherein the test point spatial pattern coding module is further configured to perform convolution processing, pooling processing along channel dimensions, and nonlinear activation processing on input data in layer forward pass using each layer of the convolutional neural network model as the feature extractor, respectively, to output the topological feature matrix from a last layer of the convolutional neural network model as the feature extractor.
6. The gathering performance optimization design system of a sports bra according to claim 5, wherein the correction module is further configured to correct the eigenvalues of each position in the classification eigenvector with the following formula to obtain a corrected classification eigenvector;
wherein the formula is:
where μ and σ are the mean and variance, respectively, of the set of eigenvalues of the classification eigenvector, and α is a bias hyperparameter, v i Is the eigenvalue of each position in the classified eigenvector, N is the number of eigenvalues in the classified eigenvector, v' i And classifying the characteristic value of each position in the characteristic vector after correction.
7. The system of claim 6, wherein the optimization result generation module is further configured to process the corrected classification feature vectors using the classifier according to the following formula to obtain the classification result;
wherein the formula is: o = softmax { (W) n ,B n ):…:(W 1 ,B 1 ) I X }, wherein W 1 To W n As a weight matrix, B 1 To B n And X is a corrected classification feature vector.
8. A gathering performance optimization design method of a sports bra is characterized by comprising the following steps:
acquiring tension values of a plurality of test points of the motion bra to be detected;
arranging tension values of a plurality of test points of the brassiere to be detected into a tension input vector, and then obtaining a multi-scale tension characteristic vector through a multi-scale neighborhood characteristic extraction module;
constructing a topological matrix of the plurality of test points, wherein the characteristic value of each position on the non-diagonal position in the topological matrix is the distance between the corresponding two test points, and the characteristic value of each position on the diagonal position in the topological matrix is zero;
passing the topological matrix through a convolutional neural network model serving as a feature extractor to obtain a topological feature matrix;
multiplying the multi-scale tension characteristic vector and the topological characteristic matrix to obtain a classified characteristic vector;
correcting the characteristic value of each position in the classification characteristic vector to obtain a corrected classification characteristic vector; and
and passing the corrected classification characteristic vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the gathering performance of the bra to be detected meets a preset standard or not.
9. The gathering performance optimization design method of the sports bra according to claim 8, wherein the step of arranging the tension values of the plurality of test points of the sports bra to be detected as a tension input vector and then obtaining a multi-scale tension feature vector through a multi-scale neighborhood feature extraction module comprises the steps of:
arranging the tension values of a plurality of test points of the to-be-detected motion bra into the tension input vector;
inputting the tension input vector into a first convolution layer of the multi-scale neighborhood region feature extraction module to obtain a first neighborhood region scale tension correlation feature vector, wherein the first convolution layer has a first one-dimensional convolution kernel with a first length;
inputting the tension input vector into a second convolution layer of the multi-scale neighborhood region feature extraction module to obtain a second neighborhood region scale tension related feature vector, wherein the second convolution layer has a second one-dimensional convolution kernel with a second length, and the first length is different from the second length; and
and cascading the first neighborhood scale tension correlation feature vector and the second neighborhood scale tension correlation feature vector to obtain the multi-scale tension feature vector.
10. The gathering performance optimization design method for sports bras according to claim 9, wherein the tension input vector is input into the first convolution layer of the multi-scale neighborhood feature extraction module to obtain a first neighborhood scale tension association feature vector, and the tension input vector is subjected to one-dimensional convolution coding by using the first convolution layer of the multi-scale neighborhood feature extraction module according to the following formula to obtain the first neighborhood scale tension association feature vector;
wherein the formula is:
wherein, a is the width of the first convolution kernel in the X direction, F is a first convolution kernel parameter vector, G is a local vector matrix operated with the convolution kernel function, w is the size of the first convolution kernel, and X represents a tension input vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210985823.9A CN115329673A (en) | 2022-08-15 | 2022-08-15 | Gathering performance optimization design system and method of sports bra |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210985823.9A CN115329673A (en) | 2022-08-15 | 2022-08-15 | Gathering performance optimization design system and method of sports bra |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115329673A true CN115329673A (en) | 2022-11-11 |
Family
ID=83924686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210985823.9A Withdrawn CN115329673A (en) | 2022-08-15 | 2022-08-15 | Gathering performance optimization design system and method of sports bra |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115329673A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115932721A (en) * | 2022-12-15 | 2023-04-07 | 中际医学科技(山东)有限公司 | Close-range detection system and method of ultra-wideband radio frequency antenna |
| CN116201316A (en) * | 2023-04-27 | 2023-06-02 | 佛山市佳密特防水材料有限公司 | Close joint paving method and system for large-size ceramic tiles |
| CN116500379A (en) * | 2023-05-15 | 2023-07-28 | 珠海中瑞电力科技有限公司 | Accurate positioning method for voltage drop of STS device |
-
2022
- 2022-08-15 CN CN202210985823.9A patent/CN115329673A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115932721A (en) * | 2022-12-15 | 2023-04-07 | 中际医学科技(山东)有限公司 | Close-range detection system and method of ultra-wideband radio frequency antenna |
| CN116201316A (en) * | 2023-04-27 | 2023-06-02 | 佛山市佳密特防水材料有限公司 | Close joint paving method and system for large-size ceramic tiles |
| CN116500379A (en) * | 2023-05-15 | 2023-07-28 | 珠海中瑞电力科技有限公司 | Accurate positioning method for voltage drop of STS device |
| CN116500379B (en) * | 2023-05-15 | 2024-03-08 | 珠海中瑞电力科技有限公司 | Accurate positioning method for voltage drop of STS device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115329673A (en) | Gathering performance optimization design system and method of sports bra | |
| CN109871886B (en) | Abnormal point proportion optimization method and device based on spectral clustering and computer equipment | |
| Salcedo-Sanz et al. | Short term wind speed prediction based on evolutionary support vector regression algorithms | |
| Cai et al. | Hypergraph-structured autoencoder for unsupervised and semisupervised classification of hyperspectral image | |
| CN115082745A (en) | Image-based cable strand quality detection method and system | |
| CN116095089B (en) | Remote sensing satellite data processing method and system | |
| CN111954250A (en) | Lightweight Wi-Fi behavior sensing method and system | |
| CN115600140A (en) | Fan variable pitch system fault identification method and system based on multi-source data fusion | |
| CN111062428A (en) | Hyperspectral image clustering method, system and equipment | |
| CN107392259A (en) | The method and apparatus for building unbalanced sample classification model | |
| Hu et al. | Convex nonnegative matrix factorization with manifold regularization | |
| CN111160443A (en) | Activity and user identification method based on deep multitask learning | |
| Gan et al. | Learning-aware feature denoising discriminator | |
| CN113821094A (en) | Enhanced heat dissipation device and operation method | |
| CN116404212B (en) | Capacity equalization control method and system for zinc-iron flow battery system | |
| CN111046786A (en) | Generation method and device of age estimation neural network and electronic equipment | |
| Chan et al. | A new method for preliminary identification of gene regulatory networks from gene microarray cancer data using ridge partial least squares with recursive feature elimination and novel brier and occurrence probability measures | |
| CN104484601B (en) | Intrusion detection method and device based on Weighted distance measurement and matrix decomposition | |
| CN117094651A (en) | Integrated energy storage management system and energy management method | |
| CN116128250A (en) | Electricity selling deviation management method and system for spot market | |
| Liu et al. | Deep Fusion of Multi-Template using Spatio-Temporal Weighted Multi-Hypergraph Convolutional Networks for Brain Disease Analysis | |
| Yang et al. | Nonconcave penalized estimation for partially linear models with longitudinal data | |
| CN109145975A (en) | A kind of multiple view cluster machine learning method of matrix norm export regularization | |
| N'Cir et al. | Kernel overlapping k-means for clustering in feature space | |
| EP3721445B1 (en) | System to improve clinical workflow |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221111 |