Component autonomous security situation assessment method, system, equipment and medium

Abstract

The invention provides a component autonomous security situation assessment method, system and device and a medium, and the method comprises the steps: collecting multi-source heterogeneous data of a component, and carrying out the preprocessing of the multi-source heterogeneous data of the component; marking the preprocessed data to obtain an original data set of the component; calculating the importance of different input features in the original data set for different classification labels, and forming an autonomous security situation assessment data set of the component through situation value calibration; word vectorization is carried out on text data of the autonomous security situation assessment data set, and dimension reduction is carried out on word vectors by utilizing principal component analysis; training an autonomous security situation assessment model of the component by using the word vector after dimension reduction; and evaluating the autonomous security situation of the component by using the trained autonomous security situation evaluation model. According to the invention, accurate evaluation of the current autonomous guarantee state of the component can be realized, and data support is provided for future development situation evaluation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, system, device and medium for assessing the autonomous support status of components. Background Technology

[0002] Currently, electronic components for aerospace products are constantly being updated and iterated, and component manufacturers frequently merge and reorganize, leading to a persistent risk of component supply disruptions and production stoppages. Against this backdrop, dynamically and accurately monitoring the self-sufficiency status of components in real time has become a crucial aspect of comprehensive support situational awareness for aerospace products. However, existing technical solutions are insufficient for effectively assessing the self-sufficiency status of components. Summary of the Invention

[0003] In view of this, the purpose of this application is to propose a method, system, device and medium for assessing the autonomous support status of components, so as to solve the above-mentioned technical problems.

[0004] Based on the above objectives, the first aspect of this application provides a method for assessing the autonomous support status of electronic components, comprising:

[0005] Collect multi-source heterogeneous data of components and preprocess the multi-source heterogeneous data of the components;

[0006] The preprocessed data is labeled to obtain the original dataset of the components;

[0007] Calculate the importance of different input features in the original dataset for different classification labels, and form an autonomous support status assessment dataset for the component through status value calibration;

[0008] The text data of the autonomous support situation assessment dataset is vectorized into word vectors, and principal component analysis is used to reduce the dimensionality of the word vectors.

[0009] The autonomous support status assessment model of the aforementioned components is trained using the dimensionality-reduced word vectors;

[0010] The autonomous support status of the component is evaluated using a trained autonomous support status assessment model.

[0011] In one embodiment, the multi-source heterogeneous data includes component design and selection data for different system platforms, associated manufacturer data, and restricted / restricted transportation data.

[0012] In one embodiment, the step of annotating the preprocessed data to obtain the original dataset of the components includes:

[0013] Based on data elements, the preprocessed data of decentralized management is correlated and mapped, and multiple experts in the field of electronic components are organized to annotate and cross-validate the preprocessed data to obtain the original dataset of the electronic components.

[0014] In one implementation, calculating the importance of different input features in the original dataset for different classification labels includes:

[0015] The importance of different input features for different classification labels in the original dataset is calculated using a random forest distributor, as shown in the following formula:

[0016]

[0017] Where FI(j) represents the importance of feature j, and T represents the number of trees in the random forest; ΔI t (j) represents the information gain brought by feature j in tree t. Information gain is a standard used by decision trees when splitting nodes to measure the contribution of a feature to the classification decision. By accumulating the contribution of each feature in each tree, the average importance of the feature is finally calculated. Information gain is calculated using the following formula:

[0018]

[0019] Among them, H(D) o ) is the original dataset D o entropy; p i This represents the proportion of the i-th class in the original dataset; It is a subset divided according to a certain feature.

[0020] In one implementation, the step of word vectorization of the text data in the autonomous support situation assessment dataset includes:

[0021] The text data of the autonomous support situation assessment dataset is vectorized using the Word2Vec model, as shown in the following formula:

[0022] ν(w i =Word2Vec(w i |C)

[0023] Wherein, ν(w i ) indicates the word w i In the vector representation of corpus C, the Word2Vec model uses co-occurring words of context window size to train the model, pulling words with similar semantics into the same vector space.

[0024] In one implementation, the dimensionality reduction of word vectors using principal component analysis includes:

[0025] Principal component analysis calculates the eigenvalues ​​and eigenvectors of word vectors using the covariance matrix, as shown in the following formula:

[0026]

[0027] Where, x i This represents the i-th sample vector. Let p be the mean vector and C be the covariance matrix. By finding the eigenvalues ​​and eigenvectors of the covariance matrix C, we can identify the eigenvectors corresponding to the largest eigenvalues ​​after sorting, which are the principal components p. i ;

[0028] Projecting the data onto these principal components yields a dimensionality-reduced data representation:

[0029] z i =[p1,p2,...,p m ] T x i

[0030] Among them, z i Let i be the representation of sample i in a low-dimensional space.

[0031] In one embodiment, training the autonomous support posture assessment model of the component using the dimensionality-reduced word vectors includes:

[0032] Local features are extracted through convolutional layers, and the feature space dimension is reduced using pooling layers to gradually construct a higher-order feature representation. The convolution operation formula is as follows:

[0033]

[0034] Among them, f i,j W represents the output of the convolutional layer. k,l For the convolution kernel weights, z i,j Here, b represents the input feature, σ represents the bias, and σ represents the activation function.

[0035] A multi-layer convolutional kernel max pooling structure is used to progressively extract the dimensionality-reduced features, and a fully connected layer is added at the end to achieve classification; the classification layer uses the softmax activation function.

[0036]

[0037] in, For the predicted probability distribution of autonomous support posture, W c and b c The weights and biases of the fully connected layer;

[0038] Then, the model parameters are optimized using the cross-entropy loss function:

[0039]

[0040] Among them, y i For actual labels, To predict probabilities for the model, the model uses stochastic gradient descent to update its parameters.

[0041] Based on the same inventive concept, a second aspect of this application provides a component autonomous support status assessment system, which includes:

[0042] The data acquisition module is used to collect multi-source heterogeneous data from components;

[0043] The data preprocessing module is used to preprocess the multi-source heterogeneous data of the components;

[0044] The data annotation module is used to annotate the preprocessed data to obtain the original dataset of the components;

[0045] The autonomous support situation assessment dataset establishment module is used to calculate the importance of different input features in the original dataset for different classification labels, and to form the autonomous support situation assessment dataset of the component through situation value calibration.

[0046] The dimensionality reduction module is used to convert the text data of the autonomous support situation assessment dataset into word vectors and to reduce the dimensionality of the word vectors using principal component analysis.

[0047] The model training module is used to train the autonomous support status assessment model of the component using the reduced-dimensional word vectors;

[0048] The situation prediction module is used to evaluate the autonomous support situation of the component using the trained autonomous support situation assessment model.

[0049] Based on the same inventive concept, a third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the component autonomous support status assessment method described in the first aspect above.

[0050] Based on the same inventive concept, a fourth aspect of this application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the component autonomous support status assessment method described in the first aspect.

[0051] As described above, the component self-sufficiency status assessment method provided in this application involves collecting multi-source heterogeneous data of components, preprocessing this data, labeling the preprocessed data to obtain the original dataset of the components, calculating the importance of different input features in the original dataset for different classification labels, and forming a component self-sufficiency status assessment dataset through status value labeling, converting the text data of the self-sufficiency status assessment dataset into word vectors, and using principal component analysis to reduce the dimensionality of the word vectors, using the dimensionality-reduced word vectors to train the component self-sufficiency status assessment model, and using the trained self-sufficiency status assessment model to assess the component self-sufficiency status. This application, through the systematic collection, processing, and analysis of component data, and based on the acquisition, identification, and understanding of key influencing factors of component self-sufficiency, achieves an accurate assessment of its current self-sufficiency status, thereby providing data support for future development status assessment and effectively supporting designers and managers in component selection, strategic planning, and scientific decision-making. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart of a component autonomous support status assessment method provided in an embodiment of this application;

[0054] Figure 2 An architecture diagram of a component autonomous support situation assessment method provided in an embodiment of this application;

[0055] Figure 3 A schematic diagram of a component autonomous support situation assessment system provided in another embodiment of this application;

[0056] Figure 4 This is a schematic diagram of an electronic device according to another embodiment of this application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0058] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0059] Reference Figure 1-2 As shown, one embodiment of this application provides a method for assessing the autonomous support status of components, which includes the following steps:

[0060] Step S10: Collect multi-source heterogeneous data of components and preprocess the multi-source heterogeneous data of components; optionally, the components are aerospace product components.

[0061] Optionally, multi-source heterogeneous data includes component design and selection data for different system platforms, data from associated manufacturers, and data on prohibited or restricted transportation.

[0062] Specifically, preprocessing checks are conducted on the data itself and between data points, including similar duplicate records, incomplete records, logical errors, and abnormal data. Non-standard data is then processed or corrected based on regular expression matching and external knowledge bases to ensure the standardization and integrity of the original data.

[0063] Step S20: Label the preprocessed data to obtain the original dataset of the components.

[0064] Specifically, the preprocessed data from decentralized management is correlated and mapped based on data elements, and multiple experts in the field of electronic components are organized to annotate and cross-validate the preprocessed data to obtain the original dataset of electronic components.

[0065] Step S30: Calculate the importance of different input features in the original dataset for different classification labels, and form an autonomous support status assessment dataset for components through status value calibration.

[0066] Step S40: Convert the text data of the autonomous support situation assessment dataset into word vectors, and use principal component analysis to reduce the dimensionality of the word vectors.

[0067] Step S50: Train the autonomous support status assessment model of the components using the reduced-dimensional word vectors.

[0068] Step S60: Use the trained autonomous support status assessment model to assess the autonomous support status of the components.

[0069] This application systematically collects, processes, and analyzes component data. Based on the acquisition, identification, and understanding of key factors influencing component self-sufficiency, it achieves an accurate assessment of the current self-sufficiency status of components, thereby providing data support for future development trend assessment and effectively supporting designers and managers in component selection, strategic planning, and scientific decision-making.

[0070] In one embodiment, step S30, calculating the importance of different input features in the original dataset for different classification labels, includes:

[0071] The importance of different input features for different classification labels in the original dataset is calculated using a random forest distributor, as shown in the following formula:

[0072]

[0073] Where FI(j) represents the importance of feature j, and T represents the number of trees in the random forest; ΔI t (j) represents the information gain brought by feature j in tree t. Information gain is a standard used by decision trees when splitting nodes to measure the contribution of a feature to the classification decision. By accumulating the contribution of each feature in each tree, the average importance of the feature is finally calculated. Information gain is calculated using the following formula:

[0074]

[0075] Among them, H(D) o ) is the original dataset D o entropy; p i This represents the proportion of the i-th class in the original dataset; It is a subset divided according to a certain feature.

[0076] The core idea of ​​random forests is to classify data by constructing a large number of decision trees. Each decision tree uses a portion of the training data and features, and the final classification result is determined by "majority voting" or "averaging". The advantage of this method is that it can effectively reduce the overfitting problem caused by a single decision tree, while improving the model's generalization ability.

[0077] In one embodiment, step S40, converting the text data of the autonomous support situation assessment dataset into word vectors, includes:

[0078] The Word2Vec model is used to vectorize the text data in the autonomous support situation assessment dataset, as shown in the following formula:

[0079] ν(w i =Word2Vec(w i |C)

[0080] Wherein, ν(w i ) indicates the word w i In the vector representation of corpus C, the Word2Vec model uses co-occurring words of context window size k to train the model, pulling words with similar semantics into the same vector space.

[0081] Specifically, the Word2Vec model includes the CBOW model, which is selected as the pre-trained model in this embodiment. The CBOW model, by utilizing information from all words in the context, can quickly generate word vectors. These vectors effectively represent the overall semantics of the text, helping the classification model better understand the text content. The CBOW model learns the embedding representation of each word by maximizing the conditional probability of predicting the center word given the context. CBOW aims to maximize the conditional probability of the center word:

[0082] P(w t |w t-k ,...,w t-1 ,w t+1 ,...,w t+k )

[0083] Where k represents the head word w t Context window size. The training objective of the CBOW model is to minimize the negative log-likelihood loss function:

[0084]

[0085] CBOW predicts the representation of the center word by aggregating contextual information, so that similar contexts produce similar word vectors.

[0086] In this embodiment, a training corpus is constructed based on fields such as component name and specifications, and the CBOW model is selected for pre-training to capture the co-occurrence pattern of each word.

[0087] In one embodiment, step S40, which involves reducing the dimensionality of word vectors using principal component analysis (PCA), includes:

[0088] Principal component analysis calculates the eigenvalues ​​and eigenvectors of word vectors using the covariance matrix, as shown in the following formula:

[0089]

[0090] Where, xi This represents the i-th sample vector. Let p be the mean vector and C be the covariance matrix. By finding the eigenvalues ​​and eigenvectors of the covariance matrix C, we can identify the eigenvectors corresponding to the largest eigenvalues ​​after sorting, which are the principal components p. i ;

[0091] Projecting the data onto these principal components yields a dimensionality-reduced data representation:

[0092] z i =[p1,p2,...,p m ] T x i

[0093] Among them, z i Let i be the representation of sample i in a low-dimensional space.

[0094] Specifically, after obtaining word vectors, the data dimensionality is high, and direct processing can easily lead to overfitting. Therefore, PCA (Programmable Dimensionality Analysis) is used for dimensionality reduction, which reduces data dimensionality redundancy while preserving key information features. The goal of PCA is to project the data onto a lower-dimensional space by constructing new coordinate axes.

[0095] Optionally, this application retains 95% of the variance by adjusting the number of principal components m to ensure the integrity of the input information.

[0096] In one embodiment, after step S40 and before step S50, the following steps are further included:

[0097] Step S41: Parameter Initialization. Set the model's internal parameters and training parameters to prepare for model training.

[0098] Step S42: Split the dataset. Divide the dimensionality-reduced data into a training set and a test set in a 7:3 ratio, that is, 70% of the data is used for training and 30% of the data is used for testing.

[0099] In one embodiment, the autonomous support situation assessment model for the components includes a Convolutional Neural Network (CNN). The dimensionality-reduced feature matrix is ​​input into the CNN for classification and situation assessment. Training data is input into the CNN model for training, and the error is distributed to each neural node using an error backpropagation algorithm, updating the weight parameters. By adjusting hyperparameters such as the number of training iterations and the learning rate, multiple training iterations are performed until the loss function converges, and finally, the trained model is saved.

[0100] Specifically, step S50 involves training the autonomous support status assessment model for components using the reduced-dimensional word vectors, including:

[0101] Local features are extracted through convolutional layers, and the feature space dimension is reduced using pooling layers to gradually construct a higher-order feature representation. The convolution operation formula is as follows:

[0102]

[0103] Among them, f i,j W represents the output of the convolutional layer. k,l For the convolution kernel weights, z i,j Here, b represents the input feature, σ represents the bias, and σ represents the activation function.

[0104] A multi-layer convolutional kernel max pooling structure is used to progressively extract the dimensionality-reduced features, and a fully connected layer is added at the end to achieve classification; the classification layer uses the softmax activation function.

[0105]

[0106] in, For the predicted probability distribution of autonomous support posture, W c and b c The weights and biases of the fully connected layer;

[0107] Then, the model parameters are optimized using the cross-entropy loss function:

[0108]

[0109] Among them, y i For actual labels, To predict probabilities for the model, the model uses stochastic gradient descent to update its parameters.

[0110] In one embodiment, after step S50 and before step S60, the following steps are further included:

[0111] Step S51: Test the performance of the trained autonomous support situation assessment model.

[0112] Specifically, based on the classification results of CNN, an autonomous protection situation assessment model is used to calculate the situation value. The model is evaluated using test set data, the difference between the predicted value and the true value is calculated, and the mean absolute error (MAE) is used to judge the quality of the model.

[0113] This application innovatively proposes a new path for autonomous support status assessment of components based on data-driven multi-source information fusion. It aims to provide new information references for traditional autonomous support status assessment of components, and to provide new ideas for subsequent research in the field. It is expected to improve assessment efficiency and objectivity while reducing assessment costs.

[0114] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method.

[0115] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides a component autonomous support situation assessment system, referring to... Figure 3 As shown, the system includes the following modules:

[0117] The data acquisition module is used to collect multi-source heterogeneous data from components;

[0118] The data preprocessing module is used to preprocess the multi-source heterogeneous data of the components;

[0119] The data annotation module is used to annotate the preprocessed data to obtain the original dataset of the components;

[0120] The autonomous support situation assessment dataset establishment module is used to calculate the importance of different input features in the original dataset for different classification labels, and to form the autonomous support situation assessment dataset of the component through situation value calibration.

[0121] The dimensionality reduction module is used to convert the text data of the autonomous support situation assessment dataset into word vectors and to reduce the dimensionality of the word vectors using principal component analysis.

[0122] The model training module is used to train the autonomous support status assessment model of the component using the reduced-dimensional word vectors;

[0123] The situation prediction module is used to evaluate the autonomous support situation of the component using the trained autonomous support situation assessment model.

[0124] The component autonomous support situation assessment system in this embodiment has the beneficial effects of the above-described method embodiments, which will not be repeated here.

[0125] This application systematically collects, processes, and analyzes component data. Based on the acquisition, identification, and understanding of key factors influencing component self-sufficiency, it achieves an accurate assessment of the current self-sufficiency status of components, thereby providing data support for future development trend assessment and effectively supporting designers and managers in component selection, strategic planning, and scientific decision-making.

[0126] Based on the same inventive concept, corresponding to any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the component autonomous support status assessment method of any of the above embodiments.

[0127] Figure 4 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1101, a memory 1102, an input / output interface 1103, a communication interface 1104, and a bus 1105. The processor 1101, memory 1102, input / output interface 1103, and communication interface 1104 are interconnected internally via the bus 1105.

[0128] The processor 1101 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0129] The memory 1102 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1102 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1102 and is called and executed by the processor 1101.

[0130] Input / output interface 1103 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0131] Communication interface 1104 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0132] Bus 1105 includes a pathway for transmitting information between various components of the device, such as processor 1101, memory 1102, input / output interface 1103, and communication interface 1104.

[0133] It should be noted that although the above-described device only shows the processor 1101, memory 1102, input / output interface 1103, communication interface 1104, and bus 1105, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0134] The electronic devices described above are used to implement the corresponding component autonomous support situation assessment method in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0135] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the component autonomous support status assessment method as described in any of the above embodiments.

[0136] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0137] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the component autonomous support status assessment method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0138] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0139] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0140] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0141] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A method for assessing the autonomous support status of electronic components, characterized in that, include: Collect multi-source heterogeneous data of components and preprocess the multi-source heterogeneous data of the components; The preprocessed data is labeled to obtain the original dataset of the components; Calculate the importance of different input features in the original dataset for different classification labels, and form an autonomous support status assessment dataset for the component through status value calibration; The text data of the autonomous support situation assessment dataset is vectorized into word vectors, and principal component analysis is used to reduce the dimensionality of the word vectors. The autonomous support status assessment model of the aforementioned components is trained using the dimensionality-reduced word vectors; The autonomous support status of the component is evaluated using a trained autonomous support status assessment model.

2. The component self-sufficiency status assessment method according to claim 1, characterized in that, The multi-source heterogeneous data includes component design and selection data for different system platforms, associated manufacturer data, and restricted / restricted transportation data.

3. The component self-sufficiency status assessment method according to claim 1, characterized in that, The step of labeling the preprocessed data to obtain the original dataset of the components includes: Based on data elements, the preprocessed data of decentralized management is correlated and mapped, and multiple experts in the field of electronic components are organized to annotate and cross-validate the preprocessed data to obtain the original dataset of the electronic components.

4. The component self-sufficiency status assessment method according to claim 1, characterized in that, The calculation of the importance of different input features in the original dataset for different classification labels includes: The importance of different input features for different classification labels in the original dataset is calculated using a random forest distributor, as shown in the following formula: Where FI(j) represents the importance of feature j, and T represents the number of trees in the random forest; ΔI t (j) represents the information gain brought by feature j in tree t. Information gain is a standard used by decision trees when splitting nodes to measure the contribution of a feature to the classification decision. By accumulating the contribution of each feature in each tree, the average importance of the feature is finally calculated. Information gain is calculated using the following formula: Among them, H(D) o ) is the original dataset D o entropy; p i D represents the proportion of class i in the original dataset; i o It is a subset divided according to a certain feature.

5. The component self-sufficiency status assessment method according to claim 1, characterized in that, The step of word vectorization of the text data in the autonomous support situation assessment dataset includes: The text data of the autonomous support situation assessment dataset is vectorized using the Word2Vec model, as shown in the following formula: ν(in i )=Word2Vec(w i |C) Wherein, ν(w i ) indicates the word w i In the vector representation of corpus C, the Word2Vec model uses co-occurring words of context window size to train the model, pulling words with similar semantics into the same vector space.

6. The component self-sufficiency status assessment method according to claim 1, characterized in that, The method of reducing the dimensionality of word vectors using principal component analysis includes: Principal component analysis calculates the eigenvalues ​​and eigenvectors of word vectors using the covariance matrix, as shown in the following formula: Where, x i This represents the i-th sample vector. Let p be the mean vector and C be the covariance matrix. By finding the eigenvalues ​​and eigenvectors of the covariance matrix C, we can identify the eigenvectors corresponding to the largest eigenvalues ​​after sorting, which are the principal components p. i ; Projecting the data onto these principal components yields a dimensionality-reduced data representation: from i =[p1,p2,...,p m ] T x i Among them, z i Let i be the representation of sample i in a low-dimensional space.

7. The component self-sufficiency status assessment method according to claim 1, characterized in that, The process of training the autonomous support posture assessment model for the component using dimensionality-reduced word vectors includes: Local features are extracted through convolutional layers, and the feature space dimension is reduced using pooling layers to gradually construct a higher-order feature representation. The convolution operation formula is as follows: Among them, f i,j W represents the output of the convolutional layer. k,l For the convolution kernel weights, z i,j Here, b represents the input feature, σ represents the bias, and σ represents the activation function. A multi-layer convolutional kernel max pooling structure is used to progressively extract the dimensionality-reduced features, and a fully connected layer is added at the end to achieve classification; the classification layer uses the softmax activation function. in, For the predicted probability distribution of autonomous support posture, W c and b c The weights and biases of the fully connected layer; Then, the model parameters are optimized using the cross-entropy loss function: Among them, y i For actual labels, To predict probabilities for the model, the model uses stochastic gradient descent to update its parameters.

8. A component autonomous support situation assessment system, characterized in that, include: The data acquisition module is used to collect multi-source heterogeneous data from components; The data preprocessing module is used to preprocess the multi-source heterogeneous data of the components; The data annotation module is used to annotate the preprocessed data to obtain the original dataset of the components; The autonomous support situation assessment dataset establishment module is used to calculate the importance of different input features in the original dataset for different classification labels, and to form the autonomous support situation assessment dataset of the component through situation value calibration. The dimensionality reduction module is used to convert the text data of the autonomous support situation assessment dataset into word vectors and to reduce the dimensionality of the word vectors using principal component analysis. The model training module is used to train the autonomous support status assessment model of the component using the reduced-dimensional word vectors; The situation prediction module is used to evaluate the autonomous support situation of the component using the trained autonomous support situation assessment model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the component autonomous support status assessment method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the component autonomous support status assessment method according to any one of claims 1 to 7.

Images