Board card configuration method, device, medium and program product

Abstract

The application provides a board card configuration method, device, medium and program product, which can be applied to the technical field of computers. The board card configuration method comprises: processing attribute information of a target board card obtained by using a configuration recommendation model to obtain a configuration recommendation type for the target board card, wherein the configuration recommendation model is trained by using attribute information of a sample board card that has been configured as a reference sample; in the case where it is determined that there is no configured template in a preset configuration template library that matches the configuration recommendation type, a candidate template in the preset configuration template library that satisfies a preset condition in terms of configuration item difference between the configuration recommendation type is determined; and the candidate template is updated based on a configuration item component according to the configuration item difference between the configuration recommendation type and the candidate template to obtain a first target template, so that the target board card is configured according to the first target template.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a board configuration method, device, medium, and program product. Background Technology

[0002] With the continuous development of hardware technology, the versions and configurations of computer hardware boards have become increasingly complex. Different versions and configurations of boards typically require different software environments. Therefore, when configuring the software environment for different boards, it is usually necessary to refer to the specific model, version, and hardware configuration of the board for targeted configuration. In related technologies, before configuring a board, a corresponding configuration file is usually set up for each type of board, and the required configuration information is saved in the configuration file. When configuring the board, the configuration file is determined according to the mapping relationship between the board type and the configuration file, and the board is configured according to the configuration information saved in the configuration file.

[0003] In the process of implementing this invention, it was found that the related technology has at least the following problems: since the configuration information is stored in the configuration file of the board, if the configuration information itself is updated, all configuration files including the configuration information need to be updated, resulting in high maintenance costs. Summary of the Invention

[0004] In view of the above problems, the present invention provides a board configuration method, device, medium and program product.

[0005] According to a first aspect of the present invention, a board configuration method is provided, comprising: processing the obtained attribute information of a target board using a configuration recommendation model to obtain a configuration recommendation type for the target board, wherein the configuration recommendation model is trained using the attribute information of a configured sample board as a reference sample; determining, in the case that there is no configured template in a preset configuration template library that matches the configuration recommendation type, a candidate template in the preset configuration template library whose configuration item differences with the configuration recommendation type satisfy a preset condition; and updating the candidate template based on configuration item components according to the configuration item differences between the configuration recommendation type and the candidate template to obtain a first target template, so as to configure the target board according to the first target template.

[0006] A second aspect of the present invention provides a board configuration apparatus, comprising: an information processing module, configured to process the obtained attribute information of a target board using a configuration recommendation model to obtain a configuration recommendation type for the target board, wherein the configuration recommendation model is trained using the attribute information of a configured sample board as a reference sample; a template determination module, configured to determine, in the case that there is no configured template in the preset configuration template library that matches the configuration recommendation type, a candidate template in the preset configuration template library whose configuration item differences with the configuration recommendation type satisfy a preset condition; and a template updating module, configured to update the candidate template based on the configuration item differences between the configuration recommendation type and the candidate template, based on configuration item components, to obtain a first target template, so as to configure the target board according to the first target template.

[0007] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0008] A fourth aspect of the present invention also provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions, when executed by a processor, implement the steps of the above-described method.

[0009] A fifth aspect of the present invention also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method.

[0010] According to embodiments of the present invention, by utilizing a configuration recommendation model, the combination of configuration items most suitable for the attribute information of the target board can be selected from a large number of configuration items to obtain a configuration recommendation type. This ensures the rationality and accuracy of the board configuration. Furthermore, since the configuration recommendation model is used for configuration recommendation and determination, it is no longer necessary to determine the configuration based on a preset configuration file. When the configuration item itself is updated, only the configuration item in the configuration recommendation model needs to be updated to complete the update of that configuration item in all configuration recommendation types, thereby reducing maintenance costs. Based on the configuration recommendation type, candidate templates whose configuration item differences with the configuration recommendation type meet preset conditions are selected from a preset configuration template library. Since the preset templates are pre-set and stored in the preset configuration template library, selection does not require template construction, improving the efficiency of template selection and use. Updating the candidate templates based on configuration item differences ensures that the obtained first target template is the same as the configuration recommendation type, thereby ensuring the accuracy of the first target template. In addition, since the candidate template is the template in the preset configuration template library that is closest to the configuration recommendation type, the amount of operation required to modify the candidate template to obtain the first target template is minimized, further improving the efficiency of template construction and board configuration. Attached Figure Description

[0011] The above-described features, other objects, and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0012] Figure 1 The diagram illustrates an application scenario of a board configuration method, device, medium, and program product according to an embodiment of the present invention.

[0013] Figure 2 A flowchart of a board configuration method according to an embodiment of the present invention is shown.

[0014] Figure 3 A schematic diagram of a configuration recommendation model for a board configuration method according to an embodiment of the present invention is shown.

[0015] Figure 4 A flowchart of a board configuration method according to another embodiment of the present invention is shown.

[0016] Figure 5 A structural block diagram of a board configuration device according to an embodiment of the present invention is shown.

[0017] Figure 6 A block diagram of an electronic device suitable for implementing a board configuration method according to an embodiment of the present invention is shown. Detailed Implementation

[0018] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0019] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0020] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0021] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0022] Since related technologies typically use the mapping relationship between boards and configuration files to determine the configuration strategy for boards, when a new version or new configuration of a board appears, a new configuration file needs to be built for that board, resulting in low file building efficiency and high labor costs.

[0023] An embodiment of the present invention provides a board configuration method, comprising: processing the obtained attribute information of a target board using a configuration recommendation model to obtain a configuration recommendation type for the target board, wherein the configuration recommendation model is trained using the attribute information of a configured sample board as a reference sample; determining, in the case that there is no configured template in the preset configuration template library that matches the configuration recommendation type, a candidate template in the preset configuration template library whose configuration item differences with the configuration recommendation type meet preset conditions; and updating the candidate template based on configuration item components according to the configuration item differences between the configuration recommendation type and the candidate template to obtain a first target template, so as to configure the target board according to the first target template.

[0024] Figure 1The diagram illustrates an application scenario of a board configuration method, device, medium, and program product according to an embodiment of the present invention.

[0025] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. Each of the first terminal device 101, second terminal device 102, and third terminal device 103 has a circuit board installed. The network 104 serves as a medium for providing a communication link between the first terminal device 101, second terminal device 102, third terminal device 103, and server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0026] Users can insert cards into the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104, receive or send messages, and use the server 105 to analyze and process the attribute information of the cards inserted into the first terminal device 101, the second terminal device 102, and the third terminal device 103, and configure the environment of the cards.

[0027] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0028] Server 105 can be a server that provides various services, and server 105 may include a processing engine such as a board configuration engine. Using the board configuration engine, server 105 can analyze and process the attribute information of the boards inserted by the user into the first terminal device 101, the second terminal device 102, and the third terminal device 103 to determine the target template that is compatible with the board and configure the board.

[0029] It should be noted that the board configuration method provided in the embodiments of the present invention can generally be executed by server 105. Correspondingly, the board configuration device provided in the embodiments of the present invention can generally be located in server 105. The board configuration method provided in the embodiments of the present invention can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the board configuration device provided in the embodiments of the present invention can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0030] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0031] The following will be based on Figure 1 The described scene, through Figures 2-4 The board configuration method of the embodiments of the invention will be described in detail.

[0032] Figure 2 A flowchart of a board configuration method according to an embodiment of the present invention is shown.

[0033] like Figure 2 As shown, the board configuration method of this embodiment includes operations S210 to S230.

[0034] In operation S210, the attribute information of the target board is processed using the configuration recommendation model to obtain the configuration recommendation type for the target board.

[0035] According to an embodiment of the present invention, when configuring a newly added board to a computer, after connecting the target board to the computer, the attribute information of the target board can be obtained using a hardware detection tool. Since different types of boards have different hardware parameters, driver versions, and other attribute information, different boards require or support different software types and versions. A configuration recommendation model can be used to process the attribute information of the target board to obtain a recommended configuration type suitable for the target board. The recommended configuration type may include one or more system software programs that need to be deployed to the target board and their corresponding versions, such as Compute Unified Device Architecture (CUDA) 10.2, Python 3.7, etc.

[0036] According to an embodiment of the present invention, the configuration recommendation model can be trained using the attribute information of the configured sample boards as reference samples. The target board, sample board, and other boards may include a type of circuit board with specific electronic components installed that is connected to a computer through an interface and performs a specific function.

[0037] In operation S220, if it is determined that there is no configured template in the preset configuration template library that matches the configuration recommendation type, a candidate template in the preset configuration template library that meets the preset conditions for the difference between the configuration items and the configuration recommendation type is determined.

[0038] According to embodiments of the present invention, a preset configuration template library may include multiple pre-configured templates, wherein each configured template may include one or more configuration item components, which can be used to deploy a preset version of system software to a target board. The configured templates can be obtained by randomly combining multiple configuration item components or by combining them based on experience, and then added to the preset configuration template library. Alternatively, they can be obtained by updating candidate templates obtained in historical operations of configuring the board using the board configuration method, and then added to the preset configuration template library.

[0039] According to an embodiment of the present invention, by analyzing the configuration recommendation type, one or more configuration item components included in the configuration recommendation type can be determined, and a matching can be performed in the preset configuration template library based on one or more configuration item components. If a matching fails, it can be determined that there is no configured template in the preset configuration template library that matches the configuration recommendation type.

[0040] In this case, the differences in configuration items between each configured template and the recommended configuration type can be determined. Configuration item differences that meet preset conditions are identified, and the corresponding configured templates are designated as candidate templates.

[0041] In operation S230, based on the configuration item differences between the recommended configuration type and the candidate template, the candidate template is updated based on the configuration item components to obtain the first target template, so that the target board can be configured according to the first target template.

[0042] According to an embodiment of the present invention, since the candidate template is the template whose configuration item components are closest to the configuration recommendation type among multiple configured templates, but the candidate template and the configuration recommendation type are not matched, that is, there is a difference between the candidate template and the configuration recommendation type, the candidate template can be updated so that the updated first target template matches the configuration recommendation type, thereby ensuring that after configuring the target board according to the first target template, the configuration items installed in the target board match the configuration recommendation type.

[0043] According to an embodiment of the present invention, configuration item components can be added or deleted to the candidate template based on the configuration item differences between the configuration recommendation type and the candidate template, thereby updating the candidate template to eliminate the configuration item differences between the configuration recommendation type and the candidate template.

[0044] According to embodiments of the present invention, by utilizing a configuration recommendation model, the combination of configuration items most suitable for the attribute information of the target board can be selected from a large number of configuration items to obtain a configuration recommendation type. This ensures the rationality and accuracy of the board configuration. Furthermore, since the configuration recommendation model is used for configuration recommendation and determination, it is no longer necessary to determine the configuration based on a preset configuration file. When the configuration item itself is updated, only the configuration item in the configuration recommendation model needs to be updated to complete the update of that configuration item in all configuration recommendation types, thereby reducing maintenance costs. Based on the configuration recommendation type, candidate templates whose configuration item differences with the configuration recommendation type meet preset conditions are selected from a preset configuration template library. Since the preset templates are pre-set and stored in the preset configuration template library, selection does not require template construction, improving the efficiency of template selection and use. Updating the candidate templates based on configuration item differences ensures that the obtained first target template is the same as the configuration recommendation type, thereby ensuring the accuracy of the first target template. In addition, since the candidate template is the template in the preset configuration template library that is closest to the configuration recommendation type, the amount of operation required to modify the candidate template to obtain the first target template is minimized, further improving the efficiency of template construction and board configuration.

[0045] According to an embodiment of the present invention, when it is determined that there is no configured template in the preset configuration template library that matches the configuration recommendation type, determining the candidate template in the preset configuration template library whose configuration item differences with the configuration recommendation type meet preset conditions includes: determining the configuration item differences between the configuration recommendation type and each of the multiple configured templates according to one or more configuration items included in the configuration recommendation type; and determining the configured template whose configuration item differences meet the preset conditions as a candidate template.

[0046] According to embodiments of the present invention, configuration item differences between multiple configured templates and configuration recommendation types can be determined based on one or more configuration item components included in each of the multiple configured templates and one or more configuration item components included in the configuration recommendation type.

[0047] According to an embodiment of the present invention, among the configuration item differences corresponding to multiple configured templates, the configured template that meets the preset conditions is determined as a candidate template. The preset conditions may include having the smallest number of configuration item differences, and the number of configuration item differences being less than a preset difference value or a preset component ratio. The number of differences may include the number of configuration item components that need to be modified when modifying the configured template according to the configuration recommendation type.

[0048] For example, if the configuration recommended type includes configuration item components A and B, and the configured template includes configuration item components A and C, when modifying the configured template according to the configuration recommended type, it is necessary to delete C from the configured template and add B to the configured template. It can be determined that the number of configuration item differences between the configured template and the configuration recommended type is 2.

[0049] In one example, with a preset difference value of 3, it can be determined whether there are configuration item differences with a difference number less than 3 among the configuration item differences corresponding to each of the multiple configured templates. If there are configuration item differences that meet the above conditions, the configuration item difference with the smallest difference number is selected from the multiple configuration item differences, and the configured template corresponding to the configuration item difference is determined as the candidate template.

[0050] According to an embodiment of the present invention, based on preset conditions, a pre-configured template that is most similar to the recommended configuration type can be selected from a preset configuration template library as a candidate template, thereby minimizing the number of modifications required when updating the candidate template and improving the efficiency and accuracy of board configuration.

[0051] Since the number of configuration item components included in different configuration recommendation types can vary, using the same preset difference value to control the selection of candidate templates can easily lead to significant differences when there are large differences in configuration item components.

[0052] For example, if the first configuration recommendation type includes 50 configuration item components and the second configuration recommendation type includes 5 configuration item components, with a preset difference value of 5, the candidate template for the first configuration recommendation type needs to have at least 45 identical configuration item components. In this case, modifying the candidate template to obtain the first target template saves a significant amount of work compared to directly constructing the first target template using the configuration item components. However, since the configuration item components in the second configuration recommendation type have the same preset difference value, any configured template can be used as a candidate template for the second configuration recommendation type. In this case, modifying the candidate template to obtain the first target template requires deleting the configuration item components from the candidate template and then adding the 5 configuration item components from the second configuration recommendation type. This process involves a greater amount of work than directly constructing the first target template using the configuration item components.

[0053] Therefore, in another example, the preset difference value of the configuration recommendation type can be determined based on the preset component ratio and the configuration recommendation type. For example, if the preset difference value is 20% and the configuration recommendation type includes 25 configuration item components, the preset difference value of the configuration recommendation type is 20% × 25 = 5. It can be determined whether there are configuration item differences with fewer than 5 differences among the configuration item differences corresponding to multiple configured templates. If no configuration item differences satisfy the above condition, it can be determined that when using the current configured template as a candidate template, updating the candidate template requires modifying a large number of configuration item components. In this case, one or more configuration item components can be selected from multiple configuration item components without using the configured template, based on the configuration recommendation type, and combined to obtain the first target template.

[0054] By controlling the magnitude of the preset difference value through preset component ratios, it is possible to ensure that, under any configuration recommendation type, the amount of operations required to modify the candidate template selected based on the preset difference value to obtain the first target template is less than the amount of operations required to directly construct the first target template using configuration item components, based on the number of configuration item components included in the configuration recommendation type. Therefore, the preset difference value obtained by using preset component ratios has stronger universality.

[0055] According to an embodiment of the present invention, updating the candidate template based on configuration item components according to the configuration item differences between the configuration recommendation type and the candidate template to obtain a first target template includes: determining one or more configuration item components according to the configuration item differences; adding one or more configuration item components to the candidate template to obtain the first target template.

[0056] According to an embodiment of the present invention, when the configuration item difference indicates that the configuration recommendation type includes configuration item components that are not present in the candidate template, one or more configuration item components are determined based on the configuration item difference, and the determined configuration item components are added to the candidate template to obtain a first target template.

[0057] According to an embodiment of the present invention, when there is no configuration item component in the configuration item difference, it indicates that there is no difference between the configuration recommendation type and the candidate template, that is, the candidate template includes only all the configuration item components included in the configuration recommendation type. Therefore, the candidate template can be directly determined as the first target template.

[0058] According to another embodiment of the present invention, when the candidate template for configuration item differences includes configuration item components that do not exist in the configuration recommendation type, one or more configuration item components are determined based on the configuration item differences, and the determined configuration item components are deleted from the candidate template to obtain a first target template.

[0059] According to another embodiment of the present invention, when the configuration item difference indicates that the candidate template includes configuration item components that are not present in the configuration recommendation type, and the configuration recommendation type includes configuration item components that are not present in the candidate template, the configuration item difference is used to determine whether the candidate template includes configuration item components that are not present in the configuration recommendation type and the configuration recommendation type includes configuration item components that are not present in the candidate template. Configuration item components that are more than the configuration recommendation type in the candidate template are deleted, and configuration item components that are more than the candidate template in the configuration recommendation type are added to the candidate template to obtain the first target template.

[0060] According to an embodiment of the present invention, based on the differences in configuration items between the recommended configuration type and the candidate template, configuration item components that differ between the two are identified. Configuration item components in the recommended configuration type that exceed those in the candidate template are added to the candidate template, and configuration item components in the candidate template that exceed the recommended configuration type are deleted. This ensures that the obtained first target template includes only all configuration item components in the recommended configuration type. By operating on the candidate template that is closest in configuration recommendation type, the amount of operations in constructing the first target template can be reduced, thereby improving the efficiency of template construction.

[0061] According to an embodiment of the present invention, a configuration recommendation model is deployed on a board configuration engine and includes a decision layer and an output layer. The configuration recommendation model processes the attribute information of the target board to obtain a configuration recommendation type for the target board, including: inputting the attribute information of the target board into the decision layer to obtain the matching degree between the sub-attributes of the attribute information and the decision nodes of the decision layer; traversing multiple decision nodes in the decision layer according to the matching degree to obtain the decision result corresponding to the attribute information; and outputting the configuration recommendation type corresponding to the decision result through the output layer.

[0062] According to embodiments of the present invention, the configuration recommendation model can be deployed in the board configuration engine so that when a new board is connected to a computer, the board configuration engine can be used to centrally recommend and load configurations for that board. This reduces the need for other system components.

[0063] According to an embodiment of the present invention, the attribute information of the target board is input into the decision layer. Through the tree structure of the decision tree in the decision layer, the attribute information is sequentially matched with multiple decision nodes. During the matching process, the system gradually traverses the nodes in the decision tree by calculating the matching degree between the attribute information and each decision node. Furthermore, since each decision node in the decision tree corresponds to a value range of a sub-attribute, the system can determine the value range to which each sub-attribute belongs based on its specific value, thereby selecting the corresponding decision node for matching. This method not only achieves accurate traversal of decision nodes but also ensures the logic and efficiency of the matching process, providing a reliable foundation for subsequent decisions.

[0064] According to an embodiment of the present invention, after traversing the decision tree based on attribute information, the corresponding leaf node in the decision tree is determined, and this leaf node is used as the final decision result. The configuration recommendation type corresponding to the leaf node is determined, and the configuration recommendation type is output using the output layer of the configuration recommendation model.

[0065] According to embodiments of the present invention, by using a decision tree as the decision layer, the recommended configuration type for the target board is determined based on the attribute information of the target board. This ensures the accuracy and logic of the configuration recommendation process, provides a reliable basis for the configuration loading of the target board, improves the automation level of board configuration, and enhances user experience and configuration efficiency.

[0066] According to an embodiment of the present invention, the configuration recommendation model can be trained in the following manner: When it is determined that the attribute information of heterogeneous boards obtained from the board configuration engine, which differs from the target board, meets predetermined conditions, the attribute information of the reference samples and the heterogeneous boards is divided proportionally to obtain multiple sample datasets; the following operations are repeated until all multiple sample datasets are selected as validation sets to obtain multiple validation results: one of the multiple sample datasets is selected as the validation set, and the rest are used as the training set; the initial configuration recommendation model is trained using the training set to obtain a first prediction model; the prediction accuracy of the first prediction model is validated using the validation set to obtain validation results; the first prediction model whose prediction accuracy reaches a preset value among the multiple validation results is determined as the configuration recommendation model.

[0067] According to an embodiment of the present invention, the sample information includes attribute information of heterogeneous boards and attribute information of target boards, wherein the attribute information of heterogeneous boards and target boards are different. Based on the attribute information of the heterogeneous boards, it is determined whether the attribute information of the heterogeneous boards obtained from the board configuration engine meets predetermined conditions. If the predetermined conditions are met, the attribute information of the reference samples and sample boards is divided into multiple sample datasets in an equal proportion. For example, when the ratio of collected heterogeneous board samples to target board samples is 3:1, the sample information can be divided into multiple sample datasets, such that the ratio of heterogeneous board samples to target board samples in each sample dataset is 3:1. All heterogeneous board samples and all target board samples are respectively assigned to sample datasets, and the data in the multiple sample datasets do not overlap. This partitioning method ensures the balance of data distribution and provides diverse data support for model training.

[0068] According to an embodiment of the present invention, after the sample dataset is divided, one dataset is selected as the validation set, and the remaining datasets are used as the training set to train the initial configuration recommendation model. For example, in the case of four sample datasets including D1, D2, D3, and D4, D2 can be selected as the validation set, and the remaining datasets, namely D1, D3, and D4, can be used as the training set. The initial configuration recommendation model is trained using the training set to obtain three decision trees, which serve as the first prediction model. The validation set D2 is input into the first prediction model, and the prediction accuracy of the first prediction model is determined based on the output of the first prediction model and the labels of the validation set. The prediction accuracy of the first prediction model is then used as the validation result.

[0069] According to an embodiment of the present invention, an initial configuration recommendation model can be trained using multiple sample datasets. Each sample dataset serves as a validation set, and the remaining sample datasets are used as training sets. The initial configuration recommendation model is then trained using these training sets to obtain multiple first prediction models. The prediction accuracy of each first prediction model is calculated using its corresponding validation set. Based on the multiple prediction accuracies and a preset value, a configuration recommendation model is determined from the multiple first prediction models. The preset value can be 1, meaning that the model with a prediction accuracy of 1 is selected as the configuration recommendation model. If no model has a prediction accuracy of 1, the first recommendation model with the highest prediction accuracy can be selected as the configuration recommendation model.

[0070] According to embodiments of the present invention, by dividing the dataset in the above manner, multiple sample datasets are obtained. This allows for the division of the dataset composed of attribute information in various ways, resulting in diverse sample datasets. This ensures the balance of data distribution and provides diverse data support for model training. Training the initial configuration recommendation model using diverse sample datasets allows for the evaluation of model performance through cross-validation, providing a reliable basis for subsequent model optimization and further improving the model's robustness.

[0071] According to an embodiment of the present invention, training an initial configuration recommendation model using a training set to obtain a first prediction model includes: determining information gain for sub-attributes based on the type of sub-attributes in the attribute information of the training set to obtain multiple gain values; sorting the multiple gain values ​​to determine the splitting attribute of the root node in the initial decision tree; dividing the training set into multiple subsets based on the multiple attribute value ranges of the splitting attribute, wherein the child nodes of the decision tree represent the subsets; determining the gain value of one or more sub-attributes in the child node when the subset is determined to be separable; redetermining the splitting attribute of one or more sub-attributes based on the gain values ​​of one or more sub-attributes; further dividing the subset based on the redetermined splitting attribute; and using the obtained target decision tree as the decision layer when the subset is determined to be unseparable.

[0072] According to an embodiment of the present invention, during the training of the initial configuration recommendation model, the information gain of each training set can be calculated based on the board type of each attribute information in the training set, wherein the information gain can be calculated and represented using cross-entropy.

[0073] According to an embodiment of the present invention, the gain value of each sub-attribute in the attribute information is calculated based on the information gain of the training set. The calculated gain values ​​are then sorted, and the sub-attribute with the largest gain value is selected as the splitting attribute of the root node. For example, if the gain value of the board storage capacity is the largest, the board storage capacity can be used as the splitting attribute of the root node, i.e., the first-level node.

[0074] According to an embodiment of the present invention, the training set is divided into multiple subsets based on the different value ranges of the splitting attribute, generating corresponding child nodes. For example, taking the board storage capacity as the root node as the splitting attribute, three child nodes can be obtained based on the board storage capacity: "less than or equal to 8G", "greater than 8G and less than 32G", and "greater than or equal to 32G". The training set is then divided into subsets corresponding to these child nodes. At each child node, the gain value of the remaining sub-attributes is recalculated based on the subset, and the sub-attribute with the largest gain value is selected as the new splitting attribute to construct the next layer of child nodes. This process is recursively performed until the stopping condition is met, i.e., the subset corresponding to the newly obtained child node is no longer divisible.

[0075] Figure 3 A schematic diagram of a configuration recommendation model for a board configuration method according to an embodiment of the present invention is shown.

[0076] like Figure 3As shown, the root node 310 of the target decision tree can use the card storage capacity as a splitting attribute. The value range of the splitting attribute can be divided into three intervals: (0, 8G], (8G, 32G), and [32G, +∞). These three intervals correspond to first-level nodes 321, 322, and 323, respectively. The sub-attribute gain value of the subset data is calculated in the first-level nodes to determine the bandwidth as the splitting attribute for the next layer. The bandwidth value range can be divided into (0, 192GB / s], (192 GB / s, 300 GB / s), [300GB / s, 1TB / s), and [1TB / s, +∞). These four intervals correspond to second-level nodes 331, 332, 333, and 334, respectively. The figure only uses the child nodes of first-level node 322 as an example; the child node division method of first-level nodes 321 and 323 is the same as that of first-level node 322. Similarly, the sub-attribute gain values ​​of the subset are calculated in the second-level nodes to determine the power as the splitting attribute for the next layer. The power value range can be divided into (0, 225W), (225W, 355W), [355W, 800W), and [800W, +∞), which correspond to the third-level nodes 341, 342, 343, and 344, respectively.

[0077] This process continues until all sub-attributes in the training set have been traversed after the new sub-nodes are obtained, or the gain values ​​of the sub-attributes are all 0. At this point, it can be determined that the corresponding subset of the newly obtained sub-nodes cannot be further divided, and the division is stopped to obtain the target decision tree.

[0078] exist Figure 3 In the target decision tree shown, leaf node 351 corresponds to configuration recommendation type a, leaf node 352 corresponds to configuration recommendation type b, leaf node 353 corresponds to configuration recommendation type c, and leaf node 354 corresponds to configuration recommendation type d.

[0079] According to embodiments of the present invention, cross-entropy is calculated as information gain based on the board type corresponding to different attribute information and the number of samples of each board type in the training set. This quantifies the distribution of different board types in the training set, providing data support for subsequent model training. Based on the gain values ​​of each sub-attribute, the splitting attribute of the root node and the child nodes of the root node in the decision tree are selected. This allows the decision tree to prioritize the attributes with the greatest proportion and impact on the classification results, thereby improving the model's classification performance. The above partitioning process is recursively performed until the subset of data corresponding to the newly obtained child node is no longer divisible, at which point the partitioning stops, resulting in a decision tree. Through recursive partitioning, a complete decision tree structure can be gradually constructed, providing efficient decision logic for the system's recommendation model.

[0080] According to an embodiment of the present invention, information gain is determined for the sub-attributes based on the type of the sub-attributes in the attribute information of the training set to obtain multiple gain values, including: dividing the training set into multiple sub-training sets according to the board type of each sample board in the training set; determining the intermediate gain value of multiple sub-attributes in the attribute information for each sub-training set; and summing the intermediate gain values ​​of the same sub-attribute in multiple sample sets to obtain the gain value of the sub-attribute.

[0081] According to an embodiment of the present invention, when calculating the gain value of each sub-attribute, the board type can be distinguished, and calculations are performed separately for different board types. The training set is divided into multiple sample sets based on the different types of sample boards for each attribute information. For each sample set, the intermediate gain values ​​of multiple sub-attributes in the attribute information are calculated, where the intermediate gain values ​​include the gain values ​​of the same sub-attribute in different types of boards and in different attribute value ranges. The final gain value of the sub-attribute is obtained by summing the intermediate gain values ​​of the same sub-attribute in multiple sample sets. The intermediate gain values ​​and the final gain value can be calculated using cross-entropy.

[0082] According to an embodiment of the present invention, by calculating the gain value of each sub-attribute, the contribution of each sub-attribute to the classification result can be quantified, thereby providing a basis for the model to select the optimal splitting attribute.

[0083] According to an embodiment of the present invention, the board configuration method further includes: when it is determined that the prediction accuracy of multiple first prediction models is less than a preset value, re-dividing the attribute information of the reference sample and the attribute information of the sample board in an equal proportion to obtain multiple updated datasets; using the multiple updated datasets to train and validate the initial configuration recommendation model until the number of validations reaches a preset number, or the prediction accuracy of the trained second prediction model reaches a preset value; when it is determined that the number of validations reaches a preset number, and the prediction accuracy of the trained multiple second prediction models is less than a preset value, determining the configuration recommendation model from the multiple second prediction models according to the prediction accuracy of the multiple second prediction models.

[0084] According to an embodiment of the present invention, after detecting the prediction accuracy of multiple first prediction models, if it is found that the prediction accuracy of all first prediction models is less than a preset value of 1, the attribute information of the reference sample and the external server is re-divided proportionally to generate multiple updated datasets. Specifically, the sample data constituting D1, D2, D3, and D4 are randomly shuffled to obtain four updated datasets D1', D2', D3', and D4'. Based on the updated datasets, the initial configuration recommendation model is trained according to the above training method to obtain the second prediction model.

[0085] According to an embodiment of the present invention, the second prediction model is validated. If the prediction accuracy reaches a preset value, i.e., 100%, the second prediction model with a prediction accuracy of 100% can be determined as the configuration recommendation model. If the prediction accuracy still does not reach the preset value, the above process can be repeated to obtain an updated dataset. Based on the updated dataset, the initial configuration recommendation model is trained according to the above training method to obtain a new second prediction model. The training is iteratively continued until the prediction accuracy of the new second prediction model reaches the preset value.

[0086] According to an embodiment of the present invention, when multiple second prediction models fail to reach the preset value and the number of verifications has reached the preset number, the prediction accuracy of each of the multiple second prediction models is sorted, and the second prediction model with the highest prediction accuracy is selected as the configuration recommendation model.

[0087] According to embodiments of the present invention, by iterative training and controlling and judging the prediction accuracy of the second prediction model using preset values, the prediction accuracy of the configuration recommendation model can be made to meet the requirements, thereby improving the accuracy of the configuration recommendation type obtained based on the configuration recommendation model. When the prediction accuracy of the second prediction model obtained through multiple training iterations fails to reach the preset value, and the number of training or validation iterations has reached the preset number, selecting the second prediction model with the highest prediction accuracy from among the currently obtained second prediction models as the configuration recommendation model can reduce the number of training rounds and improve model training efficiency while ensuring the recommendation accuracy of the configuration recommendation model.

[0088] According to an embodiment of the present invention, the board configuration method further includes: constructing configuration statements corresponding to the target configuration item components for each of the multiple target configuration item components included in the first target template; and configuring the target board based on the multiple configuration statements.

[0089] According to an embodiment of the present invention, a first target template is parsed to determine a plurality of target configuration item components included in the first target template. For each target configuration item component, a configuration statement corresponding to the target configuration item component is constructed. For example, if the target configuration item component is Python version 3.7, the corresponding configuration statement could be "winget install --id Python.Python.3.7 -e".

[0090] According to an embodiment of the present invention, after constructing a configuration statement for each target configuration item component, multiple configuration statements are stored in a command file for configuring the board. Multiple commands in the command file are executed sequentially. After all multiple commands have been executed, the configuration of the target board is completed.

[0091] According to an embodiment of the present invention, after determining the first target template, configuration statements are automatically generated and executed based on the target configuration item components in the first target template, thus completing the configuration of the target board. This improves the automation level of the board configuration process, increases configuration efficiency, reduces manual operations, and thereby improves configuration accuracy.

[0092] According to an embodiment of the present invention, the board configuration method further includes: executing a target task using the configured target board to obtain an execution result; generating a determination instruction when the execution result is determined to be normal and the execution time is less than a time threshold; and generating a modification instruction when the execution result is determined to be abnormal or the execution time is not less than a time threshold.

[0093] According to embodiments of the present invention, since different boards have different hardware parameters, driver versions, and other attribute information, boards with different attribute information possess the hardware conditions to perform different tasks. After the target board is correctly configured, the configured target board has the software environment to perform the target task. Therefore, the configured target board possesses both the hardware conditions and software environment to perform the target task, and can be used to perform the target task.

[0094] According to an embodiment of the present invention, since there is a correspondence between the target board and the target task, the target board must possess the hardware conditions to execute the target task. If the execution result obtained by executing the target task using the configured target board is abnormal, or if the execution result indicates that the execution time is not less than a time threshold, it means that the target board cannot execute or cannot complete the target task within the time threshold. It can be determined that after configuring the target board according to the first target template, the software environment for executing the target task has not been built. Therefore, generating a modification instruction indicates that the first target template needs to be modified.

[0095] According to an embodiment of the present invention, if the target task is executed using the configured target board and the execution result is normal and the execution time is less than the time threshold, it indicates that the current target board has the capability to execute the target task as required. Therefore, generating a determination instruction indicates that the first target template does not need to be modified.

[0096] According to an embodiment of the present invention, after configuring the target board, the target task is executed using the target board. The configuration result is then tested based on the execution result. This allows for a more intuitive assessment of the performance and task execution capability of the configured target board. If the performance and task execution capability of the target board do not meet the requirements, modification instructions are generated for subsequent modifications to the target board's configuration. This improves the accuracy of board configuration and ensures the performance of the configured target board.

[0097] According to an embodiment of the present invention, the board configuration method further includes: in response to a modification instruction, searching from a preset configuration template library for a configured template that can perform the target task and whose execution time is less than a time threshold, and using it as a second target template; and generating a configuration modification suggestion based on the differences in configuration items between the second target template and the first target template.

[0098] According to an embodiment of the present invention, when a modification instruction is generated, in response to the modification instruction, a configured template capable of executing the target task and with an execution time less than a time threshold is selected from a plurality of configured templates in a preset configuration template library, and this template is determined as the second target template. The second target template can build a software environment for the board to execute the target task.

[0099] According to an embodiment of the present invention, after determining the second target template, the second target template is parsed to determine the multiple configuration item components included in the second target template, and it is determined whether each configuration item component matches the hardware parameters and other attribute information of the target board, that is, whether the target board supports the installation of the system software version corresponding to the configuration item component.

[0100] According to an embodiment of the present invention, if it is determined that the target board and the second target template include multiple configuration item components that match, it means that the target board can install all configuration item components in the second target template. Therefore, the configuration item differences between the second target template and the first target template can be determined, and configuration modification suggestions can be further generated.

[0101] According to an embodiment of the present invention, the board configuration method further includes: modifying the configuration of the target board based on the configuration modification suggestion; executing the target task using the target board with the modified configuration; and updating the first target template using the second target template when it is determined that the target task can be executed correctly and the execution time is less than a time threshold.

[0102] According to embodiments of the present invention, after determining the second target template, the target board can be configured directly based on the second target template. Alternatively, configuration item components in the first target template can be changed to configuration item components in the second target template by adding or deleting configuration item components on the already configured target board.

[0103] According to an embodiment of the present invention, since the configuration modification suggestion includes the configuration item differences between the second target template and the first target template, the corresponding configuration item component can be selected according to the configuration item differences, and installed on the target board, deleted from the target board, or the version of the installed component on the target board can be updated.

[0104] According to an embodiment of the present invention, after the configuration of the target board is modified, the target task is executed using the target board with the modified configuration. If the execution result is normal and the execution time is less than the time threshold, it indicates that after configuring the target board with the second target template, the target board can correctly and quickly execute the target task. Therefore, the first target template saved in the decision tree can be updated so that the second target template can be output when making configuration recommendations for the target board in the future.

[0105] According to an embodiment of the present invention, when the first target template needs to be modified, selecting a second target template that meets the requirements of the target task from a preset configuration template library ensures that after modifying the configuration of the target board according to the subsequently generated configuration modification suggestions, the modified configuration can correctly execute the target task with the required performance. Furthermore, since the target board has already been configured according to the first target template, modifying the configuration items in the first target template is more efficient.

[0106] Figure 4 A flowchart of a board configuration method according to another embodiment of the present invention is shown.

[0107] like Figure 4 As shown, the configuration method of this board includes operations S401 to S413.

[0108] In operation S401, the first target template is determined. The first target template can be determined through... Figure 2 The process will be determined.

[0109] In operation S402, multiple target configuration item components are determined based on the first target template.

[0110] When operating S403, a command file is built based on the configuration statement corresponding to the target configuration component.

[0111] When operating the S404, execute the command file to configure the target board based on the command file.

[0112] When operating the S405, the target board is used to execute the target task.

[0113] In operation S406, based on the execution result of the target task, determine whether the target task was executed correctly and whether the execution time was less than the time threshold. If yes, proceed to operation S407; otherwise, proceed to operation S408.

[0114] During operation S407, a confirmation instruction is generated, indicating that the first target template is compatible with the target board, and after the target board is configured according to the first target template, the target board can execute the target task and the performance meets the standard.

[0115] In operation S408, a modification instruction is generated, indicating that the first target template needs to be modified so that the target board can correctly execute the target task and ensure that the execution time is less than the time threshold.

[0116] In operation S409, a second target template is selected from the preset configuration template library, and the configuration of the target board is modified according to the second target template.

[0117] When operating the S410, the target task is executed using the modified target board.

[0118] In operation S411, based on the execution result of the target task, determine whether the target task was executed correctly and whether the execution time was less than the time threshold. If yes, execute operation S412; otherwise, execute operation S413.

[0119] During the S412 operation, it is confirmed that the target board with the modified configuration can perform the target task and the performance meets the requirements. The first target template is then updated using the second target template.

[0120] When operating S413, an alarm is sent to the configuration administrator so that the administrator can intervene in a timely manner and analyze the attribute information of the target board to resolve the configuration problem of the target board.

[0121] Based on the above-described board configuration method, the present invention also provides a board configuration device. The following will be combined with... Figure 5 The device is described in detail.

[0122] Figure 5 A structural block diagram of a board configuration device according to an embodiment of the present invention is shown.

[0123] like Figure 5 As shown, the board configuration device 500 in this embodiment includes an information processing module 510, a template determination module 520, and a template update module 530.

[0124] The information processing module 510 is used to process the acquired attribute information of the target board using a configuration recommendation model to obtain a configuration recommendation type for the target board. The configuration recommendation model is trained using the attribute information of already configured sample boards as reference samples. In one embodiment, the information processing module 510 can be used to execute the operation S210 described above, which will not be repeated here.

[0125] The template determination module 520 is used to determine candidate templates in the preset configuration template library whose configuration item differences with the recommended configuration type meet preset conditions when no configured template matching the recommended configuration type exists in the preset configuration template library. In one embodiment, the template determination module 520 can be used to perform the operation S220 described above, which will not be repeated here.

[0126] The template update module 530 is used to update the candidate template based on the configuration item components according to the configuration item differences between the configuration recommendation type and the candidate template, to obtain a first target template, so as to configure the target board according to the first target template. In one embodiment, the template update module 530 can be used to perform the operation S230 described above, which will not be repeated here.

[0127] According to an embodiment of the present invention, the template determination module 520 includes a difference determination submodule and a template determination submodule.

[0128] The difference determination submodule is used to determine the differences between the configuration recommendation type and the configuration items of multiple configured templates, based on one or more configuration items included in the configuration recommendation type.

[0129] The template determination submodule is used to determine the configured templates whose configuration item differences meet preset conditions as candidate templates.

[0130] According to an embodiment of the present invention, the template update module 530 includes a component determination submodule and a component addition submodule.

[0131] The component determination submodule is used to determine one or more configuration item components based on the differences in configuration items. These configuration item components are used to deploy a preset version of the system software to the target board.

[0132] The component adds a submodule, which is used to add one or more configuration item components to the candidate template to obtain the first target template.

[0133] According to an embodiment of the present invention, the information processing module 510 includes a matching degree determination submodule, a node traversal submodule, and a type determination submodule.

[0134] The matching degree determination submodule is used to input the attribute information of the target board into the decision layer and obtain the matching degree between the sub-attributes of the attribute information and the decision nodes of the decision layer.

[0135] The node traversal submodule is used to traverse multiple decision nodes in the decision layer based on the matching degree to obtain the decision results corresponding to the attribute information.

[0136] The type determination submodule is used to output the configuration recommendation type corresponding to the decision result through the output layer.

[0137] According to an embodiment of the present invention, the board configuration device 500 further includes an information partitioning module, a dataset partitioning module, a model training module, a model verification module, and a model selection module.

[0138] The information segmentation module is used to proportionally segment the attribute information of the reference sample and the heterogeneous board when the attribute information of the heterogeneous board obtained from the board configuration engine, which is different from the target board, meets the predetermined conditions, so as to obtain multiple sample datasets.

[0139] The dataset partitioning module is used to select one dataset from multiple sample datasets as the validation set and the rest as the training set.

[0140] The model training module is used to train the initial configuration recommendation model using the training set to obtain the first prediction model.

[0141] The model validation module is used to validate the prediction accuracy of the first prediction model using a validation set and obtain the validation results.

[0142] The model selection module is used to identify the first prediction model whose prediction accuracy reaches a preset value among multiple validation results as the recommended model for configuration.

[0143] According to an embodiment of the present invention, the model training module includes a gain determination submodule, a gain ranking submodule, a dataset partitioning submodule, an iterative training submodule, and a model determination submodule.

[0144] The gain determination submodule is used to determine the information gain of sub-attributes based on the type of sub-attributes in the attribute information of the training set, and obtain multiple gain values.

[0145] The gain sorting submodule is used to sort multiple gain values ​​to determine the splitting attribute of the root node in the initial decision tree.

[0146] The dataset partitioning submodule is used to divide the training set into multiple subsets based on the value ranges of multiple attributes of the splitting attribute. The child nodes of the decision tree represent the subsets.

[0147] The iterative training submodule is used to determine the gain value of one or more sub-attributes in a child node when the subset of data is determined to be separable; to redetermine the splitting attribute of one or more sub-attributes based on the gain value of one or more sub-attributes; and to further partition the subset of data based on the redetermined splitting attribute.

[0148] The model determination submodule is used to use the obtained target decision tree as the decision layer when the determined subset of the dataset is not divisible.

[0149] According to an embodiment of the present invention, the gain determination submodule includes a dataset partitioning unit, an intermediate value determination unit, and a gain summation unit.

[0150] The dataset partitioning unit is used to divide the training set into multiple sub-training sets based on the board type of each sample board in the training set.

[0151] The intermediate value determination unit is used to determine the intermediate gain values ​​of multiple sub-attributes in the attribute information for each sub-training set.

[0152] The gain summation unit is used to sum the intermediate gain values ​​of the same sub-attribute in multiple sample sets to obtain the gain value of the sub-attribute.

[0153] According to an embodiment of the present invention, the board configuration device 500 further includes an information re-division module, a model retraining module, and a model re-determination module.

[0154] The information re-division module is used to re-divide the attribute information of the reference sample and the attribute information of the sample board in an equal proportion when the prediction accuracy of multiple first prediction models is determined to be less than the preset value, so as to obtain multiple updated datasets.

[0155] The model retraining module is used to train and validate the initial configuration recommendation model using multiple updated datasets until the number of validations reaches a preset number, or the prediction accuracy of the trained second prediction model reaches a preset value.

[0156] The model re-determination module is used to determine the configuration recommendation model from multiple second prediction models based on their prediction accuracy when the number of verifications reaches a preset number and the prediction accuracy of multiple trained second prediction models is less than a preset value.

[0157] According to an embodiment of the present invention, the board configuration device 500 further includes a statement construction module and a board configuration module.

[0158] The statement construction module is used to construct configuration statements corresponding to the target configuration item components included in the first target template.

[0159] The board configuration module is used to configure the target board based on multiple configuration statements.

[0160] According to an embodiment of the present invention, the board configuration device 500 further includes a task execution module, a first instruction generation module, and a second instruction generation module.

[0161] The task execution module is used to execute target tasks using the configured target board and obtain the execution results.

[0162] The first instruction generation module is used to generate a definite instruction when the execution result is determined to be normal and the execution time is less than the time threshold.

[0163] The second instruction generation module is used to generate modification instructions when the execution result is determined to be abnormal or the execution time is not less than the time threshold.

[0164] According to an embodiment of the present invention, the board configuration device 500 further includes a template re-determination module and a suggestion generation module.

[0165] The template redeter module is used to respond to modification commands by searching the preset configuration template library for a configured template that can execute the target task and whose execution time is less than a time threshold, and using it as the second target template.

[0166] The suggestion generation module is used to generate configuration modification suggestions based on the differences in configuration items between the second target template and the first target template.

[0167] According to an embodiment of the present invention, the board configuration device 500 further includes a configuration modification module, a task re-execution module, and a template update module.

[0168] The configuration modification module is used to modify the configuration of the target board based on configuration modification suggestions.

[0169] The task re-execution module is used to execute target tasks using target boards with modified configurations.

[0170] The template update module is used to update the first target template using the second target template when it is determined that the target task can be executed correctly and the execution time is less than the time threshold.

[0171] According to embodiments of the present invention, any plurality of modules including the information processing module 510, the template determination module 520, and the template update module 530 can be merged into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module. According to embodiments of the present invention, at least one of the information processing module 510, the template determination module 520, and the template update module 530 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any one of the three implementation methods, or in a suitable combination of any of them. Alternatively, at least one of the information processing module 510, the template determination module 520, and the template update module 530 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0172] Figure 6 A block diagram of an electronic device suitable for implementing a board configuration method according to an embodiment of the present invention is shown.

[0173] like Figure 6 As shown, an electronic device 600 according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0174] RAM 603 stores various programs and data required for the operation of electronic device 600. Processor 601, ROM 602, and RAM 603 are interconnected via bus 604. Processor 601 executes various operations of the method flow according to embodiments of the present invention by executing programs in ROM 602 and / or RAM 603. It should be noted that the programs may also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 may also execute various operations of the method flow according to embodiments of the present invention by executing programs stored in said one or more memories.

[0175] According to an embodiment of the present invention, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to a bus 604. The electronic device 600 may also include one or more of the following components connected to the input / output (I / O) interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 610 as needed so that computer programs read from it can be installed into the storage section 608 as needed.

[0176] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0177] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of the present invention, a computer-readable storage medium may include ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603 described above.

[0178] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to enable the computer system to implement the board configuration method provided in the embodiments of the present invention.

[0179] When the computer program is executed by the processor 601, it performs the functions defined in the system / apparatus of this invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0180] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 609, and / or installed from the removable medium 611. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0181] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, it performs the functions defined in the system of this embodiment of the invention. According to embodiments of the invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0182] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0183] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0184] Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention can be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or combinations fall within the scope of the present invention.

[0185] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A board configuration method, characterized in that, The method includes: The configuration recommendation model is used to process the obtained attribute information of the target board to obtain the configuration recommendation type for the target board. The configuration recommendation model is trained using the attribute information of the configured sample boards as reference samples. If it is determined that there is no configured template in the preset configuration template library that matches the recommended configuration type, then candidate templates in the preset configuration template library whose configuration item differences with the recommended configuration type meet preset conditions are identified; and Based on the configuration item differences between the recommended configuration type and the candidate template, the candidate template is updated based on the configuration item components to obtain a first target template, so that the target board can be configured according to the first target template; The configuration recommendation model is deployed on the board configuration engine and includes a decision layer and an output layer. The step of processing the target board's attribute information using a configuration recommendation model to obtain a configuration recommendation type for the target board includes: The attribute information of the target board is input into the decision layer to obtain the matching degree between the sub-attributes of the attribute information and the decision nodes of the decision layer, wherein multiple decision nodes correspond to a value range of the sub-attributes. Based on the matching degree, multiple decision nodes are traversed in the decision layer to obtain decision results corresponding to the attribute information; and The output layer outputs the configuration recommendation type corresponding to the decision result.

2. The method according to claim 1, characterized in that, The step of determining candidate templates in the preset configuration template library that meet preset conditions for configuration item differences with the recommended configuration type when it is determined that there is no configured template matching the recommended configuration type in the preset configuration template library includes: Based on one or more configuration items included in the configuration recommendation type, determine the differences in configuration items between the configuration recommendation type and each of the multiple configured templates; and The configured templates whose configuration item differences meet the preset conditions are determined as the candidate templates.

3. The method according to claim 2, characterized in that, The step of updating the candidate template based on configuration item components according to the configuration item differences between the configuration recommendation type and the candidate template to obtain the first target template includes: Based on the differences in the configuration items, one or more configuration item components are determined, wherein the configuration item components are used to deploy a preset version of system software to the target board; and Add the one or more configuration item components to the candidate template to obtain the first target template.

4. The method according to claim 1, characterized in that, The configuration recommendation model is trained in the following way: If the attribute information of the heterogeneous board obtained from the board configuration engine, which is different from the target board, meets the predetermined conditions, the attribute information of the reference sample and the heterogeneous board is divided proportionally to obtain multiple sample datasets. Repeat the following operations until all of the multiple sample datasets have been selected as the validation set, resulting in multiple validation results: One of the multiple sample datasets is selected as the validation set, and the rest are used as the training set; The initial configuration recommendation model is trained using the training set to obtain the first prediction model; The prediction accuracy of the first prediction model is verified using the validation set to obtain the verification results; as well as The first prediction model whose prediction accuracy reaches a preset value among the multiple verification results is determined as the configuration recommendation model.

5. The method according to claim 4, characterized in that, The step of training the initial configuration recommendation model using the training set to obtain the first prediction model includes: Based on the type of the sub-attributes in the attribute information of the training set, the information gain of the sub-attributes is determined to obtain multiple gain values; The multiple gain values ​​are sorted to determine the splitting attribute of the root node in the initial decision tree; The training set is divided into multiple subsets based on the value range of the multiple attributes of the splitting attribute, wherein the child nodes of the decision tree represent the subsets. If the subset of data is determined to be divisible, the gain value of one or more sub-attributes in the child node is determined; based on the gain values ​​of the one or more sub-attributes, the splitting attribute of the one or more sub-attributes is re-determined; based on the re-determined splitting attribute, the subset of data is further divided; and If it is determined that the subset of data is not divisible, the resulting target decision tree is used as the decision layer.

6. The method according to claim 5, characterized in that, The step involves determining the information gain of the sub-attributes based on their types according to the attribute information in the training set, resulting in multiple gain values, including: The training set is divided into multiple sub-training sets based on the board type of each sample board in the training set. For each of the aforementioned sub-training sets, the intermediate gain values ​​of multiple sub-attributes in the attribute information are determined respectively; and The gain value of the sub-attribute is obtained by summing the intermediate gain values ​​of the same sub-attribute in the multiple sample datasets.

7. The method according to claim 4, characterized in that, The method further includes: If the prediction accuracy of multiple first prediction models is determined to be less than the preset value, the attribute information of the reference sample and the attribute information of the sample board are re-divided proportionally to obtain multiple updated datasets. The initial configuration recommendation model is trained and validated using the multiple updated datasets until the number of validations reaches a preset number, or the prediction accuracy of the trained second prediction model reaches the preset value; and If the number of verifications reaches the preset number and the prediction accuracy of the trained second prediction models is less than the preset value, the configuration recommendation model is determined from the multiple second prediction models according to their prediction accuracy.

8. The method according to claim 1, characterized in that, The method further includes: For each of the multiple target configuration item components included in the first target template, a configuration statement corresponding to each target configuration item component is constructed; and The target board is configured based on multiple configuration statements.

9. The method according to claim 8, characterized in that, The method further includes: The target task is executed using the configured target board, and the execution result is obtained; If the execution result is determined to be normal and the execution time is less than the time threshold, a determination instruction is generated; and If the execution result is determined to be abnormal, or the execution time is not less than a time threshold, a modification instruction is generated.

10. The method according to claim 9, characterized in that, The method further includes: In response to the modification instruction, a configured template capable of executing the target task and with an execution time less than the time threshold is searched from the preset configuration template library and selected as the second target template; and Based on the differences in configuration items between the second target template and the first target template, configuration modification suggestions are generated.

11. The method according to claim 10, characterized in that, The method further includes: Based on the configuration modification suggestions, the configuration of the target board is modified; Execute the target task using a target board with the modified configuration; and If it is determined that the target task can be executed correctly and the execution time is less than the time threshold, the first target template is updated using the second target template.

12. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 11.

13. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 11.

14. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 11.

Images