Request processing method, baseboard management controller, electronic equipment and storage medium

Abstract

The invention discloses a request processing method, a backplane management controller, electronic equipment and a storage medium, and relates to the technical field of computers, the request processing method is applied to the backplane management controller, the backplane management controller comprises a first processor, a second processor and at least two types of models, and the number of each type of model is at least one; the method comprises the steps that a first processor obtains target request data input by a user; when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to a target threshold value, the first processor sends the target request data to a second processor; the second processor processes the target request data based on the target model; the first processing condition is a condition for judging whether the model is adopted to process the target request data or not, the target model is one of at least two types of models, and the technical problem that the bottom plate management controller is low in function flexibility is solved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and particularly to a request processing method, a baseboard management controller, an electronic device, and a storage medium. Background Art

[0002] A baseboard management controller (BMC) is an essential part of a server, which is responsible for monitoring and managing the health status of the server. In the face of complex business requirements such as data analysis, predictive maintenance, and adaptive adjustment, it is not easy for the traditional BMC to customize the addition and optimization of functions according to business requirements, resulting in low flexibility of BMC functions. Summary of the Invention

[0003] This application provides a request processing method, a baseboard management controller, an electronic device, and a storage medium to at least solve the technical problem of low flexibility of the functions of the baseboard management controller in the related art.

[0004] This application provides a request processing method applied to a baseboard management controller. The baseboard management controller includes a first processor, a second processor, and at least two types of models, and the number of each type of model is at least one. The method includes: The first processor obtains target request data input by a user; When the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, the first processor sends the target request data to the second processor; The second processor processes the target request data based on the target model; the first processing condition is a condition for determining whether to use a model to process the target request data, and the target model is one of at least two types of models.

[0005] This application also provides a baseboard management controller for executing the above request processing method.

[0006] Through this application, the first processor can obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. The second processor processes the target request data based on the target model, which is one of at least two types of models, so as to realize the flexible processing of request data by collaborating to call the first processor and the second processor in the baseboard management controller, and achieve the purpose of improving the function flexibility of the baseboard management controller. Brief Description of the Drawings

[0007] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0008] Figure 1 One of the flowcharts of a request processing method provided by an embodiment of the present application; Figure 2 Another flowchart of a request processing method according to an embodiment of the present application; Figure 3 A block diagram of the server logic structure according to an embodiment of the present application; Figure 4 A schematic diagram of the structure of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0010] It should be noted that in the description of the present application, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. The terms "first", "second", etc. in the present application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0011] To enable those skilled in the art of the present technology to better understand the solution of the present application, the following further details the present application with reference to the accompanying drawings and specific implementation manners.

[0012] An embodiment of the present application provides a request processing method, which is applied to a baseboard management controller. The baseboard management controller includes a first processor, a second processor, and at least two types of models, and the number of each type of model is at least one. In combination with the execution process of the request processing method, the method is described in detail.

[0013] Specifically, Figure 1 A flowchart of a request processing method according to an embodiment of the present application.

[0014] AsFigure 1 As shown in Figure 1 , the request processing method includes the following steps: In step S110, the first processor obtains the target request data input by the user.

[0015] In actual execution, the baseboard management controller can be stored in an eMMC (Embedded MultiMediaCard) circuit chip.

[0016] In some embodiments, the first processor can be a Cortex-A multi-core processor.

[0017] In actual execution, the target request data can be request data for querying information or performing maintenance operations, or any theoretically feasible request data. The target request data can include data in any format, such as text, image, etc. This application does not make specific restrictions on this.

[0018] In some embodiments, the first processor in the baseboard management controller can obtain the target request data input by the user through the Basic Input Output System (BIOS).

[0019] In some embodiments, the first processor in the baseboard management controller and the BIOS can interact based on the H2B (Host to BMC) shared memory method. The baseboard management controller can obtain the target request data input by the user from the Basic Input Output System (BIOS) based on the H2B method.

[0020] In step S120, when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, the first processor sends the target request data to the second processor; the first processing condition is the condition for determining whether to process the target request data using a model.

[0021] In some embodiments, the second processor can be a Cotex-M4 assist processor.

[0022] In some embodiments, the first processor can determine whether to process the target request data using a model based on a preset question bank, that is, determine whether the target request data meets the first processing condition.

[0023] In some embodiments, the first processor can determine the target model based on the second processing condition when the target request data does not meet the first processing condition.

[0024] In some embodiments, the first processor may update the target threshold before determining whether the target request data meets the first processing condition.

[0025] In some embodiments, when the target request data does not meet the first processing condition, the first processor may determine whether its occupancy rate is greater than or equal to the target threshold.

[0026] In step S130, the second processor processes the target request data based on the target model, and the target model is one of at least two types of models.

[0027] In some embodiments, the baseboard management controller may run a hierarchical heterogeneous architecture, which may include a preset question library and at least two types of models, and the number of each type of model is at least one.

[0028] In some embodiments, the baseboard management controller may adopt a cooperative operation mode of the first processor and the second processor. When the target request data does not meet the first processing condition, it determines the target model based on the second processing condition and processes the target request data based on the target model.

[0029] In some embodiments, the hierarchical heterogeneous architecture of the baseboard management controller may include a model for answering query requests input by users, and may also include a model for solving control requests input by users. The first processor may determine the target model corresponding to the request type of the target request data input by the user from the hierarchical heterogeneous architecture based on the second processing condition.

[0030] In some embodiments, after processing the target request data based on the target model, the first processor may store and display the processing result for the target request data.

[0031] In some embodiments, the second processor may include at least one assistance processing module, and the second processor may process the target request data based on the target model through at least one assistance processing module.

[0032] In some embodiments, when the target request data does not meet the first processing condition and the occupancy rate of the first processor itself is less than the target threshold, the first processor may process the target request data based on the target model.

[0033] In some embodiments, after determining whether the target request data meets the first processing condition based on the preset question library, when the target request data does not meet the first processing condition, the first processor and the second processor are called to determine the target model based on the second processing condition and process the target request data based on the target model.

[0034] In some embodiments, the baseboard management controller may invoke the target resources of the second processor and process the target request data based on the target model. The target resources may include resources such as memory, storage, bandwidth, and computing, or any other theoretically feasible resources.

[0035] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. The second processor processes the target request data based on the target model, and the target model is one of at least two types of models, so as to realize the flexible processing of request data based on multiple models by collaboratively invoking the first processor and the second processor in the baseboard management controller, and achieve the purpose of improving the functional flexibility of the baseboard management controller.

[0036] In some embodiments, before the first processor sends the target request data to the second processor when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, the first processor may determine whether the target request data meets the first processing condition based on a preset question bank; when the target request data meets the first processing condition, the first processor processes the target request data based on the preset question bank.

[0037] In some embodiments, the hierarchical heterogeneous architecture of the baseboard management controller may include a preprocessing module, and the first processor may determine whether the target request data meets the first processing condition based on the preset question bank through the preprocessing module.

[0038] In some embodiments, the baseboard management controller may obtain the target data under the server operating system and store it in the target database. The target data may include the running data of the server, such as the running data of the central processing unit or any other theoretically feasible data. The target database may be a Redis database that supports cache and temporary data storage. The target database may be deployed in the baseboard management controller.

[0039] In some embodiments, a preset question bank may be constructed based on the target data stored in the target database. The preset question bank may be a quick response entry, and the preset question bank may store the target data and the preset requests corresponding to each piece of data in the target data.

[0040] In some embodiments, the first processor may determine whether the target request data meets the first processing condition based on the preset question bank and the target request data, for example, retrieve whether there is a preset request similar to the target request data stored in the preset question bank, for example, whether feedback data for the target request data can be generated based on the target data currently stored in the preset question bank.

[0041] In some embodiments, when the target request data meets the first processing condition, the first processor may process the target request data based on a preset question bank. For example, the first processor may generate feedback data for the target request data based on the target data in the preset question bank.

[0042] According to the request processing method of the embodiments of the present application, when the target request data does not meet the first processing condition, before determining the target model based on the second processing condition and processing the target request data based on the target model, the first processor may determine whether the target request data meets the first processing condition based on the preset question bank; when the target request data meets the first processing condition, the first processor processes the target request data based on the preset question bank, so as to avoid processing the target request data through the model when the target request data meets the first processing condition, thereby minimizing the occupation of the baseboard management controller resources by the model.

[0043] In some embodiments, the first processor may search the preset question bank to find out whether there is feedback data matching the target request data; if there is feedback data, it is determined that the target request data meets the first processing condition.

[0044] In actual execution, the feedback data may be any one of the target data pre-stored in the preset question bank.

[0045] In some embodiments, based on the target request data, it may be retrieved and queried in the preset question bank whether there is feedback data matching the target request data, that is, whether the preset question bank can process the target request data. If there is feedback data matching the target request data in the preset question bank, it is determined that the target request data meets the first processing condition, and then the target request data is processed based on the preset question bank to obtain a processing result.

[0046] In some embodiments, the first processor may retrieve whether there is feedback data matching the target request data in the preset question bank based on the cosine similarity, Jaccard Index, or any theoretically feasible algorithm.

[0047] In some embodiments, the first processor may compare each existing target data in the preset question bank with the target request data one by one based on the cosine similarity, Jaccard Index, or any theoretically feasible algorithm to retrieve whether there is feedback data matching the target request data in the preset question bank.

[0048] In some embodiments, when there is no feedback data in the preset question library that matches the target request data, the first processor may determine that the target request data does not meet the first processing condition.

[0049] According to the request processing method of the embodiments of the present application, when the target request data does not meet the first processing condition, before determining the target model based on the second processing condition and processing the target request data based on the target model, the first processor may determine whether the target request data meets the first processing condition based on the preset question library; when the target request data meets the first processing condition, the first processor processes the target request data based on the preset question library, so as to avoid processing the target request data through the model when the target request data meets the first processing condition, thereby minimizing the occupation of the baseboard management controller resources by the model.

[0050] In some embodiments, after the first processor determines whether the target request data meets the first processing condition based on the preset question library, when the target request data does not meet the first processing condition, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold.

[0051] In actual execution, the occupancy rate of the first processor may be the occupancy rate of memory, bandwidth, storage, computing, or any theoretically feasible resource.

[0052] In some embodiments, the first processor may monitor its own occupancy rate in real time to obtain its own occupancy rate when the target request data does not meet the first processing condition.

[0053] In some embodiments, when there is no feedback data in the preset question library that matches the target request data (i.e., the target request data does not meet the first processing condition), the first processor may obtain its own occupancy rate.

[0054] In actual execution, the target threshold may be a preset value, and the target threshold may be set according to the environmental operation data.

[0055] In some embodiments, the first processor may compare the obtained occupancy rate of itself with the value of the target threshold to determine whether the occupancy rate is greater than or equal to the target threshold.

[0056] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user. When the target request data does not meet the first processing condition, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold. When the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, the target request data is sent to the second processor. The second processor processes the target request data based on the target model, and the target model is one of at least two types of models, so as to enable the first processor to collaboratively call the first processor and the second processor in the baseboard management controller through its own occupancy rate, reduce the occupancy rate of its own resources for processing request data through the model, so as to flexibly process request data based on multiple models, and achieve the purpose of improving the functional flexibility of the baseboard management controller.

[0057] In some embodiments, when the target request data does not meet the first processing condition, after the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold, when the occupancy rate is less than the target threshold, the first processor processes the target request data based on the target model and obtains the processing result.

[0058] In some embodiments, when the target request data does not meet the first processing condition, after the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold, the first processor may process the target request data based on the target model when its own occupancy rate is less than the target threshold. For example, the target threshold may be 80%, and the first processor may process the target request data based on the target model when its own occupancy rate is less than 80%.

[0059] In some embodiments, the first processor may process the target request data based on the target model by calling its own main processing module and obtain the processing result.

[0060] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user. When the target request data does not meet the first processing condition, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold. When the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, the target request data is sent to the second processor. The second processor processes the target request data based on the target model, and the target model is one of at least two types of models, so as to enable the first processor to collaboratively call the first processor and the second processor in the baseboard management controller through its own occupancy rate, reduce the occupancy rate of its own resources for processing request data through the model, so as to flexibly process request data based on multiple models, and achieve the purpose of improving the functional flexibility of the baseboard management controller.

[0061] In some embodiments, the first processor includes at least one main processing module; when the occupancy rate is less than the target threshold, each main processing module in the at least one main processing module is called to process the target request data based on the target model.

[0062] In some embodiments, the first processor may include a first main processing module, a second main processing module, a third main processing module, and a fourth main processing module.

[0063] In some embodiments, the first processor may, when the occupancy rate is less than the target threshold, call at least one of the first main processing module, the second main processing module, the third main processing module, and the fourth main processing module to process the target request data based on the target model. For example, the first processor may, when the occupancy rate is less than the target threshold, call the first main processing module to process the target request data based on the target model. The first processor may, when the occupancy rate is less than the target threshold, call the second main processing module and the third main processing module to process the target request data based on the target model.

[0064] In some embodiments, the first processor may, when the occupancy rate is less than the target threshold, call the target resources of at least one of the first main processing module, the second main processing module, the third main processing module, and the fourth main processing module to process the target request data based on the target model. For example, the first processor may call the bandwidth resources of the first main processing module, the memory resources of the second main processing module, and the computing resources of the third main processing module to process the target request data based on the target model.

[0065] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate is less than the target threshold, call each main processing module in the at least one main processing module to process the target request data based on the target model, so as to further optimize the allocation of the resources of the first processor, freely schedule each main processing module in the at least one main processing module to process the target request data, improve the resource utilization rate of each main processing module in the first processor, and improve the efficiency of the first processor in processing the target request data.

[0066] In some embodiments, after the first processor determines whether the target request data meets the first processing condition based on the preset question bank, when the target request data does not meet the first processing condition, the first processor determines the request type corresponding to the target request data based on the second processing condition; the first processor determines the target model based on the request type.

[0067] In actual execution, the target request data can be text, an image, or data in any theoretically feasible form. Based on the second processing condition, the first processor can identify and judge the target request data to determine the request type corresponding to the target request data.

[0068] In some embodiments, the hierarchical heterogeneous architecture of the baseboard management controller may include multiple types of models (such as models for answering query requests input by users, models for solving control requests input by users, or any other theoretically feasible models). In some embodiments, the first processor can determine the request type of the target request data (such as a query request or a control request, or any other theoretically feasible request type) based on the second processing condition, and then based on the determined request type, determine the model corresponding to the request type of the target request data as the target model from multiple types of models in the hierarchical heterogeneous architecture of the baseboard management controller.

[0069] According to the request processing method of the embodiments of the present application, the first processor can obtain the target request data input by the user, and when the target request data does not meet the first processing condition, determine the request type corresponding to the target request data based on the second processing condition; based on the request type, determine the target model from at least two types of models and process the target request data based on the target model, so as to determine the target model corresponding to the request type of the target request data from multiple models of the baseboard management controller, process the target request data, and achieve the purpose of flexibly processing request data through multiple models in the baseboard management controller to improve the functional flexibility of the baseboard management controller.

[0070] In some embodiments, the request type includes a query request; when the request type is a query request, the first processor determines the target model from the first type of models.

[0071] In actual execution, the request type of the target request data can be a query request. For example, the target request data can be request data representing a query of the current central processing unit resource occupancy rate, or the target request data can be request data representing a query of a certain type of data in the device database.

[0072] In some embodiments, the first processor can determine the target model from the first type of models when determining that the request type corresponding to the target request data is a query request based on the second processing condition.

[0073] In actual implementation, the first type of model can be a natural language model, and the natural language model can be a pre-trained language model. Generally speaking, it refers to designing a language model training task based on a large-scale corpus (including language training materials such as sentences, paragraphs, etc.), training a large-scale neural network algorithm structure to learn and implement. The finally obtained large-scale neural network algorithm structure and parameters are the pre-trained language model. For subsequent other tasks, feature extraction or task fine-tuning can be performed on the basis of this model to achieve specific task purposes. The idea of pre-training is to first train a task to obtain a set of model parameters, then use this set of model parameters to initialize the network model parameters, and then use the initialized network model to train other tasks to obtain a model adapted to other tasks. By pre-training on a large-scale corpus, the neural language representation model can learn powerful language representation capabilities and can extract rich syntactic and semantic information from the text. The pre-trained language model can provide word elements (tokens) containing rich semantic information and sentence-level features for downstream tasks to use, or directly perform fine-tuning for downstream tasks on the pre-trained model, so as to conveniently and quickly obtain a downstream-specific model. The neural network algorithm structure trained by the pre-trained language model can be CNN, RNN, LSTM, etc., or a model constructed by an attention network, such as transformer, bert, GPT, Clip, etc. This application does not make any limitations here. The attention network refers to a network model trained using the attention mechanism. This model assigns different weights to each part of the input sequence, thereby extracting more important feature information from the input sequence, so that the model finally obtains a more accurate output. Fine-tuning means further training on the dataset for a specific task on the basis of using the pre-trained model to adjust the model parameters to make it better adapt to the target task. During the fine-tuning process, most layers of the pre-trained model are usually frozen, and only the newly added layers or a small number of key layers are trained. Doing so can not only retain the features learned by the pre-trained model, but also quickly adapt to the specific requirements of the new task. In addition, selecting appropriate learning rates and training epochs is also the key to successful fine-tuning.

[0074] In actual implementation, the first type of model can be used to perform information retrieval, and the number of the first type of models is at least one. In some embodiments, in the case where the request type is a query request, a target model can be determined from multiple first type of models.

[0075] According to the request processing method of the embodiments of the present application, the first processor can obtain the target request data input by the user, and when the target request data does not meet the first processing condition, determine the request type corresponding to the target request data based on the second processing condition; based on the request type, determine the target model from at least two types of models and process the target request data based on the target model, so as to determine the target model corresponding to the request type of the target request data from multiple models of the baseboard management controller, and process the target request data, realizing flexible processing of request data through multiple models in the baseboard management controller, so as to achieve the purpose of improving the functional flexibility of the baseboard management controller.

[0076] In some embodiments, the request type includes control requests; when the request type is a control request, the first processor determines the target model from the second type of models.

[0077] In actual execution, the request type of the target request data can also be a control request. For example, the target request data can be request data for requesting image processing, or the target request data can be request data for requesting prediction of the cause of equipment failure and the remaining service life of a certain component of the equipment.

[0078] In actual execution, the second type of models can be various special models for control functions, such as an equipment remaining service life prediction model, a fault judgment model, etc. The second type of models can be used to execute control operations. The number of the second type of models is at least one. In some embodiments, when the request type is a control request, the target model can be determined from multiple second type of models.

[0079] In some embodiments, when the first processor determines that the request type corresponding to the target request data is a control request based on the second processing condition, it can determine the target model that matches the functional requirements of the target request data from multiple second type of models.

[0080] According to the request processing method of the embodiments of the present application, the first processor can obtain the target request data input by the user, and when the target request data does not meet the first processing condition, determine the request type corresponding to the target request data based on the second processing condition; when the request type is a query request, determine the target model from the first type of models; or, when the request type is a control request, determine the target model from the second type of models, and process the target request data based on the target model, so as to determine the target model corresponding to the request type of the target request data from multiple models of the baseboard management controller, and process the target request data, realizing flexible processing of request data through multiple models in the baseboard management controller, so as to achieve the purpose of improving the functional flexibility and scalability of the baseboard management controller.

[0081] In some embodiments, when the request type is a control request, the first processor identifies the content of the target request data, and based on the identification result, determines a target model from a second type of model.

[0082] In actual execution, the identification result may include the functional requirements requested by the target request data, such as predicting the remaining service life of the device, fault judgment, etc.

[0083] In some embodiments, the content such as text and images in the target request data may be identified to obtain an identification result representing the functional requirements requested by the target request data.

[0084] In some embodiments, based on the identification result, among multiple second-type models, the second-type model that matches the functional requirements represented by the identification result is determined as the target model.

[0085] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user, and when the target request data does not meet the first processing condition, determine the request type corresponding to the target request data based on the second processing condition; when the request type is a query request, determine a target model from the first type of model; or, when the request type is a control request, identify the content of the target request data, based on the identification result, determine a target model from the second type of model, and process the target request data based on the target model, so as to determine the target model corresponding to the functional requirements of the target request data from multiple models of the baseboard management controller according to different functional requirements identified from the target request data, and process the target request data, improving the adaptability and scalability of the baseboard management controller.

[0086] In some embodiments, when the target request data does not meet the first processing condition, before the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold, the first processor updates the target threshold based on at least one of the environmental operation data and the historical request processing results.

[0087] In some embodiments, the target threshold may represent a standard for the first processor to determine whether to process the target request data based on the target model by itself or to process the target request data based on the target model by the second processor based on its own occupancy rate. The target threshold may be a set value.

[0088] In actual execution, the environmental operation data may include the resource occupancy rate of the first processor or any other theoretically feasible operation data.

[0089] In some embodiments, when the environmental operation data indicates that the resource occupancy rate status of the first processor is poor, the target threshold can be increased (for example, the target threshold is increased from 80% to 90%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is improved, and the possibility that the first processor processes the target request data based on the target model when its own resources are insufficient is reduced.

[0090] In some embodiments, when the historical request data indicates that the probability of processing the historical request data based on the preset question bank is low, the target threshold can be increased (for example, the target threshold is increased from 80% to 90%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is improved, so as to increase the possibility that the first processor processes the target request data based on the preset question bank when its own resources are insufficient.

[0091] According to the request processing method of the embodiments of the present application, before the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold when the target request data does not meet the first processing condition, the target threshold can be updated based on at least one of the environmental operation data and the historical request processing result, so as to dynamically adjust the frequency of processing the request data through the model based on the environmental operation data and the historical request processing result, and the preprocessing module reduces the load pressure on the first processor. And the mechanism of integrating the preprocessing module and the model not only improves the intelligent level, but also enhances the robustness and stability, and can quickly respond even when facing unknown failure modes.

[0092] In some embodiments, when the environmental operation data and / or the historical request processing result meet the first target update condition, the first processor decreases the target threshold.

[0093] In actual execution, the first target update condition may be that the environmental operation data is greater than the first preset value and / or the historical request processing result is greater than the second preset value.

[0094] In actual execution, the environmental operation data meeting the first target update condition (that is, the environmental operation data is greater than the first preset value) may indicate that the resource occupancy rate status of the first processor is good. The historical request processing result meeting the first target update condition (that is, the historical request processing result is greater than the second preset value) may indicate that the probability of processing the historical request data based on the preset question bank is high.

[0095] In some embodiments, when the environmental operation data indicates that the resource occupancy rate of the first processor is in good condition, the target threshold can be decreased (for example, the target threshold is decreased from 80% to 70%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is lowered according to its own occupancy rate, and the possibility of the first processor processing the target request data based on the target model when its own resources are sufficient is increased.

[0096] In some embodiments, when the historical request data indicates that the probability of processing the historical request data based on the preset question bank is relatively high, the target threshold can be decreased (for example, the target threshold is decreased from 80% to 70%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is lowered according to its own occupancy rate, and the possibility of the first processor processing the target request data based on the target model when its own resources are sufficient is increased.

[0097] According to the request processing method of the embodiments of the present application, before the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold when the target request data does not meet the first processing condition, when the environmental operation data and / or the historical request processing result meet the first target update condition, the first processor can decrease the target threshold, and dynamically adjust the frequency of processing the request data through the model based on the environmental operation data and the historical request processing result, so as to enable the preprocessing module to reduce the load pressure of the first processor. Moreover, the mechanism of integrating the preprocessing module and the model not only improves the intelligent level, but also enhances the robustness and stability, and can quickly respond even when facing unknown failure modes.

[0098] In some embodiments, the second processor includes a first assistance processing module and a second assistance processing module; the target model includes a first model and a second model; when the target model is the first model, the second processor processes the target request data based on the first model through the first assistance processing module; when the target model is the second model, the second processor processes the target request data based on the second model through the second assistance processing module.

[0099] In actual execution, the first model can be one of the first type of models or one of the second type of models. The second model can be one of the first type of models or one of the second type of models.

[0100] In actual execution, the first model can be a model that executes the addition (ADD) algorithm. The second model can be a model that executes a multi-layer multiplication neural network (such as MUL, MUL_MAT, multiplication algorithm, multiplication matrix algorithm) algorithm.

[0101] In some embodiments, after determining the target model, the first processor may send information about the target model to the second processor. When the information about the target model indicates that the target model is the first model, the second processor may, through the first assistance processing module, process the target request data based on the first model. Correspondingly, when the information about the target model indicates that the target model is the second model, the second processor may, through the second assistance processing module, process the target request data based on the second model.

[0102] In some embodiments, the target model may be a model for simultaneously executing multiple algorithms. For example, the target model may execute algorithms such as addition (ADD), multi-layer multiplication neural networks (such as MUL, MUL_MAT, multiplication algorithm, multiplication matrix algorithm), and any theoretically feasible algorithms.

[0103] In some embodiments, the second processor may, through the first assistance processing module, execute the first algorithm of the target model, and the first algorithm may be a partial algorithm that constitutes the target model; the second processor may, through the second assistance processing module, execute the second algorithm of the target model, and the second algorithm may be another partial algorithm that constitutes the target model except for the first algorithm, thereby enabling the second processor to process the target request data based on the target model.

[0104] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. When the target model is the first model, the second processor, through the first assistance processing module, processes the target request data based on the first model; when the target model is the second model, the second processor, through the second assistance processing module, processes the target request data based on the second model, so as to improve the efficiency of obtaining the processing result of the target request data by processing the target request data through the first assistance processing module or the second assistance processing module.

[0105] In some embodiments, after the second processor processes the target request data based on the target model, the first processor may grab the processing result for the target request data from the second processor to avoid the first processor waiting for the second processor to send the processing result.

[0106] In some embodiments, after the second processor processes the target request data based on the target model and obtains the processing result, the first processor may grab the processing result for the target request data based on the inter-core communication between itself and the second processor.

[0107] In some embodiments, after the first processor grabs the processing result for the target request data, the first processor can store or display the processing result.

[0108] According to the request processing method of the embodiments of the present application, the first processor can obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. After the second processor processes the target request data based on the target model, the first processor can grab the processing result for the target request data from the second processor to avoid waiting for the processing result due to communication blockage, thereby improving the processing efficiency and response speed of the target request data.

[0109] In some embodiments, after the first processor grabs the processing result for the target request data from the second processor, the first processor updates the target request data and the processing result to a preset question bank.

[0110] In some embodiments, when the target request data does not meet the first processing condition, after the first processor or the second processor processes the target request data based on the target model, the first processor obtains the processing result for the target request data and updates the target request data and the processing result to a preset question bank.

[0111] In some embodiments, the first processor can update the target request data and the processing result to a preset question bank after grabbing the processing result for the target request data from the second processor. When the first processor obtains the target request data again, the first processor can process the target request data obtained again based on the first processing condition through the preset question bank.

[0112] According to the request processing method of the embodiments of the present application, after the first processor processes the target request data based on the target model, it obtains the processing result for the target request data and updates the target request data and the processing result to a preset question bank, reducing the frequency of model calls in the form of caching, so as to reduce the load pressure through the preprocessing module.

[0113] In some embodiments, after the first processor grabs the processing result for the target request data from the second processor, the first processor can display the processing result for the target request data based on the visualization interface.

[0114] In some embodiments, after the first processor obtains the processing result for the target request data, it can display the processing result for the target request data based on the visualization interface in the form of message prompts, pop - ups or any theoretically feasible form.

[0115] In some actual executions, after the first processor displays the processing result of the target request data, it can obtain further operations from the user.

[0116] According to the request processing method of the embodiments of the present application, after obtaining the processing result of the target request data, the first processor can display the processing result of the target request data based on the visualization interface, so as to quickly discover and solve potential problems, reducing the downtime and maintenance costs caused by equipment failures.

[0117] To better understand the request processing method provided by the embodiments of the present application, further explanations are given below. It should be understood that the following discussions are only exemplary.

[0118] The present application provides a request processing method, and the specific steps can be as Figure 2 shown: Step S210, the first processor obtains the target request data input by the user.

[0119] In some embodiments, the request processing method of this embodiment can be applied to a baseboard management controller, and the baseboard management controller includes at least two types of models, and the number of each type of model is at least one.

[0120] In some embodiments, the first processor can be a Cortex-A multi-core processor.

[0121] In actual execution, the baseboard management controller can be stored in an eMMC (Embedded MultiMediaCard) circuit chip.

[0122] In actual execution, the target request data can be request data for querying information or performing maintenance operations, or any theoretically feasible request data. The target request data can include data in any format, such as text, image and other data, and the present application does not make specific restrictions on this.

[0123] In some embodiments, the first processor in the baseboard management controller can obtain the target request data input by the user through the Basic Input Output System (BIOS).

[0124] In some embodiments, as Figure 3 shown, the first processor in the baseboard management controller and the Basic Input Output System can interact based on the shared memory method (such as H2B, that is, Host to BMC). The baseboard management controller can obtain the target request data input by the user from the Basic Input Output System (BIOS) based on the H2B method.

[0125] Step S213, the first processor determines whether the target request data meets the first processing condition based on a preset question library.

[0126] In some embodiments, as Figure 3 shown, the hierarchical heterogeneous architecture of the baseboard management controller may include a preprocessing module. The first processor may determine whether the target request data meets the first processing condition based on the preset question library through the preprocessing module.

[0127] In some embodiments, the baseboard management controller may obtain target data under the server operating system and store it in the target database. The target data may include the operating data of the server, such as the operating data of the central processing unit or any other theoretically feasible data. The target database may be a Redis database that supports cache and temporary data storage. The target database may be deployed in the baseboard management controller. The baseboard management controller may obtain the target data under the server operating system through the platform environment control interface (PECI).

[0128] In some embodiments, the baseboard management controller may also include memory, such as double data rate SDRAM (DDR), and the baseboard management controller may also include flash memory (FLASH) and the baseboard management controller common basic module (BMC CBB). Communication between the preprocessing module and the flash memory may be based on the serial peripheral interface.

[0129] In some embodiments, the baseboard management controller may communicate with the central processing unit (such as central processing unit 0 and central processing unit 1) based on the platform environment control interface. The server may also include an operating system, memory (such as DDR), a solid state drive (such as NVME (Non-Volatile Memory Express), a non-volatile storage device accessed through the PCIe interface), and a hard disk drive (HDD).

[0130] In some embodiments, a preset question library may be constructed based on the target data stored in the target database. The preset question library may be a quick response entry. The preset question library may store the target data and preset requests corresponding to each piece of data in the target data.

[0131] In some embodiments, the first processor may determine whether the target request data meets the first processing condition based on a preset question bank and the target request data. For example, it retrieves whether there is a preset request in the preset question bank that is approximate to the target request data. For example, whether it can generate feedback data for the target request data based on the target data currently stored in the preset question bank.

[0132] In some embodiments, the first processor may search the preset question bank to find out whether there is feedback data that matches the target request data; if there is feedback data, it determines that the target request data meets the first processing condition.

[0133] In actual execution, the feedback data may be any one of the target data pre-stored in the preset question bank.

[0134] In some embodiments, based on the target request data, it may be retrieved and queried in the preset question bank whether there is feedback data that matches the target request data, that is, whether the preset question bank can process the target request data. If there is feedback data that matches the target request data in the preset question bank, it determines that the target request data meets the first processing condition, and then processes the target request data based on the preset question bank to obtain a processing result.

[0135] In some embodiments, the first processor may retrieve whether there is feedback data that matches the target request data in the preset question bank based on the cosine similarity, Jaccard Index, or any theoretically feasible algorithm.

[0136] In some embodiments, the first processor may compare each existing target data in the preset question bank with the target request data one by one based on the cosine similarity, Jaccard Index, or any theoretically feasible algorithm to retrieve whether there is feedback data that matches the target request data in the preset question bank.

[0137] In some embodiments, when there is no feedback data that matches the target request data in the preset question bank, the first processor determines that the target request data does not meet the first processing condition.

[0138] Step S216, when the target request data meets the first processing condition, the first processor processes the target request data based on the preset question bank.

[0139] In some embodiments, when the target request data meets the first processing condition, the first processor may process the target request data based on the preset question bank. For example, the first processor may generate feedback data for the target request data based on the target data in the preset question bank.

[0140] Step S219, when the target request data does not meet the first processing condition, the first processor determines the request type corresponding to the target request data based on the second processing condition; the first processor determines the target model based on the request type.

[0141] In actual execution, the target request data can be text, an image, or data in any theoretically feasible form. Based on the second processing condition, the first processor can identify and judge the target request data to determine the request type corresponding to the target request data.

[0142] In some embodiments, the hierarchical heterogeneous architecture of the baseboard management controller may include multiple types of models (such as models for answering query requests input by users, models for solving control requests input by users, or any other theoretically feasible types). In some embodiments, the first processor can determine the request type of the target request data (such as a query request or a control request, or any other theoretically feasible request type) based on the second processing condition, and then determine the model corresponding to the request type of the target request data from multiple types of models in the hierarchical heterogeneous architecture of the baseboard management controller as the target model.

[0143] In some embodiments, the request type includes query requests; when the request type is a query request, the first processor determines the target model from the first type of models.

[0144] In actual execution, the request type of the target request data can be a query request. For example, the target request data can be request data representing querying the current CPU resource occupancy rate, or the target request data can be request data representing querying a certain type of data in the device's database.

[0145] In some embodiments, when the first processor determines that the request type corresponding to the target request data is a query request based on the second processing condition, the first processor determines the target model from the first type of models.

[0146] In actual execution, the first type of models can be used to perform information retrieval. The number of the first type of models is at least one, and the first type of models can be natural language models. In some embodiments, when the request type is a query request, the target model can be determined from multiple first type of models.

[0147] In some embodiments, the request type includes control requests; when the request type is a control request, the first processor determines the target model from the second type of models.

[0148] In actual execution, the request type of the target request data can also be a control type request. For example, the target request data can be request data for requesting image processing. For example, the target request data can be request data for requesting prediction of equipment failure causes and the remaining service life of a certain component of the equipment.

[0149] In actual execution, the second type of model can be various models dedicated to control functions, such as an equipment remaining service life prediction model, a fault judgment model, etc. The second type of model can be used to execute control operations. The number of the second type of models is at least one. In some embodiments, when the request type is a control type request, a target model can be determined from multiple second type of models.

[0150] In some embodiments, when the first processor determines that the request type corresponding to the target request data is a control type request based on the second processing condition, the first processor can determine a target model from multiple second type of models that matches the functional requirements of the target request data.

[0151] In some embodiments, when the request type is a control type request, the first processor identifies the content of the target request data, and based on the identification result, determines a target model from the second type of models.

[0152] In actual execution, the identification result can include the functional requirements requested by the target request data, such as prediction of the remaining service life of equipment, fault judgment, etc.

[0153] In some embodiments, the content such as text and images in the target request data can be identified to obtain an identification result representing the functional requirements requested by the target request data.

[0154] In some embodiments, based on the identification result, a second type of model that matches the functional requirements represented by the identification result can be determined as the target model from multiple second type of models.

[0155] In some embodiments, after the first processor determines the target model, the first processor can send the information of the target model to the second processor.

[0156] Step S222, when the target request data does not meet the first processing condition, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold.

[0157] In actual execution, the occupancy rate of the first processor can be the occupancy rate of memory, bandwidth, storage, computing, or any theoretically feasible resource.

[0158] In some embodiments, the first processor can monitor its own occupancy rate in real time to obtain its own occupancy rate when the target request data does not meet the first processing condition.

[0159] In some embodiments, when there is no feedback data in the preset question library that matches the target request data (i.e., the target request data does not meet the first processing condition), the first processor can obtain its own occupancy rate.

[0160] In actual execution, the target threshold can be a preset value, and the target threshold can be set according to the environmental operation data.

[0161] In some embodiments, the target threshold can represent a standard for the first processor to determine whether to process the target request data based on the target model by itself or by the second processor based on the target model based on its own occupancy rate. The target threshold can be a set value.

[0162] In actual execution, the environmental operation data can include the resource occupancy rate of the first processor or any other theoretically feasible operation data.

[0163] In some embodiments, when the environmental operation data indicates that the resource occupancy rate status of the first processor is poor, the target threshold can be increased (for example, the target threshold is increased from 80% to 90%) so that the first processor can improve the standard for determining whether to process the target request data based on the target model based on its own occupancy rate, and reduce the possibility that the first processor processes the target request data based on the target model when its own resources are insufficient.

[0164] In some embodiments, when the historical request data indicates that the probability of processing the historical request data based on the preset question library is low, the target threshold can be increased (for example, the target threshold is increased from 80% to 90%) so that the first processor can improve the standard for determining whether to process the target request data based on the target model based on its own occupancy rate, and improve the possibility that the first processor processes the target request data based on the preset question library when its own resources are insufficient.

[0165] In some embodiments, when the environmental operation data and / or the historical request processing result meet the first target update condition, the first processor decreases the target threshold.

[0166] In actual execution, the first target update condition can be that the environmental operation data is greater than the first preset value and / or the historical request processing result is greater than the second preset value.

[0167] In actual execution, the environmental operation data meeting the first target update condition (i.e., the environmental operation data is greater than the first preset value) can indicate that the resource occupancy rate status of the first processor is good. The historical request processing result meeting the first target update condition (i.e., the historical request processing result is greater than the second preset value) can indicate that the probability of processing the historical request data based on the preset question library is high.

[0168] In some embodiments, when the environmental operation data indicates that the resource occupancy rate of the first processor is in good condition, the target threshold can be reduced (for example, the target threshold is reduced from 80% to 70%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is reduced based on its own occupancy rate, and the possibility of the first processor processing the target request data based on the target model when its own resources are sufficient is improved.

[0169] In some embodiments, when the historical request data indicates that the probability of processing the historical request data based on the preset question bank is relatively high, the target threshold can be reduced (for example, the target threshold is reduced from 80% to 70%), so that the first processor determines that the standard for processing the target request data based on the target model by itself is reduced based on its own occupancy rate, and the possibility of the first processor processing the target request data based on the target model when its own resources are sufficient is improved.

[0170] In some embodiments, the first processor can compare the obtained value of its own occupancy rate with the target threshold to determine whether the occupancy rate is greater than or equal to the target threshold.

[0171] Step S225, when the occupancy rate is less than the target threshold, the first processor processes the target request data based on the target model.

[0172] In some embodiments, when the target request data does not meet the first processing condition, after the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold, the first processor can process the target request data based on the target model when its own occupancy rate is less than the target threshold. For example, the target threshold can be 80%, and the first processor can process the target request data based on the target model when its own occupancy rate is less than 80%.

[0173] In some embodiments, the first processor can process the target request data based on the target model by calling its own main processing module and obtain the processing result.

[0174] In some embodiments, the first processor includes at least one main processing module; when the occupancy rate is less than the target threshold, each main processing module in the at least one main processing module is called to process the target request data based on the target model.

[0175] In some embodiments, the first processor may include a first main processing module, a second main processing module, a third main processing module, and a fourth main processing module.

[0176] In some embodiments, when the occupancy rate is less than the target threshold, the first processor may invoke at least one of the first main processing module, the second main processing module, the third main processing module, and the fourth main processing module to process the target request data based on the target model. For example, when the occupancy rate is less than the target threshold, the first processor may invoke the first main processing module to process the target request data based on the target model. When the occupancy rate is less than the target threshold, the first processor may invoke the second main processing module and the third main processing module to process the target request data based on the target model.

[0177] In some embodiments, when the occupancy rate is less than the target threshold, the first processor may invoke the target resources of at least one of the first main processing module, the second main processing module, the third main processing module, and the fourth main processing module to process the target request data based on the target model. For example, the first processor may invoke the bandwidth resources of the first main processing module, the memory resources of the second main processing module, and the computing resources of the third main processing module to process the target request data based on the target model.

[0178] Step S228: When the occupancy rate is greater than or equal to the target threshold, the first processor sends the target request data to the second processor.

[0179] Step S231: The second processor processes the target request data based on the target model.

[0180] In some embodiments, the second processor includes a first assistance processing module and a second assistance processing module; the target model includes a first model and a second model; when the target model is the first model, the second processor processes the target request data based on the first model through the first assistance processing module; when the target model is the second model, the second processor processes the target request data based on the second model through the second assistance processing module.

[0181] In actual execution, the first model may be one of the first type of models or one of the second type of models. The second model may be one of the first type of models or one of the second type of models.

[0182] In actual execution, the first model may be a model that executes the addition (ADD) algorithm. The second model may be a model that executes a multi-layer multiplication neural network (such as MUL, MUL_MAT) algorithm.

[0183] In some embodiments, after determining the target model, the first processor may send the information of the target model to the second processor. When the information of the target model indicates that the target model is the first model, the second processor may process the target request data based on the first model through the first assistance processing module. Correspondingly, when the information of the target model indicates that the target model is the second model, the second processor may process the target request data based on the second model through the second assistance processing module.

[0184] In some embodiments, after the second processor processes the target request data based on the target model, the second processor obtains the processing result for the target request data and sends the processing result to the first processor.

[0185] In some embodiments, after the second processor processes the target request data based on the target model and obtains the processing result, the second processor may send the processing result to the first processor based on the inter-core communication between itself and the first processor.

[0186] Step S234, the first processor obtains the processing result.

[0187] In some embodiments, after the second processor processes the target request data based on the target model and obtains the processing result, the first processor may grab the processing result for the target request data based on the inter-core communication between itself and the second processor.

[0188] Step S237, the first processor obtains the processing result for the target request data and updates the target request data and the processing result to the preset question library.

[0189] In some embodiments, after obtaining the processing result for the target request data, the first processor may update the target request data and the processing result to the preset question library. When the first processor obtains the target request data again, the first processor may process the target request data obtained again through the preset question library based on the first processing condition.

[0190] In some embodiments, the first processor obtains the processing result for the target request data, updates the target request data and the processing result to the preset question library, and reduces the frequency of model calls in the form of caching, so as to reduce the load pressure through the preprocessing module.

[0191] Step S240, the first processor displays the processing result for the target request data based on the visualization interface.

[0192] In some embodiments, after obtaining the processing result for the target request data, the first processor may display the processing result for the target request data based on the visualization interface in the form of message prompts, pop-up windows, or any theoretically feasible form.

[0193] In some actual executions, after displaying the processing result for the target request data, the first processor may obtain further operations of the user.

[0194] According to the request processing method of the embodiments of the present application, the first processor may obtain the target request data input by the user, and when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. The second processor processes the target request data based on the target model, and the target model is one of at least two types of models, so as to realize the flexible processing of request data by collaboratively invoking the first processor and the second processor in the baseboard management controller based on multiple models, and achieve the purpose of improving the functional flexibility of the baseboard management controller. At the same time, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to the target threshold. When the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to the target threshold, send the target request data to the second processor. The second processor processes the target request data based on the target model, and the target model is one of at least two types of models, so as to realize that the first processor collaboratively invokes the first processor and the second processor in the baseboard management controller through its own occupancy rate, and improve the reliability and stability of the processing process of the target request data.

[0195] The embodiments of the present application also provide a baseboard management controller. The baseboard management controller is used to execute the request processing method in any of the above embodiments.

[0196] In some embodiments, as Figure 4 shown, the embodiments of the present application also provide an electronic device 400, including a processor 401, a memory 402, and a computer program stored on the memory 402 and executable on the processor 401. When the program is executed by the processor 401, it implements each process of the above request processing method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described here again.

[0197] It should be noted that the computer devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0198] The embodiments of the present application also provide a computer-readable storage medium, in which a computer program is stored. The computer program is set to execute the steps in any of the above request processing method embodiments when running.

[0199] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, read-only memory (ROM for short), random access memory (RAM for short), external hard drives, magnetic disks, or optical discs that can store computer programs.

[0200] An embodiment of the present application also provides a computer program product. The above computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above-described request processing method embodiments.

[0201] An embodiment of the present application also provides a computer program product, including a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above-described request processing method embodiments.

[0202] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0203] The above has provided a detailed introduction to a request processing method and program product provided by the present application. Specific examples are used herein to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

[0204] The above has provided a detailed introduction to a control method and program product of a disk array provided by the present application. Specific examples are used herein to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the claims of the present application.

Claims

1. A request processing method, characterized in that, Applied to a baseboard management controller, the baseboard management controller includes a first processor, a second processor, and at least two types of models, and the number of each type of model is at least one; the method includes: The first processor obtains target request data input by a user; When the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to a target threshold, the first processor sends the target request data to the second processor; The second processor processes the target request data based on a target model; the first processing condition is a condition for determining whether to process the target request data using a model, and the target model is one of the at least two types of models.

2. The method according to claim 1, wherein Before the first processor sends the target request data to the second processor when the target request data does not meet the first processing condition and the occupancy rate of the first processor is greater than or equal to a target threshold, the method includes: The first processor determines whether the target request data meets the first processing condition based on a preset question bank; When the target request data meets the first processing condition, the first processor processes the target request data based on the preset question bank.

3. The method according to claim 2, wherein The first processor determines whether the target request data meets the first processing condition based on a preset question bank, including: The first processor searches the preset question bank to find whether there is feedback data matching the target request data; When there is the feedback data, it is determined that the target request data meets the first processing condition.

4. The method according to claim 2, wherein After the first processor determines whether the target request data meets the first processing condition based on a preset question bank, the method includes: When the target request data does not meet the first processing condition, the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to a target threshold.

5. The method according to claim 4, characterized in that, After the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to a target threshold when the target request data does not meet the first processing condition, the method further includes: When the occupancy rate is less than the target threshold, the first processor processes the target request data based on a target model and obtains a processing result.

6. The method according to claim 5, characterized in that, The first processor includes at least one main processing module; when the occupancy rate is less than the target threshold, the first processor processes the target request data based on a target model, including: When the occupancy rate is less than the target threshold, each main processing module in at least one main processing module is called to process the target request data based on a target model.

7. The method according to claim 2, wherein After the first processor determines whether the target request data meets the first processing condition based on a preset question bank, the method further includes: When the target request data does not meet the first processing condition, the first processor determines the request type corresponding to the target request data based on a second processing condition; The first processor determines a target model based on the request type.

8. The method according to claim 7, wherein The request type includes query requests; The first processor determines a target model based on the request type, including: When the request type is a query request, the first processor determines a target model from the first type of models.

9. The method according to claim 7, wherein The request type includes a control request; The first processor determines a target model based on the request type, including: When the request type is a control request, the first processor determines a target model from the second type of models.

10. The method according to claim 9, wherein When the request type is a control request, the first processor determines the target model from the second type of models, including: When the request type is a control request, the first processor identifies the content of the target request data; Based on the identification result, a target model is determined from the second type of models.

11. The method according to claim 4, wherein Before the first processor obtains its own occupancy rate and determines whether the occupancy rate is greater than or equal to a target threshold when the target request data does not meet the first processing condition, the method includes: The first processor updates the target threshold based on at least one of the environment operation data and the historical request processing results.

12. The method according to claim 11, wherein The first processor updates the target threshold based on at least one of the environment operation data and the historical request processing results, including: When the environment operation data and / or the historical request processing results meet the first target update condition, the first processor decreases the target threshold.

13. The method according to claim 1, wherein The second processor includes a first assistance processing module and a second assistance processing module; The target models include a first model and a second model; The second processor processes the target request data based on the target model, including: When the target model is the first model, the second processor processes the target request data based on the first model through the first assistance processing module; When the target model is the second model, the second processor processes the target request data based on the second model through the second assistance processing module.

14. The method according to claim 1, wherein After the second processor processes the target request data based on the target model, the method further includes: The first processor grabs the processing result for the target request data from the second processor to prevent the first processor from waiting for the second processor to send the processing result.

15. The method according to any one of claims 1 to 14, characterized in that, After the first processor grabs the processing result for the target request data from the second processor, the method includes: The first processor updates the target request data and the processing result to a preset question bank.

16. The method according to any one of claims 1 to 14, characterized in that, After the first processor grabs the processing result for the target request data from the second processor, the method further includes: The first processor displays the processing result for the target request data based on a visualization interface.

17. A baseboard management controller, characterized in that, The floor management controller is used to execute the request processing method according to any one of claims 1-16.

18. An electronic device, comprising a memory, a processor, and a computer program stored on the memory, characterized in that, The processor executes the computer program to implement the steps of the request processing method according to any one of claims 1-16.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the request processing method according to any one of claims 1-16 are implemented.

20. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the request processing method according to any one of claims 1-16.

Images