Task processing method and apparatus

Abstract

Disclosed in the embodiments of the present application are a task processing method and apparatus, which are used for improving the accuracy of processing unknown prediction tasks. The method in the embodiments of the present application comprises: a computing device acquiring a machine model and a mechanism model, wherein the machine model is used for predicting mechanism parameters of the mechanism model, and the mechanism model is used for executing an unknown prediction task; the computing device inputting the machine model, as a mechanism parameter of the mechanism model, into the mechanism model, so as to obtain a fused model, and training the fused model on the basis of training data; the computing device updating the mechanism parameters of the mechanism model on the basis of a machine model corresponding to a training result of the fused model, so as to obtain an updated mechanism model, wherein the training result of the fused model is used for indicating a target model parameter of the machine model, which target model parameter is used for determining the mechanism parameters of the updated mechanism model; and the computing device executing the unknown prediction task on the basis of the updated mechanism model.

Description

Task processing method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on August 15, 2023, with application number 202311028800.X and invention name “A task processing method and device”, and priority to the Chinese patent application filed with the State Intellectual Property Office on December 28, 2023, with application number 202311844539.0 and invention name “A task processing method and device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of computers, and in particular to a task processing method and device. Background Art

[0003] With the development of artificial intelligence (AI), machine models are becoming a mainstream solution for solving unknown tasks. This refers to the problem in machine learning where computing devices attempt to solve tasks they have never seen or been trained on. Typically, machine models require specific types of training data during the training phase in order to accurately predict similar tasks during the testing phase.

[0004] To improve the effectiveness of machine models in processing unknown tasks, it is currently common to integrate machine models with mechanism models. There are many ways to integrate machine and mechanism models. For example, a computing device can integrate the machine and mechanism models to create an integrated model, train the integrated model using training data, and then use the trained integrated model to predict unknown tasks.

[0005] In the current integration method, when a computing device predicts an unknown task based on an integrated model, the sum of the prediction results of the mechanism model and the machine model is used to obtain the prediction result of the unknown task. Since the mechanism model and the machine model in the integrated model maintain their respective independence, the mechanism model and the machine model jointly play a role in the prediction result. Since the machine model is a black box model, the model has poor interpretability. At the same time, the machine model directly affects the prediction result, which leads to poor interpretability of the integrated model.

[0006] Summary of the Invention

[0007] The embodiment of the present application provides a task processing method, in which a computing device can generate a fusion model using a machine model as the mechanism parameter of a mechanism model, train the fusion model, and update the mechanism parameters of the mechanism model based on the machine model corresponding to the training result of the fusion model. Since the machine model is used to predict the mechanism parameters and does not directly act on the prediction results of unknown tasks, the embodiment of the present application improves the prediction accuracy of the mechanism model for unknown tasks while ensuring the interpretability of the prediction results. The embodiment of the present application also provides a task processing device, a computing device, a computing device cluster, a computer-readable storage medium, and a computer program product corresponding to the task processing method.

[0008] In the first aspect, an embodiment of the present application provides a task processing method, which can be executed by a computing device, or by a component of the computing device, such as a processor, chip or chip system of the computing device, or by a logic module or software that can realize all or part of the functions of the computing device. The method provided in the first aspect includes: the computing device acquires a machine model and a mechanism model, the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to perform unknown prediction tasks. The computing device uses the machine model as the mechanism parameter of the mechanism model to obtain a fusion model, and trains the fusion model based on the training data. The computing device updates the mechanism parameters of the mechanism model based on the machine model corresponding to the training result of the fusion model to obtain an updated mechanism model, and the training result of the fusion model is used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model. The computing device performs the unknown prediction task based on the updated mechanism model.

[0009] Mechanism parameters of the mechanism model In the embodiment of the present application, the computing device can determine the mechanism parameters of the mechanism model by training the fusion model. Since the machine model in the fusion model does not directly act on the prediction results of the unknown prediction task, that is, the machine model and the mechanism model are decoupled from each other, the mechanism model in the embodiment of the present application supports the fusion of multiple machine models, thereby improving the prediction accuracy of the mechanism model for unknown tasks while ensuring the interpretability of the prediction results of the unknown prediction task.

[0010] In one possible implementation, before determining the trained fusion model, the computing device obtains training data and model constraint information. The model constraint information is used to constrain the range of mechanism parameters in the mechanism model. The computing device trains the fusion model based on the training data to obtain a trained machine model. The model output of the trained machine model satisfies the model constraint information. For example, the model constraint information may constrain the slope of the mechanism model. The model constraint information may include an upper bound, a lower bound, and a positive or negative correlation.

[0011] In the embodiments of the present application, the computing device can train the fusion model based on the model constraint information, thereby reducing the training range of the machine model and improving the training efficiency of the fusion model. At the same time, the computing device uses the model constraint information to constrain the range of model parameters in the mechanism model, so that the fusion model obtained by fusing different machine models has a high degree of physical consistency.

[0012] In one possible implementation, a computing device performs data augmentation on the training data of the fusion model based on a data augmentation strategy to obtain augmented training data, and the augmented training data is used to train the fusion model. Specifically, the computing device selects a data augmentation strategy for the training data based on model constraint information, and performs data augmentation on the training data of the fusion model based on the data augmentation strategy.

[0013] In the embodiment of the present application, the computing device can select a data augmentation strategy for training data based on model constraint information, and generate augmented training data based on the data augmentation strategy, thereby improving the data quality of the augmented training data and further improving the training efficiency of the fusion model.

[0014] In one possible implementation, the computing device updates the data augmentation strategy based on the deviation between the machine model output corresponding to the augmented training data and the model constraint information, and regenerates the augmented training data based on the updated data augmentation strategy. Updating the data augmentation strategy includes reselecting the data augmentation strategy or adjusting the original data augmentation strategy.

[0015] In the embodiment of the present application, the computing device updates the data augmentation strategy based on the deviation between the machine model output and the model constraint information corresponding to the augmented training data, and regenerates the augmented training data based on the updated data augmentation strategy, thereby improving the data quality of the augmented training data and further improving the training efficiency of the fusion model.

[0016] In one possible implementation, the computing device calculates an inference deviation based on the inference results of the trained fusion model on the test data and the inference results of the mechanism model on the test data. The computing device then modifies the model parameters of the trained fusion model based on the inference deviation. For example, domain experts can conduct mechanistic research based on the inference deviation to assist in updating the mechanism model.

[0017] In the embodiment of the present application, the computing device calculates the inference deviation based on the inference results of the trained fusion model on the test data and the inference results of the mechanism model on the test data, and corrects the mechanism analysis model parameters of the trained fusion model based on the inference deviation, thereby improving the prediction accuracy of the mechanism model for unknown tasks.

[0018] In one possible implementation, a computing device calculates model parameters corresponding to different test data based on the trained machine model. The model parameters corresponding to the different test data are used to calculate the constraint satisfaction of the model constraint information. The computing device evaluates the reliability of the model constraint information based on the constraint satisfaction.

[0019] In the embodiment of the present application, the computing device calculates the model parameters output by the machine model after training based on different test data, and calculates the satisfaction degree of the model parameters output by the machine model with the model constraint information, thereby evaluating the reliability of the model constraint information and updating the model constraint information, further improving the prediction accuracy of the mechanism model for unknown tasks.

[0020] In one possible implementation, before executing an unknown prediction task, the computing device needs to identify the received task as an unknown prediction task. If the prediction task is identified as an unknown prediction task, the unknown prediction task is executed based on the trained fusion model. If the prediction task is identified as a known task, the unknown prediction task is executed based on the conventional model.

[0021] In the embodiment of the present application, before the computing device executes an unknown prediction task, the computing device needs to identify the unknown prediction task for the received task and use a conventional model to process the known task, thereby improving the task processing efficiency of the computing device.

[0022] In one possible implementation, when a computing device fuses a machine model and a mechanism model to obtain a fused model, the machine model and the mechanism model may be fused in a differentiable or non-differentiable manner. Different fusion methods for obtaining the fused model correspond to different training methods. The fused model corresponding to non-differentiable fusion is iteratively trained using an inverse coefficient solution method, while the fused model corresponding to differentiable fusion is trained using a backpropagation method.

[0023] In the embodiment of the present application, the computing device adopts a variety of fusion methods based on the characteristics of the mechanism model to obtain a fusion model, thereby improving the feasibility of the solution.

[0024] In one possible implementation, the data augmentation strategy includes one or more of the following: domain knowledge-based augmentation, adaptive augmentation, randomized augmentation, and hybrid augmentation. These data augmentation strategies can also be categorized as image data augmentation or text data augmentation, depending on the type of training data.

[0025] In the embodiment of the present application, the computing device can generate augmented training data based on multiple data augmentation strategies, thereby improving the training effect of the augmented training data on the fusion model, and further improving the accuracy of the mechanism model after training.

[0026] In one possible implementation, the computing device may search for data augmentation strategies based on the fusion model. For example, during the data augmentation process, the computing device may predict and evaluate the augmented training data based on the fusion model and select a corresponding data augmentation strategy based on the prediction and evaluation results.

[0027] In the embodiment of the present application, a fusion model can be introduced in the data augmentation strategy search process of the computing device, and the corresponding data augmentation strategy can be selected based on the prediction and evaluation results of the augmented training data by the fusion model, thereby improving the data quality of the augmented training data.

[0028] In a second aspect, an embodiment of the present application provides a task processing device, which includes an interface unit, a training unit, and a processing unit. The interface unit is used to obtain a machine model and a mechanism model, the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to perform unknown prediction tasks. The training unit is used to use the machine model as the mechanism parameter of the mechanism model to obtain a fusion model, and train the fusion model based on the training data. The processing unit is used to update the mechanism parameters of the mechanism model based on the machine model corresponding to the training result of the fusion model to obtain an updated mechanism model, and the training result of the fusion model is used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model. The processing unit also performs unknown prediction tasks based on the updated mechanism model.

[0029] In one possible implementation, training data and model constraint information are obtained, where the model constraint information is used to constrain the range of mechanism parameters in the fusion model. The training unit is further configured to train the fusion model based on the training data to obtain a trained fusion model, where the mechanism parameters of the trained fusion model satisfy the model constraint information.

[0030] In a possible implementation, the device further includes a data unit, which is used to perform data augmentation on the training data of the fusion model based on a data augmentation strategy to obtain augmented training data, and the augmented training data is used to train the fusion model.

[0031] In one possible implementation, the data unit is further configured to update a data augmentation strategy based on a deviation between a machine model output corresponding to the augmented training data and model constraint information, and to regenerate augmented training data based on the updated data augmentation strategy.

[0032] In one possible embodiment, the device also includes an analysis unit, which is used to calculate the inference deviation based on the inference results of the trained fusion model on the test data and the inference results of the mechanism model on the test data, and to correct the model parameters of the trained fusion model based on the inference deviation.

[0033] In one possible embodiment, the apparatus further includes an analysis unit, which is further configured to calculate model parameters corresponding to different test data based on the trained machine model. The model parameters corresponding to the different test data are used to statistically calculate the constraint satisfaction of the model constraint information. The reliability of the model constraint information is evaluated based on the constraint satisfaction.

[0034] In a third aspect, an embodiment of the present application provides a computing device, comprising a processor coupled to a memory, the processor being used to store instructions. When the instructions are executed by the processor, the computing device executes the method described in the first aspect or any possible implementation of the first aspect.

[0035] In a fourth aspect, an embodiment of the present application provides a computing device cluster, which includes one or more computing devices, each of which includes a processor coupled to a memory, and the processor is used to store instructions. When the instructions are executed by the processor, the computing device cluster executes the method described in the first aspect or any possible implementation method of the first aspect.

[0036] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed, the computer executes the method described in the first aspect or any possible implementation method of the first aspect.

[0037] In a sixth aspect, an embodiment of the present application provides a computer program product, which includes instructions. When the instructions are executed, the computer implements the method described in the first aspect or any possible implementation method of the first aspect.

[0038] It can be understood that the beneficial effects that can be achieved by any of the task processing devices, computing devices, computing device clusters, computer-readable media or computer program products provided above can refer to the beneficial effects in the corresponding methods and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG1 is a schematic diagram of the system architecture of a task processing system provided in an embodiment of the present application;

[0040] FIG2 is a flowchart of a task processing method provided in an embodiment of the present application;

[0041] FIG3 is a flow chart of another task processing method provided in an embodiment of the present application;

[0042] FIG4 is a schematic diagram of a model training process provided in an embodiment of the present application;

[0043] FIG5 is a schematic diagram of a model reasoning process provided in an embodiment of the present application;

[0044] FIG6 is a schematic diagram of a task processing device provided in an embodiment of the present application;

[0045] FIG7 is a schematic diagram of the structure of a computing device provided in an embodiment of the present application;

[0046] FIG8 is a schematic diagram of the structure of a computing device cluster provided in an embodiment of the present application;

[0047] FIG9 is a schematic diagram of the structure of another computing device cluster provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] Embodiments of the present application provide a task processing method and apparatus for improving the interpretability of prediction results of a computing device for unknown tasks.

[0049] The terms "first," "second," "third," "fourth," and the like (if any) in the specification and claims of this application and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0050] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0051] First, some terms involved in the embodiments of the present application are introduced to facilitate those skilled in the art to understand the technical solutions.

[0052] Unknown tasks refer to test cases during model testing that degrade the machine model's prediction performance due to significant differences in their distribution from the training samples. Unknown task processing involves performing additional processing on unknown task cases to achieve better prediction results beyond the standard process.

[0053] Data scenarios refer to data with different, artificially defined distributions. For example, data that approximates the training set distribution, data that deviates significantly from the training set distribution, data that performs well with machine models, and data that performs well with mechanism models all fall into different scenarios. A scenario classifier is a classifier that predicts data scenarios.

[0054] In order to make the technical solution of the present application clearer and easier to understand, the system architecture of the present application is introduced below with reference to the accompanying drawings.

[0055] Please refer to Figure 1, which is a schematic diagram of the system architecture of a task processing system provided as an example in this application. In the system architecture shown in Figure 1, the task processing system 10 includes a cloud-side subsystem 100 and an edge-side subsystem 200, wherein the cloud-side subsystem 100 includes a global management node 101, a cloud-side local control node 102, a model training node 103, and a cloud-side computing node 104, and the edge-side subsystem 200 includes an edge-side local control node 201, an edge-side computing node 202, and a terminal node 203. The specific functions of each part of the task processing system 10 are described below.

[0056] Global management node 101 is used to manage and coordinate the activities of various subsystems and modules in task processing system 10, including resource allocation and scheduling, task coordination and communication, fault detection and recovery, etc. Global management node 101 includes a model and dataset management module 1011 and a control module 1012. Model and dataset management module 1011 is used to manage models and datasets in the knowledge base. The models in the knowledge base include fused models composed of machine models and mechanism models, and the datasets include training datasets for the fused models.

[0057] The control module 1012 is used to manage the cloud-side local management node 102 and the cloud-side computing node 104, including creating the cloud-side computing node 104 and controlling the cloud-side computing node 104 to process unknown tasks, sending a model training control signal to the cloud-side local management node 102 based on the model training application sent by the cloud-side computing node 104, etc.

[0058] The cloud-side local management node 102 is used to distribute control instructions from the global management node 101 and configure the model training node 103. Specifically, the cloud-side local management node 102 receives control instructions from the global management node 101 and sends control instructions to the model training node 103. The control instructions can be model training instructions. The cloud-side local management node 102 can also configure model constraint information for the model training node 103 to perform model training.

[0059] Model training node 103 is used to train the fusion model and store the trained fusion model in a cloud storage system. Model training node 103 includes a data preprocessing module 1031, a fusion module 1032, and a training module 1033. Data preprocessing module 1031 is used to augment training data based on model constraint information to obtain a training dataset for the fusion model. Fusion module 1032 is used to fuse the machine model and the mechanism model to generate a fusion model. Training module 1033 is used to train the fusion model based on the training dataset and store the trained model in a cloud storage system.

[0060] The cloud-side computing node 104 is responsible for managing the knowledge base and processing unknown tasks based on the fusion model. It includes a knowledge base management module 1041 and an unknown task processing module 1042. The knowledge base management module 1041 manages the knowledge base corresponding to different tasks. Knowledge base management includes initialization, updates, and sharing of historical knowledge bases. The knowledge base includes a variety of machine models and mechanism models. The unknown task processing module 1042 receives unknown tasks, obtains the corresponding fusion model, and performs reasoning on the unknown tasks.

[0061] The edge local control node 201 is used to manage edge data and model resources, including controlling the working status and resources of the edge compute node 202. Specifically, the global management node 101 can create an edge local control node 201 on the edge. The edge local control node 201 receives control instructions sent by the global management node 101 and, based on the control instructions, initiates model deployment and unknown task processing on the edge compute node 202.

[0062] The edge computing node 202 is used to identify unknown tasks from the terminal node 203 and upload them to the cloud storage system. The edge computing node 202 notifies the global management node 101 through the edge local control node 201 to process the unknown tasks. The edge computing node 202 is also used to receive updated mechanism models from users and push the mechanism models to the cloud-side subsystem 100, thereby updating the mechanism model of the cloud-side subsystem. The edge computing node 202 is also used to obtain a trained fusion model from the cloud storage system and perform unknown task inference on the edge based on the fusion model.

[0063] The edge computing node 202 includes a system library module 2021, an unknown task identification module 2022, an edge reasoning module 2023, and a mechanism model configuration module 2024. The system library module 2021 is used to provide a calling interface for the model training node 103 and the cloud-side computing node 104. The terminal node 203 can call the model training and reasoning services provided by the cloud-side subsystem 100 through the system library module 2021. The unknown task identification module 2022 is used to receive and identify unknown tasks sent by the terminal node 203. The edge reasoning module 2023 is used to execute unknown tasks using a fusion model. The mechanism model configuration module 2024 is used to receive the mechanism model provided by the user and update the mechanism model in the cloud storage system.

[0064] Terminal node 203 includes a data acquisition and instruction forwarding module 2031 and a device module 2032. The data acquisition and instruction forwarding module 1031 is configured to receive prediction results from edge computing node 202 and send control instructions to device module 2032 based on the prediction results. The data acquisition and instruction forwarding module 1031 is also configured to obtain sensor data, such as quality inspection data from device module 2032, and send the sensor data to edge computing node 202.

[0065] The device module 2032 is used to receive and execute control instructions sent by the data acquisition and instruction forwarding module 2031. The device module 2032 can specifically execute devices, such as controlled devices, input control pipelines, and monitoring instruments.

[0066] Based on the task processing system 10 shown in Figure 1, the present application further provides a task processing method. The task processing method provided by the embodiment of the present application is introduced below in conjunction with an embodiment.

[0067] Please refer to Figure 2, which is a flowchart of a task processing method provided by an embodiment of the present application. In the example shown in Figure 2, the method includes the following steps:

[0068] 201. The task processing system 10 obtains a machine model and a mechanism model, wherein the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to execute an unknown prediction task.

[0069] The task processing system 10 receives unknown prediction tasks, wherein the unknown prediction tasks may be unknown prediction tasks sent from terminal devices, such as anomaly detection tasks, future trend prediction tasks, risk assessment tasks, and user behavior prediction tasks.

[0070] For example, in one example of step 201, the task processing system 10 receives an unknown prediction task, which is a coal production quality prediction task. The coal production quality prediction task is a regression prediction task. In this coal production quality prediction task, the task processing system 10 needs to predict the quality of the produced coke based on the detection indicators of the raw coal and various production parameters in coal production. The detection indicators of the raw coal and the various production parameters in coal production include data of multiple dimensions, such as the elements, batching ratio, and moisture content of the raw coal.

[0071] For another example, in step 201, the task processing system 10 receives an unknown prediction task, which is a human body temperature perception prediction task. In this human body temperature perception prediction task, the task processing system 10 needs to predict the human body temperature perception based on multiple collected data, such as the normal human metabolic rate MET, human excess work WME, air temperature TA, water vapor pressure PA, and mean radiant temperature TR.

[0072] In one possible implementation, before executing an unknown prediction task, the task processing system 10 needs to perform unknown prediction task identification on the received task. Specifically, after receiving the prediction task sent by the terminal device, the task processing system 10 performs unknown task identification on the prediction task. If the prediction task is identified as an unknown prediction task, the unknown prediction task is executed based on the trained mechanism model. If the prediction task is identified as a known task, the unknown prediction task is executed based on the conventional model.

[0073] Please refer to Figure 3, which is a flowchart of another task processing method provided by an embodiment of the present application. In the example shown in Figure 3, after receiving task data, the task processing system 10 performs unknown task identification based on the task data. When the task data is identified as a known task, the task processing system 10 executes the task using the conventional model corresponding to the known task. When the task data is identified as an unknown task, the task processing system 10 inputs the task data into a trained mechanism model, and the trained mechanism model executes the unknown task.

[0074] Before the task processing system 10 receives an unknown prediction task, the task processing system 10 needs to obtain a mechanism model and a machine model, and generate a fusion model based on the machine model and the mechanism model, wherein the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to execute the unknown prediction task.

[0075] 202. The task processing system 10 uses the machine model as the mechanism parameter of the mechanism model to obtain a fusion model, and trains the fusion model based on the training data.

[0076] After acquiring the mechanism model and the machine model, the task processing system 10 generates a fusion model based on the machine model and the mechanism model. Specifically, the task processing system 10 inputs the machine model as the mechanism parameter of the mechanism model into the mechanism model to obtain the fusion model. The task processing system 10 then trains the fusion model based on the training data. The following details the process:

[0077] The task processing system 10 first generates a fusion model and then trains the fusion model based on the training data to obtain a trained fusion model. The training results of the fusion model include a trained machine model. The mechanism model is used to perform unknown prediction tasks, and the trained machine model is used to update the mechanism parameters in the mechanism model.

[0078] Specifically, when task processing system 10 acquires the fusion model, it separately acquires the mechanism model and the machine model, and inputs the machine model into the mechanism model as a mechanism parameter of the mechanism model to obtain the fusion model. For example, model training node 103 of cloud-side subsystem 100 acquires the machine model and the mechanism model from the knowledge base, and generates the fusion model based on the fusion of the mechanism model and the machine model.

[0079] Please refer to Figure 4, which is a flow chart of a fusion model training process provided by an embodiment of the present application. In the example shown in Figure 4, the model training node 103 obtains the machine model and mechanism model in the knowledge base. For example, the machine model is a machine learning model selected by the user or the system default. ml The mechanism model is the formula f obtained by the user to model the actual problem phy The model training node 103 generates a fusion model based on the fusion of the mechanism model and the machine model. The fusion of the mechanism model and the machine model includes differentiable fusion and non-differentiable fusion. Differentiable fusion means that differential operations can be performed during the fusion process. Non-differentiable fusion means that differential operations cannot be performed during the fusion process.

[0080] For example, in the above-mentioned coal production quality prediction task example, the mechanism model obtained by the task processing system 10 is a linear function, for example, the formula of the mechanism model satisfies f phy (x) = b + a1x1 + a2x3 + a3x4, the task processing system 10 obtains the machine models respectively and The task processing system 10 obtains a fusion model based on the mechanism model and the machine model, which satisfies the following:

[0081] Among them, x r represents the input of the machine model, and The initial values ​​are 55, -24.3, 29.3 and 5.8.

[0082] For another example, in the human body temperature perception prediction task, the task processing system 10 determines the mechanism model based on the calculation formula of the predicted mean evaluation value PMV. The mechanism formula of the mechanism model is as follows: pmv = (0.03+0.3*exp(-2.1*met))*(-0.08*met*(34-ta)-0.001*met*(5867-pa)+ 59.4*met+0.003*met-59.4*wme-max(0,24.4met-24.4wme-24.4)-17.5-others).

[0083] Among them, pmv is the predicted mean evaluation value, met is the normal metabolic rate of the human body, ta is the air temperature, pa is the water vapor pressure, and wme is the extra work done by the human body.

[0084] In the above-mentioned human body temperature perception prediction task processing process, the task processing system 10 uses multiple neural network models a i Predict the constant parameters in the above mechanism formula respectively, and obtain a fusion model including the mechanism model and the neural network model. First, make the neural network learn a i The original constant parameters are then calculated using a neural network during the training process to further calculate the PMV value. The task processing system 10 calculates the loss value based on the label of the human body temperature perception and uses normal back propagation to train the network. The calculation of the loss value satisfies the following formula:

[0085] In the example shown in Figure 4, if the model coefficients of the mechanism model can be inversely solved, for example, if the mechanism model is a linear function, then the mechanism model and the machine model are non-differentiably fused. If the model structure of the mechanism model is more complex, for example, if the mechanism model is a discrete function, and the machine model supports backpropagation, then the mechanism model and the machine model are differentially fused.

[0086] It should be noted that both fusion methods use machine models to predict the mechanism parameters of the mechanism model. The two fusion methods correspond to different training methods. The fusion model corresponding to non-differentiable fusion uses the inverse coefficient method for iterative training, while the fusion model corresponding to differentiable fusion uses the back propagation method for training.

[0087] 203. Based on the machine model corresponding to the training result of the fusion model, the mechanism parameters of the mechanism model are updated to obtain an updated mechanism model.

[0088] The task processing system 10 updates the mechanism parameters of the mechanism model based on the machine model corresponding to the training results of the fusion model to obtain an updated mechanism model. The training results of the fusion model are used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model.

[0089] In the embodiment of the present application, the updated mechanism model can also be called the trained fusion model, because the relationship between the fusion model and the mechanism model in the present application is that when the mechanism parameters in the mechanism model are the machine model, the mechanism model can also be called the fusion model, and when the mechanism parameters in the mechanism model are the deterministic mechanism parameters output by the machine model (the deterministic mechanism parameters are the machine parameters output by the machine model when the model parameters of the machine model are the target model parameters), the mechanism model is the updated mechanism model.

[0090] In one possible implementation, the task processing system 10 obtains training data and model constraint information, wherein the training data includes an augmented training dataset obtained by data augmentation based on a data augmentation strategy, and the model constraint information is used to constrain the range of model parameters in the mechanism model. For example, when the mechanism model is a linear function, the model constraint information can constrain the slope of the mechanism model, and the model constraint information includes an upper bound, a lower bound, and a positive or negative correlation of the slope. The task processing system 10 trains the fusion model based on the training data to obtain a trained machine model, and the trained machine model satisfies the model constraint information.

[0091] For example, in an example of a coal production quality prediction task, for the fusion model The model constraint information obtained by the task processing system 10 satisfies the following:

[0092] Please continue to refer to Figure 4. In the example shown in Figure 4, after the model training node 103 obtains the fusion model based on the machine model and the mechanism model, it trains the fusion model based on the training data set. For example, for the training of the fusion model obtained by differentiable fusion, the model training node 103 embeds the machine model as a mechanism parameter into the mechanism model for joint training, and updates the model parameters of the machine model through the backpropagation algorithm. Specifically, the model training node 103 defines the loss function of the fusion model. The loss function can measure the difference between the predicted results and the actual results of the fusion model. During the fusion model training process, the model training node 103 updates the model parameters of the machine model based on the loss function.

[0093] For another example, for the training of the fusion model obtained by non-differentiable fusion, the model training node 103 determines the training data of the machine model based on the inverse solution of the training data of the fusion model. The model training node 103 trains the machine model based on the training data obtained based on the inverse solution coefficients, and then embeds the trained machine model into the mechanism model to obtain the fusion model.

[0094] In one possible implementation, during the process of acquiring training data, the task processing system 10 performs data augmentation on the training data of the fusion model based on a data augmentation strategy to obtain augmented training data. The augmented training data is then used to train the fusion model. Specifically, the model training node 103 searches for a data augmentation strategy based on the training data and model constraint information. After determining the data augmentation strategy, the model training node 103 performs data augmentation based on the data augmentation strategy.

[0095] In the embodiments of the present application, the data augmentation strategy includes one or more of the following data augmentation strategies: an augmentation strategy based on domain knowledge, an adaptive augmentation strategy, a randomized augmentation strategy, and a hybrid augmentation strategy. Among them, the augmentation strategy based on domain knowledge refers to targeted data augmentation based on knowledge of a specific domain or task. The adaptive augmentation strategy automatically adjusts the data augmentation strategy based on the feedback information of the fusion model during the training process. The randomized augmentation strategy randomly selects augmentation operations and parameters within a certain augmentation space. The hybrid augmentation strategy is a data augmentation strategy that combines multiple augmentation methods.

[0096] It can be understood that for different types of training data, data augmentation strategies can also be divided into image data augmentation strategies or text data augmentation strategies according to the type of training data. For example, the data augmentation operations in the image data augmentation strategy include data flipping, data cropping or data scaling, and the data augmentation operations in the text data augmentation strategy include synonym replacement, word insertion or word deletion, etc.

[0097] In the embodiments of the present application, the corresponding augmentation parameters in the data augmentation strategy include augmentation slope, augmentation amplitude, and augmentation count. The augmentation slope describes the parameter adjustment range for continuous transformations during the augmentation operation. The augmentation amplitude represents the degree or magnitude of the augmentation operation. The augmentation count refers to the number of times the augmentation operation is repeated.

[0098] Continuing with FIG. 4 , in the example shown in FIG. 4 , when model training node 103 performs training data augmentation based on model constraint information and training data, model training node 103 analyzes data characteristics based on the training data and performs clustering based on these characteristics. Model training node 103 then selects a data augmentation strategy based on the clustering results and the model constraint information, and performs data augmentation based on the augmentation strategy to obtain augmented training data.

[0099] In the example shown in FIG4 , after clustering the training data based on its characteristics, model training node 103 counts points in the training data whose distance deviation from the cluster center exceeds a threshold, and identifies these points as outliers. Model training node 103 can analyze these outliers, for example, by analyzing their distribution characteristics, and adjust the data augmentation strategy based on the analysis results. Furthermore, model training node 103 can also analyze outliers in the augmented training data after data augmentation and update the data augmentation strategy based on the analysis results.

[0100] In one possible implementation, while the model training node 103 searches for a data augmentation strategy based on the model constraint information and generates augmented training data, the model training node 103 updates the data augmentation strategy based on the deviation between the machine model output corresponding to the augmented training data and the model constraint information, and regenerates the augmented training data based on the updated data augmentation strategy. Updating the data augmentation strategy includes reselecting a data augmentation strategy or adjusting the original data augmentation strategy.

[0101] Please continue to refer to Figure 4. In the example shown in Figure 4, when the model training node 103 searches for a data augmentation strategy based on model constraint information, the model training node 103 can input the augmented training data into the machine model and select a data augmentation strategy based on the deviation between the machine model output and the model constraint information.

[0102] In one possible implementation, the task processing system 10 may also search for data augmentation strategies based on the fusion model. Specifically, the model training node 103 searches for data augmentation strategies based on the fusion model and model constraint information. For example, during the data augmentation process, the model training node 103 may predict and evaluate the augmented training data based on the fusion model and select a corresponding data augmentation strategy based on the prediction and evaluation results.

[0103] For example, in the above-mentioned coal production quality prediction task example, the training data set acquired by the task processing system 10 satisfies D={(x i ,y i )}, then the augmented training data set satisfies the following formula:

[0104] Among them, k is the augmentation slope, that is, the slope that the augmented data is expected to reach, within the slope constraint interval, σ is the augmentation amplitude, and the augmentation multiple is N, which means that N augmentations are performed, so that |D aug |=N|D|.

[0105] In the above example, the task processing system 10 discretizes the slope requirement interval of each dimension. For example, the slope constraint interval for dimension 1 is [-30, -20], and then discretizes to obtain 5 values ​​[-30, -27.5, -25, -22.5, -20], reducing the search space. The task processing system 10 obtains the augmentation multiple interval [0, 1, 2, 3] and the augmentation amplitude range [0, 0.5, 1] ​​through hyperparameters. The task processing system 10 traverses the augmentation slope value of each dimension, and experimentally verifies that the error of the model trained on the augmented data shows a convex function relationship with the augmentation multiple and augmentation amplitude on the data before augmentation. The task processing system 10 sets the initial value of the augmentation multiple to 0 and the initial value of the augmentation amplitude to 0. Monotonically increase the augmentation multiple and augmentation amplitude, record the prediction error and constraint satisfaction of the model on the original data under the current augmentation strategy, and obtain the augmentation penalty value. Error = Error mac +C*Error slope

[0106] Among them, C is a hyperparameter used to measure the slope satisfaction and model prediction accuracy. Represents the estimated slope of the model on the constrained dimension for the current batch of data. For the estimated slope of the model in dimension 1, consider the partial order dependence function For x1 and Do linear regression and get the estimated slope When the error value increases, the search stops. The data augmentation strategy for the current batch augmentation slope value is saved. The augmentation slope and corresponding data augmentation strategy with the lowest error value are returned.

[0107] Continuing with FIG4 , in the example shown in FIG4 , model training node 103 can use the fusion model as input for searching for data augmentation strategies. It is understood that when the fusion model is used as input, model training node 103 searches for data augmentation strategies based on the fusion model, which increases search time but improves the accuracy of the data augmentation strategies. Alternatively, model training node 103 may not input the fusion model during the data augmentation strategy search; instead, it may use the default algorithm to search for data augmentation strategies.

[0108] After the task processing system 10 trains the fusion model based on the augmented training data, it determines the trained mechanism model based on the training results of the fusion model. The training results of the fusion model include the trained machine model. The trained machine model is used to output updated parameters. The task processing system 10 updates the mechanism model based on the updated parameters to obtain the trained mechanism model.

[0109] For example, in the above-mentioned coal production quality prediction task, during the training of the fusion model, the task processing system 10 iterates N times. In each iteration, the machine model satisfies the following conditions:

[0110] The cut(x) function trims out-of-bounds values. For example, if the slope constraint of the first dimension is (-30, -20), then if the value of x is not within the interval (-30, -20), the value of x1 is forced to be the nearest boundary value -30 or -20.

[0111] Please refer to Figure 5, which is a schematic diagram of a flow chart illustrating reasoning using a fusion model according to an embodiment of the present application. In the example shown in Figure 5, the task processing system 10 performs reasoning on a trained mechanism model based on test data, where the test data includes unknown prediction tasks. Specifically, the task processing system 10 inputs the test data into the trained mechanism model to obtain reasoning results.

[0112] In one possible implementation, the task processing system 10 calculates an inference deviation based on the inference results of the trained mechanism model on the test data and the inference results of the mechanism model on the test data, and modifies the model parameters of the trained mechanism model based on the inference deviation.

[0113] Continuing with Figure 5, in the example shown in Figure 5, the task processing system 10 performs inference on the trained mechanism model based on test data. After obtaining the inference results, the task processing system 10 can also input the test data into the pre-trained mechanism model to obtain the inference results of the pre-trained model, and calculate the inference deviation based on the inference results of the mechanism model before and after training. The user can conduct mechanistic research on the mechanism model based on the inference deviation, thereby correcting the mechanism parameters of the mechanism model and improving the accuracy of the mechanism model.

[0114] For example, in the aforementioned coal production quality prediction task, the task processing system 10 uses the difference between the predictions of the trained mechanism model and the original machine model as an error estimate for the original mechanism model. When the error exceeds a set threshold, the current sample is considered difficult relative to the original mechanism model. Based on the prediction error, the task processing system 10 identifies and corrects mechanism defects in the original mechanism model.

[0115] In one possible implementation, the task processing system 10 calculates model parameters corresponding to different test data based on the trained machine model. The model parameters corresponding to different test data are used to calculate the constraint satisfaction of the model constraint information. The task processing system 10 updates and evaluates the reliability of the model constraint information based on the constraint satisfaction.

[0116] Continuing with FIG5 , in the example shown in FIG5 , task processing system 10 infers the trained machine model based on test data, obtaining machine model inference results corresponding to the test data. These inference results are the mechanism parameters of the mechanism model. Task processing system 10 can also calculate model constraint deviation values ​​corresponding to different test data based on the model constraint information, and assess the reliability of the model constraint information based on the model constraint deviation values.

[0117] For example, in the above-mentioned coal production quality prediction task example, the task processing system 10 perturbs the input test data sample x in the x domain to obtain multiple test samples, uses the trained mechanism model for inference, and then estimates the slope of the model in the x domain based on the partial order dependency function, and determines whether it exceeds the slope constraint corresponding to the model constraint information, as the content of the reliability evaluation of the model constraint information.

[0118] 204.Perform unknown prediction tasks based on the updated mechanism model.

[0119] The task processing system 10 executes unknown prediction tasks based on the updated mechanism model. The unknown prediction tasks may be unknown prediction tasks sent from terminal devices, such as anomaly detection tasks, future trend prediction tasks, risk assessment tasks, and user behavior prediction tasks.

[0120] Please continue to refer to Figure 3. In the example shown in Figure 3, before the task processing system 10 processes the task, the task processing system 10 can receive the mechanism model file, model constraint information, and machine model file provided by the user. Among them, the mechanism model file formula file includes, for example, the formula form, formula parameters, and data dimensions involved in the mechanism model, the model constraint information includes, for example, the data dimensions and slope range involved in the mechanism parameters of the mechanism model, and the machine model file can be called from the provided training and inference functions, or selected from the default machine model list.

[0121] In the example shown in Figure 3, during the model training process, the task processing system 10 receives the training data set file and fuses the mechanism model with the machine model. During the reasoning process, the task processing system 10 receives the test data set file and outputs the prediction result based on the trained mechanism model. The prediction result includes the prediction result corresponding to each test sample. The task processing system 10 can also analyze the prediction error of the mechanism model provided by the user based on the prediction result, and provide mechanism parameter adjustment suggestions for the mechanism model. Specifically, the task processing system 10 can display the mechanism model error statistics and mechanism model parameter recommendation statistics over a period of time on the interface, and provide the actual slope performance of the training mechanism model on the specified test sample.

[0122] It can be seen from the above embodiments that the computing device in the embodiments of the present application can determine the mechanism parameters of the mechanism model by training the fusion model. Since the machine model in the fusion model does not directly affect the task processing results, that is, the machine model is pluggable, the mechanism model in the embodiments of the present application supports the fusion of multiple machine models, thereby improving the prediction accuracy of the mechanism model for unknown tasks.

[0123] Based on the above method embodiment, the embodiment of the present application further provides a task processing device. The task processing device provided by the embodiment of the present application is described in detail below.

[0124] Please refer to Figure 6, which is a schematic diagram of the structure of a task processing device provided in an embodiment of the present application. In the example shown in Figure 6, the task processing device 600 is used to implement the various steps performed by the task processing system 10 in the above embodiments. The task processing device 600 includes an interface unit 601, a training unit 602, a processing unit 603, a data unit 604, and an analysis unit 605.

[0125] Among them, the interface unit 601 is used to obtain the machine model and the mechanism model, the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to perform unknown prediction tasks. The training unit 602 is used to use the machine model as the mechanism parameter of the mechanism model to obtain a fusion model, and train the fusion model based on the training data. The processing unit 603 is used to update the mechanism parameters of the mechanism model based on the machine model corresponding to the training result of the fusion model to obtain an updated mechanism model. The training result of the fusion model is used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model. The processing unit 603 also performs unknown prediction tasks based on the updated mechanism model.

[0126] In one possible implementation, training data and model constraint information are obtained, where the model constraint information is used to constrain the range of mechanism parameters in the fusion model. The training unit 602 is further configured to train the fusion model based on the training data to obtain a trained fusion model, where the mechanism parameters of the trained fusion model satisfy the model constraint information.

[0127] In a possible implementation, the apparatus further includes a data unit 604, which is configured to perform data augmentation on the training data of the fusion model based on a data augmentation strategy to obtain augmented training data, and the augmented training data is used to train the fusion model.

[0128] In a possible implementation, the data unit 604 is further configured to update the data augmentation strategy based on the deviation between the machine model output corresponding to the augmented training data and the model constraint information, and regenerate the augmented training data based on the updated data augmentation strategy.

[0129] In one possible implementation, the device further includes an analysis unit 605, which is used to calculate the inference deviation based on the inference results of the trained fusion model on the test data and the inference results of the mechanism model on the test data, and to correct the model parameters of the trained fusion model based on the inference deviation.

[0130] In one possible embodiment, the apparatus further includes an analysis unit 605, which is further configured to calculate model parameters corresponding to different test data based on the trained machine model. The model parameters corresponding to the different test data are used to calculate constraint satisfaction of the model constraint information. The reliability of the model constraint information is evaluated based on the constraint satisfaction.

[0131] It can be understood that the interface unit 601, training unit 602, processing unit 603, data unit 604 and analysis unit 605 in the task processing device 600 can be mapped as functional modules and one or more modules in each node in the task processing system 10 in Figure 1, thereby realizing the functions of each node in the task processing system 10.

[0132] It should be understood that the division of units in the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, the units in the device can all be implemented in the form of software called through processing elements; or they can all be implemented in the form of hardware; or some units can be implemented in the form of software called through processing elements, and some units can be implemented in the form of hardware. For example, each unit can be a separately established processing element, or it can be integrated into a certain chip of the device. In addition, it can also be stored in the memory in the form of a program, called by a certain processing element of the device and perform the function of the unit. In addition, all or part of these units can be integrated together, or they can be implemented independently. The processing element described here can also be a processor, which can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each unit above can be implemented by the integrated logic circuit of the hardware in the processor element or in the form of software called through the processing element.

[0133] It is worth noting that, for the sake of simplicity of description, the above method embodiments are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited to the order of the actions described. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required for this application.

[0134] Other reasonable step combinations that can be thought of by those skilled in the art based on the above description also fall within the scope of protection of this application. Secondly, those skilled in the art should also be familiar with that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by this application.

[0135] Please refer to Figure 7, which is a schematic diagram of the structure of a computing device provided in an embodiment of the present application. As shown in Figure 7, the computing device 700 includes: a processor 701, a memory 702, a communication interface 703, and a bus 704. The processor 701, the memory 702, and the communication interface 703 are coupled via a bus (not labeled in the figure). The memory 702 stores instructions. When the execution instructions in the memory 702 are executed, the computing device 700 performs the method performed by the computing device in the above method embodiment.

[0136] The computing device 700 may be one or more integrated circuits configured to implement the above method, such as one or more application specific integrated circuits (ASICs), one or more digital signal processors (DSPs), one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms. For example, when a unit in the apparatus can be implemented in the form of a processing element scheduler, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For example, these units may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0137] The processor 701 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0138] Memory 702 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Nonvolatile memory may be read-only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0139] The memory 702 stores executable program codes, and the processor 701 executes the executable program codes to respectively implement the functions of the aforementioned units or modules, thereby implementing the aforementioned task processing method. That is, the memory 702 stores instructions for executing the aforementioned task processing method.

[0140] The communication interface 703 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 700 and other devices or a communication network.

[0141] In addition to the data bus, bus 704 may also include a power bus, a control bus, and a status signal bus. The bus may be a Peripheral Component Interconnect Express (PCIe) bus, an Extended Industry Standard Architecture (EISA) bus, a unified bus (Ubus or UB), a Compute Express Link (CXL), or a Cache Coherent Interconnect for Accelerators (CCIX). Buses can be categorized as address buses, data buses, and control buses.

[0142] Please refer to FIG8 , which is a schematic diagram of a computing device cluster provided in an embodiment of the present application. As shown in FIG8 , the computing device cluster 800 includes at least one computing device 700 .

[0143] As shown in Figure 8, the computing device cluster 800 includes at least one computing device 700. The memory 702 in one or more computing devices 700 in the computing device cluster 800 may store the same instructions for executing the above-mentioned task processing method.

[0144] In some possible implementations, the memory 702 of one or more computing devices 700 in the computing device cluster 800 may also store partial instructions for executing the above-described task processing method. In other words, the combination of one or more computing devices 700 can jointly execute the instructions for executing the above-described task processing method.

[0145] It should be noted that the memory 702 in different computing devices 700 in the computing device cluster 800 may store different instructions, each for executing a portion of the functions of the task processing apparatus described above. In other words, the instructions stored in the memory 702 in different computing devices 700 may implement the functions of one or more modules among the interface unit, training unit, processing unit, data unit, and analysis unit.

[0146] In some possible implementations, one or more computing devices 700 in the computing device cluster 800 may be connected via a network, which may be a wide area network or a local area network.

[0147] Please refer to Figure 9, which is a schematic diagram of computer devices in a computer cluster provided by an embodiment of the present application connected via a network. As shown in Figure 9, two computing devices 700A and 700B are connected via a network. Specifically, the connection to the network is through a communication interface in each computing device.

[0148] In one possible implementation, the memory of computing device 700A stores instructions for executing the functions of the interface unit, the training unit, and the processing unit, while the memory of computing device 700B stores instructions for executing the functions of the data unit and the analysis unit.

[0149] It should be understood that the functions of the computing device 700A shown in Figure 9 may also be completed by multiple computing devices. Similarly, the functions of the computing device 700B may also be completed by multiple computing devices.

[0150] In another embodiment of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the processor of the device executes the computer-executable instructions, the device executes the method executed by the task processing system in the above method embodiment.

[0151] In another embodiment of the present application, a computer program product is provided, the computer program product including computer-executable instructions stored in a computer-readable storage medium. When a processor of a device executes the computer-executable instructions, the device executes the method executed by the task processing system in the above method embodiment.

[0152] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0156] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A task processing method, characterized in that: Applied to a cloud platform, the cloud platform is used to manage the infrastructure for providing cloud services, the infrastructure is used to carry the machine model and mechanism model deployed by the user, the method includes: Acquire the machine model and the mechanism model, wherein the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to perform an unknown prediction task; Using the machine model as a mechanism parameter of the mechanism model to obtain a fusion model, and training the fusion model based on training data; Based on the machine model corresponding to the training result of the fusion model, the mechanism parameters of the mechanism model are updated to obtain an updated mechanism model, wherein the training result of the fusion model is used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model; Perform unknown prediction tasks based on the updated mechanism model.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring training data and model constraint information, wherein the model constraint information is used to constrain the range of the mechanism parameters in the fusion model; The training of the fusion model based on the training data includes: The fusion model is trained based on the training data to obtain the trained fusion model, and the mechanism parameters of the trained fusion model satisfy the model constraint information.

3. The method according to claim 2, characterized in that The method further comprises: The training data of the fusion model is augmented based on a data augmentation strategy to obtain augmented training data, and the augmented training data is used to train the fusion model.

4. The method according to claim 3, characterized in that The method further comprises: Update the data augmentation strategy based on a deviation between the machine model output corresponding to the augmented training data and the model constraint information; Regenerate augmented training data based on the updated data augmentation strategy.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Calculating the inference deviation based on the inference result of the trained fusion model on the test data and the inference result of the mechanism model on the test data; Model parameters of the trained fusion model are corrected based on the inference deviation.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Calculating model parameters corresponding to different test data based on the machine model corresponding to the training result of the fusion model, wherein the model parameters corresponding to the different test data are used to count the constraint satisfaction of the model constraint information; The reliability of the model constraint information is evaluated based on the constraint satisfaction.

7. A task processing device, characterized in that: include: An interface unit, used to obtain the machine model and the mechanism model, wherein the machine model is used to predict the mechanism parameters of the mechanism model, and the mechanism model is used to perform an unknown prediction task; A training unit, used for taking the machine model as a mechanism parameter of the mechanism model to obtain a fusion model, and training the fusion model based on training data; A processing unit, configured to update the mechanism parameters of the mechanism model based on the machine model corresponding to the training result of the fusion model to obtain an updated mechanism model, wherein the training result of the fusion model is used to indicate the target model parameters of the machine model, and the target model parameters are used to determine the mechanism parameters of the updated mechanism model; The processing unit also performs unknown prediction tasks based on the updated mechanism model.

8. The device according to claim 7, characterized in that The interface unit is also used for: Acquiring training data and model constraint information, wherein the model constraint information is used to constrain the range of the mechanism parameters in the fusion model; The training unit is also used to train the fusion model based on the training data to obtain the trained fusion model, and the mechanism parameters of the trained fusion model satisfy the model constraint information.

9. The device according to claim 8, characterized in that The apparatus further comprises a data unit, wherein the data unit is configured to: Based on the data augmentation strategy, the training data of the fusion model is augmented to obtain augmented training data. The data is used to train the fusion model.

10. The device according to claim 9, characterized in that The data unit is also used for: Update the data augmentation strategy based on a deviation between the machine model output corresponding to the augmented training data and the model constraint information; Regenerate augmented training data based on the updated data augmentation strategy.

11. The device according to any one of claims 7 to 10, characterized in that The device further comprises an analysis unit, which is used for: Calculating the inference deviation based on the inference result of the trained fusion model on the test data and the inference result of the mechanism model on the test data; Model parameters of the trained fusion model are corrected based on the inference deviation.

12. The device according to any one of claims 7 to 11, characterized in that The device further comprises an analysis unit, which is further configured to: Calculating model parameters corresponding to different test data based on the machine model corresponding to the training result of the fusion model, wherein the model parameters corresponding to the different test data are used to count the constraint satisfaction of the model constraint information; The reliability of the model constraint information is evaluated based on the constraint satisfaction.

13. A computing device, characterized in that: The electronic device comprises a processor coupled to a memory, wherein the processor is used to store instructions. When the instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 6.

14. A computing device cluster, characterized in that: The system comprises at least one computing device, wherein the computing device comprises a processor, wherein the processor is coupled to a memory, and the processor is used to store instructions. When the instructions are executed by the processor, the computing device cluster executes the method according to any one of claims 1 to 6.

15. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed, the computer is caused to execute the method according to any one of claims 1 to 6.

16. A computer program product, comprising instructions, characterized in that: When the instructions are executed, the computer implements the method according to any one of claims 1 to 6.

Images