Construction method of test model, test model and method, and controller

Abstract

The invention provides a construction method of a test model, the test model, a method and a controller, and the method comprises the steps: obtaining historical test data, processing the historical test data, and obtaining the processed historical test data; then, detecting the processed historical test data to obtain a first task type and first priority information corresponding to the first task type; then, inputting the processed historical test data into a preset deep learning model, and performing information extraction through the deep learning model to obtain a second task type and second priority information corresponding to the second task type; and finally, optimizing the deep learning model according to the first task type, the first priority information, the second task type, the second priority information and a preset loss function to obtain a constructed test model. Therefore, according to the embodiment of the invention, the priority information of the test task can be obtained through the constructed test model, so that the test sequence is dynamically adjusted according to the priority information.

Description

Technical Field

[0001] This application relates to the field of testing technologies, and particularly to a method for constructing a test model, a test model and method, and a controller. Background Art

[0002] In the related art, in the current test process management, the commonly followed queuing method for the test order is to process the test items in the order of arrival, that is, to process them in turn according to the order of arrival of the test items, which is the so-called "first in, first out" principle. This test order ensures the fairness and orderliness of the test to a certain extent. However, in actual operation, when encountering urgent or high-priority test items, the existing queuing method is not flexible enough to quickly respond and arrange for an inserted test. This affects the test efficiency and the processing speed of urgent items to a certain extent. Therefore, how to achieve dynamic adjustment of the test order is the main problem faced by the industry currently. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems existing in the prior art. For this purpose, this application provides a method for constructing a test model, a test model and method, and a controller, aiming to achieve dynamic adjustment of the test order.

[0004] In a first aspect, an embodiment of this application provides a method for constructing a test model. The method for constructing the test model includes: Obtain historical test data, process the historical test data, and obtain the processed historical test data; Detect the processed historical test data to obtain a first task type and first priority information corresponding to the first task type; Input the processed historical test data into a preset deep learning model to obtain a second task type and second priority information corresponding to the second task type; Optimize the deep learning model according to the first task type, the first priority information, the second task type, the second priority information, and a preset loss function to obtain a constructed test model.

[0005] According to some embodiments of this application, the processing of the historical test data to obtain the processed historical test data includes: Obtain the completion status of the historical test data; Process the historical test data according to the completion status to obtain the processed historical test data.

[0006] According to some embodiments of this application, the processing of the historical test data according to the completion status to obtain the processed historical test data includes one of the following: When the completion status is incomplete, remove the historical test data to obtain the processed historical test data; When the completion status is complete, retain the historical test data to obtain the processed historical test data.

[0007] According to some embodiments of the present application, inputting the processed historical test data into a preset deep learning model to obtain a second task type and second priority information corresponding to the second task type includes: Input the processed historical test data into the preset deep learning model, and the deep learning model extracts information from the historical test data to obtain the second task type and second priority information corresponding to the second task type.

[0008] According to some embodiments of the present application, optimizing the deep learning model according to the first task type, the first priority information, the second task type, the second priority information, and a preset loss function to obtain a constructed test model includes: Calculate a loss value through the preset loss function according to the first task type, the first priority information, the second task type, and the second priority information, and optimize the deep learning model according to the loss value to obtain the constructed test model.

[0009] In a second aspect, an embodiment of the present application provides a test model, and the test model is constructed by the construction method described in the first aspect.

[0010] In a third aspect, an embodiment of the present application provides a test method, which is applied to the test model described in the second aspect, and the test method includes: Receive a test task; Extract information from the test task to obtain priority information corresponding to the test task; Execute the test task according to the priority information.

[0011] According to some embodiments of the present application, executing the test task according to the priority information includes: Divide the test task into corresponding priority queues according to the priority information, and execute the test tasks in the priority queues according to the priority queue order; Among them, the priority queues include a high-priority queue, a medium-priority queue, and a low-priority queue, and the priority queue order is the high-priority queue, the medium-priority queue, and the low-priority queue.

[0012] According to some embodiments of the present application, dividing the test task into a corresponding priority queue according to the priority information includes one of the following: When the priority information is high priority, divide the test task into the high-priority queue; When the priority information is medium priority, divide the test task into the medium-priority queue; When the priority information is low priority, divide the test task into the low-priority queue.

[0013] Fourthly, an embodiment of the present application provides a controller, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor runs the computer program, it executes the method for constructing a test model in the first aspect or the test method in the third aspect above.

[0014] According to the technical solution of the embodiment of the present application, it has at least the following beneficial effects: The embodiment of the present application proposes a method for constructing a test system, a test system and method, and a controller. The method includes: obtaining historical test data, processing the historical test data to obtain processed historical test data; then, detecting the processed historical test data to obtain a first task type and first priority information corresponding to the first task type; then, inputting the processed historical test data into a preset deep learning model, and performing information extraction through the deep learning model to obtain a second task type and second priority information corresponding to the second task type; finally, optimizing the deep learning model according to the first task type, the first priority information, the second task type, the second priority information, and a preset loss function to obtain a constructed test model. Therefore, the embodiment of the present application can obtain a constructed test model through the first task type, the first priority information, the second task type, the second priority information, and the loss function, so as to obtain the priority information of the test task according to the test model, and further dynamically adjust the test order according to the priority information.

[0015] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. Description of the Drawings

[0016] The drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.

[0017] Figure 1 It is a flowchart of the method for constructing a test model provided by an embodiment of the present application; Figure 2It is a flowchart of a method for constructing a test model provided by another embodiment of the present application; Figure 3 It is a flowchart of a method for constructing a test model provided by another embodiment of the present application; Figure 4 It is a flowchart of a method for constructing a test model provided by another embodiment of the present application; Figure 5 It is a flowchart of a method for constructing a test model provided by another embodiment of the present application; Figure 6 It is an overall flowchart of a method for constructing a test model provided by an embodiment of the present application; Figure 7 It is a flowchart of a test method provided by an embodiment of the present application; Figure 8 It is a flowchart of a test method provided by another embodiment of the present application; Figure 9 It is a flowchart of a test method provided by another embodiment of the present application; Figure 10 It is a flowchart of a test method provided by an overall embodiment of the present application; Figure 11 It is a schematic diagram of a controller for executing the method for constructing a test model or a test method provided by an embodiment of the present application. Detailed Description of the Embodiment

[0018] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as limiting the present application.

[0019] In the description of the present application, it should be understood that for the orientation description, such as the upper, lower, front, rear, left, right, etc., the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present application.

[0020] In the description of the present application, the meaning of "several" is one or more, the meaning of "multiple" is two or more, "greater than", "less than", "exceeding", etc. are understood as not including the present number, and "above", "below", "within", etc. are understood as including the present number. If the first and second are described only for the purpose of distinguishing technical features, they should not be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or the sequence of the indicated technical features.

[0021] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0022] In some cases, in the current test process management, the test order of the queuing method is generally followed, that is, the test items are processed in the order in which they arrive, which is the so-called "first in, first out" principle. This test order ensures the fairness and orderliness of the test to a certain extent. However, in actual operation, when encountering urgent or high-priority test items, the existing queuing method is not flexible enough and cannot respond quickly and arrange queue-jumping tests. This affects the efficiency of the test and the processing speed of urgent projects to a certain extent. Therefore, how to dynamically adjust the test order is the main problem currently facing the industry.

[0023] Based on the above situation, the embodiments of the present application propose a test model construction method, a test model and method, and a controller, aiming to dynamically adjust the test sequence.

[0024] The following further describes various embodiments of the method for constructing the test model of the present application in conjunction with the accompanying drawings.

[0025] like Figure 1 As shown, Figure 1 It is a flowchart of a method for constructing a test model provided by an embodiment of the present application; the method for constructing the test model may include but is not limited to step S110, step S120, step S130 and step S140.

[0026] Step S110: Acquire historical test data, process the historical test data, and obtain processed historical test data; Step S120: Detect the processed historical test data to obtain the first task type and first priority information corresponding to the first task type; Step S130: input the processed historical test data into a preset deep learning model to obtain a second task type and second priority information corresponding to the second task type; Step S140: Optimize the deep learning model according to the first task type, the first priority information, the second task type, the second priority information and the preset loss function to obtain a constructed test model.

[0027] In one embodiment, historical test data is obtained, processed to obtain processed historical test data; then, the processed historical test data is detected to obtain a first task type and first priority information corresponding to the first task type; next, the processed historical test data is input into a preset deep learning model, and information extraction is performed through the deep learning model to obtain a second task type and second priority information corresponding to the second task type; finally, the deep learning model is optimized according to the first task type, first priority information, second task type, second priority information, and a preset loss function to obtain a constructed test model. Therefore, the embodiments of the present application can obtain a constructed test model through the first task type, first priority information, second task type, second priority information, and loss function, so that the priority information of the test task can be obtained according to the test model, and then the test order can be dynamically adjusted according to the priority information.

[0028] It can be understood that by processing the historical test data, the data quality of the historical test data can be ensured, and then a test model can be better constructed.

[0029] In addition, as Figure 2 shown, Figure 2 is a flowchart of a method for constructing a test model provided by another embodiment of the present application; regarding the processing of the historical test data in step S110 above to obtain processed historical test data, it may include but is not limited to step S210 and step S220.

[0030] Step S210: Obtain the completion status of the historical test data; Step S220: Process the historical test data according to the completion status to obtain processed historical test data.

[0031] It can be understood that the embodiments of the present application process the test data according to the completion status, so as to ensure the data quality of the historical test data, and then a test model can be better constructed.

[0032] In addition, as Figure 3 shown, Figure 3 is a flowchart of a method for constructing a test model provided by another embodiment of the present application; regarding step S220 above, it may include but is not limited to step S310 and step S320.

[0033] Step S310: When the completion status is incomplete, remove the historical test data to obtain processed historical test data; Step S320: When the completion status is complete, retain the historical test data to obtain processed historical test data.

[0034] It can be understood that by removing the historical test data with an incomplete completion status in the embodiments of the present application, the data quality of the historical test data can be ensured, and thus a test model can be better constructed.

[0035] In addition, as Figure 4 shown, Figure 4 FIG. is a flowchart of a method for constructing a test model provided by another embodiment of the present application; regarding the above step S130, it may include but is not limited to step S410 and step S420.

[0036] Step S410: Input the processed historical test data into a preset deep learning model; Step S420: Extract information from the historical test data through the deep learning model to obtain a second task type and second priority information corresponding to the second task type.

[0037] It can be understood that inputting the processed historical test data into a preset deep learning model, such as a convolutional neural network, for simultaneous information extraction can obtain a second task type and second priority information corresponding to the second task type.

[0038] In addition, as Figure 5 shown, Figure 5 FIG. is a flowchart of a method for constructing a test model provided by another embodiment of the present application; regarding the above step S140, it may include but is not limited to step S510 and step S520.

[0039] Step S510: Calculate a loss value through a preset loss function according to the first task type, the first priority information, the second task type, and the second priority information; Step S520: Optimize the deep learning model according to the loss value to obtain a constructed test model.

[0040] It can be understood that the deep learning model is trained and optimized through the loss value, so that a constructed test model can be obtained, and then the priority information of the test task can be obtained through the test model, so as to dynamically adjust the test order according to the priority information.

[0041] It can be understood that the loss function can be a weighted cross-entropy loss function, and the weighted cross-entropy loss function is used to measure the difference between the first task type and the second task type, and the difference between the first priority information and the second priority information.

[0042] Based on the methods for constructing a test model in the above various embodiments, overall embodiments of the method for constructing a test model of the present application are respectively proposed below.

[0043] As Figure 6 shown,Figure 6 It is the overall flowchart of a method for constructing a test model provided by an embodiment of the present application.

[0044] Step S610: Obtain historical test data and obtain the completion status of the historical data; Step S620: If the completion status is incomplete, go to step S630; if the completion status is complete, go to step S640; Step S630: Remove the historical test data to obtain the processed historical test data; Step S640: Retain the historical test data to obtain the processed historical test data.

[0045] Step S650: Detect the processed historical test data to obtain the first task type and the first priority information corresponding to the first task type; Step S660: Input the processed historical test data into a preset deep learning model, and extract information from the historical test data through the deep learning model to obtain the second task type and the second priority information corresponding to the second task type; Step S670: Calculate the loss according to the first task type, the first priority information, the second task type and the second priority information through a preset loss function to obtain a loss value, and optimize the deep learning model according to the loss value to obtain the constructed test model.

[0046] It should be noted that the embodiment of the present application can obtain the constructed test model through the first task type, the first priority information, the second task type, the second priority information and the loss function, so that the priority information of the test task can be obtained according to the test model, and then the test order can be dynamically adjusted according to the priority information.

[0047] Based on the method for constructing the test model in the above various embodiments, the following presents various embodiments of the test model of the present application.

[0048] An embodiment of the present application further provides a test model, which is constructed by the above embodiment.

[0049] It should be noted that since the test model of the embodiment of the present application is constructed by the above embodiment, the priority information of the test task can be obtained, and then the test order can be dynamically adjusted according to the priority information.

[0050] Based on the test model in the above various embodiments, the following presents various embodiments of the test method of the present application.

[0051] As Figure 7 shown, Figure 7It is a flowchart of a test method provided by an embodiment of the present application; the test method may include but is not limited to step S710, step S720, and step S730.

[0052] Step S710: Receive a test task; Step S720: Extract information from the test task to obtain the priority information corresponding to the test task; Step S730: Execute the test task according to the priority information.

[0053] In one embodiment, after receiving a test task, the embodiment of the present application will extract information from the test task to obtain the priority information corresponding to the test task, and then determine the execution order of the test task according to the priority information, so as to execute the test task according to the execution order.

[0054] It should be noted that the embodiment of the present application can obtain the priority information of the test task through the test model, so as to dynamically adjust the test order according to the priority information.

[0055] In addition, as Figure 8 shown, Figure 8 It is a flowchart of a test method provided by another embodiment of the present application; regarding the above step S730, it may include but is not limited to step S810 and step S820.

[0056] Step S810: Divide the test task into the corresponding priority queue according to the priority information; Step S820: Execute the test tasks in the priority queue according to the priority queue order.

[0057] It can be understood that through the priority information, the test tasks can be divided into the corresponding priority queues, so as to execute the test tasks in the priority queues according to the priority queue order, and then dynamically adjust the test order.

[0058] It can be understood that the priority queue includes a high-priority queue, a medium-priority queue, and a low-priority queue.

[0059] It can be understood that the priority queue order is the high-priority queue, the medium-priority queue, and the low-priority queue, that is, the system will first execute the test tasks in the high-priority queue. After all the test tasks in the high-priority queue are completed, it will execute the test tasks in the medium-priority queue, and finally complete the test tasks in the low-priority queue.

[0060] It can be understood that when executing the test tasks in the medium-priority queue or the low-priority queue, if a test task belonging to the high-priority queue is received, the current test task will be interrupted and the test task in the high-priority queue will be executed first.

[0061] It can be understood that in the case of executing a test task in the low-priority queue, if a test task belonging to the medium-priority queue is received, the current test task is interrupted and the test task in the medium-priority queue is preferentially executed.

[0062] In addition, as Figure 9 shown, Figure 9 is a flowchart of a test method provided by another embodiment of the present application; regarding the above step S810, it may include but is not limited to step S910, step S920, and step S930.

[0063] Step S910: When the priority information is high priority, divide the test task into the high-priority queue; Step S920: When the priority information is medium priority, divide the test task into the medium-priority queue; Step S930: When the priority information is low priority, divide the test task into the low-priority queue.

[0064] It can be understood that the priority information of the test task corresponds to a priority queue, so that the test task can be divided into the corresponding priority queue according to the priority information.

[0065] Based on the test methods of the above various embodiments, overall embodiments of the test method of the present application are respectively proposed below.

[0066] As Figure 10 shown, Figure 10 is a flowchart of a test method provided by an overall embodiment of the present application.

[0067] Step S1010: Receive a test task; Step S1020: Extract information from the test task to obtain the priority information corresponding to the test task; Step S1030: Divide the test task into the corresponding priority queue according to the priority information, and execute the test tasks in the priority queue according to the priority queue order.

[0068] It can be understood that the priority queue includes a high-priority queue, a medium-priority queue, and a low-priority queue.

[0069] It can be understood that the priority queue order is the high-priority queue, the medium-priority queue, and the low-priority queue, that is, the system will first execute the test tasks in the high-priority queue. After all the test tasks in the high-priority queue are completed, the test tasks in the medium-priority queue will be executed, and finally the test tasks in the low-priority queue will be completed.

[0070] It can be understood that when executing a test task in the priority queue or the low-priority queue, if a test task belonging to the high-priority queue is received, the current test task is interrupted and the test task in the high-priority queue is preferentially executed.

[0071] It can be understood that when executing a test task in the low-priority queue, if a test task belonging to the medium-priority queue is received, the current test task is interrupted and the test task in the medium-priority queue is preferentially executed.

[0072] It can be understood that when the priority information is high priority, the test task is divided into the high-priority queue; when the priority information is medium priority, the test task is divided into the medium-priority queue; when the priority information is low priority, the test task is divided into the low-priority queue. It should be noted that the embodiments of the present application can obtain the priority information of the test task through the test model, so as to dynamically adjust the test order according to the priority information.

[0073] Based on the test model construction method or test method of the above respective embodiments, the respective embodiments of the controller of the present application are respectively proposed below.

[0074] As Figure 11 shown, Figure 11 is a schematic diagram of a controller for executing the test model construction method or test method provided by an embodiment of the present application. The controller 700 implemented in the present application includes: a processor 710, a memory 720, and a computer program stored on the memory 720 and executable on the processor 710. Among them, Figure 11 one processor 710 and one memory 720 are taken as an example.

[0075] The processor 710 and the memory 720 can be connected by a bus or other means, Figure 11 and taking the connection by bus as an example.

[0076] The memory 720, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory 720 may include a high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 720 may optionally include a memory 720 remotely provided with respect to the processor 710, and these remote memories 720 can be connected to the controller 700 through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0077] Those skilled in the art can understand, Figure 11The device structure shown does not constitute a limitation on the controller 700, and it may include more or fewer components than shown, or combine certain components, or have a different component arrangement.

[0078] In Figure 11 In the controller 700 shown, the processor 710 may be used to call the control program stored in the memory 720, so as to implement the power consumption detection method of the multi-connected system with domestic hot water as described above. Specifically, the non-transitory software program and instructions required to implement the power consumption detection method of the multi-connected system with domestic hot water in the above embodiments are stored in the memory 720. When executed by the processor 710, the power consumption detection method of the multi-connected system with domestic hot water in the above embodiments is executed.

[0079] It should be noted that since the controller 700 in the embodiments of the present application can execute the power consumption detection method of the multi-connected system with domestic hot water in any of the above embodiments, therefore, for the specific implementation manners and technical effects of the controller 700 in the embodiments of the present application, reference may be made to the specific implementation manners and technical effects of the power consumption detection method of the multi-connected system with domestic hot water in any of the above embodiments.

[0080] Those of ordinary skill in the art can understand that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware and their appropriate combinations. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or can be implemented as hardware, or can be implemented as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, a communication medium generally includes computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium.

[0081] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one)" or its similar expression below refers to any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0082] In several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of apparatuses or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] It should also be understood that the various embodiments provided in the embodiments of this application can be combined arbitrarily to achieve different technical effects.

[0084] The above has made a specific description of the preferred embodiments of this application, but this application is not limited to the above-mentioned embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without violating the spirit of this application. These equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for constructing a test model, characterized in that: The method for constructing the test model includes: Acquire historical test data, and process the historical test data to obtain the processed historical test data; Detecting the processed historical test data to obtain a first task type and first priority information corresponding to the first task type; Inputting the processed historical test data into a preset deep learning model to obtain a second task type and second priority information corresponding to the second task type; The deep learning model is optimized according to the first task type, the first priority information, the second task type, the second priority information and a preset loss function to obtain a constructed test model.

2. The method for constructing a test model according to claim 1, characterized in that: The processing of the historical test data to obtain the processed historical test data includes: Obtaining the completion status of the historical test data; The historical test data is processed according to the completion status to obtain the processed historical test data.

3. The method for constructing a test model according to claim 2, characterized in that: The processing of the historical test data according to the completion status to obtain the processed historical test data includes one of the following: When the completion status is incomplete, the historical test data is removed to obtain the processed historical test data; When the completion status is completed, the historical test data is retained to obtain the processed historical test data.

4. The method for constructing a test model according to claim 1, characterized in that: The step of inputting the processed historical test data into a preset deep learning model to obtain a second task type and second priority information corresponding to the second task type includes: The processed historical test data is input into the preset deep learning model, and information is extracted from the historical test data through the deep learning model to obtain the second task type and the second priority information corresponding to the second task type.

5. The method for constructing a test model according to claim 1, characterized in that: The step of optimizing the deep learning model according to the first task type, the first priority information, the second task type, the second priority information, and a preset loss function to obtain a constructed test model includes: The preset loss function is used to calculate the loss according to the first task type, the first priority information, the second task type and the second priority information to obtain a loss value, and the deep learning model is optimized according to the loss value to obtain the constructed test model.

6. A test model, characterized in that: The test model is constructed by the test model construction method described in any one of claims 1 to 5.

7. A testing method, characterized in that: Applied to the test model as claimed in claim 6, the test method comprises: Receive test tasks; Extracting information from the test task to obtain priority information corresponding to the test task; The test task is executed according to the priority information.

8. The testing method according to claim 7, characterized in that: The performing of the test task according to the priority information comprises: Dividing the test tasks into corresponding priority queues according to the priority information, and executing the test tasks in the priority queues according to the priority queue order; The priority queues include a high priority queue, a medium priority queue and a low priority queue, and the order of the priority queues is high priority queue, medium priority queue, and low priority queue.

9. The testing method according to claim 8, characterized in that: The dividing the test task into corresponding priority queues according to the priority information includes one of the following: When the priority information is high priority, the test task is assigned to the high priority queue; When the priority information is medium priority, the test task is assigned to the medium priority queue; When the priority information is low priority, the test task is assigned to the low priority queue.

10. A controller, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the test model construction method as described in any one of claims 1 to 5 or the test method as described in any one of claims 7 to 9 when executing the computer program.

Images