Machine learning progress control method and related device, storage medium and program product

Abstract

The embodiment of the present application provides a method for machine learning progress control based on working conditions and related devices, storage media and program products, the method comprising: obtaining a progress query request from the electronic device; determining the current learning status of the target working condition according to the target working condition code; determining whether the target working condition has a preparatory learning stage according to the current learning status; if so, sending the current learning status and prompt information to the electronic device, the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; if not, sending the current learning status to the electronic device. In this way, the training stage is automatically identified through the working condition, and the user is assisted in completing the entire process of machine learning by displaying information and sending prompt messages, which greatly improves the efficiency of machine learning, and the user can quickly understand the current learning progress, reducing the difficulty of the user's decision-making.

Description

Technical Field

[0001] The present application belongs to the general data processing field of the Internet industry, and specifically relates to a working condition-based machine learning progress control method and related devices, storage media and program products. Background Art

[0002] Currently, it is an increasingly popular trend to use machine learning to train production and help optimize process parameters. However, traditional machine learning training generates learning process parameter data through personnel planning and scheduling, and then arranges it into the production process. The progress and quality of the trial production training process are managed manually. At the same time, training has multiple stages, such as training, learning, and verification, which all require human decision-making, coordination and control. On the one hand, it is relatively inefficient and relies on the skills and experience of personnel, and is also prone to errors. Summary of the invention

[0003] The embodiments of the present application provide a method for controlling the progress of machine learning based on working conditions and related devices, storage media, and program products, in order to improve the efficiency of machine learning and increase the convenience for users to control the entire process of machine learning.

[0004] In a first aspect, an embodiment of the present application provides a machine learning schedule control method based on working conditions, which is applied to a server of a schedule control system, wherein the schedule control system includes the server and an electronic device, and the method includes:

[0005] Acquire a progress query request from the electronic device, wherein the progress query request includes a target operating condition code, and the target operating condition code is used to indicate a target operating condition;

[0006] Determining a current learning status of the target operating condition according to the target operating condition code, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage;

[0007] Determine whether the target operating condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered;

[0008] If the preparatory learning stage exists, sending the current learning situation and prompt information to the electronic device, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage;

[0009] If the preparatory learning stage does not exist, the current learning situation is sent to the electronic device.

[0010] In a second aspect, an embodiment of the present application provides a machine learning schedule control method based on working conditions, which is applied to an electronic device of a schedule control system, wherein the schedule control system includes a server and the electronic device, and the method includes:

[0011] Sending a progress query request to the server, the progress query request including a target operating condition code, the target operating condition code being used to indicate the target operating condition, the target operating condition being used to indicate a current learning situation, the current learning situation being used to indicate a current learning situation of the target operating condition in each learning stage, the current learning situation being used to determine whether the target operating condition has a preparatory learning stage, the preparatory learning stage being a learning stage that the target operating condition can currently enter but has not yet entered;

[0012] If the preparatory learning stage exists, obtaining the current learning status and prompt information sent from the server, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage;

[0013] If the preparatory learning stage does not exist, the current learning status is obtained from the server.

[0014] In a third aspect, an embodiment of the present application provides a machine learning progress control device based on working conditions, which is applied to a server of a progress control system, wherein the progress control system includes the server and an electronic device, and the device includes:

[0015] an acquisition unit, configured to acquire a progress query request from the electronic device, wherein the progress query request includes a target operating condition code, and the target operating condition code is used to indicate a target operating condition;

[0016] a first determining unit, configured to determine a current learning status of the target operating condition according to the target operating condition code, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage;

[0017] A second determining unit is used to determine whether the target operating condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered;

[0018] A first sending unit is used to send the current learning situation and prompt information to the electronic device if the preparatory learning stage exists, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage;

[0019] The second sending unit is used to send the current learning situation to the electronic device if the preparatory learning stage does not exist.

[0020] In a fourth aspect, an embodiment of the present application provides a machine learning progress control device based on working conditions, which is applied to an electronic device of a progress control system, wherein the progress control system includes a server and the electronic device, and the device includes:

[0021] a sending unit, configured to send a progress query request to the server, wherein the progress query request includes a target operating condition code, wherein the target operating condition code is used to indicate the target operating condition, wherein the target operating condition is used to indicate a current learning situation, wherein the current learning situation is used to indicate a current learning situation of the target operating condition in each learning stage, wherein the current learning situation is used to determine whether the target operating condition has a preparatory learning stage, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered;

[0022] A first acquisition unit is used to acquire the current learning status and prompt information sent from the server if the preparatory learning stage exists, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage;

[0023] The second acquisition unit is configured to acquire the current learning status from the server if the preparatory learning stage does not exist.

[0024] In a fifth aspect, an embodiment of the present application provides a server, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in the first aspect of the embodiment of the present application.

[0025] In a sixth aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program comprises instructions for executing the steps in the second aspect of the embodiment of the present application.

[0026] In a seventh aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect or the second aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0027] It can be seen that in the embodiment of the present application, the server first obtains a progress query request from the electronic device, and then determines the current learning status of the target working condition according to the target working condition code, and then determines whether the target working condition has a preparatory learning stage according to the current learning status. If the preparatory learning stage exists, the current learning status and prompt information are sent to the electronic device, and the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage. If the preparatory learning stage does not exist, the current learning status is sent to the electronic device. In this way, the training stage is automatically identified through the working condition, and the user is assisted in completing the entire process of machine learning by displaying information and sending prompt messages, which greatly improves the efficiency of machine learning, and the user can quickly understand the current learning progress, reducing the user's decision-making difficulty and improving the user's experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 It is a structural diagram of a progress control system provided in an embodiment of the present application;

[0030] Figure 2 It is a structural diagram of a server provided in an embodiment of the present application;

[0031] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0032] Figure 4 It is a flowchart of a method for machine learning progress control based on working conditions provided in an embodiment of the present application;

[0033] Figure 5 This is a schematic diagram of a machine learning progress control interface provided by an embodiment of the present application;

[0034] Figure 6 This is another schematic diagram of a machine learning progress control interface provided in an embodiment of the present application;

[0035] Figure 7 This is another schematic diagram of a machine learning progress control interface provided in an embodiment of the present application;

[0036] Figure 8It is a block diagram of the functional units of a machine learning progress control device based on working conditions provided in an embodiment of the present application;

[0037] Fig. 9 It is a block diagram of the functional units of another working condition-based machine learning progress control device provided in an embodiment of the present application;

[0038] Fig.10 It is a block diagram of the functional units of another working condition-based machine learning progress control device provided in an embodiment of the present application;

[0039] Fig.11 It is a block diagram of the functional units of another working condition-based machine learning progress control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0042] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0043] In process manufacturing industries such as chemical, metallurgical, and steel industries, there are many new products that need to be trial-produced, and old products are facing new working conditions that require the optimization of production process ramp-up processes. With the development of artificial intelligence technology, it is becoming more and more popular to use machine learning to train production and help optimize process parameters. However, traditional machine learning training generates learning process parameter data through personnel planning and arrangement, and arranges it into the production process. The progress and quality of the trial production training process are managed manually. At the same time, training has multiple stages, such as training, learning, and verification, which all require personnel decision-making, coordination, and control. On the one hand, the efficiency is relatively low, and it also relies on the skills and experience of personnel, and it is also prone to errors.

[0044] In response to the above problems, an embodiment of the present application provides a working condition-based machine learning progress control method and related devices. The embodiment of the present application is described in detail below in conjunction with the accompanying drawings.

[0045] See also Figure 1 , Figure 1 It is a structural diagram of a progress control system provided by an embodiment of the present application. As shown in the figure, the progress control system 10 includes a server 101 and an electronic device 102. The electronic device 102 is used to send a progress query request to the server. The server 101 obtains progress information according to the query request of the electronic device 102, and feeds back the progress to the electronic device 102 for the user to view. The user can also send change information to the server 101 through the electronic device 102 to update the current progress or change the information in the machine learning process.

[0046] The structure of the server 101 is shown in FIG. Figure 2 As shown, the server 101 includes a processor 120, a memory 130, a communication interface 140 and one or more programs 131, wherein the one or more programs 131 are stored in the above-mentioned memory 130 and are configured to be executed by the above-mentioned processor 120, and the one or more programs 131 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 120 is used to execute any step executed by the server in the following method embodiment, and when performing data transmission operations such as receiving, the communication interface 140 can be selectively called to complete the corresponding operation. It should be noted that the storage method of the server in this solution can be distributed, with multiple servers for different production lines, workshops and quality laboratories, and then the database storage technology of the blockchain is used to record the production information of each batch of materials in real time at the same time, and save it on the chain in the production time sequence of different production equipment.

[0047] The structure of the electronic device 102 is shown in FIG. Figure 3As shown, the electronic device 102 includes a processor 220, a memory 230, a communication interface 240, and one or more programs 231, wherein the one or more programs 231 are stored in the memory 230 and are configured to be executed by the processor 220, and the one or more programs 231 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 220 is used to execute any step executed by the electronic device in the following method embodiment, and when performing data transmission operations such as receiving, the communication interface 240 can be selectively called to complete the corresponding operation.

[0048] See also Figure 4 , Figure 4 1 is a flow chart of a method for machine learning progress control based on working conditions provided in an embodiment of the present application. As shown in the figure, the method for machine learning progress control based on working conditions is applied to a server of a progress control system, the progress control system includes the server and an electronic device, and the method includes:

[0049] S201, obtaining a progress query request from the electronic device, wherein the progress query request includes a target operating condition code, and the target operating condition code is used to indicate a target operating condition.

[0050] Among them, each working condition code corresponds to a type of working condition, which is used to indicate the current production situation, including the production environment, production equipment and production personnel. A machine learning task can be established for each working condition code to control the production parameters under the working condition according to the results obtained by machine learning.

[0051] S202, determining a current learning status of the target operating condition according to the target operating condition code, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage.

[0052] Among them, since the entire machine learning process is complex and time-consuming, and there may be multiple working conditions corresponding to the working condition codes undergoing machine learning at the same time, the user may not be able to quickly and efficiently and accurately control each machine learning process. Therefore, under this solution, the user inputs the working condition code corresponding to the machine learning process to be queried into the electronic device, and the server can obtain all learning conditions of the entire machine learning process corresponding to the working condition code. The current learning situation includes the learning stage that has been completed, the learning stage that is being learned, and the learning stage that has not yet been learned. Through the current learning situation sent by the server, the user can know at a glance which steps of the machine learning corresponding to the current working condition code have been carried out and which steps still need to be carried out, etc., which is convenient for the user to quickly understand the current learning progress and arrange subsequent production work according to the current learning progress.

[0053] S203, determining whether the target operating condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered.

[0054] Among them, since machine learning includes multiple learning stages and each learning stage is closely related, the subsequent learning stage can be determined according to the learning situation. For a working condition, it can correspond to multiple learning tasks, and these multiple learning tasks can include three states: completed, in progress, or newly created and not yet in progress. For the learning task in the running state, only one is included. The user can query the learning information corresponding to the completed learning stage in the learning task being learned according to the current learning situation. For example, if the completed learning stage is the verification and evaluation stage, the user can obtain the target value corresponding to each product parameter, the mean, standard deviation and process capability index (Complex Process Capability index, CPK) and other data information corresponding to the product parameter before learning, as well as the mean, standard deviation and CPK and other data information of the product parameter corresponding to a certain learning version of each product parameter.

[0055] S204, if the preparatory learning stage exists, sending the current learning status and prompt information to the electronic device, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage;

[0056] S205: If the preparatory learning stage does not exist, sending the current learning status to the electronic device.

[0057] Among them, if there is a preparatory learning stage, it means that the current production stage is not the last production stage of machine learning, and there is at least one learning task that has completed the current learning stage or the creation of the initial stage learning task has not been performed under the working condition code. For example, there are multiple learning tasks corresponding to this working condition code, among which learning task 5 has been completed in the current learning stage, so a prompt message can be sent to the user to prompt the user to enter the next learning stage for this learning task. If there is no preparatory learning stage, it means that the current learning stage has not been completed, and it is impossible to enter the next learning stage, or the information required for the next learning stage has not been obtained. For example, at least 40 sets of training information are required in the learning stage, but the data results obtained according to the current training stage have not been completed, so it is impossible to enter the learning stage. If the training data obtained in the training stage reaches the minimum value, even if the training stage has not been completed, it can enter the learning stage.

[0058] It can be seen that in this example, the server first obtains a progress query request from the electronic device, and then determines the current learning status of the target working condition according to the target working condition code, and then determines whether the target working condition has a preparatory learning stage according to the current learning status. If so, the current learning status and prompt information are sent to the electronic device, and the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage. If not, the current learning status is sent to the electronic device. In this way, the training stage is automatically identified through the working condition, and the user is assisted in completing the entire process of machine learning by displaying information and sending prompt messages, which greatly improves the efficiency of machine learning, and the user can quickly understand the current learning progress, reducing the user's decision-making difficulty and improving the user's experience.

[0059] In a possible instance, the learning progress of the target working condition includes a learning task creation stage, a learning target confirmation stage, a learning production scheduling stage, a training stage, a multi-target learning stage and a verification and evaluation stage. The determining whether the target working condition has a preparatory learning stage based on the current learning situation includes: determining the next learning stage of the current learning stage, the learning task creation stage is the initial learning stage, the learning target confirmation stage is the next learning stage of the learning task creation stage, the learning production scheduling stage is the next stage of the learning target confirmation stage, the training stage is the next stage of the learning production scheduling stage, the multi-target learning stage is the next stage of the training stage, and the verification and evaluation stage is the next stage of the multi-target learning stage; determining whether the learning task of the target working condition in the current learning stage has been completed; if so, determining that the next learning stage of the current learning stage is the preparatory learning stage.

[0060] Among them, Figure 5 As shown, Figure 5As shown in the interface of "Multi-objective Optimization Learning Task Navigation for Product A", the machine learning may refer to multi-objective optimization learning, which includes 6 learning stages, namely, in the learning task creation stage, a multi-objective machine learning task is created for a working condition corresponding to a working condition code, after the learning task is created, the user determines the learning goal of this learning in the learning goal confirmation stage, and then enters the learning production scheduling stage according to the learning goal, in this stage, multiple training data can be generated, and then enters the training stage after obtaining enough training data, and trains the multi-objective optimization model according to the training data, and enters the multi-objective learning stage after the training is completed. In this stage, the multi-objective optimization model will be used for calculation to obtain the optimized product parameter value, and then in the verification and evaluation stage, the verification and evaluation will be performed based on the learned product parameter value, product parameter target value and product parameter value before learning to determine the version that can be used for actual production. The user can view the learning status of the completed learning stage according to the current learning status, and when there is a preparatory learning stage, the user can also be prompted to enter the next stage. For example, the figure prompts the user that the current working condition has not learned production scheduling, so the user can click "Go to Scheduling" on the electronic device to enter the next learning stage. In particular, information on the current learning situation, such as information on each learning batch, including progress data, test information, operators, inspectors and other information, can be obtained through blockchain technology according to the time nodes of the blockchain to ensure the traceability and reliability of the information.

[0061] In the specific implementation, when confirming the learning goal, you can first determine whether the target product has undergone machine learning of other working conditions. If so, obtain the learning goal determined when performing machine learning of other working conditions, and then determine the learning goal as the learning goal template for this machine learning. The user only needs to make corresponding changes to the template, or the user does not change the learning goal template and can directly confirm the learning goal template as the learning goal for this machine learning. The learning goal includes the target value, priority, expected trend, and upper and lower limits of specifications for each product parameter of the target product. When confirming the learning goal, you can also obtain the initial product parameters of the product determined in the laboratory stage, and then directly import the initial product parameters as the learning goal template.

[0062] It can be seen that in this example, the whole process of multi-objective optimization learning is managed and displayed in a process-based manner, so that users can determine the learning progress of each machine learning at any time, and can also perform subsequent operations according to prompts, thereby improving the convenience and efficiency of machine learning and improving user experience.

[0063] In a possible instance, the initial stage of the learning progress of the target working condition is the stage of creating learning tasks, and the current learning status of the target working condition includes that the target working condition has not yet created a learning task. After determining the current learning status of the target working condition according to the target working condition code, the method further includes: determining the working condition type of the target working condition according to the target working condition code; determining a recommended task quantity according to the working condition type, the recommended task quantity being used to recommend the number of learning tasks for the target working condition that the user needs to create in the stage of creating learning tasks; and sending the recommended task quantity to the electronic device.

[0064] Among them, the target working condition coding can include four aspects, that is, the production environment information, production equipment information, production material information and production personnel information can be determined according to the working condition coding, and the current working condition type can be determined according to these four aspects. Among them, the working condition coding, combined with the progress information of machine learning, can know which stage it is currently in and which type of production it belongs to. For example, training production, multi-objective machine learning production, mass production verification production, and mass production production can recommend the corresponding number of learning tasks based on the achievement of quality goals of different production types. And it can be determined whether it is in the mass production verification stage or mass production stage of the trial production of production according to the version status of the parameter database corresponding to the working condition coding.

[0065] It can be seen that in this example, recommending the corresponding number of learning tasks according to different working conditions can improve the efficiency of machine learning, reduce the burden of machine learning, and reduce resource waste.

[0066] In a possible example, determining the recommended number of tasks based on the operating condition type includes: determining a similar operating condition code based on the target operating condition code, wherein the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; obtaining a preparatory operating condition, wherein the preparatory operating condition is a condition that has completed all learning stages among the similar operating conditions corresponding to the similar operating condition codes; determining the number of learning tasks corresponding to the preparatory operating condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory operating condition; determining the quality distribution based on the comprehensive product quality index of each learning task; determining a recommended task number interval based on the quality distribution and the number of learning tasks; and determining the recommended task number based on the recommended task number interval.

[0067] Among them, since the working condition code can reflect the production conditions in multiple aspects, if there is only one aspect of the production conditions that is different among these multiple aspects of production conditions, that is, only one digit in this type of working condition code is different from the target working condition code. And there can be multiple types of working condition codes of the same type. For example, the target working condition code and its working condition codes of the same type only differ in the production personnel situation. The production personnel of the target working condition code is group A, while the production personnel of the working condition code of the same type 1 is group B, and the production personnel of the working condition code of the same type 2 is group C. When there are multiple different types of working condition codes of the same type, for example, some working condition codes of the same type are different from the target working condition code in terms of the production environment situation, and some working condition codes of the same type are different from the target working condition code in terms of the production personnel situation. Therefore, the obtained working condition codes of the same type can be grouped according to the situation. For example, if there are four aspects of production conditions in total, then those with different production environment situations can be grouped into one group, those with different production equipment situations can be grouped into one group, those with different production material situations can be grouped into one group, and then those with different production personnel situations can be grouped into one group. Then, determine the group with the largest number of working conditions that have completed all learning stages among these four groups of working condition codes of the same type as the final working condition code of the same type.

[0068] In specific implementation, if a factory has multiple production lines, and there are M (M < N) working conditions where N production line devices simultaneously produce and learn a similar product. The learning tasks of similar working condition codes (the production lines are different, but the device types are the same, and other working conditions are the same). When there is only a production line difference in the working conditions, that is, (similar working conditions, the same device type, etc.), there are multiple similar working conditions, and M (M < N) out of N production lines simultaneously learn. If the learning pass rate is relatively high and the learning parameter consistency is relatively good, then the parameters of the M production lines can be benchmarked and set to other unlearned production lines to reduce the number of learning times.

[0069] When there are multiple preparatory working conditions, the method of determining the recommended task quantity interval according to the quality distribution and the number of learning tasks includes: determining the first product comprehensive quality index corresponding to all learning tasks of each preparatory working condition, and then determining the average product comprehensive quality index corresponding to the preparatory working condition according to the number of learning tasks corresponding to each preparatory working condition, and then determining the total quality distribution interval according to the average product comprehensive quality index of all preparatory working conditions, and then dividing the total quality distribution interval into equal parts, and determining the recommended task quantity interval from the equally divided intervals, the recommended task quantity interval including the largest number of preparatory working conditions, determining the target preparatory working condition corresponding to the recommended task quantity interval, and then determining the number of learning tasks for each target preparatory working condition, determining the number of preparatory recommended tasks according to the number of learning tasks for each target preparatory working condition, determining the gap between the product comprehensive quality index corresponding to the recommended task quantity interval and the target value of the product comprehensive quality index, and determining the final recommended task quantity according to the gap and the number of preparatory recommended tasks. For example, if the product comprehensive quality index corresponding to the recommended task quantity interval includes the target value, the preliminary recommended task quantity is determined to be the final recommended task quantity; if the recommended task quantity interval is less than the target value, the preliminary recommended task quantity is determined to be less than the final recommended task quantity; if the recommended task quantity interval is greater than the target value, the preliminary recommended task quantity is determined to be greater than the final recommended task quantity. Alternatively, the recommended ratio is determined according to the gap value, and the final recommended task quantity is determined according to the recommended ratio and the preliminary recommended task quantity.

[0070] It can be seen that in this example, determining the number of recommended tasks when creating learning tasks based on the same type of working condition codes can improve the efficiency of machine learning, reduce the burden of machine learning, and reduce resource waste.

[0071] In a possible instance, the current learning situation includes the learning situation in the training phase, and determining the current learning situation of the target working condition according to the target working condition code includes: determining the total training batch of the target working condition in the training phase; obtaining the production situation of each production process for the target working condition, the production situation is used to indicate the production situation of the current production batch corresponding to the production process; determining the completion progress corresponding to each production process according to the total training batch and the current production batch; determining the training progress of the target working condition in the training phase according to the completion progress corresponding to each production process; sending the current learning situation to the electronic device includes: sending the production situation and the training progress to the electronic device.

[0072] Among them, Figure 6 As shown, Figure 6It is another schematic diagram of the machine learning progress control interface provided by an embodiment of the present application. During training, the acquired training parameters can be used to generate production tasks of different batches, and when the user queries the progress of machine learning, the production status of different batches can be displayed. For example, which batch of products is currently produced in a certain process, and what is the completion progress of the process in the total training. Determining the completion progress may include: determining the total training batch, determining the current production batch of the target process, determining the number of completed batches based on the current production batch, determining the production progress of the current production batch, and determining the completion progress of the target process based on the production progress of the current production batch, the number of completed production batches and the total training batch. For example, if the current production batch of process 5 is the 21st batch, it means that process 5 has completed 20 batches. If the production progress of the current production batch has been completed by 50%, the completion progress of process 5 can be determined based on the acquired information.

[0073] It can be seen that in this example, the production status of each process, the training progress and other information are displayed to the user during the training phase, which helps the user understand the current machine learning progress and improves user management efficiency.

[0074] In a possible instance, determining the training progress of the target working condition in the training phase according to the completion progress corresponding to each production process includes: determining a preliminary production process, the completion progress corresponding to the preliminary production process is less than 1; numbering the preliminary production processes according to the production sequence, the larger the numbering sequence, the later the production sequence; determining a progress coefficient for each preliminary production process according to the production sequence, the later the production sequence of the preliminary production process, the higher the progress coefficient; determining the training progress of the target working condition in the training phase according to the progress coefficient and the completion progress corresponding to the preliminary production process.

[0075] Among them, the completion progress equal to 1 means that the process has completed the production of all training batches. The sum of the progress coefficients of all pre-production processes is S∈[0, N], where N is the number of production processes. The training progress of the current training stage can be intuitively displayed through the training progress bar.

[0076] It can be seen that in this example, the production status of each process, the training progress and other information are displayed to the user during the training phase, which helps the user understand the current machine learning progress and improves user management efficiency.

[0077] In a possible instance, when the current learning situation includes a multi-target learning stage, determining the current learning situation of the target working condition according to the target working condition code includes: determining the learned rounds of the target working condition; obtaining product parameter information obtained from each round of learning in the learned rounds; sorting the learned rounds according to the product parameter information; sending the current learning situation to the electronic device includes: sending product parameter information corresponding to the target learning round to the electronic device, the target learning round being the learned round sorted before a preset order; after sending the product parameter information corresponding to the target learning round to the electronic device, the method also includes: receiving a setting request for a version of the target learning round from the electronic device, the learning parameters corresponding to each round of multi-target learning being a version; updating the version of the target learning round to a preset version according to the version setting request; and determining that the preset version is a version that can enter the verification and evaluation stage.

[0078] Among them, multiple rounds of multi-objective learning are required for one working condition coding, and corresponding product parameter information will be obtained after each round of multi-objective learning, and the product parameter information includes parameter information of multiple parameters. Sorting the learned rounds according to the product parameter information includes: determining the priority of each parameter information in the multiple parameter information, obtaining the parameter target interval corresponding to each parameter information, determining the comprehensive product index corresponding to each round of learning according to the parameter target interval and priority, and determining the arrangement order according to the comprehensive product index. When sending the current learning situation to the electronic device, only the learning results of the top-ranked learning rounds can be sent. After receiving the request information from the electronic device, the learning results of other ranked learning rounds are sent to the electronic device.

[0079] In a specific implementation, you can set the version of the top-ranked learning rounds. After setting the learning information of this round to the preset version, you can perform verification and evaluation based on the learning information of this round. As the number of learning rounds increases, the current top-ranked learning rounds may change, that is, some of the top-ranked learning rounds may have preset versions, while some of the top-ranked learning rounds may not have preset versions. In this case, you can set the versions of these learning rounds. For example Figure 7 In the example, you can add the version corresponding to the 5th learning round and set it as the preset version for verification and evaluation.

[0080] In the specific implementation, Figure 7 As shown, the learning information for each product parameter can also be obtained, including the parameter name, unit, target value, upper and lower limits of the specification, and expected learning direction of the product parameter, as well as the parameter value of each learning of the parameter in the form of a line graph, which is convenient for intuitively analyzing the learning status of each parameter.

[0081] It can be seen that in this example, the learning situation is fully displayed in the multi-objective learning stage, which is convenient for users to analyze the learning situation according to their needs.

[0082] The present solution also provides a working condition-based machine learning progress control method, which is applied to an electronic device of a progress control system, wherein the progress control system includes a server and the electronic device, and the method includes: sending a progress query request to the server, wherein the progress query request includes a target working condition code, wherein the target working condition code is used to indicate the target working condition, wherein the target working condition is used to indicate the current learning status, wherein the current learning status is used to indicate the current learning status of the target working condition in each learning stage, wherein the current learning status is used to determine whether the target working condition has a preparatory learning stage, wherein the preparatory learning stage is a learning stage that the target working condition can currently enter but has not yet entered; if the preparatory learning stage exists, obtaining the current learning status and prompt information sent from the server, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; if the preparatory learning stage does not exist, obtaining the current learning status from the server.

[0083] It can be seen that in this example, the user can obtain the machine learning status corresponding to each working condition in real time through the electronic device, which facilitates the user to control the entire machine learning progress.

[0084] For the above embodiments, please refer to Figure 8 , Figure 8 It is a block diagram of the functional units of a working condition-based machine learning progress control device provided in an embodiment of the present application. The working condition-based machine learning progress control device 300 is applied to a server of a progress control system, the progress control system includes the server and an electronic device, and the device includes: an acquisition unit 301, used to acquire a progress query request from the electronic device, the progress query request includes a target working condition code, and the target working condition code is used to indicate the target working condition; a first determination unit 302, used to determine the current learning status of the target working condition according to the target working condition code, and the current learning status is used to indicate the current learning status of the target working condition in each learning stage; a second determination unit 303, used to determine whether the target working condition has a preparatory learning stage according to the current learning status, and the preparatory learning stage is a learning stage that the target working condition can currently enter but has not yet entered; a first sending unit 304, used to send the current learning status and prompt information to the electronic device if the preparatory learning stage exists, and the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; a second sending unit 305, used to send the current learning status to the electronic device if the preparatory learning stage does not exist.

[0085] In a possible instance, the learning progress of the target working condition includes a learning task creation stage, a learning target confirmation stage, a learning production scheduling stage, a training stage, a multi-target learning stage and a verification and evaluation stage. In terms of determining whether the target working condition has a preparatory learning stage based on the current learning situation, the second determination unit 303 is specifically used to: determine the next learning stage of the current learning stage, the learning task creation stage is the initial learning stage, the learning target confirmation stage is the next learning stage of the learning task creation stage, the learning production scheduling stage is the next stage of the learning target confirmation stage, the training stage is the next stage of the learning production scheduling stage, the multi-target learning stage is the next stage of the training stage, and the verification and evaluation stage is the next stage of the multi-target learning stage; determine whether the learning task of the target working condition in the current learning stage has been completed; if so, determine that the next learning stage of the current learning stage is the preparatory learning stage.

[0086] In a possible instance, the initial stage of the learning progress of the target working condition is the stage of creating learning tasks, and the current learning status of the target working condition includes that the target working condition has not yet created a learning task. After determining the current learning status of the target working condition according to the target working condition code, the device 300 is also used to: determine the working condition type of the target working condition according to the target working condition code; determine the recommended task number according to the working condition type, and the recommended task number is used to recommend the number of learning tasks for the target working condition that the user needs to create in the stage of creating learning tasks; and send the recommended task number to the electronic device.

[0087] In a possible example, in terms of determining the recommended number of tasks based on the operating condition type, the device 300 is used to: determine a similar operating condition code based on the target operating condition code, wherein the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; obtain a preparatory operating condition, wherein the preparatory operating condition is a condition that has completed all learning stages among the similar operating conditions corresponding to the similar operating condition code; determine the number of learning tasks corresponding to the preparatory operating condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory operating condition; determine the quality distribution based on the comprehensive product quality index of each learning task; determine the recommended task number interval based on the quality distribution and the number of learning tasks; and determine the recommended task number based on the recommended task number interval.

[0088] In a possible instance, the current learning situation includes the learning situation in the training phase. In terms of determining the current learning situation of the target working condition according to the target working condition code, the first determination unit 302 is specifically used to: determine the total training batch of the target working condition in the training phase; obtain the production situation of each production process for the target working condition, and the production situation is used to indicate the production situation of the current production batch corresponding to the production process; determine the completion progress corresponding to each production process according to the total training batch and the current production batch; determine the training progress of the target working condition in the training phase according to the completion progress corresponding to each production process; in terms of sending the current learning situation to the electronic device, the first sending unit 304 or the second sending unit 305 is used to: send the production situation and the training progress to the electronic device.

[0089] In a possible example, in terms of determining the training progress of the target working condition in the training phase according to the completion progress corresponding to each production process, the first determination unit 302 is specifically used to: determine a preparatory production process, the completion progress corresponding to the preparatory production process is less than 1; number the preparatory production processes according to the production sequence, the larger the numbering sequence, the later the production sequence; determine a progress coefficient for each preparatory production process according to the production sequence, the later the production sequence of the preparatory production process, the higher the progress coefficient; determine the training progress of the target working condition in the training phase according to the progress coefficient and the completion progress corresponding to the preparatory production process.

[0090] In a possible example, when the current learning situation includes a multi-target learning stage, in the aspect of determining the current learning situation of the target working condition according to the target working condition code, the first determining unit 302 is specifically used to: determine the learned rounds of the target working condition; obtain product parameter information obtained in each round of learning in the learned rounds; sort the learned rounds according to the product parameter information; in terms of sending the current learning situation to the electronic device, the first sending unit 304 or the second sending unit 305 is specifically used to: send the product parameter information corresponding to the target learning round to the electronic device, the target learning round is the learned round sorted before the preset order; after sending the product parameter information corresponding to the target learning round to the electronic device, the method also includes: receiving a setting request for a version of the target learning round from the electronic device, the learning parameters corresponding to each round of multi-target learning being a version; updating the version of the target learning round to a preset version according to the version setting request; and determining that the preset version is a version that can enter the verification and evaluation stage.

[0091] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0092] In the case of an integrated unit, such as Fig. 9 As shown, Fig. 9 This is a functional unit block diagram of another working condition-based machine learning progress control device provided in an embodiment of the present application. Fig. 9 In the embodiment, the machine learning progress control device 400 based on working conditions includes: a processing module 412 and a communication module 411. The processing module 412 is used to control and manage the actions of the machine learning progress control device based on working conditions, for example, to execute the steps of the acquisition unit 301, the first determination unit 302, the second determination unit 303, the first sending unit 304, and the second sending unit 305, and / or to execute other processes of the technology described herein. The communication module 411 is used for the interaction between the machine learning progress control device based on working conditions and other devices. Fig. 9 As shown, the operating condition-based machine learning progress control device may further include a storage module 413, which is used to store program code and data of the operating condition-based machine learning progress control device.

[0093] Among them, the processing module 412 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 411 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 413 can be a memory.

[0094] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here. The above working condition-based machine learning progress control device 400 can execute the above Figure 4 The working condition-based machine learning progress control method shown.

[0095] For the above embodiments, please refer to Fig.10 , Fig.10It is a functional unit composition block diagram of another working condition-based machine learning progress control device provided in an embodiment of the present application. The working condition-based machine learning progress control device 500 is applied to an electronic device of a progress control system, the progress control system includes a server and the electronic device, and the device includes: a sending unit 501, used to send a progress query request to the server, the progress query request includes a target working condition code, the target working condition code is used to indicate the target working condition, the target working condition is used to indicate the current learning situation, the current learning situation is used to indicate the current learning situation of the target working condition in each learning stage, and the current learning situation is used to determine whether the target working condition has a preparatory learning stage, the preparatory learning stage is a learning stage that the target working condition can currently enter but has not yet entered; a first acquisition unit 502, used to obtain the current learning situation and prompt information sent from the server if the preparatory learning stage exists, the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; a second acquisition unit 503, used to obtain the current learning situation from the server if the preparatory learning stage does not exist.

[0096] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0097] In the case of an integrated unit, such as Fig.11 As shown, Fig.11 This is a functional unit block diagram of another working condition-based machine learning progress control device provided in an embodiment of the present application. Fig.11 In the embodiment, the machine learning progress control device 600 based on working conditions includes: a processing module 612 and a communication module 611. The processing module 612 is used to control and manage the actions of the machine learning progress control device based on working conditions, for example, to execute the steps of the sending unit 501, the first acquisition unit 502 and the second acquisition unit 503, and / or to execute other processes of the technology described in this article. The communication module 611 is used for the interaction between the machine learning progress control device based on working conditions and other devices. Fig.11 As shown, the operating condition-based machine learning progress control device may further include a storage module 613, which is used to store program code and data of the operating condition-based machine learning progress control device.

[0098] Among them, the processing module 612 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 611 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 613 can be a memory.

[0099] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0100] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and a software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0101] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0102] An embodiment of the present application also provides a chip, wherein the chip includes a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes some or all of the steps described for the electronic device in the above method embodiment.

[0103] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0104] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0105] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0106] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, 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 through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0108] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0110] If the above-mentioned 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 memory. 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 memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0111] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0112] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0113] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A machine learning progress control method based on working conditions, characterized in that: The method comprises: Acquire a progress query request from an electronic device, wherein the progress query request includes a target operating condition code, and the target operating condition code is used to indicate a target operating condition; Determining a current learning status of the target operating condition according to the target operating condition code, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage; Determine whether the target operating condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered; If the preparatory learning stage exists, sending the current learning situation and prompt information to the electronic device, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; If the preparatory learning stage does not exist, sending the current learning situation to the electronic device; The initial stage of the learning progress of the target working condition is a stage of creating a learning task, the current learning status of the target working condition includes that the target working condition has not yet created a learning task, and after determining the current learning status of the target working condition according to the target working condition code, the method further includes: Determining the operating condition type of the target operating condition according to the target operating condition code; Determine the recommended task quantity according to the working condition type, wherein the recommended task quantity is used to recommend the number of learning tasks for the target working condition that the user needs to create in the learning task creation stage; sending the recommended task quantity to the electronic device; Wherein, determining the recommended task quantity according to the working condition type includes: Determine a similar operating condition code according to the target operating condition code, wherein the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; Acquire a preparatory working condition, where the preparatory working condition is a working condition of the same type corresponding to the same type working condition code and has completed all learning stages; Determine the number of learning tasks corresponding to the preparatory working condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory working condition; Determining the quality distribution according to the comprehensive quality index of the product of each learning task; Determine a recommended task quantity interval according to the quality distribution and the number of learning tasks; The recommended task quantity is determined according to the recommended task quantity interval.

2. The method according to claim 1, characterized in that The learning progress of the target working condition includes a learning task creation stage, a learning target confirmation stage, a learning production scheduling stage, a training stage, a multi-target learning stage, and a verification and evaluation stage. The determining whether the target working condition has a preparatory learning stage according to the current learning situation includes: Determine the next learning stage of the current learning stage, the learning task creation stage is the initial learning stage, the learning target confirmation stage is the next learning stage of the learning task creation stage, the learning production scheduling stage is the next stage of the learning target confirmation stage, the training stage is the next stage of the learning production scheduling stage, the multi-objective learning stage is the next stage of the training stage, and the verification and evaluation stage is the next stage of the multi-objective learning stage; Determining whether the learning task of the target working condition in the current learning stage has been completed; If so, it is determined that the next learning stage of the current learning stage is a preparatory learning stage.

3. The method according to any one of claims 1 to 2, characterized in that: The current learning situation includes the learning situation in the training phase, and the determining the current learning situation of the target operating condition according to the target operating condition code includes: Determining a total training batch of the target operating condition in the training phase; Obtaining the production status of each production process for the target working condition, wherein the production status is used to indicate the production status of the current production batch corresponding to the production process; Determine the completion progress of each production process according to the total training batch and the current production batch; Determining the training progress of the target working condition in the training phase according to the completion progress corresponding to each production process; The sending the current learning situation to the electronic device includes: The production situation and the training progress are sent to the electronic device.

4. A machine learning progress control method based on working conditions, characterized in that: The method comprises: Sending a progress query request to a server, the progress query request including a target operating condition code, the target operating condition code being used to determine a current learning status of the target operating condition, the current learning status being used to indicate a current learning status of the target operating condition in each learning stage, the current learning status being used to determine whether the target operating condition has a preparatory learning stage, the preparatory learning stage being a learning stage that the target operating condition can currently enter but has not yet entered; If the preparatory learning stage exists, obtaining the current learning status and prompt information sent from the server, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; If the preparatory learning stage does not exist, obtaining the current learning status from the server; The server is used to obtain a progress query request from an electronic device, wherein the progress query request includes a target working condition code; determine whether the target working condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target working condition can currently enter but has not yet entered; if the preparatory learning stage exists, send the current learning situation and prompt information to the electronic device, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; if the preparatory learning stage does not exist, send the current learning situation to the electronic device; wherein the initial stage of the learning progress of the target working condition is the stage of creating a learning task, and the current learning situation of the target working condition includes that the target working condition has not yet created a learning task, and after determining the current learning situation of the target working condition according to the target working condition code, determine the working condition type of the target working condition according to the target working condition code; determine the number of recommended tasks according to the working condition type, wherein the number of recommended tasks is used to recommend the number of learning tasks for the target working condition that the user needs to create in the stage of creating a learning task; and send the recommended number of tasks to the electronic device; Wherein, determining the recommended task quantity according to the working condition type includes: Determine a similar operating condition code based on the target operating condition code, and the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; obtain a preparatory operating condition, and the preparatory operating condition is a condition that has completed all learning stages among the similar operating conditions corresponding to the similar operating condition code; determine the number of learning tasks corresponding to the preparatory operating condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory operating condition; determine the quality distribution based on the comprehensive product quality index of each learning task; determine a recommended task quantity interval based on the quality distribution and the number of learning tasks; determine the recommended task quantity based on the recommended task quantity interval.

5. A machine learning progress control device based on working conditions, characterized in that: The device comprises: an acquisition unit, configured to acquire a progress query request from an electronic device, wherein the progress query request includes a target operating condition code, and the target operating condition code is used to indicate a target operating condition; a first determining unit, configured to determine a current learning status of the target operating condition according to the target operating condition code, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage; A second determining unit is used to determine whether the target operating condition has a preparatory learning stage according to the current learning situation, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered; A first sending unit is used to send the current learning situation and prompt information to the electronic device if the preparatory learning stage exists, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; A second sending unit, configured to send the current learning situation to the electronic device if the preparatory learning stage does not exist; Wherein, the initial stage of the learning progress of the target working condition is the stage of creating learning tasks, the current learning status of the target working condition includes that the target working condition has not yet created a learning task, and after determining the current learning status of the target working condition according to the target working condition code, the device is further used to: determine the working condition type of the target working condition according to the target working condition code; determine the recommended task number according to the working condition type, and the recommended task number is used to recommend the number of learning tasks for the target working condition that the user needs to create in the stage of creating learning tasks; send the recommended task number to the electronic device; Wherein, determining the recommended task quantity according to the working condition type includes: Determine a similar operating condition code according to the target operating condition code, wherein the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; Acquire a preparatory working condition, where the preparatory working condition is a working condition of the same type corresponding to the same type working condition code and has completed all learning stages; Determine the number of learning tasks corresponding to the preparatory working condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory working condition; Determining the quality distribution according to the comprehensive quality index of the product of each learning task; Determine a recommended task quantity interval according to the quality distribution and the number of learning tasks; The recommended task quantity is determined according to the recommended task quantity interval.

6. A machine learning progress control device based on working conditions, characterized in that: The device comprises: a sending unit, configured to send a progress query request to a server, wherein the progress query request includes a target operating condition code, wherein the target operating condition code is used to determine a current learning status of the target operating condition, wherein the current learning status is used to indicate a current learning status of the target operating condition in each learning stage, wherein the current learning status is used to determine whether the target operating condition has a preparatory learning stage, wherein the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered; A first acquisition unit is used to acquire the current learning status and prompt information sent from the server if the preparatory learning stage exists, wherein the prompt information is used to prompt the user to create a task for the target working condition in the preparatory learning stage; A second acquisition unit, configured to acquire the current learning status from the server if the preparatory learning stage does not exist; The server is used to obtain a progress query request from an electronic device, the progress query request includes a target operating condition code, the target operating condition code is used to indicate the target operating condition; determine the current learning status of the target operating condition according to the target operating condition code, the current learning status is used to indicate the current learning status of the target operating condition in each learning stage; determine whether the target operating condition has a preparatory learning stage according to the current learning status, the preparatory learning stage is a learning stage that the target operating condition can currently enter but has not yet entered; if the preparatory learning stage exists, send the current learning status and prompt information to the electronic device, the prompt information is used to prompt the user to create the target operating condition in the preparatory learning stage. tasks in the learning stage; if the preparatory learning stage does not exist, sending the current learning situation to the electronic device; wherein the initial stage of the learning progress of the target working condition is the stage of creating learning tasks, the current learning situation of the target working condition includes that the learning task has not been created for the target working condition, after determining the current learning situation of the target working condition according to the target working condition code, determining the working condition type of the target working condition according to the target working condition code; determining the number of recommended tasks according to the working condition type, the recommended number of tasks is used to recommend the number of learning tasks for the target working condition that the user needs to create in the stage of creating learning tasks; sending the recommended number of tasks to the electronic device; Wherein, determining the recommended task quantity according to the working condition type includes: Determine a similar operating condition code based on the target operating condition code, and the similarity between the similar operating condition code and the target operating condition code is greater than a preset value; obtain a preparatory operating condition, and the preparatory operating condition is a condition that has completed all learning stages among the similar operating conditions corresponding to the similar operating condition code; determine the number of learning tasks corresponding to the preparatory operating condition and the comprehensive product quality index corresponding to each learning task corresponding to the preparatory operating condition; determine the quality distribution based on the comprehensive product quality index of each learning task; determine a recommended task quantity interval based on the quality distribution and the number of learning tasks; determine the recommended task quantity based on the recommended task quantity interval.

7. A device, characterized in that: The method comprises a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 4.

8. A computer-readable storage medium or a computer program product, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 4, or the computer program product enables a computer to execute the method according to any one of claims 1 to 4.

Images