Joint learning task viewing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a joint learning task viewing method and device, electronic equipment and storage medium. The method comprises: receiving a task viewing request sent by a participant, in response to the task viewing request, calling a joint learning task list, and setting a task filtering condition according to the task viewing request; using a preset task filtering rule corresponding to the task filtering condition to perform a filtering operation on the joint learning tasks in the joint learning task list to obtain a filtering result; receiving a detail viewing request sent by the participant, in response to the detail viewing request, determining task detail information of a current task state corresponding to the joint learning task according to the current task state corresponding to each joint learning task in the filtering result. The present disclosure can multi-dimensionally display the joint learning task process, facilitate users to quickly understand the task details, and improve the joint learning experience of the users.

Description

Technical Field

[0001] This disclosure relates to the field of federated learning technology, and in particular to a method, apparatus, electronic device, and storage medium for viewing federated learning tasks. Background Technology

[0002] With the development of artificial intelligence and distributed machine learning technologies, collaborative learning, which involves uniting different stakeholders, has become a mainstream trend in training AI models. As a novel distributed machine learning framework, collaborative learning meets the needs of multiple clients for model training while maintaining data security. In collaborative learning platforms, to ensure users clearly understand the process and can easily select and join collaborative learning tasks, the execution process of these tasks needs to be visualized and presented to the user.

[0003] In existing technologies, when displaying collaborative learning tasks, the process is limited because collaborative learning involves multiple parties, each participating at different stages of the task. Traditional workflow display methods based on collaborative learning tasks have limited display dimensions and lack features such as task filtering and quick joining. Users also cannot view task details, thus reducing the user's collaborative learning experience.

[0004] In view of the problems in the existing technology, there is a need to provide a method for viewing collaborative learning tasks that can increase the multi-dimensional display of tasks, have task filtering and quick joining functions, facilitate users to quickly understand task details, and improve the user's collaborative learning experience. Summary of the Invention

[0005] In view of this, the present disclosure provides a method, apparatus, electronic device, and storage medium for viewing federated learning tasks, in order to solve the problems of insufficient dimensions for viewing federated learning tasks, limited functionality, inability to view task details, and reduced user federated learning experience in the prior art.

[0006] A first aspect of this disclosure provides a method for viewing joint learning tasks, comprising: receiving a task viewing request sent by a participant; responding to the task viewing request, retrieving a joint learning task list and setting task filtering conditions according to the task viewing request; performing a filtering operation on the joint learning tasks in the joint learning task list using preset task filtering rules corresponding to the task filtering conditions, and obtaining filtering results; receiving a details viewing request sent by a participant; responding to the details viewing request, determining task details information of the current task status corresponding to each joint learning task in the filtering results.

[0007] A second aspect of this disclosure provides a device for viewing collaborative learning tasks, comprising: a receiving module configured to receive a task viewing request sent by a participant, and in response to the task viewing request, retrieve a collaborative learning task list and set task filtering conditions according to the task viewing request; a filtering module configured to perform a filtering operation on the collaborative learning tasks in the collaborative learning task list using preset task filtering rules corresponding to the task filtering conditions, and obtain filtering results; and a determining module configured to receive a details viewing request sent by a participant, and in response to the details viewing request, determine task details information of the current task status corresponding to each collaborative learning task in the filtering results based on the current task status of each collaborative learning task.

[0008] The above-described at least one technical solution adopted in the embodiments of this disclosure can achieve the following beneficial effects:

[0009] By receiving task viewing requests from participants, the system responds by retrieving the collaborative learning task list and setting task filtering conditions based on the requests. Using pre-defined task filtering rules corresponding to the filtering conditions, it performs filtering operations on the collaborative learning tasks in the task list, obtaining the filtering results. Upon receiving detail viewing requests from participants, the system responds by determining the task details for each collaborative learning task based on its current task status in the filtering results. This disclosure enables a multi-dimensional display of the collaborative learning task process, providing the collaborative learning platform with functions such as task filtering and quick joining, facilitating users' rapid understanding of task details and enhancing their collaborative learning experience. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is a schematic diagram of a joint learning architecture provided in an embodiment of this disclosure;

[0012] Figure 2 This is a flowchart illustrating the method for viewing collaborative learning tasks provided in this embodiment of the disclosure;

[0013] Figure 3 This is a schematic diagram of the structure of the collaborative learning task viewing device provided in this embodiment of the disclosure;

[0014] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this disclosure. Detailed Implementation

[0015] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0016] Federation learning refers to the comprehensive utilization of multiple AI (Artificial Intelligence) technologies, under the premise of ensuring data security and user privacy, to collaboratively explore the value of data and foster new intelligent business forms and models based on joint modeling. Federation learning has at least the following characteristics:

[0017] (1) Participating nodes control their own data in a weakly centralized joint training mode to ensure data privacy and security in the process of co-creating intelligence.

[0018] (2) In different application scenarios, various model aggregation optimization strategies are established by using screening and / or combination of AI algorithms and privacy-preserving computing to obtain high-level and high-quality models.

[0019] (3) Under the premise of ensuring data security and user privacy, based on multiple model aggregation optimization strategies, obtain methods to improve the performance of the federated learning engine. The performance methods can be improved by solving problems such as parallel computing architecture, information interaction under large-scale cross-domain networks, intelligent perception, and anomaly handling mechanisms.

[0020] (4) Obtain the needs of multiple users in various scenarios, determine the true contribution of each joint participant through a mutual trust mechanism, and allocate incentives accordingly.

[0021] Based on the above approach, an AI technology ecosystem based on collaborative learning can be established, fully leveraging the value of industry data and promoting the implementation of scenarios in vertical fields.

[0022] Figure 1 This is a schematic diagram of a joint learning architecture provided in an embodiment of this disclosure. Figure 1 As shown, the architecture of joint learning may include a server (central node) 101 and participants 102, 103 and 104.

[0023] In the joint learning process, a basic model can be established through server 101, which then sends this model to participants 102, 103, and 104 with whom it has established a communication connection. Alternatively, any participant can establish the basic model and upload it to server 101, which then sends it to other participants with whom it has established a communication connection. Participants 102, 103, and 104 construct models based on the downloaded basic structure and model parameters, train the models using local data, obtain updated model parameters, and encrypt and upload these updated model parameters to server 101. Server 101 aggregates the model parameters sent by participants 102, 103, and 104 to obtain global model parameters, which are then transmitted back to participants 102, 103, and 104. Participants 102, 103, and 104 iterate on their respective models based on the received global model parameters until the models converge, thus achieving model training. During the collaborative learning process, the data uploaded by participants 102, 103, and 104 are model parameters. Local data is not uploaded to server 101, and all participants can share the final model parameters. Therefore, collaborative modeling can be achieved while ensuring data privacy.

[0024] It should be noted that the number of participants is not limited to the three mentioned above, but can be set as needed, and this embodiment does not impose any restrictions on this.

[0025] A method and apparatus for viewing collaborative learning tasks according to embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings.

[0026] Figure 2 This is a flowchart illustrating the joint learning task viewing method provided in this embodiment. Figure 2 The method for viewing federated learning tasks can be executed by the federated learning server. For example... Figure 2 As shown, the specific methods for viewing this joint learning task may include:

[0027] S201, Receive a task viewing request sent by a participant, respond to the task viewing request, retrieve the joint learning task list, and set task filtering conditions according to the task viewing request.

[0028] S202, using the preset task filtering rules corresponding to the task filtering conditions, perform a filtering operation on the joint learning tasks in the joint learning task list to obtain the filtering results;

[0029] S203, Receive a details viewing request sent by the participants, and in response to the details viewing request, determine the task details information of the current task status corresponding to each joint learning task in the filtering results.

[0030] Specifically, the federated learning platform of this disclosure mainly consists of the following modules: a circle selection module, a data addition module, a task viewing module, a task creation module, a training module, a training result display module, and a model repository. The federated learning platform can be considered as a client running on the devices of each participating party. Each participating party can use the federated learning platform to select federated learning scenarios, upload training data, view the federated learning process, create federated learning tasks, and perform inference and prediction. The federated learning platform provides a unified federated learning engine based on the Industrial Internet of Things (IIoT), enabling it to redefine federated learning products and services from the perspective of ecosystem users, allowing users to experience federated learning capabilities on the platform.

[0031] Furthermore, each participant corresponds to a node in the federated learning framework, and each node corresponds to a participant device. Participant devices can be PCs, tablets, smartphones, smart wearable devices, etc. Each participant device has a client terminal for the federated learning participants, but the participant devices are not limited to these devices or clients. The federated learning framework also has nodes that provide services to the clients (i.e., servers). Servers can be servers used to perform aggregation operations. Servers can coordinate multiple clients to perform federated learning to obtain a federated learning model. Servers can be independent physical servers, server clusters composed of multiple physical servers, or cloud computing servers.

[0032] According to the technical solution provided in this disclosure, by receiving a task viewing request sent by a participant, responding to the task viewing request, retrieving the joint learning task list, and setting task filtering conditions according to the task viewing request; using preset task filtering rules corresponding to the task filtering conditions, performing a filtering operation on the joint learning tasks in the joint learning task list to obtain filtering results; receiving a details viewing request sent by a participant, responding to the details viewing request, and determining the task details information of the current task status corresponding to each joint learning task in the filtering results. This disclosure can display the joint learning task process from multiple dimensions, enabling the joint learning platform to have functions such as task filtering and quick joining, facilitating users to quickly understand task details and improving the user's joint learning experience.

[0033] In some embodiments, receiving a task viewing request sent by a participant and retrieving a joint learning task list in response to the task viewing request includes: receiving a task viewing request sent by a participant through a client; in response to the task viewing request, obtaining a list identifier in the task viewing request and determining a joint learning task list corresponding to the list identifier; wherein the joint learning task list includes a first joint learning task list and a second joint learning task list; the first joint learning task list contains joint learning tasks created by the participant, and the second joint learning task list contains joint learning tasks created by other participants.

[0034] Specifically, the following section uses user operations from a participating client in a real-world scenario as an example to illustrate the task viewing process in detail, which may include the following:

[0035] The first gesture operation is a click operation. Upon receiving the user's first gesture operation on the federated learning platform interface, the federated learning platform interface is switched to the federated learning task interface. This includes: when a click operation by the user on the federated learning task interface within the federated learning platform interface is detected, the federated learning platform interface is switched to the federated learning task interface. The federated learning task interface contains a first federated learning task list and a second federated learning task list. The first federated learning task list contains federated learning tasks created by the user, and the second federated learning task list contains federated learning tasks created by other users.

[0036] Furthermore, when a user clicks on the joint learning task interface of the joint learning platform, the current interface of the joint learning platform will switch to the joint learning task interface. User operations such as filtering joint learning tasks and viewing task details are all performed based on the joint learning task interface. The following detailed description, in conjunction with specific embodiments, illustrates the content of the joint learning task interface provided in this disclosure embodiment. This joint learning task interface may specifically include the following:

[0037] The joint learning task interface displays multiple task filter boxes side-by-side at the top, allowing users to input different filtering criteria. Below the filter boxes are two buttons: "My Tasks" and "Other Tasks." Clicking these buttons switches between different joint learning task lists; "My Tasks" corresponds to the first joint learning task list, and "Other Tasks" corresponds to the second joint learning task list. When all task filter boxes are empty, meaning the user has not entered any filtering criteria, all joint learning tasks corresponding to that list will be displayed in either the first or second joint learning task list.

[0038] In some embodiments, setting task filtering conditions based on a task viewing request includes: obtaining a condition identifier in the task viewing request, determining the task filtering conditions corresponding to the condition identifier, and setting the task filtering conditions as conditions for filtering the list of joint learning tasks; wherein, the task filtering conditions include task name filtering, task scenario filtering, task status filtering, and task initiator filtering.

[0039] Specifically, each task filter box corresponds to a specific task filtering condition. For example, the filter box corresponding to the task name can only be used to enter the task name, and the filter box corresponding to the task scenario can only be used to enter the task scenario. In practical applications, joint learning tasks can be filtered according to different task filtering conditions. Users can input one or more task filtering conditions, and joint learning tasks that simultaneously meet the task filtering conditions will be used as the final filtering results.

[0040] Furthermore, when selecting joint learning tasks using task filtering conditions, the filtering can include, but is not limited to, the following conditions: filtering by task name (by entering the task name); filtering by task scenario (by selecting a circle from all supported circles from a drop-down menu); filtering by task status (by selecting a task status from all task statuses from a drop-down menu, including four statuses: pending training, training in progress, completed, and training error (or training terminated); and filtering by task initiator (by entering the initiator's name).

[0041] In some embodiments, a filtering operation is performed on the joint learning tasks in the joint learning task list using preset task filtering rules corresponding to the task filtering conditions to obtain filtering results. This includes: calling the task filtering rules that have a mapping relationship with the task filtering conditions according to the task filtering conditions, and using the task filtering rules to filter all joint learning tasks in the joint learning task list to obtain joint learning tasks that simultaneously satisfy the task filtering rules; wherein, the task filtering rules include name filtering rules, scene filtering rules, state filtering rules, and initiator filtering rules.

[0042] Specifically, after the user enters the task filtering criteria, clicking the "Filter" button will display the filtering results. Tasks in the joint learning task list are filtered using task filtering rules that match the filtering criteria. When the user enters multiple filtering criteria, there are also multiple corresponding task filtering rules. Joint learning tasks that simultaneously meet the task filtering rules are selected and displayed as the filtering results.

[0043] In some embodiments, receiving a details viewing request sent by a participant includes: receiving a details viewing request sent by a participant through a client, and obtaining the current task status corresponding to each joint learning task in the filtering results; wherein, the filtering results also include the task name, task initiator, task scenario, number of participants, joint learning type, joint learning algorithm, task creation time, task status, and task operation corresponding to the joint learning task.

[0044] Specifically, the following section uses the user operations of a participating client in a real-world scenario as an example to explain in detail the process of viewing task details, which may include the following:

[0045] The joint learning task interface displays all joint learning tasks that meet the task selection criteria. In addition to displaying the task names corresponding to the joint learning tasks that meet the selection criteria, the interface can also display the following dimensions: the current task status of the joint learning task, the name of the initiator of the joint learning task, the task scenario of the joint learning task, the number of participants in the joint learning task, the joint type of the joint learning task, the algorithm used by the joint learning task, the creation time of the joint learning task, whether the task can be joined, and task operations, etc.

[0046] Furthermore, the task scenarios for joint learning tasks include, but are not limited to, the following scenarios: electricity load prediction, gas load prediction, and electricity and gas detection; the joint learning task types include horizontal joint learning and vertical joint learning; the algorithms used in joint learning tasks include XGBOOST, YOLO, LR, and other algorithms; the task operation button is used by users to quickly click to join a joint learning task or click to view task details.

[0047] In some embodiments, based on the current task status of each joint learning task in the filtering results, the task details information of the current task status of the joint learning task is determined, including: determining the task operation of the participant on the joint learning task based on the operation identifier in the details viewing request, and obtaining the task details information of the joint learning task in the current task status, so as to generate a task details window based on the task details information and display the task details window in a pop-up window; wherein, the current task status includes the waiting state, the training state, the training completed state, and the training abnormal state.

[0048] Specifically, in the joint learning task interface, each joint learning task corresponds to a task operation button (used to trigger the task operation). This task operation button can be either a button to join a joint learning task or a button to view task details. The following section uses user operations from participating clients in a real-world scenario as an example to explain in detail the process of displaying task details, which may include the following:

[0049] After a user clicks the "Task Details" button, the platform selects the corresponding task details template based on the current task status of the joint learning task, loads the task details information of the joint learning task into the template, and generates a task details window, which is then displayed as a pop-up. For example, clicking the "Task Details" button for a joint learning task that is in training (i.e., currently training) automatically pops up the task details window for real-time viewing; clicking the "Task Details" button for a joint learning task that has finished training (i.e., training completed) automatically pops up the task details window for completed training.

[0050] It should be noted that the current task status and task details for each collaborative learning task are different. The task detail template is only a display medium; the specific task details for each collaborative learning task under different current task statuses need to be obtained from the collaborative learning server.

[0051] In some embodiments, when the current task status is "waiting to train," the waiting time is calculated based on the queued tasks, and the waiting time is displayed as a countdown in the task details window, while online participants are highlighted. When the current task status is "training in progress," the interaction logs between each participant and the joint learning engine generated during the joint learning training process are displayed, and the aggregated periodic curve of the joint learning training is dynamically generated based on a preset joint learning completion metric. When the current task status is "training completed," the interaction logs are displayed, along with the corresponding aggregated periodic curve after the joint learning training is completed, and a notification that the joint learning training is complete is sent. When the current task status is "training abnormal," tasks with abnormal data are marked in the interaction logs, and the LSH collision detection algorithm is used to perform collision detection on the data between participants. The decision to terminate training is based on the collision detection results.

[0052] Specifically, the task details template differs depending on the current task status, and the content displayed also varies. The following section uses a collaborative learning platform in a real-world application scenario as an example to explain in detail the content of the task details window under different task statuses, which may include the following:

[0053] Scenario 1: In the task details window corresponding to the training state, the joint learning task is in a queue waiting state. After adding a joint learning task, since it can support training of only a single task and does not consider parallel task training, a waiting period is required when there is a joint learning task being trained in front. If the waiting time of the preceding task can be calculated, the last half-minute countdown will be displayed on this screen.

[0054] The task details window displays the participants for the current task at the top. To prevent clutter from too many participants, only 6 participants are shown, with the remaining participants indicated by "...". Each task can support 10 participants. The task details window includes the collaborative learning engine, the task initiator's identifier (also known as the team leader), and the names of the other participants. The team leader can be listed first on the left. The number of participants is displayed as 8 / 10, and the online status of each participant is indicated; online participants are highlighted, while offline participants are grayed out.

[0055] Scenario 2: In the task details window corresponding to the training state, view the task details of the joint learning task in training. For example, you can view the real-time training process of the task, including the interaction log between each participant and the engine, as well as the dynamic curve changes. In addition, the content in the task details window corresponding to the untrained state will also be displayed in the task details window corresponding to the training state, such as the interaction diagram of the participants and the engine displayed at the top.

[0056] Scenario 3: In the task details window for the training completion status, the overall display logic and information are basically the same as those in the training status. The difference is that the training completion status displays the final aggregated periodicity curve obtained after training. At this time, the aggregated periodicity curve no longer changes dynamically but becomes a static graph. In addition, after the joint learning training ends, a bubble notification "Training completed" appears on the interface.

[0057] Scenario 4: In the task details window for abnormal training states, if an anomaly occurs during training, the anomaly details can be viewed. LSH collision detection sends an anomaly alarm to the backend; severe anomalies will directly terminate training. If none of the participant's data collides, a corresponding prompt will appear on the interface. The task will not stop as long as at least two participant data collides normally.

[0058] Furthermore, in federated learning, an aggregation cycle refers to one round of training for the federated learning model. Each participating client uses local data to train its local model. When the local model training converges, the trained local model parameters are obtained and sent to the server. In each aggregation cycle, all participants upload their local model parameters, and the server performs a weighted average to derive a federated model. Therefore, each participant contributes in each cycle, and a cycle here represents a complete training of the federated learning model by the server.

[0059] Furthermore, Locality Sensitive Hashing (LSH) is an algorithm for similarity searching in massive datasets. LSH can handle queries and matching operations on high-dimensional data, and in this embodiment, it is used to calculate the similarity between participant data. In practical applications, besides using LSH to calculate the similarity between participant data, other similarity calculation methods can also be used, such as Euclidean distance, cosine similarity, or Jaccard similarity. In this embodiment, the joint learning platform can provide LSH anomaly alarm logic, facilitating the interface to prepare corresponding reminders to alert the user when training anomalies occur.

[0060] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0061] Figure 3 This is a schematic diagram of the structure of the collaborative learning task viewing device provided in an embodiment of this disclosure. Figure 3 As shown, the collaborative learning task viewing device includes:

[0062] The receiving module 301 is configured to receive task viewing requests sent by the participants, and in response to the task viewing requests, retrieve the joint learning task list and set task filtering conditions according to the task viewing requests.

[0063] The filtering module 302 is configured to perform a filtering operation on the joint learning tasks in the joint learning task list using preset task filtering rules corresponding to the task filtering conditions, and obtain the filtering results.

[0064] The determination module 303 is configured to receive a details viewing request sent by the participants, and in response to the details viewing request, determine the task details information of the current task status corresponding to each joint learning task in the filtering results.

[0065] In some embodiments, Figure 3 The receiving module 301 receives a task viewing request sent by a participant through a client, and in response to the task viewing request, obtains the list identifier in the task viewing request and determines the joint learning task list corresponding to the list identifier; wherein, the joint learning task list includes a first joint learning task list and a second joint learning task list; the first joint learning task list contains joint learning tasks created by the participant, and the second joint learning task list contains joint learning tasks created by other participants.

[0066] In some embodiments, Figure 3The receiving module 301 obtains the condition identifier in the task viewing request, determines the task filtering conditions corresponding to the condition identifier, and sets the task filtering conditions as conditions for filtering the joint learning task list; wherein, the task filtering conditions include task name filtering, task scenario filtering, task status filtering, and task initiator filtering.

[0067] In some embodiments, Figure 3 The filtering module 302 calls the task filtering rules that are mapped to the task filtering conditions according to the task filtering conditions, and uses the task filtering rules to filter all joint learning tasks in the joint learning task list to obtain joint learning tasks that simultaneously meet the task filtering rules; among them, the task filtering rules include name filtering rules, scenario filtering rules, status filtering rules, and initiator filtering rules.

[0068] In some embodiments, Figure 3 The determination module 303 receives a details viewing request sent by the participants through the client and obtains the current task status corresponding to each joint learning task in the filtering results. The filtering results also include the task name, task initiator, task scenario, number of participants, joint learning type, joint learning algorithm, task creation time, task status, and task operation corresponding to the joint learning task.

[0069] In some embodiments, Figure 3 The determination module 303 determines the task operation of the participants on the joint learning task based on the operation identifier in the details viewing request, and obtains the task details information of the joint learning task in the current task state, so as to generate a task details window based on the task details information and display the task details window as a pop-up window; wherein, the current task state includes the waiting state, the training state, the training completed state, and the training abnormal state.

[0070] In some embodiments, Figure 3When the current task status of the determination module 303 is in the "waiting for training" state, it calculates the waiting time based on the queued tasks, displays the waiting time as a countdown in the task details window, and highlights the participants in the online state. When the current task status is in the "training" state, it displays the interaction logs between each participant and the joint learning engine generated during the joint learning training process, and dynamically generates the aggregated periodic curve of the joint learning training based on the preset joint learning completion index. When the current task status is in the "training completed" state, it displays the interaction logs, displays the corresponding aggregated periodic curve after the joint learning training is completed, and sends a prompt that the joint learning training has been completed. When the current task status is in the "training abnormal" state, it marks the tasks with abnormal data in the interaction logs, uses the LSH collision detection algorithm to perform collision detection on the data between the participants, and determines whether to terminate the training based on the collision detection results.

[0071] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0072] Figure 4 This is a schematic diagram of the structure of the electronic device 4 provided in an embodiment of this disclosure. For example... Figure 4 As shown, the electronic device 4 of this embodiment includes a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. When the processor 401 executes the computer program 403, it implements the steps in the various method embodiments described above. Alternatively, when the processor 401 executes the computer program 403, it implements the functions of each module / unit in the various device embodiments described above.

[0073] For example, computer program 403 may be divided into one or more modules / units, which are stored in memory 402 and executed by processor 401 to perform the present disclosure. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 403 in electronic device 4.

[0074] Electronic device 4 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 4 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 4 and does not constitute a limitation on electronic device 4. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0075] Processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0076] The memory 402 can be an internal storage unit of the electronic device 4, such as a hard disk or RAM. The memory 402 can also be an external storage device of the electronic device 4, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 402 can include both internal and external storage units of the electronic device 4. The memory 402 is used to store computer programs and other programs and data required by the electronic device. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0077] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0078] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0079] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0080] In the embodiments provided in this disclosure, it should be understood that the disclosed apparatus / computer devices and methods can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. Multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0081] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0082] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0083] If an integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. A computer-readable medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in a computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0084] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A method for viewing joint learning tasks, characterized in that, include: The system receives a task viewing request from a participant, responds to the request by retrieving a joint learning task list, and sets task filtering conditions based on the request. The joint learning task list includes a first joint learning task list and a second joint learning task list. The first joint learning task list contains joint learning tasks created by the participant, and the second joint learning task list contains joint learning tasks created by other participants. The task filtering conditions include task name filtering, task scenario filtering, task status filtering, and task initiator filtering. Using preset task filtering rules corresponding to the task filtering conditions, a filtering operation is performed on the joint learning tasks in the joint learning task list to obtain the filtering results; the task filtering rules include name filtering rules, scene filtering rules, state filtering rules, and initiator filtering rules. The system receives a details viewing request from a participant and, in response to the details viewing request, determines the task details information of the current task status corresponding to each joint learning task in the filtering results; the current task status includes a waiting state, a training state, a training completed state, and a training abnormal state.

2. The method according to claim 1, characterized in that, The receiving participant sends a task viewing request, and in response to the task viewing request, retrieves the joint learning task list, including: The system receives a task viewing request sent by the participating party through a client, responds to the task viewing request, obtains the list identifier in the task viewing request, and determines the joint learning task list corresponding to the list identifier.

3. The method according to claim 1, characterized in that, The step of setting task filtering conditions based on the task viewing request includes: Obtain the condition identifier in the task viewing request, determine the task filtering condition corresponding to the condition identifier, and set the task filtering condition as a condition for filtering the joint learning task list.

4. The method according to claim 1, characterized in that, The step of using preset task filtering rules corresponding to the task filtering conditions to perform a filtering operation on the joint learning tasks in the joint learning task list to obtain the filtering results includes: Based on the task filtering conditions, the task filtering rules that are mapped to the task filtering conditions are invoked, and the task filtering rules are used to filter all joint learning tasks in the joint learning task list to obtain joint learning tasks that simultaneously satisfy the task filtering rules.

5. The method according to claim 4, characterized in that, The receipt of the details viewing request sent by the participating party includes: Receive a details viewing request sent by the participant through the client, and obtain the current task status corresponding to each of the joint learning tasks in the filtering results; The filtering results also include the task name, task initiator, task scenario, number of participants, joint learning type, joint learning algorithm, task creation time, task status, and task operation corresponding to the joint learning task.

6. The method according to claim 5, characterized in that, The step of determining the task details information of the current task status corresponding to each joint learning task based on the current task status of each joint learning task in the filtering results includes: Based on the operation identifier in the details viewing request, determine the task operation of the participant on the joint learning task, and obtain the task details information of the joint learning task in the current task state, so as to generate a task details window based on the task details information and display the task details window as a pop-up window.

7. The method according to claim 6, characterized in that, The method further includes: When the current task status is in the training state, the waiting time is calculated based on the queued task, and the waiting time is displayed in the task details window in the form of a countdown. Participants who are online are highlighted. When the current task status is in the training state, the interaction logs between each participant and the joint learning engine generated during the joint learning training process are displayed, and the aggregated cycle curve of joint learning training is dynamically generated based on the preset joint learning completion index. When the current task status is training completed, the interaction log is displayed, along with the corresponding aggregation period curve after the joint learning training is completed, and a notification that the joint learning training has been completed is sent. When the current task status is a training anomaly, the task with abnormal data is marked in the interaction log, and the LSH collision detection algorithm is used to perform collision detection on the data between the participants. Based on the collision detection result, it is determined whether to terminate the training.

8. A device for viewing collaborative learning tasks, characterized in that, include: The receiving module is configured to receive task viewing requests sent by participants, and in response to the task viewing requests, retrieve a joint learning task list and set task filtering conditions according to the task viewing requests; wherein, the joint learning task list includes a first joint learning task list and a second joint learning task list; the first joint learning task list contains joint learning tasks created by the participants, and the second joint learning task list contains joint learning tasks created by other participants; the task filtering conditions include task name filtering, task scenario filtering, task status filtering, and task initiator filtering; The filtering module is configured to perform a filtering operation on the joint learning tasks in the joint learning task list using preset task filtering rules corresponding to the task filtering conditions, and obtain the filtering results; the task filtering rules include name filtering rules, scene filtering rules, state filtering rules, and initiator filtering rules. The determination module is configured to receive a details viewing request sent by a participant, and in response to the details viewing request, determine the task details information of the current task status corresponding to each joint learning task in the filtering results; the current task status includes a waiting state, a training state, a training completed state, and a training abnormal state.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images