Task display method and device and related product

Abstract

The invention provides a task display method and device and a related product, and relates to the technical field of computers and Internet. The method comprises the steps of obtaining a plurality of to-be-processed tasks of a target object and task content and task description information of each to-be-processed task; scoring the task content of the to-be-processed task through the large model to obtain a content importance score of the to-be-processed task; adjusting the content importance score value through the target network model to obtain a content score adjustment value of the to-be-processed task; performing weighted summation processing on the content score adjustment values of the to-be-processed tasks and the task description information to obtain task importance score values of the to-be-processed tasks; sorting the plurality of to-be-processed tasks according to the task importance score values to obtain a target task; and placing the target task at the significant position for display. According to the embodiment of the invention, the task which is relatively important for the target object can be displayed at the significant position, so that the target object can process the important task in time.

Description

Technical Field

[0001] The present disclosure relates to the field of computer and Internet technology, and in particular to a task display method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] In the related art, some applications have a To-Do List function, which contains all the to-do tasks that the current user needs to handle. However, the existing to-do list simply lists information according to time. This display method will cause too many low-priority tasks to overwhelm important tasks, resulting in a low frequency of use of the to-do task function on the user side. Summary of the invention

[0004] The purpose of the present disclosure is to provide a task display method, device, electronic device, computer-readable storage medium and computer program product, which can screen out target tasks that are more important to the target object from multiple pending tasks of the target object and display them prominently, thereby improving user experience.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] The disclosed embodiment provides a task display method, comprising: acquiring multiple pending tasks of a target object, and task content and task description information of each pending task; scoring the task content of the pending tasks through a large model to obtain content importance score values ​​of the pending tasks; adjusting the content importance score values ​​of the pending tasks through a target network model to obtain content score adjustment values ​​of the pending tasks; performing weighted summation processing on the content score adjustment values ​​of the pending tasks and importance influence values ​​corresponding to each task description information to obtain task importance score values ​​of each pending task; sorting the multiple pending tasks according to the task importance score values ​​to obtain the top N target tasks, where N is an integer greater than or equal to 1; and placing the target tasks in a prominent position for display.

[0007] In some embodiments, the method further includes: combining the task description information and summarizing the task content of the target task through the large model to obtain summary content of each target task; wherein, placing the target task in a prominent position for display includes: while placing the target task in a prominent position for display, displaying the summary content of the target task in an associated manner.

[0008] In some embodiments, the multiple tasks to be processed include a first task; the method also includes: determining a content score adjustment value of the task content of the first task through the large model and the target network model; obtaining an actual content importance value of the task content of the first task; and adjusting the parameters of the target network model according to the content score adjustment value and the actual content importance value of the first task.

[0009] In some embodiments, the multiple tasks to be processed include a second task; wherein, after weighted summing up the content score adjustment value of the tasks to be processed and the importance influence value corresponding to each task description information to obtain the task importance score value of each task to be processed, the method further includes: determining the actual task importance value of the second task according to the processing order of the second task among the multiple tasks to be processed; obtaining the task importance score value of the second task; and adjusting the weights corresponding to the content score adjustment value and the task description information according to the difference between the actual task importance value of the second task and the task importance score value.

[0010] In some embodiments, determining the actual task importance value of the second task according to the processing order of the second task among the multiple tasks to be processed includes: obtaining multiple tasks that have been processed by the target object, the multiple tasks including the second task; determining the actual task importance value of the second task according to the processing order of the second task among the multiple tasks that have been processed by the target object.

[0011] In some embodiments, the method further includes: performing calculation of the task importance score value once in a periodic manner; and / or, triggering calculation of the task importance score value once after the target object has processed M tasks, where M<=N, and M is an integer greater than 0.

[0012] In some embodiments, the task description information includes: at least one of: task type, task creation time, task tag, task trigger object, task associated object, task difficulty, and task deadline.

[0013] The embodiment of the present disclosure provides a task display device, including: a task information acquisition module, a scoring module, a score adjustment module, a weighted summation module, a sorting module and a display module.

[0014] Among them, the task information acquisition module is used to obtain multiple pending tasks of the target object, as well as the task content and task description information of each pending task; the scoring module can be used to score the task content of the pending task through a large model to obtain the content importance score of the pending task; the score adjustment module can be used to adjust the content importance score of the pending task through a target network model to obtain the content score adjustment value of the pending task; the weighted summation module can be used to perform weighted summation processing on the content score adjustment value of the pending task and the importance influence value corresponding to each task description information to obtain the task importance score value of each pending task; the sorting module can be used to sort the multiple pending tasks according to the task importance score value to obtain the top N target tasks, where N is an integer greater than or equal to 1; the display module can be used to place the target task in a prominent position for display.

[0015] An embodiment of the present disclosure provides an electronic device, which includes: a memory and a processor; the memory is used to store computer program instructions; the processor calls the computer program instructions stored in the memory to implement any of the task display methods described above.

[0016] The embodiment of the present disclosure provides a computer-readable storage medium on which computer program instructions are stored to implement any of the above-mentioned task display methods.

[0017] The embodiment of the present disclosure provides a computer program product or a computer program, which includes computer program instructions stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and a processor executes the computer program instructions to implement the above-mentioned task display method.

[0018] The task display method, device, electronic device, computer-readable storage medium, and computer program product provided by the embodiments of the present disclosure can first score the task content of the task to be processed through a large model; then fine-tune the score value through the target network model to accurately determine the importance of the task content of the task to be processed to the target object; finally, by weighted summing the content score adjustment value of the target object and each task description information, the importance of each task to be processed to the target object is determined, thereby screening out the N most important tasks for the target object for prominent display. Through the above method, the target tasks that are relatively important to the target object can be screened out and displayed in a prominent position, so that the target object can understand and process the target task in a timely manner, thereby improving the user experience.

[0019] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0021] Figure 1 A schematic diagram of a scenario that can be applied to a task display method or a task display device in an embodiment of the present disclosure is shown.

[0022] Figure 2 The figure is a schematic diagram of a task display list according to the related art.

[0023] Figure 3 The figure is a flowchart of a task display method according to an exemplary embodiment.

[0024] Figure 4 The figure is a flowchart of a task display method according to an exemplary embodiment.

[0025] Figure 5 The present invention is a flowchart of a method for training a target network model according to an exemplary embodiment.

[0026] Figure 6 The figure is a flow chart of a weight adjustment method according to an exemplary embodiment.

[0027] Figure 7 The figure is a flowchart of a method for determining an actual importance value of a task according to an exemplary embodiment.

[0028] Figure 8 The figure is a block diagram of a task display device according to an exemplary embodiment.

[0029] Fig. 9 A schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0030] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0031] Those skilled in the art will appreciate that the embodiments of the present disclosure may be a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0032] The features, structures or characteristics described in the present disclosure may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0033] In the embodiments of the present disclosure, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0034] The accompanying drawings are only schematic diagrams of the present disclosure, and the same reference numerals in the drawings represent the same or similar parts, so their repeated description will be omitted. Some block diagrams shown in the accompanying drawings do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0035] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and steps, nor must they be executed in the order described. For example, some steps can be decomposed, and some steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0036] In the description of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a kind of association relationship describing the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" means one or more, and "plurality" means two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different; the terms "comprising", "including" and "having" are used to express the meaning of open inclusion and mean that in addition to the listed elements / components / etc., there may be other elements / components / etc.

[0037] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0038] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0039] First, some terms involved in the embodiments of the present disclosure are explained below to facilitate understanding by those skilled in the art.

[0040] 1. GitLab To-Do List: GitLab To-Do List is a feature of GitLab (an open source platform for code hosting and version control, which integrates code review, project management, issue tracking, CI / CD (continuous integration / continuous deployment) and other functions, providing a comprehensive solution for software development teams.) It displays all the to-do tasks of the current user. It contains the content description of the task, and you can jump to the source of the task by clicking it, and the user can actively mark it as completed.

[0041] 2. LLM: Large Language Model, which has powerful language understanding and generation capabilities and is particularly good at natural language processing tasks.

[0042] 3. RM: Reward model, a model used in reinforcement learning to evaluate and estimate rewards under specific states or behaviors.

[0043] The foregoing introduces some terms and concepts involved in the embodiments of the present disclosure. The following introduces the technical features involved in the embodiments of the present disclosure.

[0044] The exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0045] Figure 1 A schematic diagram of a scenario that can be applied to a task display method or a task display device in an embodiment of the present disclosure is shown.

[0046] Please refer to Figure 1 , which shows a schematic diagram of an implementation environment provided by an exemplary embodiment of the present disclosure.

[0047] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0048] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, virtual reality devices, smart homes, etc.

[0049] The server 105 may be a server that provides various services, such as a background management server that provides support for devices operated by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received request data, and feed back the processing results to the terminal device.

[0050] The server can be an independent physical server or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as basic cloud computing services such as big data and artificial intelligence platforms, etc. The present disclosure does not impose any restrictions on this.

[0051] The server 105 may, for example, obtain multiple pending tasks of the target object, as well as the task content and task description information of each pending task. The server 105 may, for example, score the task content of the pending task through a large model to obtain a content importance score value of the pending task. The server 105 may, for example, adjust the content importance score value of the pending task through a target network model to obtain a content score adjustment value of the pending task. The server 105 may, for example, perform weighted summation processing on the content score adjustment value of the pending task and the importance influence value corresponding to each task description information to obtain a task importance score value of each pending task. The server 105 may, for example, sort multiple pending tasks by task importance score value to obtain the top N target tasks, where N is an integer greater than or equal to 1. The server 105 may, for example, place the target task in a prominent position for display.

[0052] It should be understood that Figure 1 The number of terminal devices, networks and servers in the figure is only for illustration. The server 105 may be a physical server or may be composed of multiple servers. According to actual needs, it may have any number of terminal devices, networks and servers.

[0053] In many cases, 80% of the results are caused by 20% of the reasons. Higgins's Law guides us that if we want to work well and efficiently, we should focus on a small number of important tasks instead of spending a lot of time on other unimportant tasks.

[0054] In the related art, the task to-do list in the existing application always receives a large number of to-do tasks, and the task list simply lists the information or filters the information according to tags (such as Figure 2 As shown, the related technology only lists the tasks in the actual order). The existing display method will cause too many low-priority tasks to overwhelm the important tasks, resulting in the low frequency of use of the to-do task function on the user side.

[0055] In order to solve the above technical problems, the present application proposes the following task display method.

[0056] Figure 3 is a flowchart of a task display method according to an exemplary embodiment. The method provided by the embodiment of the present disclosure can be executed by any electronic device with computing and display capabilities. For example, the method can be executed by the above Figure 1 The server or terminal device in the embodiment may be executed, or the server and the terminal device may be executed together. In the following embodiments, the server is used as the execution subject for example, but the present disclosure is not limited to this.

[0057] Reference Figure 3The task display method provided by the embodiment of the present disclosure may include the following steps.

[0058] Step S302: Acquire multiple pending tasks of the target object, as well as the task content and task description information of each pending task.

[0059] In some embodiments, in an application, a target object may correspond to a plurality of pending tasks, which may be pending messages, pending emails, or pending programming tasks, etc., which are not limited in this application.

[0060] In some embodiments, each task may have corresponding task content, such as task text information described by the task creator in the task.

[0061] In some embodiments, each pending task may correspond to task description information, which is used to describe the attributes of the pending task. The task description information may be at least one of the task type, task creation time, task label, task trigger object, task associated object, task difficulty, and task deadline.

[0062] Task Type: The task type could be an issue, epic, or merge request, etc.

[0063] Task creation time: Tasks created during a specific time period may have a significant impact on their importance. Tasks created in the morning and early morning are more important.

[0064] Task label: The label marks the category of the source, often with categories such as "Priority 1", "Priority 2", and "Priority 3". The higher the priority, the more important the task.

[0065] Task trigger object (such as task owner): that is, who triggered the to-do task. The closer the relationship between the task owner and the current user, such as colleagues in the same group or superiors and subordinates, the more important the task is. The method to measure the relationship between two people: count the number of groups that the two people exist in together. The more common groups, the closer the relationship. At the same time, the higher the level of the task owner, the more important the task is.

[0066] Task related objects: other related persons in the task. The more related persons there are, the more important the task may be.

[0067] Task difficulty: The creator or editor of a task rates the difficulty of the task. For example, there may be four levels: 1 is the easiest, 4 is the hardest, and the harder the task, the more important it may be.

[0068] Task Deadline: The closer the deadline is, the more important the task is.

[0069] Step S304: score the content of the task to be processed using the large model to obtain a content importance score of the task to be processed.

[0070] In some embodiments, the large model can be used in combination with the prompt word to score the task content of the task to be processed to obtain a content importance score value of the task content of the task to be processed. The content importance score value can be an importance score given according to the task content (such as text content) of the task to be processed.

[0071] Step S306: adjusting the content importance score of the task to be processed by using the target network model to obtain an adjusted content score of the task to be processed.

[0072] In some embodiments, the large model may not be very accurate in scoring the task content of the task to be processed. The present application uses the target network model to adjust the content importance score value output by the large model.

[0073] Among them, the target network model can be a network model of any structure, for example, it can be a reward model RM, or it can be an ordinary network model composed of convolutional layers, or it can be a model such as MLP (Machine Language Program). In short, any network model that is convenient for adjusting network parameters can be the target network model in this application.

[0074] The target network model may be a lightweight network, and the number of parameters of the target network model is much smaller than the model parameters of the large model. The model parameters of the target network are easy to adjust.

[0075] Step S308 , performing weighted sum processing on the content score adjustment value of the task to be processed and the importance impact value corresponding to each task description information, to obtain the task importance score value of each task to be processed.

[0076] In some embodiments, the importance impact value corresponding to each task description information of the task to be processed can be determined. For example, for task difficulty, there can be four levels: 1 is the easiest and 4 is the hardest. The harder the task, the more important it may be, and the larger the corresponding importance impact value; for another example, for task deadlines, the closer the deadline is, the more important the task is, and the larger the corresponding importance impact value is.

[0077] In some embodiments, each task description information and content score adjustment value of the task to be processed may be weighted and summed using weights to obtain the task importance score value of the task to be processed.

[0078] The weights used in the weighted summation process can be adjusted during the process of the target object actually processing the task.

[0079] It should be noted that the content score adjustment values ​​of the above-mentioned tasks to be processed and the importance influence values ​​corresponding to the description information of each task may have different orders of magnitude. The content score adjustment values ​​of the above-mentioned tasks to be processed and the importance influence values ​​corresponding to the description information of each task may be normalized first, and then weighted summed.

[0080] Step S310, sorting the multiple tasks to be processed by task importance score values ​​to obtain the top N target tasks, where N is an integer greater than or equal to 1.

[0081] In some embodiments, the top N tasks to be processed in terms of importance may be used as target tasks.

[0082] Step S312: placing the target task in a prominent position for display.

[0083] In some embodiments, the target task can be displayed separately in a prominent position; or the target task can be displayed in the first N items of the list of tasks to be processed. In short, any display method that can highlight the target task so that the target object can pay attention to and process it in time is within the scope of protection of this application.

[0084] In some embodiments, the task importance score value may be calculated periodically; and / or, when the target object completes processing of M tasks, the task importance score value calculation is triggered, where M<=N, and M is an integer greater than 0. For example, M may be equal to half of N.

[0085] Through the above steps, one solution can complete the N target tasks displayed to the target object according to the actual cycle, so as to avoid no important tasks being displayed after the target object has processed the target tasks; on the other hand, the N target tasks to be processed can be completed in time after the target object has processed M tasks, so that there are always more important target tasks pushed to the target object, thereby improving the user experience.

[0086] Figure 4 The figure is a flowchart of a task display method according to an exemplary embodiment.

[0087] refer to Figure 4 , the above-mentioned task display method may include the following steps.

[0088] Step S402: Acquire multiple pending tasks of the target object, as well as the task content and task description information of each pending task.

[0089] Step S404: score the content of the task to be processed using the large model to obtain a content importance score of the task to be processed.

[0090] Step S406: adjusting the content importance score of the task to be processed by using the target network model to obtain an adjusted content score of the task to be processed.

[0091] Step S408 , performing weighted sum processing on the content score adjustment value of the task to be processed and the importance impact value corresponding to each task description information, to obtain the task importance score value of each task to be processed.

[0092] Step S410, sorting the multiple tasks to be processed by task importance score values ​​to obtain the top N target tasks, where N is an integer greater than or equal to 1.

[0093] Step S412, combining the task description information and summarizing the task contents of the target tasks through the large model to obtain summary contents of each target task.

[0094] In some embodiments, the task content of the task to be processed can be summarized and extracted by combining the large model with the prompt words to extract the task summary of the task to be processed.

[0095] In some other embodiments, summary information may be extracted from the task content by other methods (such as natural language processing or text summary processing).

[0096] Step S414: while placing the target task in a prominent position for display, a summary of the target task is displayed in association.

[0097] In some embodiments, only the content of the target task may be displayed in association with the target task.

[0098] This application can improve user efficiency, allowing users to more easily and conveniently find important tasks among a large number of to-do tasks, and further reduce the burden of selecting tasks by reading summarized short information.

[0099] Figure 5 The present invention is a flowchart of a method for training a target network model according to an exemplary embodiment.

[0100] In some embodiments, the plurality of pending tasks of the target object may include a first task.

[0101] Below, this application will take the first task as an example to explain how to train the target network model. Those skilled in the art can expand the training method of the target network model corresponding to the first task to use other tasks to train the target network model, and this application does not limit this.

[0102] refer to Figure 5 , the training method of the above-mentioned target network model may include the following steps.

[0103] Step S502: determining a content score adjustment value of the task content of the first task through the large model and the target network model.

[0104] Step S504: obtaining the actual importance value of the task content of the first task.

[0105] In some embodiments, the actual importance value of the content of the first task can be determined according to the processing order of the target object processing the first task. If the target object is the first to process the first task within a time period, the actual importance value of the content of the first task is relatively large, for example, it can be 1; if the target object is the last to process the first task within a time period, the actual importance value of the content of the first task is relatively small, for example, it can be 0.1.

[0106] In addition, the target object may be asked to manually rate the importance of the first task to determine the actual importance value of the task content of the first task.

[0107] Step S506: adjusting the parameters of the target network model according to the content score adjustment value of the first task and the actual importance value of the content.

[0108] In some embodiments, the large model has too many parameters and is not easy to adjust. In this embodiment, the large model can no longer be adjusted, but a target network model is connected in series after the large model, and then the target network model is fine-tuned according to the difference between the actual importance value and the content score adjustment value, so that the content score adjustment value jointly output by the large model and the target network model can more accurately describe the importance of the task content of the task to be processed.

[0109] Figure 6 The figure is a flow chart of a weight adjustment method according to an exemplary embodiment.

[0110] In some embodiments, the plurality of tasks to be processed includes a second task.

[0111] Below, this application will take the second task as an example to explain how to adjust the weighted sum weight corresponding to the task importance score value of the target object.

[0112] It is understandable that a person skilled in the art can also expand the weight adjustment method corresponding to the second task to more tasks, and this application does not impose any limitation on this.

[0113] refer to Figure 6 After performing weighted sum processing on the content score adjustment value of the task to be processed and the importance impact value corresponding to each task description information to obtain the task importance score value of each task to be processed, the above weight adjustment method may include the following steps.

[0114] Step S602: determining the actual task importance value of the second task according to the processing order of the second task among the plurality of tasks to be processed.

[0115] In some embodiments, the task importance score value may be calculated according to a cycle or a preset number of tasks, and the actual importance value of the second task may be determined based on the order in which the target object processes the second task within the cycle or the preset number of tasks.

[0116] Step S604: Obtain the task importance score of the second task.

[0117] In some embodiments, the task importance score of the second task may be determined through steps S302 to S306.

[0118] Step S606: adjusting the content score adjustment value and the weight corresponding to the task description information according to the difference between the actual task importance value and the task importance score value of the second task.

[0119] In some embodiments, the content score adjustment value and the weight corresponding to the task description information are reversely adjusted according to the difference between the actual task importance value and the task importance score value of the second task. The present application does not limit the weight adjustment method.

[0120] Through the above method, the weights corresponding to the content score adjustment values ​​and the task description information can more clearly and accurately describe the importance of each content score adjustment value and task description information to the target object.

[0121] It is understandable that for objects with different goals, the weights corresponding to the content score adjustment value and the task description information may be different.

[0122] Figure 7 The figure is a flowchart of a method for determining an actual importance value of a task according to an exemplary embodiment.

[0123] refer to Figure 7 , the above-mentioned method for determining the actual importance value of the task may include the following steps.

[0124] Step S702: Acquire multiple tasks that have been processed by the target object, where the multiple tasks include the second task.

[0125] In some embodiments, a plurality of tasks that have been processed by the target object in a processing cycle or a time period may be obtained, or a preset number of tasks that have been completed by the target object may be obtained as the plurality of processed tasks.

[0126] In some embodiments, the above-mentioned multiple tasks may include a second task. Below, this application will take the second task as an example to explain how to determine the actual importance value of the task.

[0127] Step S704: determining the actual task importance value of the second task according to the processing order of the second task among the multiple tasks that have been processed by the target object.

[0128] Through the above method, the actual task importance value of each processed task can be determined according to the actual order in which the target object processes the tasks.

[0129] Below, this application will introduce an important task display method in conjunction with a specific embodiment.

[0130] (1) Perform “importance calculation” regularly.

[0131] "Importance calculation" is the core process of this embodiment. Here we introduce when to trigger this calculation work.

[0132] Trigger timing 1: For each user (ie, target object), a scheduled task is set to perform "importance calculation" regularly to obtain the most important N tasks, where N is an integer greater than or equal to 1.

[0133] Triggering time 2: When the user completes M important tasks, an "importance calculation" will also be triggered. M is an integer greater than 0.

[0134] Regarding the choice of N: N is configurable, and the default value is recommended to be 8. 8 is the upper limit of the number of lines that an average person can read quickly. The desired effect is that the user can select the task that he needs to handle most at a glance.

[0135] Regarding the selection of M: 1<=M<=N, it can be configured according to the user load. The recommended default value is N / 2, which means that users always have sufficient important tasks to choose from at all times, while avoiding excessive system load.

[0136] (2) Prepare a “materiality calculation”.

[0137] To-do tasks in GitLab can be traced back to the source of the task, through which more structured information can be obtained. For example, at least one of the following information can be obtained.

[0138] Type of task source: The source of a task may be an issue, epic, merge request, etc.

[0139] Task creation time: Tasks created during a specific time period may have a significant impact on their importance. Tasks created in the morning and early morning are more important.

[0140] Tags: Tags mark the category of the source, often with categories such as "Priority 1", "Priority 2", "Priority 3", the higher the priority, the more important the task.

[0141] Task owner: that is, who triggered the to-do task. The closer the relationship between the task owner and the current user, such as colleagues in the same group or superiors and subordinates, the more important the task is. The method to measure the relationship between two people: count the number of groups in which the two people exist together. The more groups in common, the closer the relationship. At the same time, the higher the level of the task owner, the more important the task is.

[0142] Task related persons: other related persons in the task. The more related persons there are, the more important the task may be.

[0143] Task Difficulty: The creator or editor of the task rates the difficulty of the task. There are four levels, 1 being the easiest and 4 being the hardest. The more difficult the task, the more important it may be.

[0144] Task Deadline: The closer the deadline is, the more important the task is.

[0145] The text content of the task itself is also rich in information, but traditional technology makes it difficult to fully and accurately understand it. The large model combined with appropriate prompt words can score the importance of the task content itself, which is also an important dimension that affects the importance of the task.

[0146] In addition, since the large model may not accurately score the task content, this embodiment also uses the reward model to adjust the score output by the large model to obtain a scoring result that can accurately evaluate the importance of the task content.

[0147] The importance of each task is calculated as:

[0148] Score = w1·Type (type) + w2·CreatedAt (creation time) + w3·Label (label) + w4·Host (task owner) + w5·Related (task related person) + w6·Weight (task difficulty) + w7·DeadLine (task deadline) + w8·frm (LLM) (large model output result after adjustment by reward function) + b (bias term).

[0149] Among them, w i is the weight in the importance formula. i is an integer greater than or equal to 1.

[0150] It should be noted that a user may have his or her own importance calculation formula, that is, the weights in the importance calculation formulas of different users may be different or the same.

[0151] (3) Initialize “importance calculation”.

[0152] Collect user behavior data in advance to form a data set, train the basic model, and use this result as the default parameter for initialization of each user.

[0153] (4) Update and iterate “importance calculation”

[0154] When a user selects a task from the task list, it is assumed that the selected task should be the most important. The characteristics of the task and the expected score are saved to form a data set. For each user's private task data, the importance calculation formula for the user is retrained regularly, such as triggering execution once a week, or quantitative training can be performed, such as triggering execution once every 10,000 tasks collected.

[0155] w of training iterative model i parameter.

[0156] In order to allow LLM to obtain a more accurate importance score, for all task data of all users, other dimensions are eliminated and the reward function RM is trained only for the LLM dimension: Score = frm(LLM).

[0157] Specifically, only the scores related to the large model are retained in the "importance calculation" formula, and then the scoring results of the large model and the actual importance evaluation results are obtained, and the parameters of the reward function are adjusted. For details, please refer to Figure 5 The embodiment shown is not described in detail in this embodiment.

[0158] (5) Summarize important tasks and present them

[0159] After obtaining the most important N tasks, the summary information of the tasks is summarized using the large model in combination with the descriptive information of the task sources.

[0160] Make this summary information a separate module and display it above the original to-do tasks.

[0161] In combination with the above process, the task display method proposed in this application may include the following steps.

[0162] 1. Scan the user’s task list and extract parameters that affect task importance.

[0163] 2. Calculate the importance of the tasks and select the N most important ones.

[0164] 3. Use large models to summarize and present the content of important tasks.

[0165] 4. Collect the completion status of the user's task processing and update the user's own importance parameters.

[0166] The above method can improve the efficiency of users in identifying important tasks and help users plan their time and tasks more efficiently.

[0167] The embodiment of the present application provides a method for extracting important tasks. First, the user's to-do tasks are scanned, and then the task content is evaluated using LLM. Then, the original tag information and project information (such as project description information) in the application are combined to extract the N most important tasks for the user. And continuously collect feedback from users on the processing of to-do tasks, and iterate the algorithm parameters of each user accordingly, so as to provide each user with more personalized and accurate recommendation results. In addition, the extracted N important tasks are displayed in a more convenient location for users to select, and they are summarized using LLM to further facilitate user reading and improve task processing efficiency.

[0168] It should be particularly pointed out that the various steps in the various embodiments of the above-mentioned task display method can be mutually crossed, replaced, added, or deleted. Therefore, these reasonable permutations, combinations, and transformations of the task display method should also fall within the protection scope of the present disclosure, and the protection scope of the present disclosure should not be limited to the embodiments.

[0169] Based on the same inventive concept, the present disclosure also provides a task display device, as described in the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0170] Figure 8 is a block diagram of a task display device according to an exemplary embodiment. Figure 8 The task display device 800 provided in the embodiment of the present disclosure may include: a task information acquisition module 801, a scoring module 802, a score adjustment module 803, a weighted summation module 804, a sorting module 805 and a display module 806.

[0171] Among them, the task information acquisition module 801 can be used to obtain multiple pending tasks of the target object, as well as the task content and task description information of each pending task; the scoring module 802 can be used to score the task content of the pending task through a large model to obtain the content importance score of the pending task; the score adjustment module 803 can be used to adjust the content importance score of the pending task through a target network model to obtain the content score adjustment value of the pending task; the weighted summation module 804 can be used to perform weighted summation processing on the content score adjustment value of the pending task and the importance influence value corresponding to each task description information to obtain the task importance score value of each pending task; the sorting module 805 can be used to sort the multiple pending tasks according to the task importance score value to obtain the top N target tasks, where N is an integer greater than or equal to 1; the display module 806 can be used to place the target task in a prominent position for display.

[0172] It should be noted that the task information acquisition module 801, the scoring module 802, the score adjustment module 803, the weighted sum module 804, the sorting module 805, and the display module 806 correspond to S302 to S312 in the method embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the method embodiment. It should be noted that the modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0173] In some embodiments, the task display device 800 may further include: a summary processing module.

[0174] The summary processing module may be used to combine the task description information and perform summary processing on the task content of the target task through the large model to obtain summary content of each target task.

[0175] The display module 806 may include: an associated display unit.

[0176] The associated display unit may be used to display the target task in a prominent position and at the same time associate and display the summary content of the target task.

[0177] In some embodiments, the plurality of tasks to be processed include a first task; the display module 806 may further include: a first task content score adjustment value determination module, a first task content actual importance value determination module, and a parameter adjustment module.

[0178] Among them, the first task content score adjustment value determination module can be used to determine the content score adjustment value of the task content of the first task through the large model and the target network model; the first task content actual importance value determination module can be used to obtain the content actual importance value of the task content of the first task; the parameter adjustment module can be used to adjust the parameters of the target network model according to the content score adjustment value and the content actual importance value of the first task.

[0179] In some embodiments, the plurality of tasks to be processed include a second task; wherein the task display device 800 may further include: a task actual importance value determination module for the second task, a task importance score value determination module for the second task, and a weight adjustment module.

[0180] Among them, the module for determining the actual task importance value of the second task is used to perform weighted summation processing on the content score adjustment value of the task to be processed and the importance influence value corresponding to each task description information, and after obtaining the task importance score value of each task to be processed, determine the actual task importance value of the second task according to the processing order of the second task among the multiple tasks to be processed; the module for determining the task importance score value of the second task can be used to obtain the task importance score value of the second task; the weight adjustment module can be used to adjust the content score adjustment value and the weight corresponding to the task description information according to the difference between the actual task importance value of the second task and the task importance score value.

[0181] In some embodiments, the task actual importance value determination module of the second task may include: a processed task acquisition submodule and a task actual importance value determination submodule.

[0182] Among them, the processed task acquisition submodule can be used to obtain multiple tasks that have been processed by the target object, and the multiple tasks include the second task; the task actual importance value determination submodule can be used to determine the task actual importance value of the second task according to the processing order of the second task among the multiple tasks that have been processed by the target object.

[0183] In some embodiments, the task display device 800 may further include: a first task importance score value calculation module and / or a second task importance score value calculation module.

[0184] Among them, the first calculation module of the task importance score value is used to perform the calculation of the task importance score value once in a periodic manner; the second calculation module of the task importance score value is used to trigger the calculation of the task importance score value once after the target object has processed M tasks, where M<=N, and M is an integer greater than 0.

[0185] In some embodiments, the task description information includes: at least one of: task type, task creation time, task tag, task trigger object, task associated object, task difficulty, and task deadline.

[0186] Since the functions of the device 800 have been described in detail in the corresponding method embodiments, the present disclosure will not elaborate on them here.

[0187] The module units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The module units described may also be set in a processor. The names of these module units do not, in some cases, constitute limitations on the module units themselves.

[0188] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a part of a module or program segment, and a part of the above-mentioned module or program segment contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer program instructions.

[0189] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0190] Fig. 9 FIG. 1 shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiment of the present disclosure. It should be noted that: Fig. 9 The electronic device 900 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0191] like Fig. 9As shown, the electronic device 900 includes a central processing unit (CPU) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the electronic device 900 are also stored. The CPU 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0192] The following components are connected to the I / O interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage section 908 as needed.

[0193] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains computer program instructions for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 909, and / or installed from a removable medium 911. When the computer program is executed by a central processing unit (CPU) 901, the above-mentioned functions defined in the system of the present disclosure are executed.

[0194] It should be noted that the computer-readable storage medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable computer program instructions. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The computer program instructions contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0195] As another aspect, the present disclosure also provides a computer-readable storage medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by a device, the device can realize functions including: obtaining multiple pending tasks of the target object, as well as the task content and task description information of each pending task; scoring the task content of the pending task by the large model to obtain the content importance score value of the pending task; adjusting the content importance score value of the pending task by the target network model to obtain the content score adjustment value of the pending task; performing weighted summation processing on the content score adjustment value of the pending task and the importance influence value corresponding to each task description information to obtain the task importance score value of each pending task; sorting multiple pending tasks by the task importance score value to obtain the top N target tasks, where N is an integer greater than or equal to 1; placing the target task in a prominent position for display.

[0196] According to one aspect of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer program instructions, the computer program instructions being stored in a computer-readable storage medium. The computer program instructions are read from the computer-readable storage medium, and a processor executes the computer program instructions to implement the methods provided in various optional implementations of the above embodiments.

[0197] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of computer program instructions for enabling an electronic device (which can be a server or a terminal device, etc.) to execute the method according to the embodiment of the present disclosure.

[0198] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0199] It should be understood that the present disclosure is not limited to the detailed structures, drawings or implementations shown herein, but rather the present disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A task display method, characterized in that: include: Obtain multiple pending tasks of the target object, as well as the task content and task description information of each pending task; Scoring the task content of the task to be processed by using the large model to obtain a content importance score of the task to be processed; Adjusting the content importance score of the task to be processed by using the target network model to obtain a content score adjustment value of the task to be processed; Performing weighted sum processing on the content score adjustment value of the pending task and the importance impact value corresponding to each task description information to obtain the task importance score value of each pending task; Sort the multiple tasks to be processed by the task importance score values ​​to obtain the top N target tasks, where N is an integer greater than or equal to 1; The target task is placed in a prominent position for display.

2. The method according to claim 1, characterized in that: The method further comprises: Combining the task description information and summarizing the task content of the target task through the large model to obtain summary content of each target task; The step of placing the target task in a prominent position for display includes: While the target task is displayed in a prominent position, a summary of the target task is displayed in association therewith.

3. The method according to claim 1, characterized in that: The plurality of tasks to be processed include a first task; and the method further includes: Determine a content score adjustment value of the task content of the first task by using the large model and the target network model; Obtaining an actual importance value of the content of the task content of the first task; The parameters of the target network model are adjusted according to the content score adjustment value of the first task and the actual importance value of the content.

4. The method according to claim 1, characterized in that: The plurality of tasks to be processed include a second task; wherein, after performing weighted sum processing on the content score adjustment value of the tasks to be processed and the importance impact value corresponding to each task description information to obtain the task importance score value of each task to be processed, the method further includes: Determine the actual task importance value of the second task according to the processing order of the second task among the multiple tasks to be processed; Obtaining a task importance score value of the second task; The content score adjustment value and the weight corresponding to the task description information are adjusted according to the difference between the actual task importance value of the second task and the task importance score value.

5. The method according to claim 4, characterized in that: Determining the actual task importance value of the second task according to the processing order of the second task among the multiple tasks to be processed includes: Acquire a plurality of tasks that have been processed by the target object, wherein the plurality of tasks include the second task; An actual task importance value of the second task is determined according to a processing order of the second task among a plurality of tasks that have been processed by the target object.

6. The method according to claim 1, characterized in that: The method further comprises: Calculating the task importance score value once in a periodic manner; and / or, When the target object has processed M tasks, calculation of the task importance score is triggered once, where M<=N, and M is an integer greater than 0.

7. The method according to claim 1, characterized in that: The task description information includes: At least one of the task type, task creation time, task tag, task trigger object, task associated object, task difficulty, and task deadline.

8. A task display device, characterized in that: include: The task information acquisition module is used to acquire multiple pending tasks of the target object, as well as the task content and task description information of each pending task; A scoring module is used to score the task content of the task to be processed by using a large model to obtain a content importance score value of the task to be processed; A score adjustment module, used to adjust the content importance score of the task to be processed through a target network model to obtain a content score adjustment value of the task to be processed; A weighted summation module is used to perform weighted summation processing on the content score adjustment value of the task to be processed and the importance impact value corresponding to each task description information to obtain the task importance score value of each task to be processed; A sorting module is used to sort the multiple tasks to be processed according to the task importance score value to obtain the top N target tasks, where N is an integer greater than or equal to 1; A display module is used to place the target task in a prominent position for display.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer program instructions; the processor calls the computer program instructions stored in the memory to implement the task display method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the task display method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising computer program instructions, wherein the computer program instructions are stored in a computer-readable storage medium, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images