Task processing method and device, computer equipment, readable storage medium and program product
By extracting task features and assigning tasks to the corresponding queue, the problem of low efficiency in traditional task processing is solved and more efficient task processing is achieved.
Patent Information
- Application Number
- CN202411736941.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-29
- Publication Date
- 2025-03-14
AI Technical Summary
In the case of large amount of level tasks, the manual classification processing has the problem of low processing efficiency.
By responding to the user's task registration event, obtain task information, including task content and priority, extract task characteristics, determine task types, and allocate task content to the task queue according to task priority.
Improve task processing efficiency, ensure that tasks with higher priority are processed first, and thus improve the efficiency and accuracy of task processing.
Smart Images
Figure CN119621334A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of big data technology, and in particular to a task processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art
[0002] With the development of big data technology, task processing technology has emerged, which can classify and process tasks registered by users according to their characteristics, making it easier to summarize and process the work content of the tasks later.
[0003] In conventional technology, tasks registered by users are generally classified and processed manually. However, when the amount of hierarchical tasks is large, manual classification processing has the problem of low processing efficiency. Summary of the invention
[0004] Based on this, it is necessary to provide a task processing method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve task processing efficiency in response to the above technical problems.
[0005] In a first aspect, the present application provides a task processing method, comprising:
[0006] In response to task registration events respectively initiated by different users, obtaining task information respectively input by each of the users; the task information includes task content and task priority;
[0007] For each of the task information, based on task features obtained by extracting task features from the task content in the task information, determine the task type to which the task content belongs;
[0008] When the same task type corresponds to multiple task contents, each task content is allocated to the task queue corresponding to the task type in turn according to the task priority corresponding to each task content; the processing priority of the task content in the task queue is positively correlated with the task priority.
[0009] In one embodiment, the method further comprises:
[0010] Performing character splitting on the task content in the task information to obtain a plurality of task characters corresponding to the task content;
[0011] Performing abnormality judgment on each of the task characters, deleting abnormal task characters from each of the task characters, and obtaining a plurality of updated task characters;
[0012] Task features are extracted from the multiple update task characters to obtain task features corresponding to the task information.
[0013] In one embodiment, the determining the task type to which the task content belongs based on the task feature extracted from the task content in the task information includes:
[0014] Obtain task feature information corresponding to each candidate task type;
[0015] Based on task features obtained by extracting task features from task contents in the task information, determining a target task type matching the task features from each of the task feature information;
[0016] The target task type is determined to be a task type corresponding to the task content.
[0017] In one embodiment, the step of sequentially allocating each of the task contents to a task queue corresponding to the task type includes:
[0018] For each of the task contents, according to the content structure corresponding to the task content, a data structure for storing the task content is created;
[0019] Based on a preset data format, the task content stored in the data structure is converted into a format to obtain updated content;
[0020] The updated content is distributed to the task queue corresponding to the task type.
[0021] In one embodiment, the method further comprises:
[0022] Obtaining a summary format configured for each of the task contents;
[0023] The contents of each task are summarized according to the summary format to obtain summary information.
[0024] In one embodiment, the determining the task type to which the task content belongs based on the task feature extracted from the task content in the task information includes:
[0025] Call the task classification model through the large model interface;
[0026] The task content in the task information is input into the task classification model; the task classification model extracts task features from the task content in the task information to obtain task features, and determines the prediction type corresponding to the task information according to the task features;
[0027] Based on the predicted type, the task type to which the task content belongs is determined.
[0028] In a second aspect, the present application further provides a task processing device, comprising:
[0029] A task information acquisition module, for responding to task registration events respectively initiated by different users, and acquiring task information respectively input by each of the users; the task information includes task content and task priority;
[0030] A task type determination module, for each of the task information, based on task features obtained by extracting task features from the task content in the task information, determines the task type to which the task content belongs;
[0031] The task allocation module is used to allocate each task content to the task queue corresponding to the task type in turn according to the task priority corresponding to each task content when the same task type corresponds to multiple task contents; the processing priority of the task content in the task queue is positively correlated with the task priority.
[0032] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.
[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0034] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0035] The above-mentioned task processing method, apparatus, computer equipment, computer-readable storage medium and computer program product, in response to task registration events initiated by different users, obtain task information input by each user, and can determine the user's task registration status, wherein the task information includes task content and task priority. For each task information, based on the task feature obtained by extracting the task feature of the task content in the task information, the task type corresponding to each task content can be accurately determined. In the case where the same task type corresponds to multiple task contents, each task content is sequentially allocated to the task queue corresponding to the task type according to the task priority corresponding to each task content. Since the processing priority of the task content in the task queue is positively correlated with the task priority, in the subsequent task tracing or task summarization process, it can be ensured that the task with higher priority is processed first, thereby improving the task processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0037] Figure 1 An application environment diagram of a task processing method in an embodiment;
[0038] Figure 2 is a flowchart of a task processing method in one embodiment;
[0039] Figure 3 is a flowchart of a task processing method in another embodiment;
[0040] Figure 4 is a structural block diagram of a task processing device in one embodiment;
[0041] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION
[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0043] The task processing method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. Specifically, in the process of task processing by the server 104, it can respond to the task registration events initiated by different users based on the terminal 102, and obtain the task information input by each user; the task information includes task content and task priority; for each task information, the task type to which the task content belongs is determined based on the task features obtained by extracting the task features of the task content in the task information; when the same task type corresponds to multiple task contents, each task content is allocated in turn to the task queue corresponding to the task type according to the task priority corresponding to each task content; the processing priority of the task content in the task queue is positively correlated with the task priority.
[0044] In an exemplary embodiment, Figure 2 As shown, a task processing method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S202 to S206. Among them:
[0045] Step S202 , in response to task registration events respectively initiated by different users, obtain task information respectively input by each user.
[0046] Among them, a task registration event usually refers to the act of recording the relevant information of a task (such as task name, description, priority, deadline, etc.) into a task management system or log. Task information includes task content and task priority. It can be understood that task content is the task content that the user needs to register, such as the content of the user's work or the type of work. Task priority refers to the process of sorting and classifying tasks based on factors such as the importance, urgency, and resource requirements of the task. It helps technicians determine which tasks need to be handled first and which can be handled later, so as to manage time and resources more effectively.
[0047] Specifically, task registration helps ensure the transparency of tasks, enables team members to understand the current task allocation and progress, and can also track and monitor tasks to ensure that tasks are completed on time. After the user initiates a task registration event, the server can obtain the task information entered by each user and understand the user's task registration status. It can be understood that the operation of obtaining the task information entered by each user can be active or passive.
[0048] Step S204 , for each piece of task information, based on the task features obtained by extracting the task features from the task content in the task information, determine the task type to which the task content belongs.
[0049] Among them, task characteristics mainly describe the essential attributes and requirements of a task or project. Task type refers to the classification and induction of tasks. For example, task types can be divided into two categories: "data quality improvement" and "theme construction" for easy management and analysis.
[0050] Specifically, after obtaining the task information input by each user, the server can first distinguish the types of task contents in the task information, that is, it can extract the task features of the task content in the task information to obtain the task features, and then determine the task type to which the task content belongs based on the task features. In a specific embodiment, the server can obtain the task feature information corresponding to each candidate task type, and based on the task features obtained by extracting the task features of the task content in the task information, determine the target task type that matches the task features from each task feature information, and determine the target task type as the task type to which the task content belongs. In another specific embodiment, the server can also call the task classification model through the large model interface, and input the task content in the task information into the task classification model; the task classification model extracts the task features of the task content in the task information to obtain the task features, and determines the prediction type corresponding to the task information according to the task features, and determines the task type to which the task content belongs based on the prediction type.
[0051] Step S206 , when the same task type corresponds to multiple task contents, the task contents are sequentially allocated to the task queues corresponding to the task types according to the task priorities corresponding to the task contents.
[0052] Among them, the task queue is used to store and manage the task contents corresponding to a series of tasks to be processed. These tasks are usually executed asynchronously by different worker threads, processes or computer nodes. The processing priority of the task content in the task queue is positively correlated with the task priority. The processing priority refers to the priority level of the task content being processed. The higher the processing priority, the higher the priority of the task will be processed.
[0053] Specifically, after determining the task type to which each task content belongs, if a task type corresponds to multiple task contents, then each task content can be sequentially assigned to the task queue corresponding to the task type according to the task priority corresponding to each task content, so that the task content with a higher task priority can be seen or processed first in the subsequent task summary and tracing process. In a specific embodiment, the server can create a data structure for storing task content for each task content according to the content structure corresponding to the task content, perform format conversion on the task content stored in the data structure based on a preset data format, obtain updated content, and assign the updated content to the task queue corresponding to the task type.
[0054] Exemplarily, the server may allocate the contents of each task to the task queue corresponding to the task type in order of task priority from low to high, or may allocate the contents of each task to the task queue corresponding to the task type in order of task priority from high to low, or may allocate the contents of each task to the task queue corresponding to the task type in order of preset task priority rules, which is not limited in this embodiment.
[0055] The above-mentioned task processing method responds to task registration events initiated by different users, obtains task information input by each user, and can determine the user's task registration status, wherein the task information includes task content and task priority. For each task information, based on the task feature extracted from the task content in the task information, the task type corresponding to each task content can be accurately determined. In the case where the same task type corresponds to multiple task contents, each task content is sequentially allocated to the task queue corresponding to the task type according to the task priority corresponding to each task content. Since the processing priority of the task content in the task queue is positively correlated with the task priority, in the subsequent task tracing or task summarizing process, it can be ensured that the task with higher priority is processed first, thereby improving the task processing efficiency.
[0056] In an exemplary embodiment, the task processing method also includes: performing character splitting on the task content in the task information to obtain multiple task characters corresponding to the task content; performing abnormality judgment on each task character, deleting abnormal task characters from each task character, and obtaining multiple updated task characters; performing task feature extraction on the multiple updated task characters to obtain task features corresponding to the task information.
[0057] Characters are widely used in computers, and they are used to form various data such as text, images, and sounds. Task characters refer to multiple characters in the task content. Update task characters are task characters after preprocessing.
[0058] Specifically, in order to ensure the accuracy of the task features, the task content can be preprocessed first, and then the task features of the updated task characters obtained after the preprocessing can be extracted. That is, the server can first split the task content in the task information into characters to obtain multiple task characters corresponding to the task content, and perform abnormality judgment on each task character. If there is a situation where the task character is garbled or the value is too large or too small, it can be judged that the task character is an abnormal character, and the abnormal task character needs to be deleted from each task character to obtain multiple updated task characters, and finally the task features of the multiple updated task characters obtained are extracted to obtain the task features corresponding to the task information.
[0059] In this embodiment, the task content is preprocessed first, and then the task feature is extracted from the updated task characters obtained after the preprocessing, so as to ensure the accuracy of the task feature.
[0060] In an exemplary embodiment, based on task features obtained by extracting task features from task content in task information, determining the task type to which the task content belongs includes: obtaining task feature information corresponding to each candidate task type; based on task features obtained by extracting task features from task content in task information, determining a target task type that matches the task features from each task feature information; and determining the target task type as the task type to which the task content belongs.
[0061] The candidate task type refers to a task type that has not been specifically assigned and has the potential to be executed or owned. Task feature information refers to information that can represent the characteristics of the candidate task type. The target task type is the task type that serves as a specific target.
[0062] Specifically, the server can first obtain multiple candidate task types, and obtain the task feature information corresponding to each candidate task type, and match the task features corresponding to the task content with each task feature information. If there is task feature information that matches the task content, it means that the task information belongs to the candidate task type corresponding to the task feature information. Then, the candidate task type can be used as the target task type for matching the task features, that is, the target task type can be determined as the task type to which the task content belongs.
[0063] In this embodiment, the task characteristics based on the task information are matched with the task characteristic information corresponding to each candidate task type, and the task type to which the task content belongs is finally determined, which can ensure the accuracy of task type distinction and further ensure the accuracy of task processing.
[0064] In an exemplary embodiment, each task content is sequentially assigned to a task queue corresponding to the task type, including: for each task content, according to the content structure corresponding to the task content, creating a data structure for storing the task content; based on a preset data format, converting the task content stored in the data structure to obtain updated content; and assigning the updated content to the task queue corresponding to the task type.
[0065] Among them, the data structure is used to store the task content, for example, it can be an array, a dictionary, an object, etc. The content structure refers to the content structure corresponding to the task content, corresponding to the data structure, and the server can select the data structure corresponding to the task content according to the content structure. The data format refers to the format of the final output data, which is used to standardize the output data. In this embodiment, the data format is pre-established, for example, it can be a string in JSON format. The updated content is the content obtained by formatting the task content stored in the data structure.
[0066] Specifically, for each task content, the server can first determine the content structure corresponding to the task content, and create a data structure for storing the task content based on the content structure. After that, the server can obtain the preset data format, clarify the target format that the task content ultimately needs to be converted into, and then based on the preset data format, convert the format of the task content stored in the data structure to obtain updated content, and assign the updated content to the task queue corresponding to the task type.
[0067] In a specific embodiment, the Python standard library can be called to perform format conversion. Specifically, since the Python standard library includes a json module, it can easily convert Python objects into strings in JSON format. Therefore, after the server creates a data structure for storing the task content, it can call the json module to convert the task content stored in the data structure Python object into a string in JSON format.
[0068] In this embodiment, the task content may be formatted according to a preset data format, so that the format of the task content can be unified, which facilitates subsequent processing of the task content.
[0069] In an exemplary embodiment, the task processing method further includes: obtaining a summary format configured for each task content; and summarizing each task content according to the summary format to obtain summary information.
[0070] Summarization refers to the process of organizing, summarizing and summarizing multiple related information, data or resources according to certain rules and methods, and the summary format can be represented by the above rules and methods. Summarized information refers to the summary information obtained after summarizing the contents of each task.
[0071] Specifically, the server may first obtain a summary format configured for each task content, and summarize each task content according to the summary format to obtain the summarized summary information, so that subsequent users can obtain required information more quickly and conveniently.
[0072] In an exemplary embodiment, based on task features obtained by extracting task features from task content in task information, determining the task type to which the task content belongs includes: calling a task classification model through a large model interface; inputting the task content in the task information into the task classification model; and determining the task type to which the task content belongs based on the prediction type.
[0073] The large model interface refers to an interface for applying large-scale pre-trained models (often referred to as large models) to various NLP (Natural Language Processing) or other machine learning tasks. The task classification model extracts task features from the task content in the task information to obtain task features, and determines the prediction type corresponding to the task information based on the task features. The prediction type is obtained by the task classification model predicting the task type of the task information based on the task features.
[0074] Specifically, the server can also call the task classification model through the large model interface, and the task classification model extracts the task features from the task content in the task information to obtain the task features, and determines the prediction type corresponding to the task information according to the task features. After the server obtains the prediction type, it can determine the task type to which the task content belongs according to the prediction type. It can be understood that if there are multiple prediction types, the confidence corresponding to each prediction type can be obtained, and the prediction type with a higher confidence is used as the task type to which the task content belongs.
[0075] Exemplarily, the server can also combine the prediction type output by the task classification model and the target task type matched by the server based on the task features to jointly confirm the task type to which the final task content belongs. For example, the server can determine the confidence corresponding to the prediction type and the matching degree corresponding to the target task type, and based on the comparison relationship between the confidence and the matching degree, the task type with higher accuracy after the comparison is used as the task type to which the final task content belongs.
[0076] In this embodiment, the server can call the task classification model through the large model interface to determine the task type to which the task content belongs, which can improve the task processing efficiency while ensuring the accuracy of task processing.
[0077] In a specific embodiment, an intelligent task management and classification system based on a large model interface in a specific application scenario is provided, which aims to automatically collect, classify and summarize the work tasks of team members. The system includes the following key modules:
[0078] 1. Task registration module:
[0079] Function: Provides a user-friendly interface for team members to check in tasks while handling their daily work.
[0080] Implementation: Users enter task information through the system interface, including task type, description, priority, etc.
[0081] 2. Data collection module:
[0082] Function: Automatically collect and store task information.
[0083] Implementation: The system stores the registered task information in the central database to ensure the integrity and security of the information.
[0084] 3. Automatic classification module:
[0085] Function: According to preset rules, task information is automatically classified into two categories: "data quality improvement" and "theme construction".
[0086] Implementation: The system runs the classification algorithm regularly every week to classify task information based on its characteristics and content.
[0087] 4. Intelligent summary module:
[0088] Function: Call the large model interface to conduct in-depth analysis and intelligent classification of task information.
[0089] accomplish:
[0090] Input: The system takes the task content (all personnel names and work content) as input and passes it to the large model interface.
[0091] Processing: Large model interfaces apply advanced natural language processing techniques for recognition and classification tasks.
[0092] Output: The interface returns a string in JSON format, containing data summarized by job category.
[0093] Specifically, the functions of the above modules are as follows:
[0094] Task registration module:
[0095] Definition: A functional module in the system that provides a user interface for team members to input and record their daily work tasks.
[0096] Role: Ensure that all task information is accurately recorded for subsequent data collection and analysis.
[0097] 2. Data collection module:
[0098] Definition: A functional module in the system that is responsible for automatically collecting and storing task information.
[0099] Function: Store task information in a central database to ensure the integrity and accessibility of the information.
[0100] 3. Automatic classification module:
[0101] Definition: A functional module in the system that automatically classifies tasks according to preset rules.
[0102] Function: Divide the tasks into two categories: "data quality improvement" and "theme construction" to facilitate management and analysis.
[0103] 4. Intelligent summary module:
[0104] Definition: A functional module in the system that calls the large model interface to perform in-depth analysis and intelligent classification of tasks.
[0105] Function: Generates a JSON string containing a summary of all work categories to improve the accuracy and efficiency of data aggregation.
[0106] 5. Large model interface:
[0107] Definition: An interface developed in-house or integrated that uses advanced natural language processing techniques for task analysis and classification.
[0108] Function: Receive personnel name and job content as input, and output data summarized by job category.
[0109] 6. Natural Language Processing (NLP):
[0110] Definition: An artificial intelligence technology designed to enable computers to understand, interpret, and generate human language.
[0111] Function: Used to analyze and classify task content in this system.
[0112] 7.JSON format:
[0113] Definition: A lightweight data interchange format that is easy for humans to read and write, and easy for machines to parse and generate.
[0114] Function: Used to represent the classified and summarized data output by the system to facilitate data transmission and processing.
[0115] 8. Improved data quality:
[0116] Definition: A class of tasks aimed at improving the accuracy, completeness, and consistency of data.
[0117] Function: Ensure the reliability of enterprise data and provide high-quality data support for decision-making.
[0118] 9. Theme construction:
[0119] Definition: A type of assignment that involves the development and refinement of a specific topic or project.
[0120] Function: Support the company's strategic goals and project advancement.
[0121] 10. Central Database:
[0122] Definition: A database used to store all task data in the system.
[0123] Function: Provide centralized storage and management of data to ensure data security and accessibility.
[0124] 11. Preset rules:
[0125] Definition: The set of rules used to guide task classification in the system.
[0126] Function: Ensure the consistency and accuracy of task classification and support the system's automated classification function.
[0127] 12. In-depth analysis:
[0128] Definition: A detailed and comprehensive analysis of the mission content using a large model interface.
[0129] Function: Improve the accuracy of task classification and identify the characteristics and patterns of tasks.
[0130] In a specific embodiment, Figure 3 As shown, a task processing method is also provided, including:
[0131] Step S301, in response to task registration events respectively initiated by different users, obtaining task information respectively input by each user;
[0132] Among them, the task information includes task content and task priority;
[0133] Step S302, splitting the task content in the task information into characters to obtain a plurality of task characters corresponding to the task content;
[0134] Step S303, performing abnormality determination on each task character, deleting abnormal task characters from each task character, and obtaining a plurality of updated task characters;
[0135] Step S304, extracting task features from multiple update task characters to obtain task features corresponding to the task information;
[0136] Step S305, for each task information, calling the task classification model through the large model interface;
[0137] Step S306, inputting the task content in the task information into the task classification model, and determining the task type to which the task content belongs based on the predicted type output by the task classification model;
[0138] Among them, the task classification model extracts task features from the task content in the task information to obtain task features, and determines the prediction type corresponding to the task information based on the task features;
[0139] Step S307, for each task information, obtaining task feature information corresponding to each candidate task type;
[0140] Step S308, based on the task characteristics, determine the target task type that matches the task characteristics from each task characteristic information, and determine the target task type as the task type to which the task content belongs;
[0141] Step S309, when the same task type corresponds to multiple task contents, according to the task priorities corresponding to the task contents, for each task content, according to the content structure corresponding to the task content, a data structure for storing the task content is created;
[0142] Step S310, based on a preset data format, converting the task content stored in the data structure to obtain updated content, and assigning the updated content to a task queue corresponding to the task type;
[0143] Among them, the processing priority of the task content in the task queue is positively correlated with the task priority;
[0144] Step S311, obtaining a summary format configured for each task content, summarizing each task content according to the summary format, and obtaining summary information.
[0145] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0146] Based on the same inventive concept, the embodiment of the present application also provides a task processing device for implementing the task processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more task processing device embodiments provided below can refer to the limitations on the task processing method above, and will not be repeated here.
[0147] In an exemplary embodiment, Figure 4 As shown, a task processing device 400 is provided, comprising: a task information acquisition module 402, a task type determination module 404 and a task allocation module 406, wherein:
[0148] The task information acquisition module 402 is used to respond to the task registration events initiated by different users and acquire the task information input by each user; the task information includes task content and task priority;
[0149] The task type determination module 404 is used to determine the task type to which the task content belongs based on the task features obtained by extracting the task features from the task content in the task information for each task information;
[0150] The task allocation module 406 is used to allocate each task content to the task queue corresponding to the task type in turn according to the task priority corresponding to each task content when the same task type corresponds to multiple task contents; the processing priority of the task content in the task queue is positively correlated with the task priority.
[0151] In an exemplary embodiment, the task processing device 400 further includes a task feature extraction module, which is specifically used to:
[0152] Performing character splitting on the task content in the task information to obtain multiple task characters corresponding to the task content;
[0153] Perform abnormality judgment on each task character, delete the abnormal task characters from each task character, and obtain multiple updated task characters;
[0154] Task features are extracted from multiple update task characters to obtain task features corresponding to the task information.
[0155] In an exemplary embodiment, the task type determination module 404 is used to:
[0156] Obtain task feature information corresponding to each candidate task type;
[0157] Based on the task features obtained by extracting the task features from the task content in the task information, determine the target task type matching the task features from each task feature information;
[0158] Determine the target task type as the task type to which the task content belongs.
[0159] In an exemplary embodiment, the task allocation module 406 is specifically configured to:
[0160] For each task content, according to the content structure corresponding to the task content, a data structure for storing the task content is created;
[0161] Based on the preset data format, the task content stored in the data structure is converted into a format to obtain updated content;
[0162] Assign the updated content to the task queue corresponding to the task type.
[0163] In an exemplary embodiment, the task processing device 400 further includes an information aggregation module, which is specifically used to:
[0164] Get the summary format configured for each task content;
[0165] The contents of each task are summarized according to the summary format to obtain summary information.
[0166] In an exemplary embodiment, the task type determination module 404 is further configured to:
[0167] Call the task classification model through the large model interface;
[0168] The task content in the task information is input into the task classification model; the task classification model extracts task features from the task content in the task information to obtain task features, and determines the prediction type corresponding to the task information according to the task features;
[0169] Based on the prediction type, determine the task type to which the task content belongs.
[0170] Each module in the above task processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0171] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a task processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
[0172] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0173] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above method when executing the computer program.
[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0175] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.
[0176] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0177] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.
[0178] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0179] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A task processing method, characterized in that: The method comprises: In response to task registration events respectively initiated by different users, obtaining task information respectively input by each of the users; the task information includes task content and task priority; For each of the task information, based on task features obtained by extracting task features from the task content in the task information, determine the task type to which the task content belongs; When the same task type corresponds to multiple task contents, each task content is allocated to the task queue corresponding to the task type in turn according to the task priority corresponding to each task content; the processing priority of the task content in the task queue is positively correlated with the task priority.
2. The method according to claim 1, characterized in that The method further comprises: Performing character splitting on the task content in the task information to obtain a plurality of task characters corresponding to the task content; Performing abnormality judgment on each of the task characters, deleting abnormal task characters from each of the task characters, and obtaining a plurality of updated task characters; Task features are extracted from the multiple update task characters to obtain task features corresponding to the task information.
3. The method according to claim 1, characterized in that The step of determining the task type to which the task content belongs based on the task feature extracted from the task content in the task information includes: Obtain task feature information corresponding to each candidate task type; Based on task features obtained by extracting task features from task contents in the task information, determining a target task type matching the task features from each of the task feature information; The target task type is determined to be a task type corresponding to the task content.
4. The method according to claim 1, characterized in that: The step of sequentially allocating each of the task contents to the task queue corresponding to the task type includes: For each of the task contents, according to the content structure corresponding to the task content, a data structure for storing the task content is created; Based on a preset data format, the task content stored in the data structure is converted into a format to obtain updated content; The updated content is distributed to the task queue corresponding to the task type.
5. The method according to claim 1, characterized in that The method further comprises: Obtaining a summary format configured for each of the task contents; The contents of each task are summarized according to the summary format to obtain summary information.
6. The method according to any one of claims 1 to 5, characterized in that The step of determining the task type to which the task content belongs based on the task feature extracted from the task content in the task information includes: Call the task classification model through the large model interface; The task content in the task information is input into the task classification model; the task classification model extracts task features from the task content in the task information to obtain task features, and determines the prediction type corresponding to the task information according to the task features; Based on the predicted type, the task type to which the task content belongs is determined.
7. A task processing device, characterized in that: The device comprises: A task information acquisition module, for responding to task registration events respectively initiated by different users, and acquiring task information respectively input by each of the users; the task information includes task content and task priority; A task type determination module, for each of the task information, based on task features obtained by extracting task features from the task content in the task information, determines the task type to which the task content belongs; The task allocation module is used to allocate each task content to the task queue corresponding to the task type in turn according to the task priority corresponding to each task content when the same task type corresponds to multiple task contents; the processing priority of the task content in the task queue is positively correlated with the task priority.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.