Timing task processing method and device, equipment, medium and program product

Abstract

The invention provides a timed task processing method and device, equipment, a medium and a program product, relates to the technical field of artificial intelligence, and can be applied to the field of financial science and technology or other fields. The method comprises the steps of inputting first text data to a target large model, wherein the first text data comprises a task plan of a first timed task; the first text data is processed through a target large model, a first task configuration instruction used for submitting a first timed task to the timed scheduling framework is generated, and the target large model is obtained by conducting fine adjustment on a pre-trained large language model through a task configuration instruction data set of the timed scheduling framework; the task configuration instruction is a program language instruction matched with the timed scheduling framework; and submitting a first task configuration instruction to the timed scheduling framework to enable the timed scheduling framework to configure the first timed task.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence and can be used in the field of financial technology or other fields. More specifically, it relates to a method, apparatus, device, medium, and program product for processing timed tasks. Background Technology

[0002] Online services such as banking frequently utilize scheduled tasks. Examples include triggering a batch billing job at midnight on the 1st of each month to generate the previous month's bills, or scanning server storage space or memory usage every ten minutes. Adding or modifying scheduled tasks often requires specialized personnel. For instance, scheduled tasks in mainframe systems typically require defining timers and executing them using specialized system automation tools, demanding a high level of expertise and often having unfriendly interfaces. Conversely, using scheduling frameworks on open platforms often necessitates proficiency in the relevant programming language to configure and manage scheduled tasks through code. Summary of the Invention

[0003] In view of the above problems, the present invention provides a method, apparatus, device, medium and program product for processing timed tasks that can reduce the professional requirements of users.

[0004] A first aspect of this invention provides a method for processing a scheduled task. The method includes: inputting first text data into a target large model, the first text data including a task plan for a first scheduled task; processing the first text data using the target large model to generate a first task configuration instruction for submitting the first scheduled task to a scheduling framework, wherein the target large model is obtained by fine-tuning a pre-trained large language model using the task configuration instruction dataset of the scheduling framework; and submitting the first task configuration instruction to the scheduling framework to enable the scheduling framework to configure the first scheduled task, wherein the task configuration instruction is a programming language instruction adapted to the scheduling framework.

[0005] According to an embodiment of the present invention, the step of processing the first text data using the target large model to generate a first task configuration instruction for submitting the first scheduled task to the timed scheduling framework includes: using the target large model to retrieve a task data knowledge base based on the task plan of the first scheduled task, and generating the first task configuration instruction by combining the retrieval results through retrieval enhancement.

[0006] According to an embodiment of the present invention, inputting the first text data into the target large model includes: receiving multimodal input data, the multimodal input data including at least one of speech, text or image; identifying the multimodal input data to obtain the first text data; and submitting the first text data to the target large model.

[0007] According to an embodiment of the present invention, inputting the first text data into the target large model includes: forming a task plan for the first timed task through one or more rounds of user interaction with the target large model.

[0008] According to an embodiment of the present invention, the method further includes: inputting second text data into the target large model, the second text data including a temporary change plan for the first scheduled task; processing the second text data using the target large model to generate a second task configuration instruction for temporarily changing the task plan of the first scheduled task in the timed scheduling framework; and sending the second task configuration instruction to the timed scheduling framework so that the timed scheduling framework adjusts the temporary scheduling configuration of the first scheduled task according to the temporary change plan.

[0009] According to an embodiment of the present invention, after submitting the first task configuration instruction to the timed scheduling framework, the method further includes: in response to the fulfillment of the triggering condition of the first timed task, the timed scheduling framework triggers the host system to execute the first timed task through interaction with the host system.

[0010] A second aspect of this invention provides a processing apparatus for timed tasks. The apparatus includes a user interaction module and a large model processing module.

[0011] The user interaction module is used to input first text data into the target large model, the first text data including the task plan of the first timed task.

[0012] The large model processing module is used to process the first text data using the target large model, generate a first task configuration instruction for submitting the first scheduled task to the timed scheduling framework, and submit the first task configuration instruction to the timed scheduling framework so that the timed scheduling framework configures the first scheduled task; wherein, the target large model is obtained by fine-tuning using the task configuration instruction dataset of the timed scheduling framework.

[0013] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0014] A fourth aspect of the present invention also provides a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions, when executed by a processor, implement the steps of the above-described method.

[0015] A fifth aspect of the present invention also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method. Attached Figure Description

[0016] The above-described features, other objects, and advantages of the present invention will become clearer from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0017] Figure 1 The illustration schematically depicts application scenarios of a timed task processing method, apparatus, device, medium, and program product according to embodiments of the present invention.

[0018] Figure 2 A flowchart illustrating a method for processing a timed task according to an embodiment of the present invention is shown schematically;

[0019] Figure 3 A flowchart illustrating a method for processing a timed task according to another embodiment of the present invention is shown schematically;

[0020] Figure 4 A flowchart illustrating a method for processing a timed task according to yet another embodiment of the present invention is shown.

[0021] Figure 5 A block diagram of a timed task processing apparatus according to an embodiment of the present invention is shown schematically;

[0022] Figure 6 This illustration schematically shows an example of a system architecture for a timed task processing method and apparatus applying embodiments of the present invention;

[0023] Figure 7 Schematic illustration Figure 6 The example system architecture includes a structural diagram of the UI page-side modules;

[0024] Figure 8 Schematic illustration Figure 6 The example system architecture includes a diagram of the query and change modules.

[0025] Figure 9 Schematic illustration Figure 6 The example system architecture includes a structural diagram of the task scanning module.

[0026] Figure 10 Schematic illustration Figure 6 The example system architecture includes a structural diagram of the task execution module.

[0027] Figure 11 Schematic illustration Figure 6 The example system architecture includes a diagram of the compute and update modules.

[0028] Figure 12 Schematic illustration Figure 6 Example system architecture processing flowchart; and

[0029] Figure 13 A block diagram schematically illustrates an electronic device suitable for implementing a processing method for a timed task according to an embodiment of the present invention. Detailed Implementation

[0030] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0031] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0032] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0033] This invention provides a method, apparatus, device, medium, and program product for processing scheduled tasks. Users can submit task plans for scheduled tasks via text methods such as natural language, and configure the processing flow of scheduled tasks within a scheduling framework using a large model. This lowers the barrier to entry for configuring scheduled tasks within the scheduling framework and facilitates user operation. In some embodiments, the scheduling framework can trigger the host system to execute scheduled tasks through interaction with the host system. This leverages both the ease of task configuration and scheduling of the scheduling framework and the efficient task processing performance of the host system, thereby improving the processing efficiency of scheduled tasks.

[0034] It should be noted that the timed task processing methods, apparatus, devices, media, and program products determined in the embodiments of the present invention can be used in the field of financial technology, or in any field other than financial technology. The present invention does not limit the application field.

[0035] Figure 1The illustration schematically depicts an application scenario of a timed task processing method, apparatus, device, medium, and program product according to embodiments of the present invention.

[0036] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first terminal device 11, a second terminal device 12, a third terminal device 13, a network 14, and a service system 15. The network 14 serves as a medium for providing a communication link between the first terminal device 11, the second terminal device 12, the third terminal device 13, and the service system 15. The network 14 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0037] Users can use the first terminal device 11, the second terminal device 12, and the third terminal device 13 to interact with the service system 15 via the network 14 to receive or send messages, etc. Various communication client applications, such as browser applications and large-scale client applications, can be installed on the first terminal device 11, the second terminal device 12, and the third terminal device 13. The first terminal device 11, the second terminal device 12, and the third terminal device 13 can be various electronic devices with displays that support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers, etc.

[0038] Service system 15 may include one or more servers that can provide various services. In some embodiments, service system 15 may deploy a large model and a scheduling framework. The large model may be obtained by fine-tuning a pre-trained large language model using a task configuration instruction dataset from the scheduling framework; it is also referred to herein as the target large model. In other embodiments, service system 15 may also include a host system that can communicate with the scheduling framework. Service system 15 can receive user requests sent by users using client applications in first terminal device 11, second terminal device 12, and third terminal device 13, perform business processing based on the user requests, and feed back the processing results to first terminal device 11, second terminal device 12, and third terminal device 13.

[0039] It should be noted that the timed task processing method provided in the embodiments of the present invention can generally be executed by the service system 15. Correspondingly, the timed task processing apparatus, device, medium, and program product provided in the embodiments of the present invention can generally be located in the service system 15. The timed task processing method provided in the embodiments of the present invention can also be executed by a server or server cluster that is different from the service system 15 and capable of communicating with the first terminal device 11, the second terminal device 12, the third terminal device 13, and / or the service system 15. Correspondingly, the timed task processing apparatus, device, medium, and program product provided in the embodiments of the present invention can also be located in a server or server cluster that is different from the service system 15 and capable of communicating with the first terminal device 11, the second terminal device 12, the third terminal device 13, and / or the service system 15.

[0040] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0041] The following will be based on Figure 1 The described scene, through Figures 2-4 A method for processing timed tasks according to embodiments of the present invention will be described in detail.

[0042] Figure 2 A flowchart illustrating a method for processing timed tasks according to an embodiment of the present invention is shown.

[0043] like Figure 2 As shown, the method for processing timed tasks according to this embodiment includes operations S201 to S203.

[0044] First, in operation S201, input the first text data into the target large model. The first text data includes the task plan of the first scheduled task. The task plan of the first scheduled task can be text data represented by natural language (e.g., "Run the bill batch job at midnight on the first of each month to generate the bills for Company A for the previous month"), or it can be structured text data, such as represented in tabular form, where the fields are semantic text fields.

[0045] Then, in operation S202, the first text data is processed using the target large model to generate the first task configuration instruction for submitting the first timed task to the timed scheduling framework. The target large model is obtained by fine-tuning the pre-trained large language model using the task configuration instruction dataset of the timed scheduling framework.

[0046] The timed scheduling framework is used to trigger scheduled tasks according to execution time rules. It can manage the entire lifecycle of tasks, ensuring reliable and efficient execution. The task configuration instructions are programming language instructions adapted to the timed scheduling framework, which can include multi-dimensional information such as task details and trigger conditions.

[0047] In one embodiment, operation S202 can utilize the target big model to retrieve task data knowledge base based on the task plan of the first scheduled task, and combine the retrieval results to generate the first task configuration instruction through retrieval enhancement. For example, for the scheduled task "Run a batch billing job at midnight on the first of each month to generate the previous month's bills for Company A", the target big model can retrieve detailed information about Company A (such as enterprise identifier), business scope (such as business identifier), job library address, etc. from the database, and then combine this information to generate the configuration instruction. Based on retrieval enhancement, the detailed information required to generate the task configuration instruction for the scheduled task is supplemented by retrieving the knowledge base, thereby improving the quality of the generated task configuration instruction.

[0048] Next, in operation S203, a first task configuration instruction is submitted to the timed scheduling framework so that the timed scheduling framework can configure the first timed task.

[0049] The configuration of the first scheduled task within the scheduling framework can include, but is not limited to: setting a scheduled task identifier, job library address, and job name; defining execution rule components, execution logic components, and scheduling containers. After the first scheduled task is configured, the scheduling framework can schedule corresponding computing resources to run the first scheduled task when its triggering conditions are met. In one embodiment, the scheduling framework can be deployed on an open platform and can communicate with a mainframe system to trigger the mainframe system to execute the scheduled task. For example, in response to the fulfillment of the triggering conditions for the first scheduled task, the scheduling framework can trigger the mainframe system to execute the first scheduled task through interaction with the mainframe system.

[0050] The embodiments of the present invention can use a large model to convert task plan text data into programming language instructions for configuring a scheduled task framework, saving users the process of writing program code according to the task plan, lowering the threshold for configuring scheduled tasks in the scheduled scheduling framework, and realizing the rapid configuration and automated processing of scheduled tasks.

[0051] In one embodiment, the specific process of inputting the first text data into the target large model in the above operation S201 can be: receiving multimodal input data, which includes at least one of voice, text, or image; recognizing the multimodal input data to obtain the first text data; and submitting the first text data to the target large model. For example, a UI page can be designed to provide user interaction. This UI page can be embedded in the large model client or intelligent agent. Through this UI page, users can input in multiple ways such as voice, text, or images, and then the user input is recognized to form the first text data. For example, users can input task plans by voice, or users can upload a task list or image containing multiple scheduled tasks, and then the UI page can automatically recognize the task plan of the scheduled tasks from the user input for user convenience.

[0052] In some embodiments, when inputting the first text data to the target large model in operation S201, the task plan for the first scheduled task can be improved through one or more rounds of user interaction with the large model. For example, after the user provides the initial task plan, the large model can check the initial task plan based on the various dimensions of information required to configure the scheduled task framework. If any missing information is found, the model can request the user to supplement the missing information through dialogue. This makes the way the user submits the task plan for the first scheduled task more flexible and further facilitates user use.

[0053] Figure 3 A flowchart illustrating a method for processing a timed task according to another embodiment of the present invention is shown.

[0054] like Figure 3 As shown, in addition to operations S201 to S203, the timed task processing method according to this embodiment may also include operations S304 to S306.

[0055] Operations S201 to S203 are consistent with the previous description.

[0056] Next, in operation S304, the second text data is input into the target large model. The second text data includes a temporary change plan for the first scheduled task. For example, the scheduled task "Run a batch job to generate Company A's invoices for the previous month at 1 AM on the first of each month" is temporarily postponed by one day.

[0057] Similar to operation S201, the input of the second text data in operation S304 can also be obtained by receiving multimodal input through the UI page and then recognizing that multimodal input. Furthermore, the temporary change plan for the first scheduled task can be supplemented and improved through multiple rounds of user interaction with the large model.

[0058] In operation S305, the second text data is processed using the target large model to generate a second task configuration instruction for temporarily modifying the task plan of the first scheduled task in the timed scheduling framework. This second task configuration instruction is used to adjust the upcoming single execution of the first scheduled task (such as adjusting the execution time or the content of the task).

[0059] In operation S306, a second task configuration command is sent to the scheduling framework to adjust the temporary scheduling configuration of the first scheduled task according to the temporary change plan. After the scheduling framework performs the temporary scheduling configuration for the first scheduled task, it will execute the upcoming single scheduling according to the changed plan, and maintain the original plan for the first scheduled task in subsequent scheduling after this single scheduling. During task execution, the scheduling framework can trigger the execution of the host system by interacting with the host system.

[0060] According to an embodiment of the present invention, once a scheduled task is configured, any temporary changes can be quickly implemented through interaction with a large model, and such temporary changes do not affect the subsequent execution plan of the scheduled task, thus providing high flexibility.

[0061] Figure 4 A flowchart illustrating a method for processing a timed task according to another embodiment of the present invention is shown.

[0062] like Figure 4 As shown, the timed task processing method according to this embodiment may include operations S401 to S405.

[0063] When operating the S401, a large model is trained to extract task plans from batch tasks and to learn the task configuration instructions of the timed scheduling framework.

[0064] When operating S402, it receives scheduled tasks assigned by the user via voice.

[0065] When operating S403, the large model automatically generates task configuration instructions for the timed scheduling framework based on the user-assigned timed tasks, configures the timed scheduling framework, and generates timed tasks.

[0066] When operating S404, if the triggering conditions of the scheduled task are met, the interactive command interface of the job login subsystem is invoked to send the task execution instruction to the host system. The job login subsystem manages the scheduling, execution, input / output information, and other aspects of all jobs on the host system.

[0067] When operating S405, the host system executes scheduled tasks.

[0068] This invention utilizes large model technology and can be combined with enhanced retrieval and multi-modal input data recognition to improve the user interaction convenience of scheduled tasks. The task configuration, task status, and other information involved can all be visualized and customized through a more intuitive and user-friendly interface.

[0069] Some embodiments of this invention are also very convenient for scenarios that require temporary modification of execution time. After the temporary task is completed, it can automatically revert to the normal scheduled time. Temporary changes to scheduled tasks are implemented more flexibly, take effect in real time, do not require restarting the scheduling system, are not limited to a fixed change window, and do not affect the services of the scheduling framework and the host system.

[0070] In some embodiments of the present invention, the configuration, modification and scheduling of scheduled tasks are separated from the host system and executed by the scheduled task framework, thereby making the configuration and maintenance of scheduled tasks on the host system simpler and requiring less host skills.

[0071] Figure 5 A block diagram of a timed task processing apparatus 200 according to an embodiment of the present invention is shown schematically.

[0072] like Figure 5 As shown, the processing device 200 for the timed task may include a user interaction module 21 and a large model processing module 22.

[0073] User interaction module 21 is used to input first text data into the target large model. The first text data includes the task plan of the first timed task.

[0074] The large model processing module 22 is equipped with a target large model, which is used to process the first text data, generate a first task configuration instruction for submitting the first timed task to the timed scheduling framework, and submit the first task configuration instruction to the timed scheduling framework so that the timed scheduling framework configures the first timed task. The target large model is fine-tuned using the task configuration instruction dataset of the timed scheduling framework.

[0075] In some embodiments, the user interaction module 21 is further configured to input second text data into the target large model, the second text data including a temporary change plan for the first scheduled task. Correspondingly, the large model processing module 21 is further configured to process the second text data using the target large model, generate a second task configuration instruction for temporarily changing the task plan of the first scheduled task in the timed scheduling framework; and send the second task configuration instruction to the timed scheduling framework so that the timed scheduling framework adjusts the temporary scheduling configuration of the first scheduled task according to the temporary change plan.

[0076] The device 200 can perform reference Figures 2-4The methods for handling scheduled tasks introduced above can be found in the previous text and will not be repeated here.

[0077] According to embodiments of the present invention, any plurality of modules in the user interaction module 21 and the large model processing module 22 can be merged into one module, or any one of the modules can be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules can be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of the present invention, at least one of the user interaction module 21 and the large model processing module 22 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any appropriate combination of any of these three implementation methods. Alternatively, at least one of the user interaction module 21 and the large model processing module 22 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0078] Figure 6 The illustration schematically shows an example of a system architecture for a timed task processing method and apparatus that applies embodiments of the present invention.

[0079] like Figure 6 The system architecture shown includes a UI page (001), a large model (013), batch tasks (014), a query and modification module (002), a database (003), a task scanning module (004), a task execution module (005), a calculation and update module (006), an alarm module (007), a log module (008), an interactive command interface (009), a job login subsystem (010), a dataset (011), a host database (012), and a host system (390).

[0080] According to this embodiment, the user interaction module 21 may include a UI page 001 and a query and modification module 002. The large model 013 constitutes the core of the large model processing module 22.

[0081] UI page 001 can communicate with the large model 013. For example, the client of the large model 013 can be embedded into the UI page 001. The UI page 001 can receive the user's voice 000 and obtain the task plan for the scheduled task by recognizing the voice 000. The large model 013 can be obtained by fine-tuning and training using batch tasks 014.

[0082] The query and change module 002 can provide users with information on the configuration, changes, and execution status of scheduled tasks.

[0083] UI page 001 is also connected to query and change module 002, providing a user-facing input and operation interface, and also displaying processing results.

[0084] According to this embodiment, the timed scheduling framework may include a database 003, a task scanning module 004, a task execution module 005, a calculation and update module 006, an alarm module 007, a log module 008, and an interactive command interface 009. Specifically, the database 003 stores the configuration information of the scheduled tasks. The task scanning module 004, task execution module 005, and calculation and update module 006 are responsible for the timed scheduling and execution of tasks. The alarm module 007 and log module 008 are responsible for monitoring the operation of the timed scheduling framework. The interactive command interface 009 is responsible for interacting with the host system 390.

[0085] According to this embodiment, the host system 390 executes the scheduled task based on the task data pushed by the timed scheduling framework through the interactive command interface 009.

[0086] Figure 7 and Figure 8 The diagrams illustrate the structure of UI page 001 and the query and change module 002, respectively.

[0087] like Figure 7 As shown, the UI page 001 includes an input module 101, a communication module 102, and a display module 103.

[0088] The input module 101 is used to receive user input and may include an interface for interacting with the large model 003, such as a text input interface or a voice input interface. The input module 101 may also include, but is not limited to, input items such as next execution time and task schedule, and the input items may also include operation buttons such as pause, resume, save, refresh, and invalidate.

[0089] The communication module 102 enables network connection and data transmission between the UI page 001 and the query and change module 002.

[0090] The display module 103 displays the results returned by the query and change module 002 to the user on the UI page 001.

[0091] The query and change module 002 can be a program that runs normally on the platform server, used to retrieve relevant data from the database 003, and to receive change requests and data from the UI page 001 and update them in the database.

[0092] The query and change module 002 can encapsulate query and change functions and provide external service interfaces with standard format input and output.

[0093] like Figure 8 As shown, the query and change module 002 may include a query unit 201, a communication unit 202, and an update storage unit 203.

[0094] The query unit 201 provides task plan information, execution time information, and status information to the UI page 001 by accessing database tables. In some embodiments, the large model 013 can also communicate with the database 003, for example, it can retrieve task plans from the database 003 based on user input, and generate task configuration instructions through retrieval enhancement.

[0095] The communication unit 202 is used to respond to user requests and establish a connection with the database 003; the update storage unit 203 writes the change requests and data transmitted from the UI page 001 into the database 003.

[0096] Figures 9-11 The structural diagrams of the task scanning module 004, the task execution module 005, and the calculation and update module 006 are shown respectively.

[0097] like Figure 9 As shown, the task scanning module 004 includes a communication unit 401 and a scanning unit 402. The communication unit 401 is responsible for establishing a connection with the database 003 and for establishing a network connection and data transmission with the task execution module 005, distributing execution tasks to the task execution module 005. The scanning unit 402 is responsible for scanning the database 003 for tasks that have reached their designated time and are in a normal state.

[0098] like Figure 10 As shown, the task execution module 005 includes a communication unit 501 and an execution unit 502. The communication unit 501 is responsible for establishing communication with the task scanning module 004 and the calculation and update module 006; the execution unit 502 is responsible for receiving requests and data transmitted from the task scanning module 004, executing tasks, and transmitting the task plan and current execution time information to the calculation and update module 006.

[0099] The calculation and update module 006 is a program deployed on the platform server. For example... Figure 11As shown, the system includes a calculation unit 601, a communication unit 602, and an update storage unit 603. The communication unit 602 is responsible for establishing a network connection and data transmission with the task execution module 005, and for establishing a connection with the database 003. The communication unit 602 responds to time calculation requests from the task execution module 005 and distributes them to the calculation unit 601 for processing; simultaneously, it receives execution time updates and saves tasks and data from the task execution module 005, and distributes them to the update storage unit 603 for processing. The calculation unit 601 is responsible for calculating the next execution time of the task plan, while the update storage unit 603 is responsible for updating and saving the next execution time and the current execution time to the database 003.

[0100] Log module 008 records information such as user operations, task execution, and task changes for querying and tracing.

[0101] The alarm module 007 scans the information recorded by the log module 008 and sends alarms via web pages, emails, or other means for abnormal user operations, task execution errors, and plan change failures.

[0102] The interactive command interface 009 connects to the task execution module 005 of the open platform and the job login subsystem 010 of the host system 390. The interactive command interface 009 is responsible for receiving job and command execution requests from the task execution module 005, opening the interactive command interface 009 by executing the interaction command with the host system, and pushing the job and command execution requests from the task execution module 005 to the job login subsystem 010 for execution.

[0103] The job login subsystem 010 executes the jobs and commands pushed by the interactive command interface 009. Based on actual operational needs, the job login subsystem 010 accesses the dataset 011 and host database 012 in the host system 390 to exchange the data and related information required for runtime.

[0104] Figure 12 Schematic illustration Figure 6 Example system architecture processing flowchart.

[0105] like Figure 12 As shown, the processing flow may include steps S101 to S119. The explanation is as follows:

[0106] Step S101: Design a UI page 001 and embed an intelligent interactive object based on a multimodal large model into the UI page 001.

[0107] In step S102, the user can automatically input scheduled task plans by interacting with the intelligent interactive object via voice on the interface; the user can also view and adjust the execution time. This intelligent interactive object can receive multimodal input, including voice, and after recognizing the user's voice through a large model, it extracts and processes the required information, outputting an executable structured query statement.

[0108] In step S103, the user enters a task plan or temporarily changes the execution time via voice input.

[0109] In step S104, the large model 013 uses retrieval enhancement generation technology to process the user input task and generate the execution time of the task plan or changes.

[0110] In step S105, the query and modification module 002 saves the execution time of the task plan or modification generated by the large model 013 to the database 003.

[0111] Step S106: Task scanning module 004 scans task data in database 003.

[0112] Step S107: Determine if there are any tasks that have reached their deadline and are in a normal state. If yes, proceed to step S108; otherwise, continue to step S106.

[0113] Step S108: The task that has arrived and is in normal status is sent to the task execution module 005.

[0114] In step S109, the task execution module 005 opens the interactive command interface 009 through interactive instructions to execute the push transmission of the task.

[0115] In step S110, the job login subsystem 010 receives commands from the open platform and performs tasks such as job submission, obtaining job status and job output, and job deletion.

[0116] In step S111, the job login subsystem 010 accesses the dataset 011 and host database 012 of the host system 390 according to the actual operation and processing needs, and performs necessary data and related information interaction during operation.

[0117] Step S112: Task processing in host system 390 is completed.

[0118] Step S113: Task execution module 005 obtains the task execution result of host system 390.

[0119] In step S114, the task execution module 005 transmits the execution time and task plan to the calculation and update module 006.

[0120] In step S115, the calculation and update module 006 updates the execution time to the open platform database 003.

[0121] In step S116, the calculation and update module 006 calculates the next execution time according to the task plan and updates it to the open platform database 003.

[0122] In step S117, the query and modification module 002 reads information such as task plan, next execution time and past execution time from the database 003 and transmits it to the UI page 001.

[0123] In step S118, the relevant task information is displayed on the UI page 001.

[0124] Step S119: This completes one cycle of host timed task processing via the open platform. Next, proceed to step S104 to begin the next cycle of host timed task processing via the open platform.

[0125] Figure 13 A block diagram schematically illustrates an electronic device suitable for implementing a processing method for a timed task according to an embodiment of the present invention.

[0126] like Figure 13 As shown, an electronic device 900 according to an embodiment of the present invention includes a processor 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 portion 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0127] RAM 903 stores various programs and data required for the operation of electronic device 900. Processor 901, ROM 902, and RAM 903 are interconnected via bus 904. Processor 901 executes various operations of the method flow according to embodiments of the present invention by executing programs in ROM 902 and / or RAM 903. It should be noted that programs may also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 may also execute various operations of the method flow according to embodiments of the present invention by executing programs stored in one or more memories.

[0128] According to an embodiment of the present invention, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to a bus 904. The electronic device 900 may also include one or more of the following components connected to the input / output (I / O) interface 905: an input section 906 including a keyboard, mouse, etc.; an output section 907 including a cathode ray tube (CRT), 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, modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output (I / O) interface 905 as needed. A removable medium 911, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 910 as needed so that computer programs read from it can be installed into the storage section 908 as needed.

[0129] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0130] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of the present invention, a computer-readable storage medium may include ROM 902 and / or RAM 903 and / or one or more memories other than ROM 902 and RAM 903 described above.

[0131] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code is used to cause the computer system to implement the methods provided in the embodiments of the present invention.

[0132] When the computer program is executed by the processor 901, it performs the functions defined in the system / apparatus of this invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0133] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and downloaded and installed via the communication section 909, and / or installed from a removable medium 911. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0134] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, it performs the functions defined in the system of this embodiment of the invention. According to embodiments of the invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0135] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0136] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0137] Those skilled in the art will understand that the features described in the various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, the features described in the various embodiments of the present invention can be combined and / or combined in various ways without departing from the spirit and teachings of the present invention. All such combinations and / or combinations fall within the scope of the present invention.

Claims

1. A method for processing scheduled tasks, comprising: Input the first text data into the target large model, the first text data including the task plan of the first timed task; The first text data is processed using the target large model to generate a first task configuration instruction for submitting the first scheduled task to the scheduling framework. The target large model is obtained by fine-tuning a pre-trained large language model using the task configuration instruction dataset of the scheduling framework. The task configuration instruction is a programming language instruction adapted to the scheduling framework. Submit the first task configuration instruction to the timed scheduling framework so that the timed scheduling framework configures the first timed task.

2. The method according to claim 1, wherein, The step of processing the first text data using the target large model to generate a first task configuration instruction for submitting the first scheduled task to the scheduling framework includes: The target large model is used to retrieve the task data knowledge base based on the task plan of the first timed task, and the first task configuration instruction is generated by combining the retrieval results through retrieval enhancement.

3. The method according to claim 1, wherein, The input of the first text data into the target large model includes: Receive multimodal input data, wherein the multimodal input data includes at least one of speech, text, or image; Identify the multimodal input data to obtain the first text data; and The first text data is submitted to the target large model.

4. The method according to claim 3, wherein, The input of the first text data into the target large model includes: The task plan for the first timed task is formed through one or more rounds of user interaction with the target large model.

5. The method according to claim 1, wherein, The method further includes: Input second text data into the target large model, the second text data including the temporary change plan of the first timed task; The second text data is processed using the target large model to generate a second task configuration instruction for temporarily changing the task plan of the first timed task in the timed scheduling framework. Send the second task configuration instruction to the timed scheduling framework so that the timed scheduling framework adjusts the temporary scheduling configuration of the first timed task according to the temporary change plan.

6. The method according to any one of claims 1 to 5, wherein, After submitting the first task configuration instruction to the timed scheduling framework, the method further includes: In response to the fulfillment of the triggering condition of the first timed task, the timed scheduling framework triggers the host system to execute the first timed task through interaction with the host system.

7. A processing device for a timed task, comprising: The user interaction module is used to input first text data into the target large model, and the first text data includes the task plan of the first timed task. as well as The large model processing module is used to process the first text data using the target large model, generate a first task configuration instruction for submitting the first scheduled task to the timed scheduling framework, and submit the first task configuration instruction to the timed scheduling framework so that the timed scheduling framework configures the first scheduled task; wherein, the target large model is obtained by fine-tuning the task configuration instruction dataset of the timed scheduling framework, and the task configuration instruction is a programming language instruction adapted to the timed scheduling framework.

8. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instructions stored thereon, wherein, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program or instructions, wherein, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 6.

Images