Task updating method and device based on task processing system, equipment and medium

Abstract

The embodiment of the invention discloses a task updating method and device based on a task processing system, equipment and a medium. A specific embodiment of the method comprises the following steps: extracting a task index configuration set; generating an index association configuration and an index association graph; displaying the index association graph and the task index configuration set so as to process task index related information; inputting the corresponding information into a first large language model to obtain a task execution rule configuration set and a rule configuration basis set; displaying the task execution rule configuration set and the rule configuration basis set on a task processing page; in response to the fact that the packaged file is checked to be correct, filling the packaged file and the information of each task execution terminal into the initial task updating message to obtain a task updating message queue; and distributing the task update message queue to each task execution terminal. According to the embodiment, the task execution information is updated in time in the mode that the task indexes are configurable and in the form of the large language model and the message queue.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a task updating method, device, electronic device, and computer-readable medium based on a task processing system. Background Art

[0002] Currently, tasks in various fields are constantly updated as scenarios change, and the corresponding task logic is constantly updated to adapt to the needs of the scenario. Task updates are typically implemented by manually rewriting the corresponding source files. The updated source files are then sent to each task execution terminal in sequence.

[0003] However, when using the above method to update tasks, the following technical problems often occur:

[0004] For complex task updates, rewriting the source files is time-consuming and labor-intensive, leading to low task update efficiency. Furthermore, for complex tasks, the source files are often large in size, creating bandwidth bottlenecks and inefficient transmission.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure provide a task updating method, apparatus, device, and medium based on a task processing system to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In the first aspect, some embodiments of the present disclosure provide a task updating method based on a task processing system, comprising: extracting a task indicator configuration set from the task execution information corresponding to the target task; utilizing the heavyweight first language model deployed by the above-mentioned task processing system to generate an indicator association configuration and an indicator association map corresponding to the above-mentioned task indicator configuration set; displaying the above-mentioned indicator association map and the above-mentioned task indicator configuration set on the indicator processing page of the above-mentioned task processing system to process the task indicator related information; inputting the task adjustment prompt information, the adjusted task indicator configuration set and the adjusted indicator association configuration into the above-mentioned first language model to obtain the task execution rule configuration set and the rule configuration basis set, and the above-mentioned task adjustment The entire prompt information is the adjustment information entered on the task processing page; the above-mentioned task execution rule configuration set and the above-mentioned rule configuration basis set are displayed on the above-mentioned task processing page to determine the task execution rule configuration; in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration corresponding to the packaged file review, the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message and obtain a task update message queue; the above-mentioned task update message queue is distributed to each task execution terminal to perform parallel task updates.

[0009] In a second aspect, some embodiments of the present disclosure provide a task updating device based on a task processing system, comprising: an extraction unit configured to extract a task indicator configuration set from task execution information corresponding to a target task; a first generation unit configured to generate an indicator association configuration and an indicator association map corresponding to the task indicator configuration set using a heavyweight first language model deployed by the above-mentioned task processing system; a first display unit configured to display the above-mentioned indicator association map and the above-mentioned task indicator configuration set on an indicator processing page in the above-mentioned task processing system to process task indicator related information; an input unit configured to input task adjustment prompt information, the adjusted task indicator configuration set and the adjusted indicator association configuration into the above-mentioned first language model to obtain a task execution rule configuration set and a rule configuration basis set. The above-mentioned task adjustment prompt information is the adjustment information input on the task processing page. The second display unit is configured to display the above-mentioned task execution rule configuration set and the above-mentioned rule configuration basis set on the above-mentioned task processing page to determine the task execution rule configuration; the filling unit is configured to respond to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration. The corresponding package file is reviewed and found to be correct, and the compressed information corresponding to the above-mentioned task execution rule configuration and each task execution terminal information is filled into the initial task update message to generate a task update message and obtain a task update message queue; the distribution unit is configured to distribute the above-mentioned task update message queue to each task execution terminal to perform parallel task updates.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0012] The aforementioned embodiments of the present disclosure have the following beneficial effects: Through the task update method based on a task processing system in some embodiments of the present disclosure, timely updates of task execution information are achieved through configurable task indicators, a large language model, and a message queue. Specifically, the reason for the inefficiency of related task updates and transmissions is that the update of complex tasks requires a large workload and wastes a lot of time to rewrite the source files, resulting in low task update efficiency. In addition, for complex tasks, the source files are often large in size, resulting in bandwidth bottlenecks and low transmission efficiency. Based on this, the task update method based on a task processing system in some embodiments of the present disclosure first extracts a task indicator configuration set from the task execution information corresponding to the target task. By extracting the task indicator configuration set, efficient configuration is achieved at the task indicator level, thereby filtering out the task indicators required for subsequent task updates. Then, using the heavyweight first language model deployed by the task processing system, an indicator association configuration and an indicator association map corresponding to the task indicator configuration set can be efficiently and accurately generated. By generating the indicator association configuration, the indicator association relationships between the various task indicators can be effectively reflected. The indicator association map allows the processing object of the task update to promptly understand the association relationships between the various indicators. Next, the indicator association map and the task indicator configuration set are displayed on the indicator processing page of the task processing system to process the task indicator-related information. Displaying them on the indicator processing page allows for a visual display of the associations between the various indicators, facilitating adaptive adjustments to the task indicators and the associations between them by the processing object. Next, the task adjustment information, the adjusted task indicator configuration set, and the adjusted indicator association configuration are input into the first language model to generate a task execution rule configuration set and a rule configuration basis set. The task adjustment prompt information is the adjustment information input into the task processing page. Here, using the task indicator configuration set corresponding to the target task and the adjusted indicator association configuration set, the first language model can generate, based on the task adjustment prompt information, the accurately updated execution rule configurations corresponding to the task and the reasons for each rule configuration. Furthermore, the task execution rule configuration set and the rule configuration basis set are displayed on the task processing page to determine the task execution rule configuration, enabling visual processing and enabling adaptive adjustments by the processing object. Furthermore, in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the packaged files corresponding to the determined task execution rule configuration being reviewed and found to be correct, the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message and obtain a task update message queue.By configuring each task's execution rules in a configurable and modular manner, we can streamline the configuration of rules corresponding to updated tasks, reducing the size of each task update message and avoiding the issues of high bandwidth usage and long transmission times. Finally, the task update message queue is distributed to each task execution terminal for parallel task updates. In summary, by configuring and graphing indicators and their relationships, and utilizing the first language model, efficient task updates can be achieved. By generating a task update message queue, we avoid the issues of high bandwidth usage and long transmission times. This significantly improves task update efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flowchart of some embodiments of a task updating method based on a task processing system according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of some embodiments of a task updating device based on a task processing system according to the present disclosure;

[0016] Figure 3 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] refer to Figure 1 , shows a process 100 of some embodiments of the task updating method based on the task processing system according to the present disclosure. The task updating method based on the task processing system includes the following steps:

[0024] Step 101: Extract a task indicator configuration set from the task execution information corresponding to the target task. In some embodiments, the execution subject (e.g., an electronic device) of the task update method based on a task processing system can extract the task indicator configuration set from the task execution information corresponding to the target task. The task processing system can be a processing system that performs various tasks. In practice, the various tasks may include, but are not limited to, at least one of the following: task flow adjustment, task definition, task data storage, task flow chart display, and task parameter adjustment. The target task can be a task to be subjected to execution logic adjustment. The execution logic can be the sequential execution content during the task execution process. The task execution information can be the logical content of the task execution logic. In practice, the task execution information can be the task execution record corresponding to the target task. The task indicator configuration set can be the configuration set of all task indicators corresponding to the target task. For example, in a salary calculation scenario, the corresponding target task can be salary calculation, and the corresponding task execution information can be the salary calculation rules for personnel at each level. In a personnel assessment scenario, the corresponding target task can be an assessment task, and the task execution information can be the assessment rules for personnel at each level. In a replenishment scenario, the target task can be a replenishment task, and the task execution information can be the replenishment logic for each item. In practice, target tasks can be specific tasks in various scenarios. Task indicator configuration can be configuration content related to task indicators associated with the target tasks. In practice, task indicator configuration can include: task indicators, task indicator identifiers, task indicator descriptions, and task indicator calculation rules. Business metrics are quantitative data that measure the performance of an enterprise or team's tasks and are used to evaluate operational efficiency, goal achievement, and strategic execution effectiveness. In practice, for salary calculation scenarios, corresponding task indicators can include, but are not limited to, one of the following: basic job indicators, individual performance indicators, team / company-wide indicators, and behavioral or ability indicators. Basic job indicators can include: job level and attendance compliance rate. Individual performance indicators can include: KPI completion rate and project contribution. Team / company-wide indicators can include: team goal achievement rate and company profit share. Behavioral or ability indicators can include: skill certification and customer evaluation. For replenishment scenarios, corresponding task indicators can include, but are not limited to, one of the following: efficiency indicators, cost indicators, quality indicators, and collaboration indicators. Efficiency indicators can include: inventory turnover rate, replenishment cycle time, and order fill rate. Cost metrics can include: out-of-stock costs, excess inventory rate, and replenishment transportation cost ratio. Quality metrics can include: inventory accuracy and replenishment error rate. It should be noted that the configuration of each task metric for the target task can be stored in the basic metric library.

[0025] As an example, the execution entity may utilize BOM (Bill of Materials) indicator settings to quantify the task indicator configuration set in the task execution information.

[0026] Step 102 : Using the heavyweight first language model deployed by the task processing system, generate an indicator association configuration and an indicator association graph corresponding to the task indicator configuration set.

[0027] In some embodiments, the execution entity may utilize the heavyweight first language model deployed by the task processing system to generate an indicator association configuration and an indicator association map corresponding to the task indicator configuration set. The heavyweight first language model may be a large language model (LLM) that leads the industry in terms of parameter scale, computing power, training data volume, and overall performance. The first language model has the following characteristics: ultra-large parameters (e.g., hundreds of billions of parameters), massive training data (with trillions of tokens), cutting-edge hardware support (relying on tens of thousands of GPUs / TPUs), and multi-task generalization capabilities (near-human performance in tasks such as text generation, logical reasoning, and code writing). The indicator association configuration may be the configuration content of the indicator association relationship between various task indicators. The indicator association relationship may be, but is not limited to, one of the following: a positive driving relationship, a synergistic and complementary relationship, a hierarchical decomposition relationship, or a dynamic equilibrium relationship. For example, there may be a dynamic equilibrium relationship between efficiency indicators and cost indicators. For another example, there may be a synergistic and complementary relationship between inventory accuracy and replenishment error rate. The indicator association map may represent the map of associations between various task indicators.

[0028] In some optional implementations of some embodiments, the indicator association configuration includes an indicator relationship configuration and an indicator parameter relationship configuration, and the indicator association map includes an indicator relationship map and an indicator parameter relationship map. The indicator relationship configuration may be the configuration content of the relationship between the various indicators. That is, the indicator relationship configuration may be textual information representing the relationship between the various indicators. The indicator parameter relationship configuration may be textual information representing the relationship between the corresponding parameters of the various indicators. For example, for indicator 1 and indicator 2, the indicator parameter corresponding to indicator 1 affects the indicator parameter corresponding to indicator 2. The indicator parameter relationship configuration may be textual information representing the relationship between the corresponding parameters of the various indicators. The indicator relationship map may be a map that displays the relationship between the various indicators. The indicator parameter relationship map may be a map that displays the relationship between the corresponding parameters of the various indicators. The indicator parameters may be the parameters corresponding to the indicators. The indicator parameters may include indicator parameter names and indicator parameter values.

[0029] Optionally, the execution entity may utilize the heavyweight first language model deployed by the task processing system to generate an indicator association configuration and an indicator association graph corresponding to the task indicator configuration set, including the following steps:

[0030] The first step is to decompose the task execution information into task nodes to obtain a set of task node execution information. The target task includes multiple task nodes. A task node may correspond to a subtask. Each of the multiple task nodes may be arranged in a directed acyclic graph (DAG). The DAG may represent the execution order of each subtask. Each task node execution information may represent the execution information of the corresponding subtask during the execution process.

[0031] In the second step, for each task node execution information, the first important indicator relationship configuration group and the first important indicator parameter relationship configuration group within the task corresponding to the task node execution information are determined. The first important indicator relationship configuration may be a crucial indicator relationship configuration within the subtask. The first important indicator parameter relationship configuration may be a crucial indicator parameter relationship configuration within the subtask.

[0032] As an example, the execution entity may determine the task node corresponding to the task node execution information in the domain corresponding to the target task from a task knowledge base. The task knowledge base stores important indicator relationships and important indicator parameters for each task node in each domain. The execution entity then searches the indicator table corresponding to the task node for a first important indicator relationship configuration group and a first important indicator parameter relationship configuration group.

[0033] The third step is to determine a second important indicator relationship configuration group and a second important indicator parameter relationship configuration group corresponding to at least two consecutive task node execution information in the task node execution information set. The at least two consecutive task node execution information correspond to at least two consecutive task nodes in a directed acyclic graph. The at least two consecutive task nodes can indicate that the task nodes are executed sequentially.

[0034] Similarly, the second important indicator relationship configuration group and the second important indicator parameter relationship configuration group corresponding to every at least two consecutive task node execution information in the above task node execution information set can be determined based on the task execution library and the second largest language model.

[0035] In the fourth step, in response to clicking on the target task node execution information on the above-mentioned indicator processing page or entering the task node identifier corresponding to the above-mentioned target task node execution information, the first important indicator relationship configuration group, the first important indicator parameter relationship configuration group and at least one associated second important indicator relationship configuration group and at least one second important indicator parameter relationship configuration group corresponding to the above-mentioned target task node execution information are displayed on the above-mentioned indicator processing page for determining the important indicator relationship configuration and the important indicator parameter relationship configuration.

[0036] In the fifth step, in response to the input of the indicator screening requirement information on the above-mentioned indicator processing page, the above-mentioned indicator screening requirement information is screened to obtain a screening direction set. The indicator screening requirement information may be the requirement information determined by the user for performing indicator screening on the indicator processing page. The indicator screening requirement information may be in text form or in audio form. For the indicator screening requirement information in audio form, the audio needs to be converted into text in order to determine the subsequent screening direction. The screening direction may be the direction for performing indicator screening. In practice, the screening direction may be the direction for screening indicators. For example, the screening direction may be the direction for task execution efficiency or the direction for task execution speed.

[0037] In step 6, based on the aforementioned screening direction set, the first important indicator relationship configuration group set, the first important indicator parameter relationship configuration group set, the second important indicator relationship configuration group set, and the second important indicator parameter relationship configuration group set, an initial important indicator relationship configuration and an initial important indicator parameter relationship configuration are generated. The initial important indicator relationship configuration may be a candidate important indicator relationship configuration selected from the preliminary screening. The initial important indicator parameter relationship configuration may be a candidate important indicator parameter relationship configuration selected from the preliminary screening.

[0038] As an example, for each screening direction, the execution entity may determine at least one first screening indicator relationship configuration in the first important indicator relationship configuration group set, at least one first screening indicator parameter relationship configuration in the first important indicator parameter relationship configuration group set, at least one second screening indicator relationship configuration in the second important indicator parameter relationship configuration group set, and at least one second screening indicator parameter relationship configuration in the second important indicator parameter relationship configuration group set corresponding to the screening direction. Then, frequency screening is performed on each of the obtained first screening indicator relationship configurations and each of the second screening indicator relationship configurations to obtain a first screening indicator relationship configuration set and a second screening indicator relationship configuration set with a frequency higher than a target frequency. Frequency screening is performed on each of the obtained first screening indicator parameter relationship configurations and each of the second screening indicator parameter relationship configurations to obtain a first screening indicator parameter relationship configuration set and a second screening indicator parameter relationship configuration set with a frequency higher than a target frequency. Finally, the first screening indicator relationship configuration set and the second screening indicator relationship configuration set are determined as the initial important indicator relationship configuration, and the first screening indicator parameter relationship configuration set and the second screening indicator parameter relationship configuration set are determined as the initial important indicator parameter relationship configuration.

[0039] In the seventh step, the above-mentioned initial important indicator relationship configuration and the above-mentioned initial important indicator parameter relationship configuration are displayed on the above-mentioned indicator processing page.

[0040] Step 8: Obtain the important indicator relationship configuration and important indicator parameter relationship configuration selected from the task indicator configuration set on the indicator processing page. The important indicator relationship configuration includes: an important task indicator set and important indicator relationship relationships representing the relationships between each important task indicator; the important indicator parameter relationship configuration includes: an important indicator parameter set and important indicator parameter relationship relationships representing the parameter relationships between each important indicator parameter. The important indicator relationship configuration may be an indicator relationship configuration that is crucial and cannot be deleted during the update task selected by the corresponding page operation object on the indicator processing page. The important indicator parameter relationship configuration may be an indicator parameter relationship configuration that is crucial and cannot be deleted during the update task selected by the corresponding page operation object on the indicator processing page. In practice, the page operation object may label each selected indicator relationship configuration and each selected indicator parameter relationship configuration as important on the indicator processing page to facilitate selection of the important indicator relationship configuration and important indicator parameter relationship configuration. The important task indicator set may be a set of task indicators that must be used during the update task selected by the page operation object.

[0041] In the ninth step, the important indicator relationship configuration and the task indicator configuration set are input into the first language model to generate the indicator relationship configuration. The associations between the important task indicators in the indicator relationship configuration are the important indicator association relationships. That is, during the generation of the indicator relationship configuration, the associations between the important task indicators must not be tampered with and must remain consistent with the configuration of the page operation object.

[0042] As an example, the execution entity may first generate a first configuration generation prompt word representing the indicator relationship configuration generated based on the important indicator relationship configuration and the task indicator configuration set. The first configuration generation prompt word is then input into the first large language model to obtain the indicator relationship configuration.

[0043] In the tenth step, the indicator association configuration and the important indicator parameter relationship configuration are input into the first language model to generate the indicator parameter relationship configuration. The parameter relationships between the important indicator parameters in the indicator parameter relationship configuration are the important indicator parameter association relationships. That is, during the generation of the indicator parameter relationship configuration, the association relationships between the parameters corresponding to the important task indicators must not be tampered with and must remain consistent with the configuration of the page operation object.

[0044] As an example, the execution entity may first generate a second configuration prompt word that represents the generation of an indicator parameter relationship configuration based on the association relationship between the indicators in the indicator association configuration and the important indicator parameter relationship configuration. The second configuration prompt word is then input into the first large language model to obtain the indicator parameter relationship configuration.

[0045] In the eleventh step, the indicator parameter relationship configuration and the indicator relationship configuration are input into the first language model to obtain the indicator relationship graph and the indicator parameter relationship graph.

[0046] As an example, the execution entity may first generate a graph prompt word representing the generation of a corresponding graph based on the indicator parameter relationship configuration and the indicator relationship configuration. Then, the graph prompt word is input into the first language model to obtain the indicator relationship graph and the indicator parameter relationship graph.

[0047] In step 12, an indicator parameter mapping relationship is established between the indicator association configuration and the important indicator parameter relationship configuration, and a graph mapping relationship is established between the indicator relationship graph and the indicator parameter relationship graph, thereby obtaining the indicator association configuration and the indicator association graph. The indicator parameter mapping relationship may be a correspondence between an indicator name and an indicator parameter. The graph mapping relationship may be a node mapping relationship between a node in the indicator relationship graph and a node in the indicator parameter relationship graph (i.e., an indicator parameter mapping relationship).

[0048] Step 103 : Display the indicator association map and the task indicator configuration set on the indicator processing page in the task processing system to process the task indicator related information.

[0049] In some embodiments, the above-mentioned execution entity may display the above-mentioned indicator association map and the above-mentioned task indicator configuration set on the indicator processing page in the above-mentioned task processing system to process the information related to the task indicator. Among them, the indicator processing page may be a page for performing various processing operations on the indicator. In practice, the various processing operations may include but are not limited to: indicator addition operations, indicator deletion operations, indicator modification operations, and indicator display operations. Processing the information related to the task indicator may be performing various processing on the indicator on the indicator processing page. In practice, processing the information related to the task indicator may be adaptive processing by the user through relevant page operations on the indicator processing page. For example, the user deletes the target task indicator configuration on the indicator processing page.

[0050] In some optional implementations of some embodiments, after step 103, the steps further include:

[0051] In the first step, in response to determining that at least one task indicator configuration in the task indicator configuration set displayed on the indicator processing page needs to be adjusted, a large language model selection page is displayed on the indicator processing page. The large language model selection page includes a selection control for selecting a first large language model and a selection control for selecting a lightweight second large language model. The at least one task indicator configuration may be the task indicator configuration to be adjusted. The large language model selection page may be a page for selecting a large language model for further updating of subsequent task indicator configurations. In practice, the large language model selection page displays a selection control corresponding to the first large language model and a selection control corresponding to the second large language model. The first large language model can be selected by clicking the selection control corresponding to the first large language model. The second large language model may be a lightweight large language model with smaller model parameters, training dataset, and training duration than the first large language model. The output accuracy of the second large language model is lower than that of the first large language model. However, the output accuracy of the second large language model must be higher than a preset accuracy (e.g., 90%). The model response time of the second large language model is shorter than that of the first large language model.

[0052] In the second step, in response to selecting the selection control corresponding to the second largest language model, the adjustment information corresponding to the at least one task indicator configuration and the indicator association map are sent to the lightweight second largest language model deployed by the task processing system to obtain a temporary indicator association map. The temporary indicator association map may be an indicator association map that is subsequently further verified to be reasonable and meets the requirements of the operation object. The adjustment information may be the actual adjustment content of the at least one task indicator configuration adjusted on the page.

[0053] As an example, first, the execution entity may generate temporary generation prompt information for generating a temporary indicator association map based on the adjustment information and the indicator association map, and then input the temporary generation prompt information into the second language model to obtain the temporary indicator association map.

[0054] The third step is to display the temporary indicator association graph on the indicator processing page. The indicator processing page supports various graph processing operations on the edges and nodes in the temporary indicator association graph. In practice, these graph processing operations may include edge deletion, edge addition, edge modification, node deletion, node addition, and node modification.

[0055] In step 4, in response to receiving graph adjustment information for the temporary indicator association graph, an adjusted initial indicator association graph is generated based on the graph adjustment information and the temporary indicator association graph using the second language model. The graph adjustment information may be the adjustment content of nodes or edges in the temporary indicator association graph made by the page operation subject on the indicator processing page.

[0056] As an example, the execution entity may first generate a graph generation prompt word for a new indicator association graph based on the graph adjustment information and the temporary indicator association graph. The graph generation prompt word is then input into the second language model to obtain an adjusted initial indicator association graph.

[0057] In step 5, upon confirming on the indicator processing page that the adjusted initial indicator association map is correct, the adjusted initial indicator association map and the adjusted initial task indicator configuration set are input into the first language model to obtain a matching result between the map and the configuration set. Here, after confirming on the indicator processing page that the adjusted initial indicator association map is correct, the first language model is used to further verify the accuracy of the information between the map and the configuration set, given that the second language model may not be as accurate as the first language model.

[0058] In a sixth step, in response to the first matching result representing the match, the adjusted initial indicator association map is determined as the adjusted indicator association map.

[0059] Optionally, the steps further include:

[0060] In the first step, in response to the first matching result indicating a mismatch, the following determination operations are performed:

[0061] Sub-step 1: Generate at least one mismatched configuration information between the adjusted initial indicator association map and the adjusted initial task indicator configuration set. The at least one mismatched configuration information may be at least one configuration information with content mismatching between the adjusted initial indicator association map and the adjusted initial task indicator configuration set. For example, the at least one mismatched configuration information may be: configuration information with three mismatched task indicators and configuration information with five mismatched task indicator association relationships. Mismatched configuration information may indicate mismatched configuration relationships between task indicators, or mismatched configuration relationships between association relationships between task indicators.

[0062] As an example, the execution entity may determine at least one mismatched configuration information by performing task indicator association matching and task indicator matching on any two task indicators. That is, each edge in the adjusted initial indicator association graph may be polled to determine whether a corresponding configuration exists in the adjusted initial task indicator configuration set, thereby determining at least one mismatched configuration information.

[0063] Sub-step 2, add at least one mismatch control to the area corresponding to the adjusted initial indicator association map displayed in the indicator processing page for the at least one mismatch configuration information, wherein the matching control supports clicking to display the mismatch configuration information in the form of a pop-up window, and each mismatch control corresponds to the bottom area of ​​the pop-up window with a confirmation control, a deletion control and a modification control, wherein clicking the confirmation control indicates that the corresponding mismatch configuration information is recognized, and clicking the deletion control indicates that the corresponding mismatch configuration information is not recognized. The area for displaying the adjusted initial indicator association map can be a local page area in the indicator processing page. There is a one-to-one correspondence between the mismatch configuration information in at least one mismatch configuration information and the mismatch control in at least one mismatch control. Clicking the mismatch control can pop up a pop-up window to display the corresponding mismatch configuration information in the pop-up window. Clicking the modification control indicates that the information of the mismatch configuration information is adjusted.

[0064] Sub-step 3, in response to determining to perform a corresponding processing operation on the at least one unmatched control, generates modification information for the at least one unmatched configuration information based on the click information corresponding to the at least one confirmation control, the click information corresponding to the at least one deletion control, and the at least one configuration modification information corresponding to the at least one modification control.

[0065] As an example, identification information corresponding to a first subset of unmatched configuration information corresponding to at least one clicked confirmation control, deletion information corresponding to a second subset of unmatched configuration information corresponding to at least one clicked deletion control, and configuration modification information corresponding to a third subset of unmatched configuration information corresponding to at least one clicked modification control are generated. The identification information, deletion information, and configuration modification information are then aggregated to obtain modification information.

[0066] Sub-step 4: Based on the modification information, make corresponding adjustments to the adjusted initial indicator association map and the adjusted initial task indicator configuration set to obtain a re-adjusted initial indicator association map and a re-adjusted initial task indicator configuration set.

[0067] As an example, the above-mentioned execution entity can use the target map adjustment script and the configuration adjustment script to make corresponding adjustments to the above-mentioned adjusted initial indicator association map and the above-mentioned adjusted initial task indicator configuration set according to the modification content of the task indicators and the task indicator relationship in the modification information, and obtain the re-adjusted initial indicator association map and the re-adjusted initial task indicator configuration set.

[0068] Sub-step 5: Input the readjusted initial indicator association graph and the readjusted initial task indicator configuration set into the first large language model to obtain a second matching result between the graph and the configuration set. The second matching result may indicate whether the corresponding configuration contents of the readjusted initial indicator association graph and the readjusted initial task indicator configuration set match.

[0069] Sub-step 6: In response to the second matching result representing the match, the re-adjusted initial indicator association map is determined as the adjusted indicator association map, and the re-adjusted initial task indicator configuration set is determined as the adjusted task indicator configuration set.

[0070] In the second step, in response to determining the mismatch, the second matching result is used as the first matching result, the re-adjusted initial indicator association map is used as the adjusted initial indicator association map, and the re-adjusted initial task indicator configuration set is used as the adjusted initial task indicator configuration set, and the above determination steps are continued.

[0071] Step 104 : Input the task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration into the first language model to obtain a task execution rule configuration set and a rule configuration basis set.

[0072] In some embodiments, the execution entity may input the task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration into the first language model to obtain a task execution rule configuration set and a rule configuration basis set. The task execution rule configuration may be a rule configuration for the task execution rules. That is, the task execution rule configuration may represent the task execution logic of the target task after the task execution information is updated. The task execution rule configuration set may include at least one task execution rule configuration. Each task execution rule configuration may represent the task execution logic corresponding to each subtask within the target task. Each subtask corresponds to a different task type. For example, in a salary calculation scenario, salary calculation objects of different levels correspond to different subtasks. For example, within a company, users of different positions correspond to different subtasks, i.e., different task execution rule configurations (i.e., salary calculation rule configurations). The rule configuration basis in the rule configuration basis set has a one-to-one correspondence with the task execution rule configuration in the task execution rule configuration set. The rule configuration basis may be the reason for generating the task execution rule configuration by the first language model. The task adjustment prompt information may be a description of the adjustment made to the target task. The task adjustment prompt information is the adjustment information entered on the task processing page. The task processing page may be a page for processing task-related information. For example, the task-related information processing may include inputting task adjustment content and task description information.

[0073] As an example, the execution entity may first generate a generation prompt word that represents the generation of a task execution rule configuration set and a rule configuration basis set based on the task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration. The generation prompt word, the task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration are then input into the first language model to obtain the task execution rule configuration set and the rule configuration basis set.

[0074] In some optional implementations of some embodiments, the execution entity may input task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration into the first language model to obtain a task execution rule configuration set and a rule configuration basis set, wherein the task adjustment prompt information is adjustment information input on the task processing page, and the steps include:

[0075] In a first step, in response to determining that the indicator information corresponding to the task indicator configuration set exceeds the target information requirement, difference configuration information representing the indicator difference between the task indicator configuration set and the adjusted task indicator configuration set is determined. The indicator information may represent the data volume of the indicators and the data volume of the indicator relationships in the task indicator configuration set. The target information requirement may be that the sum of the data volume of the indicators and the data volume of the indicator relationships exceeds the target indicator volume.

[0076] The second step is to determine the indicator relationship differences and indicator parameter relationship differences corresponding to the adjusted indicator association configuration and the above indicator association configuration.

[0077] In the third step, for each task node corresponding to the above target task, perform the following determination steps:

[0078] Sub-step 1: Filter out the indicator difference sub-configuration information corresponding to the task node from the difference configuration information. The indicator difference sub-configuration information may be adjustment configuration information for adjusting task indicators in the task node.

[0079] Sub-step 2: Filtering the indicator relationship sub-differences corresponding to the task nodes from the indicator relationship differences and filtering the indicator parameter relationship sub-differences corresponding to the task nodes from the indicator parameter relationship differences. The indicator relationship sub-differences may be adjustment configuration information related to adjustments to existing indicator relationships within the task nodes. The indicator parameter relationship sub-differences may be adjustment configuration information related to adjustments to existing indicator parameter relationships within the task nodes.

[0080] The fourth step is to remove from each task node the task nodes that do not have corresponding indicator difference sub-configuration information, indicator relationship sub-difference, and indicator parameter relationship sub-difference with empty information, and obtain a set of task nodes after removal.

[0081] In the fifth step, based on the directed acyclic graph corresponding to the target task, each task node in the removed task node set is continuously connected to obtain at least one continuous node information. The continuous node information includes at least one task node whose execution order is sequential.

[0082] Step 6: For each consecutive node information, perform the following first sending step:

[0083] Sub-step 1: Determine the comprehensive indicator difference sub-configuration information, comprehensive indicator relationship sub-difference, and comprehensive indicator parameter relationship sub-difference corresponding to the continuous node information after information integration. The comprehensive indicator difference sub-configuration information may be the comprehensive content of the indicator difference sub-configuration information corresponding to each task node in the continuous node information. The comprehensive indicator relationship sub-difference may be the comprehensive content of the indicator relationship sub-difference corresponding to each task node in the continuous node information. The comprehensive indicator parameter relationship sub-difference may be the comprehensive content of the indicator parameter relationship sub-difference corresponding to each task node in the continuous node information.

[0084] Sub-step 2: Pack the above continuous node information, the above comprehensive indicator difference sub-configuration information, the comprehensive indicator relationship sub-difference and the comprehensive indicator parameter relationship sub-difference to obtain task node adjustment information.

[0085] In the seventh step, the obtained at least one task node adjustment information, the above-mentioned task adjustment prompt information and the above-mentioned indicator association map are sent to the distributed cluster, so that the above-mentioned distributed cluster can generate a task execution rule configuration set and a rule configuration basis set according to the computing resources and large language model of each corresponding node.

[0086] Optionally, the distributed cluster generates a task execution rule configuration set and a rule configuration basis set through the following steps:

[0087] In the first step, using the master node in the above distributed cluster, perform the following processing steps:

[0088] Sub-step 1: For each task node adjustment information in the at least one task node adjustment information, perform the following second sending step:

[0089] In the first sub-step, the task adjustment prompt information is adaptively adjusted for the sub-tasks to obtain the first adjustment prompt sub-information and the second adjustment prompt sub-information corresponding to the task node adjustment information. The distributed cluster includes: a master node and multiple slave nodes. The master node is used to assign tasks to each slave node. For example, the master node is used to allow each slave node to generate a task execution rule configuration and a rule configuration basis based on the task node adjustment information. The first adjustment prompt sub-information is prompt information for generating the task execution rule configuration and the rule configuration basis. The second adjustment prompt sub-information is prompt information for generating a local knowledge graph.

[0090] The second sub-step is to adjust at least one task node identifier corresponding to the at least one task node information.

[0091] The third sub-step is to determine the graph position identifier corresponding to the at least one task node identifier, wherein the graph position identifier may represent the graph position of the at least one task node identifier in the indicator association graph.

[0092] The second sub-step is determining the node difference information volume and node difference importance corresponding to the task node adjustment information. The node difference information volume may be the difference information volume of the total difference corresponding to the comprehensive indicator difference sub-configuration information, the comprehensive indicator relationship sub-difference, and the comprehensive indicator parameter relationship sub-difference. The node difference importance may be the importance of at least one task node to the task node chain.

[0093] In practice, the weight of the node can be obtained by adding at least one node weight corresponding to at least one task node. The node weight can represent the importance of the task node in the target task.

[0094] In the third sub-step, based on the amount of node difference information and the importance of the node differences, the target slave nodes for generating the task execution rule configuration and the rule configuration basis are screened out from each slave node. Among them, each slave node stores the sub-large language model included in the lightweight first large language model configured. That is, the first large language model is a heavyweight model, which can be divided into multiple small sub-large language models through a distributed cluster. Through each sub-large language model, efficient processing of the corresponding small tasks can be achieved. And for small tasks with less task content, the output accuracy and timeliness can be effectively guaranteed. And if each slave node deploys a heavyweight large language model, it may lead to a situation where the overall task processing efficiency is low. Because the master node is responsible for summarizing the task completion information corresponding to each slave node, the master node can adaptively deploy a heavyweight large language model.

[0095] In a fourth sub-step, the task node adjustment information, the first adjustment prompt sub-information, and the second adjustment prompt sub-information are sent to the target sub-node, so that the target sub-node generates, based on the corresponding large language model, at least one task execution rule configuration, at least one rule configuration basis, and a local graph corresponding to the at least one task node. The local graph can represent the node association relationship corresponding to the at least one task node.

[0096] The second step is to obtain the task execution rule configuration set, rule configuration basis set and local graph set.

[0097] The third step is to modify the atlas content in the indicator association atlas into the obtained local atlas set according to the obtained atlas position identifier set, and obtain the modified indicator association atlas.

[0098] The fourth step is to use the large language model corresponding to the master node to verify the validity of the indicator association information in the modified indicator association map and obtain the verification result. The validity can be whether the association between each indicator is reasonable and effective.

[0099] In the fifth step, in response to determining that the verification result representation does not have a problem, the task execution rule configuration set, the rule configuration basis set and the modified indicator association map are sent to the task processing system.

[0100] Optionally, as one of the inventors of this disclosure, the aforementioned "Steps 1-5" solve another technical problem: "How to quickly and accurately generate task execution rule configurations and rule configuration basis when the amount of information corresponding to the task indicator configuration set is high?" Based on this, this disclosure utilizes a distributed cluster, a master node and at least one slave node, and uses the master node to correspond to a large language model and the slave node to correspond to a large language model. Based on this, while fully utilizing computing resources, it can achieve efficient and accurate output of demand information.

[0101] Optionally, after the fifth step, the steps further include:

[0102] In the first step, in response to determining that the verification result indicates a problem, determining that there is at least one first validity problem, wherein the validity problem may be a problem of unreasonable indicator association in the modified indicator association map.

[0103] In the second step, for each first validity question in the at least one first validity question, the following processing steps are performed:

[0104] Sub-step 1: Determine the continuous node information corresponding to the first validity question.

[0105] Sub-step 2: Determine the problem slave node corresponding to the continuous node information. The problem slave node may be a slave node suspected of having a problem with the graph output.

[0106] Sub-step 3: Generate graph adjustment prompt words corresponding to the validity issue. The graph adjustment prompt words can be prompt words for further adjusting the graph based on the validity issue.

[0107] Sub-step 4: sending the graph adjustment prompt word, the original local graph generated corresponding to the problem slave node and the task node adjustment information to the problem slave node, so that the above-mentioned problem slave node can regenerate the local graph corresponding to the continuous node information.

[0108] In the third step, according to the obtained atlas position identification set, the corresponding atlas content in the indicator association atlas is modified to the obtained regenerated local atlas set to obtain the modified indicator association atlas.

[0109] The fourth step is to use the large language model corresponding to the master node to verify the validity of the modified indicator association map and obtain the verification result. The validity can be whether the association between each indicator is reasonable and effective.

[0110] In the fifth step, in response to determining that the verification result characterization does not have any problems, the modified indicator association map is sent to the task processing system.

[0111] In step 6, in response to the verification result indicating that there are still issues, a comprehensive graph adjustment prompt corresponding to the at least one validity issue and at least one second validity issue are generated. The comprehensive graph adjustment prompt may be adjustment prompt information for comprehensively adjusting the indicator association graph based on the at least one validity issue.

[0112] In the seventh step, the above-mentioned comprehensive graph adjustment prompt words and the modified indicator association graph are input into the large language model included in the main node to obtain the indicator association graph generated by the main node.

[0113] In the eighth step, the indicator correlation map generated by the master node is sent to the task processing system.

[0114] In the ninth step, an indicator association graph is generated based on at least one first validity question, at least one second validity question, and the master node, and model training is performed on at least one large language model corresponding to at least one associated slave node through back propagation.

[0115] As an example, the execution entity may generate a first training dataset based on at least one first validity question and at least one corresponding local graph, and generate a second training dataset based on at least one second validity question and at least one corresponding regenerated local graph. Based on the first and second training datasets, the master node generates an indicator association graph as a label, and performs model training on at least one large language model corresponding to at least one associated slave node through backpropagation.

[0116] Optionally, the above-mentioned "first step to ninth step" as one of the inventors of the present disclosure solves another technical problem "there is a difference in accuracy between the large language model corresponding to the master node and the large language model corresponding to the slave node in the distributed cluster, which makes it impossible to effectively generate the graph". Based on this, the present disclosure allows at least one slave node corresponding to the large language model to perform multiple rounds of graph regeneration according to the graph adjustment prompt words as much as possible, and when it is determined that the effect of the graph generated in multiple rounds is still not good, it is output through the heavyweight large language model of the master node. On this basis, based on the content output by the master node as the output standard, the large language model corresponding to at least one slave node is adaptively adjusted to achieve the model accuracy of the lightweight large language model corresponding to the slave node constantly approaching the model accuracy of the large language model corresponding to the master node.

[0117] Step 105 : Display the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration.

[0118] In some embodiments, the execution entity may display the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration.

[0119] In some optional implementations of some embodiments, the rule configuration basis in the rule configuration basis set includes: a set of advantage keywords, a set of advantage degree information corresponding to the advantage keyword set, and a rule configuration summary. The advantage keywords may be the advantage content generated by the task execution rule configuration in the rule configuration basis. Each advantage keyword corresponds to a dominant feature of the task execution rule configuration. There is a one-to-one correspondence between the advantage keywords in the advantage keyword set and the dominant degree information in the dominant degree information set. The dominant degree information may represent the degree of advantage of the task execution rule configuration under a particular dominant feature. For example, the dominant degree information may be numerical information, where the higher the numerical value, the more pronounced the description of the dominant feature of the task execution rule configuration under a particular advantage keyword. For example, the advantage keyword may be "accuracy." The corresponding dominant degree information may be "70%," which may represent that the accuracy corresponding to the task execution rule configuration is "70%." The rule configuration summary may be configuration description information generated corresponding to the task execution rule configuration. In other words, the rule configuration summary may be a summary of the configuration characteristics of the task execution rule configuration.

[0120] Optionally, the execution entity may display the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration. The method may further include:

[0121] The first step is to filter out at least one target task execution rule configuration from the above-mentioned task execution rule configuration set in response to performing a filtering operation for at least one target advantage keyword and at least one target advantage degree information on the above-mentioned task processing page, wherein, for each target advantage keyword, the advantage degree information of the target task execution rule configuration under the target advantage keyword is not lower than the corresponding target advantage degree information. In practice, the task execution rule configuration can be selected based on the advantage keywords and advantage degree information in the target control bar on the task processing page. That is, for the target task, the target control bar in the task processing page displays a selection bar that supports the selection of advantage keywords and advantage degree information. After selecting the advantage keywords and advantage degree information, the task processing page will automatically display the filtered at least one target task execution rule configuration.

[0122] In the second step, based on the at least one target advantage keyword, the at least one target advantage degree information, and the at least one rule configuration summary, a second language model is used to generate at least one advantage configuration summary corresponding to the at least one target task execution rule configuration. The at least one rule configuration summary corresponds one-to-one to the at least one target task execution rule configuration. The advantage configuration summary may be a summary of the configuration advantages corresponding to each target task execution rule configuration. Each target task execution rule configuration has a corresponding advantage configuration summary.

[0123] As an example, first, a summary prompt word is generated to summarize the at least one target advantage keyword, the at least one target advantage degree information, and the at least one rule configuration summary to generate an advantage configuration summary. Then, the at least one target advantage keyword, the at least one target advantage degree information, the at least one rule configuration summary, and the summary prompt word are input into a second language model to obtain at least one advantage configuration summary corresponding to at least one target task execution rule configuration.

[0124] In the third step, the at least one advantage configuration summary, the at least one rule configuration summary, the advantage degree information set corresponding to each target task execution rule configuration, and the at least one target task execution rule configuration are displayed on the task processing page.

[0125] In step 4, in response to receiving click information for the target task execution rule configuration, the clicked target task execution rule configuration is determined as the determined task execution rule configuration. The click information may be an operation of clicking a control corresponding to the target task execution rule configuration on the page.

[0126] Step 106, in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration corresponding to the packaged file being reviewed and found to be correct, the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message and obtain a task update message queue.

[0127] In some embodiments, in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration corresponding to the packaged file audited and found to be correct, the above-mentioned execution subject can fill the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information into the initial task update message to generate a task update message and obtain a task update message queue. In practice, the above-mentioned execution subject can send the packaged file to the audit terminal for the audit terminal to audit the task indicator related information of the packaged file. The compressed information can be the information obtained by splicing the task execution rule configuration and the task execution terminal information and then compressing it. The task execution terminal information can be the terminal information of the terminal that executes the target task. For example, the task execution terminal information can be a terminal identifier. The initial task update message can be a message template that has not yet been filled with the compressed information. The task update message can be a message that indicates that the task execution terminal is updating the task according to the task execution rule configuration.

[0128] Step 107: Distribute the task update message queue to each task execution terminal to perform parallel task updates.

[0129] In some embodiments, the execution entity may distribute the task update message queue to each task execution terminal to perform parallel task updates.

[0130] In some optional implementations of some embodiments, each of the above-mentioned task execution terminals performs the following processing steps:

[0131] The first step is to use the rule engine in the task execution terminal to generate the task processing rule configuration corresponding to the packaged file. The task processing rule configuration can be a rule configuration for processing the target task.

[0132] The second step is to set the configuration version number corresponding to the above task processing rule configuration, and bind the above configuration version number to the task processing time.

[0133] In the third step, in response to the current time being the task processing time, the task data set at the current time is obtained.

[0134] The fourth step is to generate a task processing result corresponding to the task data set using the task processing rule configuration corresponding to the task processing time.

[0135] The fifth step is to display the above task processing results on the corresponding page of the above task execution terminal.

[0136] The aforementioned embodiments of the present disclosure have the following beneficial effects: Through the task update method based on a task processing system in some embodiments of the present disclosure, timely updates of task execution information are achieved through configurable task indicators, a large language model, and a message queue. Specifically, the reason for the inefficiency of related task updates and transmissions is that the update of complex tasks requires a large workload and wastes a lot of time to rewrite the source files, resulting in low task update efficiency. In addition, for complex tasks, the source files are often large in size, resulting in bandwidth bottlenecks and low transmission efficiency. Based on this, the task update method based on a task processing system in some embodiments of the present disclosure first extracts a task indicator configuration set from the task execution information corresponding to the target task. By extracting the task indicator configuration set, efficient configuration is achieved at the task indicator level, thereby filtering out the task indicators required for subsequent task updates. Then, using the heavyweight first language model deployed by the task processing system, an indicator association configuration and an indicator association map corresponding to the task indicator configuration set can be efficiently and accurately generated. By generating the indicator association configuration, the indicator association relationships between the various task indicators can be effectively reflected. The indicator association map allows the processing object of the task update to promptly understand the association relationships between the various indicators. Next, the indicator association map and the task indicator configuration set are displayed on the indicator processing page of the task processing system to process the task indicator-related information. Displaying them on the indicator processing page allows for a visual display of the associations between the various indicators, facilitating adaptive adjustments to the task indicators and the associations between them by the processing object. Next, the task adjustment information, the adjusted task indicator configuration set, and the adjusted indicator association configuration are input into the first language model to generate a task execution rule configuration set and a rule configuration basis set. The task adjustment prompt information is the adjustment information input into the task processing page. Here, using the task indicator configuration set corresponding to the target task and the adjusted indicator association configuration set, the first language model can generate, based on the task adjustment prompt information, the accurately updated execution rule configurations corresponding to the task and the reasons for each rule configuration. Furthermore, the task execution rule configuration set and the rule configuration basis set are displayed on the task processing page to determine the task execution rule configuration, enabling visual processing and enabling adaptive adjustments by the processing object. Furthermore, in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the packaged files corresponding to the determined task execution rule configuration being reviewed and found to be correct, the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message and obtain a task update message queue.By configuring each task's execution rules in a configurable and modular manner, we can streamline the configuration of rules corresponding to updated tasks, reducing the size of each task update message and avoiding the issues of high bandwidth usage and long transmission times. Finally, the task update message queue is distributed to each task execution terminal for parallel task updates. In summary, by configuring and graphing indicators and their relationships, and utilizing the first language model, efficient task updates can be achieved. By generating a task update message queue, we avoid the issues of high bandwidth usage and long transmission times. This significantly improves task update efficiency.

[0137] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a task updating device based on a task processing system. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the task updating device based on the task processing system can be specifically applied to various electronic devices.

[0138] like Figure 2As shown, a task updating device 200 based on a task processing system includes: an extraction unit 201, a first generation unit 202, a first display unit 203, an input unit 204, a second display unit 205, a filling unit 206 and a distribution unit 207. The extraction unit 201 is configured to extract a task indicator configuration set from the task execution information corresponding to the target task; the first generation unit 202 is configured to generate an indicator association configuration and an indicator association map corresponding to the task indicator configuration set using the heavyweight first language model deployed by the task processing system; the first display unit 203 is configured to display the indicator association map and the task indicator configuration set on the indicator processing page of the task processing system to process the task indicator related information; the input unit 204 is configured to input the task adjustment prompt information, the adjusted task indicator configuration set and the adjusted indicator association configuration into the first language model to obtain a task execution rule configuration set and a rule configuration basis set, wherein the task adjustment prompt information is generated by the task processing system. The second display unit 205 of the adjustment information input on the task processing page is configured to display the above-mentioned task execution rule configuration set and the above-mentioned rule configuration basis set on the above-mentioned task processing page to determine the task execution rule configuration; the filling unit 206 is configured to respond to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration. The package file corresponding to the configuration is reviewed and found to be correct, and the compressed information corresponding to the above-mentioned task execution rule configuration and each task execution terminal information is filled into the initial task update message to generate a task update message and obtain a task update message queue; the distribution unit 207 is configured to distribute the above-mentioned task update message queue to each task execution terminal to perform parallel task updates.

[0139] It is understandable that the units described in the task updating device 200 based on the task processing system are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the task updating device 200 based on the task processing system and the units included therein, and will not be described in detail here.

[0140] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0141] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0142] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0143] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0144] It should be noted that in some embodiments of the present disclosure, the computer-readable medium mentioned above may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the 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, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0145] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0146] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: extracts the task indicator configuration set from the task execution information corresponding to the target task; generates the indicator association configuration and indicator association map corresponding to the above-mentioned task indicator configuration set using the heavyweight first language model deployed by the above-mentioned task processing system; displays the above-mentioned indicator association map and the above-mentioned task indicator configuration set on the indicator processing page of the above-mentioned task processing system to process the task indicator related information; inputs the task adjustment prompt information, the adjusted task indicator configuration set and the adjusted indicator association configuration into the above-mentioned first language model to obtain the task execution rule configuration set and the rule configuration basis set. , the above-mentioned task adjustment prompt information is the adjustment information input on the task processing page; the above-mentioned task execution rule configuration set and the above-mentioned rule configuration basis set are displayed on the above-mentioned task processing page to determine the task execution rule configuration; in response to the above-mentioned adjusted task indicator configuration set, the above-mentioned adjusted indicator association configuration, the adjusted indicator association map, the above-mentioned task adjustment information and the determined task execution rule configuration corresponding to the packaged file review, the above-mentioned task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message and obtain a task update message queue; the above-mentioned task update message queue is distributed to each task execution terminal to perform parallel task updates.

[0147] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0148] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0149] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor. For example, they may be described as follows: a processor comprising an extraction unit, a first generation unit, a first display unit, an input unit, a second display unit, a filling unit, and a distribution unit. The names of these units do not, in some cases, constitute a limitation on the units themselves. For example, the extraction unit may also be described as a "unit for extracting a task indicator configuration set from the task execution information corresponding to the target task."

[0150] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0151] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A task updating method based on a task processing system, comprising: Extracting a task indicator configuration set from the task execution information corresponding to the target task; Generate an indicator association configuration and an indicator association graph corresponding to the task indicator configuration set using the heavyweight first language model deployed by the task processing system; Displaying the indicator association map and the task indicator configuration set on an indicator processing page in the task processing system to process task indicator related information; Inputting the task adjustment prompt information, the adjusted task indicator configuration set, and the adjusted indicator association configuration into the first language model to obtain a task execution rule configuration set and a rule configuration basis set, wherein the task adjustment prompt information is the adjustment information input on the task processing page; Displaying the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration; In response to the adjusted task indicator configuration set, the adjusted indicator association configuration, the adjusted indicator association map, the task adjustment information, and the determined task execution rule configuration corresponding to the packaged file being reviewed and found to be correct, the task execution rule configuration and the compressed information corresponding to each task execution terminal information are filled into the initial task update message to generate a task update message, thereby obtaining a task update message queue; The task update message queue is distributed to each task execution terminal to perform parallel task updates.

2. The method according to claim 1, wherein Each of the task execution terminals performs the following processing steps: Utilizing a rule engine in a task execution terminal to generate a task processing rule configuration corresponding to the packaged file; Setting a configuration version number corresponding to the task processing rule configuration, and binding the configuration version number to the task processing time; In response to the current time being the task processing time, obtaining a task data set at the current time; Generate a task processing result corresponding to the task data set by configuring a task processing rule corresponding to the task processing time; The task processing result is displayed on a corresponding page in the task execution terminal.

3. The method according to claim 1, wherein After displaying the indicator association map and the task indicator configuration set on the indicator processing page in the task processing system to process task indicator related information, the method further includes: In response to determining that at least one task indicator configuration in the task indicator configuration set displayed on the indicator processing page is to be adjusted, displaying a large language model selection page on the indicator processing page, wherein the large language model selection page includes: a selection control for selecting a first large language model, and a selection control for selecting a lightweight second large language model; In response to selecting a selection control corresponding to the second largest language model, sending adjustment information corresponding to the at least one task indicator configuration and the indicator association map to a lightweight second largest language model deployed by the task processing system to obtain a temporary indicator association map; Displaying the temporary indicator association graph on the indicator processing page, wherein the indicator processing page supports various graph processing operations on the edges and nodes in the temporary indicator association graph; In response to receiving the graph adjustment information for the temporary indicator association graph, generating an adjusted initial indicator association graph using the second largest language model according to the graph adjustment information and the temporary indicator association graph; In response to confirming on the indicator processing page that the adjusted initial indicator association map is correct, inputting the adjusted initial indicator association map and the adjusted initial task indicator configuration set into the first language model to obtain a matching result between the map and the configuration set; In response to the first matching result representing a match, the adjusted initial indicator association map is determined as an adjusted indicator association map.

4. The method according to claim 3, wherein: The method further comprises: In response to the first matching result indicating a mismatch, performing the following determination operations: generating at least one mismatch configuration information between the adjusted initial indicator association map and the adjusted initial task indicator configuration set; Add at least one mismatch control to the area of ​​the indicator processing page corresponding to the display of the adjusted initial indicator association map for the at least one mismatch configuration information, wherein the mismatch control supports click to display the mismatch configuration information in the form of a pop-up window, and each mismatch control corresponds to a pop-up window with a confirmation control, a delete control, and a modification control in the bottom area, wherein clicking the confirmation control indicates approval of the corresponding mismatch configuration information, clicking the delete control indicates disapproval of the corresponding mismatch configuration information, and clicking the modification control indicates adjustment of the mismatch configuration information; In response to determining to perform a corresponding processing operation on the at least one unmatched control, generating modification information for the at least one unmatched configuration information based on the obtained click information corresponding to the at least one confirmation control, the click information corresponding to the at least one deletion control, and the at least one configuration modification information corresponding to the at least one modification control; According to the modification information, the adjusted initial indicator association map and the adjusted initial task indicator configuration set are adjusted accordingly to obtain a re-adjusted initial indicator association map and a re-adjusted initial task indicator configuration set; Inputting the readjusted initial indicator association graph and the readjusted initial task indicator configuration set into the first language model to obtain a second matching result between the graph and the configuration set; In response to the second matching result indicating a match, determining the re-adjusted initial indicator association map as the adjusted indicator association map, and determining the re-adjusted initial task indicator configuration set as the adjusted task indicator configuration set; In response to determining a mismatch, the second matching result is used as the first matching result, the re-adjusted initial indicator association map is used as the adjusted initial indicator association map, and the re-adjusted initial task indicator configuration set is used as the adjusted initial task indicator configuration set, and the determination step is continued.

5. The method according to claim 1, wherein The rule configuration basis in the rule configuration basis set includes: a dominant keyword set, a dominant degree information set corresponding to the dominant keyword set, and a rule configuration summary; and After displaying the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration, the method further includes: In response to performing a screening operation on the task processing page for at least one target advantage keyword and at least one target advantage degree information, screening out at least one target task execution rule configuration corresponding to the task execution rule configuration set, wherein, for each target advantage keyword, the advantage degree information of the target task execution rule configuration under the target advantage keyword is not lower than the corresponding target advantage degree information; generating, using a second language model, at least one advantage configuration summary corresponding to the at least one target task execution rule configuration based on the at least one target advantage keyword, the at least one target advantage degree information, and the at least one rule configuration summary, wherein the at least one rule configuration summary corresponds one-to-one to the at least one target task execution rule configuration; Displaying the at least one advantage configuration summary, the at least one rule configuration summary, the advantage degree information set corresponding to each target task execution rule configuration, and the at least one target task execution rule configuration on the task processing page; In response to receiving click information for the target task execution rule configuration, the clicked target task execution rule configuration is determined as the determined task execution rule configuration.

6. The method according to claim 1, wherein The indicator association configuration includes: indicator relationship configuration and indicator parameter relationship configuration, and the indicator association map includes: indicator relationship map and indicator parameter relationship map; and The step of utilizing the heavyweight first language model deployed by the task processing system to generate an indicator association configuration and an indicator association graph corresponding to the task indicator configuration set includes: Decomposing the task execution information into task nodes to obtain a task node execution information set; For each task node execution information, determining a first important indicator relationship configuration group and a first important indicator parameter relationship configuration group within the task corresponding to the task node execution information; Determine a second important indicator relationship configuration group and a second important indicator parameter relationship configuration group corresponding to every at least two consecutive task node execution information in the task node execution information set; In response to clicking on the target task node execution information or inputting the task node identifier corresponding to the target task node execution information on the indicator processing page, the first important indicator relationship configuration group, the first important indicator parameter relationship configuration group, and at least one associated second important indicator relationship configuration group and at least one second important indicator parameter relationship configuration group corresponding to the target task node execution information are displayed on the indicator processing page for determining the important indicator relationship configuration and the important indicator parameter relationship configuration; In response to inputting indicator screening requirement information on the indicator processing page, screening the indicator screening requirement information to obtain a screening direction set; generating an initial important indicator relationship configuration and an initial important indicator parameter relationship configuration according to the screening direction set, the first important indicator relationship configuration group set, the first important indicator parameter relationship configuration group set, the second important indicator relationship configuration group set, and the second important indicator parameter relationship configuration group set; and displaying the initial important indicator relationship configuration and the initial important indicator parameter relationship configuration on the indicator processing page; Obtaining an important indicator relationship configuration and an important indicator parameter relationship configuration selected from the task indicator configuration set on the indicator processing page, wherein the important indicator relationship configuration includes: an important task indicator set and an important indicator relationship relationship representing a relationship between each important task indicator; and the important indicator parameter relationship configuration includes: an important indicator parameter set and an important indicator parameter relationship relationship representing a parameter relationship between each important indicator parameter; Inputting the important indicator relationship configuration and the task indicator configuration set into the first language model to obtain the indicator relationship configuration, wherein the association relationship between the important task indicators in the indicator relationship configuration is the important indicator association relationship; Inputting the indicator association configuration and the important indicator parameter relationship configuration into the first language model to obtain the indicator parameter relationship configuration, wherein the parameter relationship between each important indicator parameter in the indicator parameter relationship configuration is the important indicator parameter association relationship; Inputting the indicator parameter relationship configuration and the indicator relationship configuration into the first large language model to obtain the indicator relationship graph and the indicator parameter relationship graph; An indicator parameter mapping relationship is established between the indicator association configuration and the important indicator parameter relationship configuration, and a graph mapping relationship is established between the indicator relationship graph and the indicator parameter relationship graph, to obtain the indicator association configuration and the indicator association graph.

7. The method according to claim 6, wherein: The method further comprises: In response to acquiring execution adjustment information corresponding to the task execution information, determining an indicator relationship difference and an indicator parameter relationship difference corresponding to the execution adjustment information; generating at least one indicator difference configuration corresponding to the indicator relationship difference; generating at least one indicator parameter difference configuration corresponding to the indicator parameter relationship difference; In response to determining that there is no conflict between the at least one indicator difference configuration and the at least one indicator parameter difference configuration, obtaining an indicator modification configuration template and an indicator parameter modification configuration template corresponding to the indicator relationship map; for each indicator difference configuration, filling the indicator difference configuration into the indicator modification configuration template to obtain an indicator modification configuration; Fill each indicator parameter difference configuration into the indicator parameter modification configuration template to obtain the indicator parameter modification configuration; Replacing the corresponding indicator relationship configuration and indicator parameter relationship configuration in the indicator association configuration with the obtained at least one indicator modification configuration and at least one indicator parameter modification configuration; generating at least one first indicator modification chain corresponding to the at least one indicator modification configuration and at least one second indicator modification chain corresponding to the at least one indicator parameter modification configuration; Locating at least one first modification position corresponding to the indicator relationship map according to the at least one first indicator modification chain, and replacing at least one corresponding indicator relationship chain in the indicator relationship map with the at least one first indicator modification chain according to the at least one first modification position; Locating at least one second modification position corresponding to the indicator relationship map according to the at least one second indicator modification chain, and replacing at least one corresponding indicator relationship chain in the indicator parameter relationship map with the at least one second indicator modification chain according to the at least one second modification position; The replaced indicator relationship map, the replaced indicator parameter relationship map and the replaced indicator association configuration are displayed on the indicator processing page to perform user adaptive adjustment.

8. A task updating device based on a task processing system, comprising: an extraction unit configured to extract a task indicator configuration set from task execution information corresponding to the target task; A first generating unit is configured to generate an indicator association configuration and an indicator association graph corresponding to the task indicator configuration set using a heavyweight first language model deployed by the task processing system; A first display unit is configured to display the indicator association map and the task indicator configuration set on an indicator processing page in the task processing system to process task indicator related information; The input unit is configured to input the task adjustment prompt information, the adjusted task indicator configuration set and the adjusted indicator association configuration into the first language model to obtain the task execution rule configuration set and the rule configuration basis set, wherein the task adjustment prompt information is the adjustment information input on the task processing page. a second display unit configured to display the task execution rule configuration set and the rule configuration basis set on the task processing page to determine the task execution rule configuration; The filling unit is configured to fill the compressed information corresponding to the task execution rule configuration and each task execution terminal information into the initial task update message in response to the package file corresponding to the adjusted task indicator configuration set, the adjusted indicator association configuration, the adjusted indicator association map, the task adjustment information, and the determined task execution rule configuration being reviewed and found to be correct, so as to generate a task update message and obtain a task update message queue; The distribution unit is configured to distribute the task update message queue to each task execution terminal to perform parallel task updates.

9. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images