Intelligent Agent Automatic Reasoning Method and System Based on Task Dependency Planning

Abstract

The present invention proposes an intelligent agent automatic reasoning method and system based on task-dependent planning, belonging to the technical field and system of model automatic reasoning. The method includes: according to the status information of the current task, using a forward reasoning module to predict the subtasks to be executed and generate the dependency relationship between the subtasks and the status; according to the dependency relationship between the subtasks and the status, using backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status; by performing statistical analysis on the parameter uncertainty of the predicted output subtasks, generating the probability distribution of the results and quantifying the uncertainty of the subtasks; by performing decision uncertainty analysis on the historical behavior and current status of the executor, evaluating the credibility of its decision. It solves the problem that the predefined task dependency relationship cannot adapt to different task inputs and topological structures, and avoids the problem that the large language model is too confident when expressing oral uncertainty.

Description

Technical Field

[0001] The present invention belongs to the technical field of model automatic reasoning, and in particular relates to an intelligent agent automatic reasoning method and system based on task-dependent planning. Background Art

[0002] The statements in this section merely provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] Task-dependent planning aims to plan subtasks to complete a goal, decompose the goal task into individual tasks, and model the dependencies between tasks. Existing planning methods mainly use predefined dependency structures to model task dependencies and evaluate the reliability of intermediate results through the verbalized uncertainty generated by the model. However, the predefined dependency structures are not common in practice, and the uncertainty of verbal expression faces the challenge of overconfidence.

[0004] In addition, task-dependent planning supported by large language models still faces two challenges:

[0005] First, the predefined task dependencies are not common in practice. Most methods use reasoning ideas to model task dependencies as predefined structures, such as chains, trees, and graphs. Although recent research has explored the dynamic planning of tasks to improve interpretability, this cannot dynamically simulate the appropriate dependencies between the tasks to be executed and the states, which record the user input and historical task execution. For example, ReAct uses a large language model to reason about the chain of thought, obtain observations, and update the task plan simultaneously. The dependency topology of the task is linear. However, under different task inputs, the target task can be decomposed into subtasks with different numbers and topological dependency structures. Some tasks only need to select appropriate logical rules to prove the goal, while other tasks need to be decomposed into subtasks with linear or graphical dependencies respectively. Therefore, the predefined task dependencies cannot solve all problems in a specific task domain.

[0006] Second, most autonomous planning methods evaluate the reliability of intermediate results through the reliability generated by the model. However, when expressing verbal uncertainty, large language models tend to be overconfident. Summary of the Invention

[0007] To overcome the deficiencies of the above-mentioned prior art, the present invention provides an intelligent agent automatic reasoning method and system based on task-dependent planning, which is used to adaptively model the dependencies between planned tasks and states, and estimate the uncertainty of intermediate results during the planning process, solve the limitations of existing large language models in task-dependent planning and uncertainty evaluation, and thus improve the accuracy, flexibility, and reliability of decision-making.

[0008] To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:

[0009] The first aspect of the present invention provides an intelligent agent automatic reasoning method based on task-dependent planning;

[0010] The intelligent agent automatic reasoning method based on task-dependent planning includes:

[0011] Step S1, according to the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the status information;

[0012] Step S2, according to the dependency relationship between the subtasks and the status, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold;

[0013] Step S3, use the executor to execute the remaining subtasks and output the intermediate results of the subtasks;

[0014] Step S4, through the uncertainty analysis of the intermediate results of the subtasks, obtain the uncertainty score of the intermediate results of the subtasks; wherein, the uncertainty analysis includes parameter uncertainty analysis and decision uncertainty analysis;

[0015] The parameter uncertainty statistical analysis quantifies the uncertainty of the subtasks by generating the probability distribution of the intermediate results of the subtasks;

[0016] The decision uncertainty analysis evaluates the credibility of the decision by performing uncertainty analysis on the intermediate results of the subtasks and the tasks to be executed in the subsequent reasoning process;

[0017] Step S5, iterate steps S1 to S4, stop iterating when the maximum number of iterations is reached or the target task is completed, and summarize and output the final reasoning result according to all the intermediate results generated during the iteration process.

[0018] As a further technical solution, the status information of the current task includes user input information, historical task execution records, task definitions and their results.

[0019] As a further technical solution, the process of using the forward reasoning module to predict the subtasks to be executed and generate the dependency relationship between the subtasks and the status is:

[0020] Analyze the current status information, including user input information, historical task execution records, and task definitions;

[0021] Based on the results of the status analysis, decompose the target task into subtasks with different dependency relationships;

[0022] Prioritize according to the importance and urgency of subtasks to determine the order of task execution.

[0023] As a further technical solution, the process of using backward inference to generate the confidence score of the dependency relationship between each subtask and the status information is as follows:

[0024] According to the task definitions of each status and subtask, determine whether there is a dependency relationship between the subtask and each status information and the probability of the existence of the dependency relationship;

[0025] Calculate the backward inference probability, construct the confidence score calculation formula, and obtain the confidence score of the dependency relationship between each subtask and the status information.

[0026] As a further technical solution, the confidence score calculation formula is:

[0027]

[0028] In the formula, is the confidence score; represents linear transformation; is the status; is the subtask; is the probability of the forward inference result, used to represent the confidence of the subtask depending on all historical tasks; is the probability of the backward inference result, used to represent the confidence of the subtask depending on only one historical task.

[0029] As a further technical solution, the parameter uncertainty analysis and the decision uncertainty analysis are respectively evaluated by information entropy; among them, the uncertainty of the subtask intermediate result is evaluated by calculating the information entropy of the subtask intermediate result;

[0030] The credibility of the decision is evaluated by calculating the information entropy of the inference result obtained in the previous inference process and the task planned by the current planner.

[0031] As a further technical solution, the uncertainty analysis of the intermediate result of the subtask is performed to obtain the uncertainty score of the subtask intermediate result, including:

[0032] The uncertainty score of the subtask intermediate result is obtained by calculating the arithmetic mean of the parameter uncertainty and the decision uncertainty analysis results, as shown in the following formula:

[0033]

[0034] In the formula, is the uncertainty score of the subtask intermediate result; represents the result of the parameter uncertainty analysis; Represents the result of decision uncertainty analysis.

[0035] The second aspect of the present invention provides an intelligent agent automatic reasoning system based on task-dependent planning.

[0036] The intelligent agent automatic reasoning system based on task-dependent planning includes:

[0037] A forward reasoning module, configured to: according to the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the status;

[0038] A backward reasoning module, configured to: according to the dependency relationship between the subtasks and the status, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold;

[0039] An intermediate result acquisition module, configured to: use an executor to execute the remaining subtasks and output the intermediate results of the subtasks;

[0040] An uncertainty analysis module, configured to: perform uncertainty analysis on the intermediate results of the subtasks to obtain the uncertainty score of the intermediate results of the subtasks; wherein, the uncertainty analysis includes parameter uncertainty analysis and decision uncertainty analysis;

[0041] The parameter uncertainty statistical analysis quantifies the uncertainty of the subtasks by generating the probability distribution of the intermediate results of the subtasks;

[0042] The decision uncertainty analysis evaluates the credibility of the decision by performing uncertainty analysis on the intermediate results of the subtasks and the tasks to be executed in the subsequent reasoning process;

[0043] An inference result generation module, configured to: iterate the above process, stop iterating when the maximum number of iterations is reached or the target task is completed, and summarize and output the final inference result according to all the intermediate results generated during the iteration process.

[0044] The third aspect of the present invention provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps in the intelligent agent automatic reasoning method based on task-dependent planning as described in the first aspect of the present invention.

[0045] The fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps in the intelligent agent automatic reasoning method based on task-dependent planning as described in the first aspect of the present invention.

[0046] The above one or more technical solutions have the following beneficial effects:

[0047] (1) By means of a two-way reasoning module (forward reasoning and backward reasoning), the present invention dynamically models the dependency relationship between tasks and states, solving the problem that predefined task dependency relationships cannot adapt to different task inputs and topological structures. Forward reasoning predicts subtasks based on the current state, while backward reasoning evaluates the confidence of the dependency relationship between subtasks and states, thereby being able to flexibly meet the requirements of different task domains and enhancing the adaptability and accuracy of task planning.

[0048] (2) By introducing an uncertainty estimation module, the present invention can evaluate the reliability of the intermediate results generated during the planning process. By considering parameter uncertainty and decision-making uncertainty, the system can more accurately judge the credibility of the generated results, avoiding the problem that large language models are too confident when expressing verbal uncertainty. This helps to improve the reliability and safety of decision-making and reduce incorrect decisions caused by the overconfidence of the model.

[0049] (3) The present invention does not require model training or rely on demonstration examples, making it more practical and convenient in actual applications. This method reduces the complexity of deployment and maintenance, can be quickly applied to various fields, reduces the dependence on external data or complex training processes, and enhances the scalability and usability of the system.

[0050] Advantages of additional aspects of the present invention will be given in part in the following description, will become apparent in part from the following description, or will be learned through the practice of the present invention. Description of the Drawings

[0051] The specification drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention.

[0052] Figure 1 It is a flowchart of the method for the first embodiment.

[0053] Figure 2 It is a system structure diagram of the second embodiment. Detailed Description of the Invention

[0054] It should be noted that the following detailed description is exemplary and is intended to provide further illustration of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0055] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0056] In the case of no conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0057] The two-way reasoning module in the present invention explicitly models the dependency relationship between tasks and states through two processes: forward reasoning and backward reasoning; and proposes an uncertainty estimation module for quantitatively evaluating the reliability of intermediate results.

[0058] Embodiment 1

[0059] This embodiment discloses an intelligent agent automatic reasoning method based on task dependency planning. Task dependency modeling is a core component of the intelligent agent automatic reasoning framework, aiming to dynamically capture the complex dependency relationship between tasks and states, so as to support flexible and efficient task planning. Traditional task planning methods usually rely on predefined task dependency structures, such as chain, tree, or graph structures. However, these methods have obvious limitations in practical applications because the dependency relationship of tasks often dynamically adjusts with the change of input conditions. To solve this problem, a two-way reasoning module is proposed in this embodiment, which explicitly models the dependency relationship between tasks and states through two processes: forward reasoning and backward reasoning.

[0060] As Figure 1 shown, the intelligent agent automatic reasoning method based on task dependency planning includes:

[0061] Step S1, according to the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the states;

[0062] In step S1, the status information of the current task includes user input information, historical task execution records, task definitions, and execution results of historical tasks. Directly predicting the subtasks to be executed based on the above status information can dynamically adapt to different task inputs and context environments. For example, in the face of complex tasks, forward reasoning can flexibly generate subtask dependency relationships with different topological structures according to the specific requirements of the tasks, rather than being limited to fixed chain or tree structures.

[0063] Furthermore, the forward reasoning process is as follows:

[0064] Step S11, status analysis. The system first analyzes the current status information, including user input, historical task execution records, and task definitions. Through status analysis, comprehensively understand the context environment of the task.

[0065] Step S12, task decomposition. Based on the results of status analysis, the system decomposes the target task into multiple subtasks. These subtasks may have different dependency relationships, such as linear dependency, parallel dependency, or graphical dependency.

[0066] Step S13, priority sorting. The system sorts the subtasks according to their importance and urgency to determine the order of task execution.

[0067] Through forward reasoning, the system can quickly generate the subtask dependency relationships suitable for different task inputs, thereby improving the flexibility and adaptability of task planning.

[0068] Step S2, according to the dependency relationship between the subtasks and the states, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the state information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold;

[0069] Backward reasoning is used to evaluate the confidence score of the dependency relationship between each subtask and the state. Through backward reasoning, the system can quantify the importance of each subtask in the current state and its relevance to other tasks. This process not only enhances the transparency of task planning but also provides reliable support for subsequent decision-making. By combining forward reasoning and backward reasoning, it can dynamically adapt to the needs of different task domains and avoid the limitations caused by relying on predefined structures in traditional methods. This adaptive task dependency relationship modeling method significantly improves the flexibility and scalability of task planning.

[0070] During the forward reasoning process, the planner used for planning the task execution order passes through predicting subtasks , with a probability of , which represents the belief of the subtask in and depends on all states S.

[0071] To explicitly simulate the dependency relationship between states and subtasks, quantitatively calculate the confidence score of the task dependency relationship between subtask and state through backward reasoning.

[0072] During the backward reasoning process, the planner first judges whether there is a dependency relationship between subtask and according to the task definitions of and each state in S. The probability that there is a dependency relationship between subtask and state is . Subsequently, calculate , which represents the probability of backward reasoning, that is, depends on the states in S, but is excluded, which represents the belief that the target task depends on The difference reveals that the belief only depends on the probability value.

[0073] Therefore, the confidence score of the task dependency between subtask and state is defined as:

[0074]

[0075] In the formula, is the confidence score; represents a linear transformation to ensure that the range of the confidence score is [0, 1], is the state; is the subtask; is the belief of the subtask; is the reverse inference probability; by setting a belief score threshold , to determine and whether there is a dependency relationship. When , and there is a task dependency relationship, which indicates that depends on .

[0076] Step S3, use the executor to execute the remaining subtasks and output the intermediate results of the subtasks.

[0077] The executor executes the subtasks through , where Executor is an executor based on a large model, inputting the task description and the current inference state , and outputting the intermediate result of the subtask .

[0078] Step S4, through uncertainty analysis of the intermediate results of the subtasks, obtain the uncertainty score of the intermediate results of the subtasks.

[0079] During the task planning process, the reliability of the intermediate results directly affects the quality of the final decision. However, existing large language models tend to be overconfident when expressing uncertainty, resulting in potential risks that may be overlooked during the decision-making process. To address this issue, an uncertainty estimation module is also proposed in this embodiment to quantitatively evaluate the reliability of the intermediate results. Among them, the uncertainty analysis process includes parameter uncertainty analysis and decision uncertainty analysis.

[0080] Parameter uncertainty mainly focuses on the credibility of the results generated by the model. Through statistical analysis of the model output, this module can estimate the probability distribution of the generated results, thereby quantifying its uncertainty. This process evaluates the uncertainty by calculating the information entropy of the intermediate results of the subtasks. The higher the information entropy, the greater the uncertainty of the subtask results. The information entropy is as follows:

[0081]

[0082] In the formula, is the parameter uncertainty, which is used to evaluate the uncertainty of the intermediate results of the subtasks; is the information entropy; is the intermediate result of the subtask.

[0083] For example, when the model generates multiple possible subtasks, the parameter uncertainty module can evaluate the probability of each subtask and select the most reliable option as the basis for the next step of planning. Through parameter uncertainty estimation, the system can comprehensively evaluate the credibility of the intermediate results, thereby reducing the risk of wrong decisions caused by the overconfidence of the model.

[0084] Decision uncertainty focuses on the reliability of the speech or instructions generated by the executor during the planning process. This module evaluates the credibility of its decisions by analyzing the historical behavior and current state of the executor. Specifically, uncertainty analysis is performed on the intermediate results of the subtasks and the tasks to be executed in the subsequent reasoning process, and its information entropy is calculated to evaluate the credibility of the decision. The information entropy is as follows:

[0085]

[0086] In the formula, is the decision uncertainty; D represents the result of the decision, which is used to determine whether the result generated by the decision is reliable.

[0087] The higher the decision uncertainty, the less reliable the decision made by the executor when generating the subtask results. For example, when the executor proposes a high-risk suggestion during the planning process, the decision uncertainty module can identify its potential uncertainty and remind the system to take additional verification steps. By combining parameter uncertainty and decision uncertainty, the reliability of the intermediate results can be comprehensively evaluated, thereby reducing the risk of wrong decisions caused by the overconfidence of the model. This function is particularly important in complex task planning because it can help the system make more cautious and reliable decisions at critical nodes.

[0088] In the specific execution process, when the actuator executes the subtask , it is based on the dependency state . Then, the actuator is for Generate the reliability label D. The intermediate result of the uncertainty score is calculated as the arithmetic mean of two parts, including two aspects of the uncertainty score: parameter uncertainty and decision uncertainty. The specific calculation method is as follows:

[0089]

[0090] where represents the parameter uncertainty, which is obtained by calculating the information entropy based on the output probability of the actuator. represents the decision uncertainty, which is obtained by calculating the information entropy based on the probability of the actuator accompanying the production of D.

[0091] Example 2

[0092] This example discloses an intelligent agent automatic reasoning system based on task-dependent planning;

[0093] As Figure 2 shown, the intelligent agent automatic reasoning system based on task-dependent planning includes:

[0094] The intelligent agent automatic reasoning system based on task-dependent planning includes:

[0095] A forward reasoning module, configured to: according to the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the status;

[0096] A backward reasoning module, configured to: according to the dependency relationship between the subtasks and the status, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold;

[0097] An intermediate result acquisition module, configured to: use the actuator to execute the remaining subtasks and output the intermediate results of the subtasks;

[0098] An uncertainty analysis module, configured to: perform uncertainty analysis on the intermediate results of the subtasks to obtain the uncertainty score of the intermediate results of the subtasks; wherein, the uncertainty analysis includes parameter uncertainty analysis and decision uncertainty analysis;

[0099] The parameter uncertainty statistical analysis quantifies the uncertainty of the subtasks by generating the probability distribution of the intermediate results of the subtasks;

[0100] The decision uncertainty analysis evaluates the credibility of the decision by performing uncertainty analysis on the intermediate results of the subtasks and the tasks to be executed in the subsequent reasoning process;

[0101] The inference result generation module is configured to: iterate over the above process, stop the iteration when the maximum number of iterations is reached or the target task is completed, and summarize and output the final inference result based on all the intermediate results generated during the iteration.

[0102] Embodiment III

[0103] The purpose of this embodiment is to provide a computer-readable storage medium.

[0104] A computer-readable storage medium has a computer program stored thereon, and when the program is executed by a processor, it implements the steps in the method for automatic inference of an agent based on task dependency planning as described in Embodiment 1.

[0105] Embodiment IV

[0106] The purpose of this embodiment is to provide an electronic device.

[0107] An electronic device includes a memory, a processor, and a program stored on the memory and executable on the processor. When the processor executes the program, it implements the steps in the method for automatic inference of an agent based on task dependency planning as described in Embodiment 1.

[0108] The steps involved in the devices in the above Embodiments II, III, and IV correspond to those in Method Embodiment 1. For the specific implementation manners, reference may be made to the relevant description part of Embodiment 1. The term "computer-readable storage medium" should be understood to include a single medium or multiple media containing one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0109] Those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computer device. Optionally, they can be implemented by program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0110] Although the specific implementation manners of the present invention have been described above in conjunction with the accompanying drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications or deformations that can be made without creative efforts by those skilled in the art on the basis of the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. An intelligent agent automatic reasoning method based on task-dependent planning, characterized in that, including: Step S1, according to the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the status information; The status information of the current task includes user input information, historical task execution records, task definitions, and their results; Step S2, according to the dependency relationship between the subtasks and the status, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold; Step S3, use the executor to execute the remaining subtasks and output the intermediate results of the subtasks; Step S4, through the uncertainty analysis of the intermediate results of the subtasks, obtain the uncertainty score of the intermediate results of the subtasks; among them, the uncertainty analysis includes parameter uncertainty analysis and decision uncertainty analysis; The parameter uncertainty statistical analysis quantifies the uncertainty of the subtasks by generating the probability distribution of the intermediate results of the subtasks; The decision uncertainty analysis evaluates the credibility of the decision by performing uncertainty analysis on the intermediate results of the subtasks and the tasks to be executed in the subsequent reasoning process; Step S5, iterate steps S1 to S4, stop iterating when the maximum number of iterations is reached or the target task is completed, and summarize and output the final reasoning result according to all the intermediate results generated during the iteration.

2. The intelligent agent automatic reasoning method based on task-dependent planning according to claim 1, wherein The process of using the forward reasoning module to predict the subtasks to be executed and generate the dependency relationship between the subtasks and the status is as follows: Analyze the current status information, including user input information, historical task execution records, and task definitions; Based on the results of the status analysis, decompose the target task into subtasks with different dependency relationships; Perform priority sorting according to the importance and urgency of the subtasks to determine the order of task execution.

3. The intelligent agent automatic reasoning method based on task-dependent planning according to claim 1, wherein, The process of using backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information is as follows: According to the task definitions of each status and subtask, judge whether there is a dependency relationship between the subtask and each status information and the probability of the existence of the dependency relationship; Calculate the backward reasoning probability, construct the confidence score calculation formula, and obtain the confidence score of the dependency relationship between each subtask and the status information.

4. The intelligent agent automatic reasoning method based on task-dependent planning according to claim 3, characterized in that The confidence score calculation formula is: In the formula, is the confidence score; represents a linear transformation; is the state; is the subtask; is the probability of the forward inference result, which is used to represent the confidence of the subtask depending on all historical tasks; is the probability of the backward inference result, which is used to represent the confidence of the subtask depending on only one historical task.

5. The intelligent agent automatic reasoning method based on task-dependent planning according to claim 1, characterized in that The parameter uncertainty analysis and decision uncertainty analysis are respectively evaluated through information entropy; among them, the uncertainty of the subtask intermediate result is evaluated by calculating the information entropy of the subtask intermediate result; The credibility of the decision is evaluated by calculating the information entropy of the reasoning result obtained in the previous reasoning process and the task planned by the current planner.

6. The intelligent agent automatic reasoning method based on task-dependent planning according to claim 1, characterized in that The uncertainty analysis of the intermediate results of the subtasks to obtain the uncertainty score of the intermediate results of the subtasks includes: By calculating the arithmetic mean of the parameter uncertainty and decision uncertainty analysis results, the uncertainty score of the intermediate results of the subtasks is obtained, as shown in the following formula: In the formula, is the uncertainty score of the sub-task intermediate result; represents the result of the parameter uncertainty analysis; represents the result of the decision uncertainty analysis.

7. An intelligent agent automatic reasoning system based on task-dependent planning, characterized in that: including: The forward reasoning module is configured to: based on the status information of the current task, use forward reasoning to predict the subtasks to be executed, and generate the dependency relationship between the subtasks and the status; the status information of the current task includes user input information, historical task execution records, task definitions, and their results. The backward reasoning module is configured to: based on the dependency relationship between the subtasks and the status, use backward reasoning to generate the confidence score of the dependency relationship between each subtask and the status information, and eliminate the subtasks that do not meet the task dependency relationship according to the set belief score threshold. The intermediate result acquisition module is configured to: use the executor to execute the remaining subtasks and output the intermediate results of the subtasks. The uncertainty analysis module is configured to: obtain the uncertainty score of the subtask intermediate result by performing uncertainty analysis on the intermediate result of the subtask; wherein, the uncertainty analysis includes parameter uncertainty analysis and decision-making uncertainty analysis. The parameter uncertainty statistical analysis quantifies the uncertainty of the subtask by generating the probability distribution of the subtask intermediate result. The decision-making uncertainty analysis evaluates the credibility of the decision by performing uncertainty analysis on the intermediate result of the subtask and the tasks to be executed in the subsequent reasoning process. The inference result generation module is configured to: iterate the above process, stop the iteration when the maximum iteration number is reached or the target task is completed, and summarize and output the final inference result based on all the intermediate results generated during the iteration.

8. A computer-readable storage medium having a program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the intelligent agent automatic inference method based on task dependency planning according to any one of claims 1-6.

9. An electronic device, comprising a memory, a processor, and a program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the intelligent agent automatic inference method based on task dependency planning according to any one of claims 1-6.

Images