Emergency planning optimization method and device based on action parallelization and graph conversion, equipment, medium and product

By building an emergency planning tree and converting it into a hierarchical map, identifying parallel relationships and achieving parallel execution of actions at the same level, the problem of inefficient execution of existing emergency planning methods in complex scenarios is solved, and the execution efficiency of emergency planning is improved.

CN119539040AActive Publication Date: 2025-02-28NAT UNIV OF DEFENSE TECH
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411603854.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-11
Publication Date
2025-02-28
Estimated Expiration
2044-11-11

AI Technical Summary

Technical Problem

Existing emergency planning methods are inefficient in long-term, parallel scenarios, and are difficult to effectively apply in complex robot tasks.

Method used

By building an emergency planning tree, the effect actions and belief states between observation action nodes are extracted, parallel relationships are identified, and converted into a hierarchical graph to realize the parallel execution of the effect actions at the same level. By recursively merging the hierarchical graph and observing the action branch structure, an optimized global emergency planning tree is built.

Benefits of technology

It improves the execution efficiency of emergency planning, can support parallel execution of actions in complex scenarios, and improves the completion speed and efficiency of robot tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119539040A_ABST
    Figure CN119539040A_ABST
Patent Text Reader

Abstract

The invention discloses an emergency planning optimization method and device based on motion parallelization and graph conversion, equipment, a medium and a product, and relates to the field of artificial intelligence and robotics.The method comprises the steps that according to tasks corresponding to user requirements, an emergency planner is selected, and an emergency planning tree is constructed; performing branch construction of an observation action branch structure based on each observation result of the observation action; extracting an effect action and a belief state between two observation action nodes in the emergency planning tree; based on the belief state, effect action pairs capable of being paralleled in the linear effect action sequence are determined; on the basis of the planning graph model, the effect action pairs capable of being parallel are expressed as a hierarchical graph; the same-level effect actions in the hierarchical diagram can be executed in parallel; all the hierarchical diagrams and the observation action branch structures are recursively merged, an optimized global emergency planning tree is constructed, tasks corresponding to user requirements are executed according to the global emergency planning tree, and the execution efficiency of emergency planning is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and robotics, and in particular to an emergency planning optimization method, device, equipment, medium and product based on action parallelization and graph transformation. Background Art

[0002] In the field of artificial intelligence and robotics, the decision-making ability of an intelligent agent is an important indicator of its degree of intelligence. Task planning, as an important way to achieve effective decision-making of intelligent agents, guides the intelligent agent to transform the current state to the target state and complete the task requirements by generating a series of action sequences based on the current environmental state information.

[0003] In the real world, environmental uncertainty often brings many challenges to the task planning of intelligent agents. For this reason, contingency planning, as an important branch of traditional task planning, aims to focus on the planning problem of such uncertain initial states. The contingency planner generates a tree-structured contingency plan by forward searching the available effect actions and observation actions. The output contingency plan consists of effect actions and observation actions, and its execution can be regarded as traversing the entire planning tree from the root node to the leaf node in sequence, and selecting the correct branch according to the observation results obtained by the observation action. In the forward state search process, the planner selects the action with the highest utility value in the current state, and applies its action effect to transform the current state until the target state is met.

[0004] However, in the forward state search process, the contingency planner only considers the action with the highest utility value in each search state and takes it as the successor action in that state. Therefore, the contingency planning results obtained are only allowed to be executed sequentially, which will lead to low execution efficiency of contingency planning in long-term, parallelizable scenarios. For complex robot tasks in the real world, this limitation becomes more prominent, further hindering the implementation of contingency planning methods in actual production. Summary of the invention

[0005] The purpose of this application is to provide an emergency planning method, device, equipment, medium and product based on action parallelization and graph transformation to solve the problem of low efficiency in emergency planning execution.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides an emergency planning method based on action parallelization and graph transformation, comprising:

[0008] According to the task corresponding to the user's needs, a contingency planner is selected to construct a contingency planning tree; the contingency planning tree includes a plurality of nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the contingency planning tree has a belief state; there are a plurality of effect actions between the observation actions corresponding to the two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state;

[0009] Based on each observation result of the observation action, a branch structure of observation action is constructed; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes multiple effect actions;

[0010] Extracting effect actions and belief states between two observation action nodes in the emergency planning tree;

[0011] Based on the belief state, determining effect-action pairs that can be parallelized in the linear effect-action sequence;

[0012] Based on the planning graph model, the parallelizable effect-action pairs are represented as a hierarchical graph; the same-level effect-actions in the hierarchical graph can be executed in parallel;

[0013] All hierarchical graphs and the observation action branch structures are recursively merged to construct an optimized global emergency planning tree, and tasks corresponding to user needs are executed according to the global emergency planning tree.

[0014] In a second aspect, the present application provides an emergency planning device based on action parallelization and graph conversion, comprising:

[0015] The emergency planning tree construction module is used to select an emergency planner and construct an emergency planning tree according to the task corresponding to the user's needs; the emergency planning tree includes multiple nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the emergency planning tree has a belief state; there are multiple effect actions between the observation actions corresponding to the two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state;

[0016] An observation action branch structure construction module, used for constructing an observation action branch structure by branching based on each observation result of the observation action; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes a plurality of effect actions;

[0017] An extraction module, used for extracting effect actions and belief states between two observation action nodes in the emergency planning tree;

[0018] A parallelizable effect-action pair determination module, used to determine parallelizable effect-action pairs in the linear effect-action sequence based on the belief state;

[0019] A hierarchical graph construction module is used to represent the parallelizable effect-action pairs as a hierarchical graph based on a planning graph model; the same-level effect-actions in the hierarchical graph can be executed in parallel;

[0020] The optimized global emergency planning tree construction module is used to recursively merge all hierarchical graphs and the observation action branch structure to construct an optimized global emergency planning tree, and execute tasks corresponding to user needs according to the global emergency planning tree.

[0021] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-mentioned emergency planning methods based on action parallelization and graph transformation.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned emergency planning methods based on action parallelization and graph transformation.

[0023] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned emergency planning methods based on action parallelization and graph transformation.

[0024] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0025] Firstly, according to the tasks corresponding to the user needs, an emergency planning tree is constructed, and an observation action branch structure is constructed, the effect action and belief state between two observation action nodes in the emergency planning tree are extracted, the hidden parallel relationship between the actions in the emergency planning tree is identified, and the parallel effect action pairs in the linear effect action sequence are obtained; secondly, based on the planning graph model, the above-obtained parallel effect action pairs are converted into a hierarchical graph, in which the effect actions at the same level can be executed in parallel. Different from the traditional technical scheme in which these actions can only be sorted and executed in sequence in the original planning tree, the present application determines the parallel effect action pairs and converts them into a hierarchical graph, realizes the parallel execution of effect actions at the same level, and improves the execution efficiency of emergency planning.

[0026] In addition, the present application identifies parallelizable effect actions, converts the parallelizable effect actions into a single hierarchical graph based on a planning graph model, and then recursively merges the hierarchical graph into a contingency planning tree step by step, so that the final result can support the parallel execution of effect actions and handle uncertain observation results through observation actions. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 A flowchart of an emergency planning method based on action parallelization and graph conversion in one embodiment of the present application;

[0029] Figure 2 A schematic diagram of an architecture of an emergency planning method based on action parallelization and graph conversion provided in one embodiment of the present application;

[0030] Figure 3 This is a schematic diagram of the planning results of the traditional emergency planner;

[0031] Figure 4 A schematic diagram of the planning results of the optimized global emergency planning tree constructed by this application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0034] The embodiment of the present application provides an emergency planning method based on action parallelization and graph conversion, which is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, Figure 1 As shown, the method includes the following steps.

[0035] S1: According to the task corresponding to the user's needs, a contingency planner is selected to construct a contingency planning tree; the contingency planning tree includes multiple nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the contingency planning tree has a belief state; there are multiple effect actions between the observation actions corresponding to two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state.

[0036] S2: constructing an observation action branch structure by branching based on each observation result of the observation action; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes multiple effect actions.

[0037] S3: Extracting the effect action and belief state between two observation action nodes in the emergency planning tree.

[0038] S4: Based on the belief state, determine the effect-action pairs that can be run in parallel in the linear effect-action sequence.

[0039] S5: Based on the planning graph model, the parallelizable effect-action pairs are represented as a hierarchical graph; the effect-actions at the same level in the hierarchical graph can be executed in parallel.

[0040] S6: recursively merge all the hierarchical graphs and the observation action branch structures to construct an optimized global emergency planning tree, and execute tasks corresponding to user needs according to the global emergency planning tree.

[0041] In an exemplary embodiment, S4 specifically includes: based on the belief state, filtering and identifying parallel effect-action pairs in the linear effect-action sequence according to screening rules; the screening rules include that actions are applicable in the same belief state; the execution of an action cannot invalidate the remaining actions; the action cannot cause the generated new belief state to be inconsistent; observation actions are processed separately; wherein, the action is an observation action or an effect action.

[0042] Furthermore, in emergency planning, the planning tree solved by the emergency planner consists of two types of actions: effect actions that change the state of the environment and observation actions that obtain information about the state of the environment, and branches according to each possible observation result of the observation action. In each branch, there are a large number of potential parallelizable actions in the sequence of actions. In order to identify such parallelizable actions, this application lays the foundation for the subsequent parallelization based on a set of rules. The rules are as follows:

[0043] (1) Actions should be applicable in the same belief state. For actions to be parallelizable, their prerequisites must be satisfied in the same belief state.

[0044] (2) The execution of one action should not invalidate other actions. The applicability of actions does not necessarily mean that they can be executed in parallel. During execution, the effect of one action may conflict with the prerequisites of other actions, thereby invalidating the other actions.

[0045] (3) Actions should not lead to inconsistent new beliefs. If applicable actions within the same belief produce inconsistent effects, the new belief generated will be uncertain, leading to conflicts in subsequent optimization.

[0046] (4) Observation actions should be processed separately. For an initially unknown world predicate, applying observation action a helps the robot observe the true value p or This results in two subsequent beliefs b ′+ and b ′- , both beliefs are valid but inconsistent with each other.

[0047] In an exemplary embodiment, S5 specifically includes: the planning graph model includes two types of nodes and edges; the two types of nodes occupy the proposition layer and the action layer respectively, and the proposition layer and the action layer alternate with each other; the proposition node in the proposition layer is an instantiated proposition; the action corresponding to the action node in the action layer is an effect action or a maintenance action; the maintenance action is used to convert the proposition node from the previous level to the next level without changing the belief state; the edge before the action node represents the prerequisite connection, and the edge after the action node represents the effect connection; the prerequisite and effect of the maintenance action are the same; the level is the proposition layer; the initial belief, target belief and the linear effect action sequence between the initial belief and the target belief in the emergency planning tree are used as the input of the planning graph model, and the local hierarchical graph conversion algorithm is called, and the parallel relationship between the effect actions is converted into a hierarchical relationship in an extended manner until all propositions in the target belief are in the last proposition layer in the planning graph model, and a hierarchical graph is determined; wherein the initial belief is the belief state after the previous observation action node; the target state is the belief state before the next observation action node; and the first level of the planning graph model includes all propositions in the initial belief.

[0048] In an exemplary embodiment, during the expansion process, if in the linear effect-action sequence, there is any effect action whose prerequisite is satisfied in the previous proposition layer, then the effect action is inserted into the next action layer, and the effect of the effect action is added to the next proposition layer.

[0049] In an exemplary embodiment, during the expansion process, a mutually exclusive relationship between nodes in the planning graph model is constructed; three types of mutually exclusive constraints are included between two actions on the same level; the mutually exclusive constraints include demand competition constraints, inconsistent effect constraints and execution interference constraints; the demand competition constraint is that the two actions have mutually exclusive prerequisites in the previous proposition layer; the inconsistent effect constraint is that the effect of one action is the negation of the effect of another action; the execution interference constraint is that the effect of one action negates the prerequisite of another action; if the inconsistent support condition is met, the two propositions at the same level are mutually exclusive; the inconsistent support condition is that the two propositions negate each other, or all actions that implement the proposition in the previous action layer are combined into pairs and are mutually exclusive.

[0050] Furthermore, the parallel relationship between actions can be represented by a graph structure. This application uses a graph-based transformation technology to transform the linear effect action sequence in the original planning tree into a set of hierarchical graph structures, so that the parallel relationship between non-conflicting and parallelizable actions in the original planning results can be explicitly represented, and provide a basis for the subsequent parallel execution of these actions.

[0051] In this application, the hierarchical graph can be represented as a tuple γ=<N,L> , where N is a set of action nodes and L is a function that maps each node in γ to a level in a set of levels.

[0052] For two nodes n1 and n2 in N, L(n1)=L(n2) means that operations n1(a) and n2(a) can be executed in parallel.

[0053] The transformation of this hierarchical graph utilizes the planning graph model. In this model, there are two types of nodes and edges. The two types of nodes occupy the proposition layer Ip and the action layer Ia respectively, and they alternate with each other. The nodes in the proposition layer are composed of instantiated propositions. In the action layer, the nodes represent effect actions or maintenance actions. The prerequisites and effects of maintenance actions are the same, and the purpose is to transform proposition nodes from the previous level to the next level without changing any state. The edges before the action nodes in the planning graph represent the prerequisite connections, while the edges after them represent the effect connections.

[0054] The hierarchical graph conversion process is described as follows: It takes the initial belief, target belief, and a set of effective actions extracted from the contingency planning tree as input. Then, it seeks solutions by expanding and extracting the planning graph. The first level of the planning graph consists of the propositions in the initial belief. Starting from the first level, the planning graph is continuously expanded until all the target belief propositions appear in the last level.

[0055] During the expansion process, if any of the actions in the input effect action set have prerequisites that are satisfied in the previous propositional layer, they will be inserted into the next action layer. Then, the effects of these actions will be added to the next new propositional layer.

[0056] Based on the above planning graph structure, the parallelism between actions can now be characterized by a hierarchical relationship. However, during the expansion process, since the search space is largely relaxed, there may be mutual exclusion between actions and propositions. It is crucial to avoid potential conflicts in the hierarchical graph that may arise from mutual exclusion. Therefore, while expanding the planning graph process, it is also necessary to build mutually exclusive relationships between nodes. Generally speaking, there are three types of mutual exclusion constraints between two actions on the same level for the following reasons:

[0057] (1) Demand competition constraint: two actions have mutually exclusive prerequisites in the previous proposition level.

[0058] (2) Inconsistent effect constraints: The effect of one action is the negation of the effect of another action.

[0059] (3) Execution interference constraint: The effect of one action negates the prerequisite of another action.

[0060] In addition, two propositions at the same level will also be mutually exclusive when the following inconsistent support conditions are met:

[0061] Inconsistent support conditions: The two propositions negate each other, or all combinations that realize the proposition in the previous action layer are pairwise exclusive.

[0062] The above expansion process is repeated until all propositions in the target belief are satisfied in the last proposition layer.

[0063] After ensuring that all pairs of target propositions are not mutually exclusive, start extracting solutions from back to front.

[0064] The extraction of solutions proceeds as follows: For each goal proposition in the last propositional level, the previous action level is searched to find actions that appear in its effect. If any action achieves the goal, it is marked. The prerequisites of the marked actions are then stored as new goals for the previous propositional level. When extracting an action level, if all marked actions on that level are pairwise exclusive, the extraction process fails and the planning graph is extended by one level. The extraction of solutions is then retried from the last level again. Once the initial propositional level is extracted, the marked actions in each level are returned as feasible solutions. The returned hierarchical graph consists of several levels of effect actions, where actions at the same level can be executed in parallel without any conflicts.

[0065] In an exemplary embodiment, S6 specifically includes: based on the task corresponding to the user demand, traverse from the root node of the emergency planning tree to the next node, and record the intermediate effect action set as a linear effect action sequence; the next node is an observation action node or a leaf node; take the initial belief, the target belief related to the next node traversed, the linear effect action sequence and the next node as input, call the local hierarchical graph conversion algorithm, determine the initial hierarchical graph, and construct an optimized global emergency planning tree; the initial hierarchical graph currently only contains effect actions; if the next traversed node is a leaf node, return to the previous hierarchical graph; if the next traversed node is an observation action node, take the observation action as a new level in the hierarchical graph, append it to the original hierarchical graph, and process the two observation action branch structures corresponding to the observation action node respectively; traverse from the initial hierarchical layer to the last layer of the hierarchical graph in sequence, and execute the actions in the nodes in the hierarchical graph step by step.

[0066] Furthermore, based on the previously transformed hierarchical graph, the parallel relationship between the effect actions in each branch can be intuitively represented. Then, the entire contingency planning tree is optimized and executed by recursively merging these hierarchical graphs with the observation-action branch structure, thereby achieving planning parallelism and addressing the uncertainty in the overall planning scale.

[0067] The present application formalizes the optimized overall emergency plan as Π = <Γ, E>, where Γ is a set of hierarchical graph nodes and E is a set of edges representing observation connections between nodes. Each node γ∈Γ consists of a transformed hierarchical graph.

[0068] The specific process of optimizing emergency planning is as follows:

[0069] (1) First, use the selected contingency planner to solve and obtain the initial contingency planning tree τ.

[0070] (2) Traverse from the root node of τ to the next observation action node or leaf node n G , record the intermediate effect action set in A * Inside.

[0071] (3) Recursively construct the optimization tree. I , and n G Related target beliefs, extracted A * and n G As input, the local hierarchy graph conversion algorithm is called to obtain the initial hierarchy graph, which currently only contains effect actions.

[0072] (4) If the traversed node n G is a leaf node, then the hierarchical graph is returned; if n GObserve the action node, attach the observation action as a new level in the hierarchy graph to the original hierarchy graph, and process the two subsequent branches of the node separately:

[0073] (4.1) The branch that handles the observation result of the observation action n(a) is true. First, in the belief b G Apply n(a) to get the new belief b + . Then continue from the next node in this branch n.next + Start traversing until the next observation action node or leaf node n + G , record the intermediate effect action A in this branch *+ Then repeat steps (2)-(4) to recursively construct the local hierarchical graph in the branch and connect the hierarchical graph to the current hierarchical graph node γ.

[0074] (4.2) The process of handling the branch where the observation result of the observation action n(a) is false is similar to that of (4.1).

[0075] The execution of the optimized plan can be viewed as a sequential traversal of the global hierarchical graph from the first level to the last level, and the actions in the hierarchical graph nodes are executed level by level. Effect actions at the same level in the hierarchical graph can be executed in parallel. When an observation action is executed in the graph, the next graph node is executed according to the actual observation value until the end of the tree.

[0076] like Figure 2 As shown, the present application selects a suitable emergency planner to solve and obtain an initial emergency planning tree according to user needs. Based on the above planning tree, a series of effect actions between two observation action nodes and related belief states in the planning tree are first extracted. Then, the extracted effect action and other information are filtered and identified through a number of rules to obtain all hidden parallel effect action pairs. Then, based on the planning graph model, the linear effect action set is converted into a set of hierarchical graphs, and the effect actions at the same level in the hierarchical graph can be executed in parallel. After completing the above-mentioned local parallelization conversion, the hierarchical graph is recursively merged with the observation action branch structure to obtain the optimized global emergency planning tree, thereby optimizing the parallelization of the overall planning, and having the ability to handle uncertain observation results through observation actions.

[0077] Take the scenario of a service robot delivering coffee as an example. Figure 3 As shown in the figure, in the initial state, there is a robot at the PS position and a cup of coffee at the P1 or P2 position, which needs to be confirmed by observation. The actions that the robot can perform are:

[0078] (1) Effect actions: 1. GoTo(a,b) - run from position a to position b; 2. PickUp(p) - pick up the coffee at position p; 3. Stir() - stir the coffee in your hand; 4. Place(p) - put the coffee down at position p.

[0079] (2) Observation action: SenseCoffee(p) - observe whether the coffee is at position p.

[0080] The robot's task is to plan a series of actions starting from PS, determine the location of the coffee by executing the actions, pick up the coffee and deliver it to the guest's position PG. The coffee needs to be stirred before being handed to the guest.

[0081] The results directly obtained by using the traditional emergency planner are as follows Figure 3 As shown in the figure, the robot starts from PS and runs to P2 first, where it observes whether there is coffee. If there is, it picks up the coffee, runs to PG, stirs the coffee, and finally places the coffee in PG; if there is no coffee, it means that the coffee is at P1, so the robot moves from P2 to P1, picks up the coffee at P2, then runs to PG, stirs the coffee, and finally places the coffee in PG.

[0082] The results of parallel optimization of the above plan using this application are as follows: First, starting from the root node, traverse the entire emergency plan, encounter observation action node 2, extract the effect action between the initial state and the observation action node, there is only one effect action 1, so it cannot be further parallelized; continue to traverse from observation action node 2, the node generates two branches, corresponding to two belief states St and Sf respectively: first start traversing from the branch with the true result until the leaf node 6, the belief state after 6 is set to Stg, and extract the effect actions 3, 4, 5, 6 between 2 and 6 and put them into the set A*={PickUp(P2), Stir(), GoTo(P2,PG), Place(PG)}. Using the above extracted St, Stg, A* as input, the planning graph model and conversion algorithm in this application are used to parallelize the actions in this branch. After this optimization, the actions Stir() and GoTo(P2,PG) are parallelized, and both can be executed at the same time, so that the time used for the entire task is reduced to a certain extent. Similarly, the same extraction and parallelization steps are applied to the other branch of observation action 2, and the final result is as follows Figure 4 shown.

[0083] Based on the same inventive concept, the embodiment of the present application also provides an emergency planning device based on action parallelization and graph conversion for implementing the emergency planning method based on action parallelization and graph conversion involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the emergency planning device based on action parallelization and graph conversion provided below can refer to the limitations of the emergency planning method based on action parallelization and graph conversion above, and will not be repeated here.

[0084] In an exemplary embodiment, a contingency planning device based on action parallelization and graph conversion is provided, comprising:

[0085] The emergency planning tree construction module is used to select an emergency planner and construct an emergency planning tree according to the tasks corresponding to user needs; the emergency planning tree includes multiple nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the emergency planning tree has a belief state; there are multiple effect actions between the observation actions corresponding to two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state.

[0086] The observation action branch structure construction module is used to construct the observation action branch structure by branching based on each observation result of the observation action; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes multiple effect actions.

[0087] The extraction module is used to extract the effect action and belief state between two observation action nodes in the emergency planning tree.

[0088] A parallel effect-action pair determination module is used to determine the parallel effect-action pairs in the linear effect-action sequence based on the belief state.

[0089] The hierarchical graph construction module is used to represent the parallelizable effect-action pairs as a hierarchical graph based on a planning graph model; the same-level effect-actions in the hierarchical graph can be executed in parallel.

[0090] The optimized global emergency planning tree construction module is used to recursively merge all hierarchical graphs and the observation action branch structure to construct an optimized global emergency planning tree, and execute tasks corresponding to user needs according to the global emergency planning tree.

[0091] This application has the following advantages:

[0092] 1. The execution efficiency of the planning results is greatly improved. When executing, the planning tree generated by the existing emergency planning method is executed by traversing from the root node to the leaf node one by one. When the tree branch contains actions that can be executed in parallel, this method cannot support the occurrence of such behavior well. The present application adopts a new hierarchical graph structure to represent the original planning results, which contains richer information, and the parallel relationship between actions is represented by a hierarchical relationship. The original process of traversing a single action node is now transformed into traversing multiple nodes at a time by layer, and the nodes traversed at the same time can be executed in parallel. This execution strategy greatly reduces the total time required to complete the entire plan, which is of great significance in practical applications.

[0093] 2. Highly compatible with various existing emergency planners. Existing emergency planners mostly focus on improving the speed of single solutions, and for different problem domains, the efficiency of solutions varies greatly due to the different heuristic functions adopted. This application integrates the above planners in a modular way and performs secondary optimization based on the results of the above planners. Therefore, it has good enough compatibility to cope with various emergency planning scenarios.

[0094] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store emergency planning data based on action parallelization and graph conversion. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for emergency planning based on action parallelization and graph conversion is implemented.

[0095] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above method is implemented when the processor executes the computer program.

[0096] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the above method when executed by a processor.

[0097] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above method when executed by a processor.

[0098] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ReadOnlyMemory, ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (Magnetoresistive RandomAccess Memory, MRAM), ferroelectric random access memory (Ferroelectric RandomAccess Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (RandomAccess Memory, RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0099] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0100] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0101] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0102] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A contingency planning method based on action parallelization and graph transformation, characterized in that: The emergency planning method based on action parallelization and graph conversion includes: According to the task corresponding to the user's needs, a contingency planner is selected to construct a contingency planning tree; the contingency planning tree includes a plurality of nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the contingency planning tree has a belief state; there are a plurality of effect actions between the observation actions corresponding to the two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state; Based on each observation result of the observation action, a branch structure of observation action is constructed; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes multiple effect actions; Extracting effect actions and belief states between two observation action nodes in the emergency planning tree; Based on the belief state, determining effect-action pairs that can be parallelized in the linear effect-action sequence; Based on the planning graph model, the parallelizable effect-action pairs are represented as a hierarchical graph; the same-level effect-actions in the hierarchical graph can be executed in parallel; All hierarchical graphs and the observation action branch structures are recursively merged to construct an optimized global emergency planning tree, and tasks corresponding to user needs are executed according to the global emergency planning tree.

2. The method for emergency planning based on action parallelization and graph transformation according to claim 1, characterized in that: Based on the belief state, determining the effect-action pairs that can be parallelized in the linear effect-action sequence specifically includes: Based on the belief state, the effect-action pairs that can be run in parallel in the linear effect-action sequence are filtered and identified according to screening rules; the screening rules include that actions are applicable in the same belief state; the execution of an action cannot invalidate the remaining actions; the action cannot cause inconsistency in the generated new belief state; observation actions are processed separately; wherein the action is an observation action or an effect action.

3. The method for emergency planning based on action parallelization and graph transformation according to claim 1, characterized in that: Based on the planning graph model, the parallelizable effect-action pairs are represented as a hierarchical graph, specifically including: The planning graph model includes two types of nodes and edges; the two types of nodes occupy the proposition layer and the action layer respectively, and the proposition layer and the action layer alternate with each other; the proposition nodes in the proposition layer are instantiated propositions; the actions corresponding to the action nodes in the action layer are effect actions or maintenance actions; the maintenance actions are used to convert proposition nodes from the previous level to the next level without changing the belief state; the edges before the action nodes represent the prerequisite connections, and the edges after the action nodes represent the effect connections; the prerequisites and effects of the maintenance actions are the same; the level is the proposition layer; The initial belief, target belief and the linear effect action sequence between the initial belief and the target belief in the emergency planning tree are used as the input of the planning graph model, and the local hierarchical graph conversion algorithm is called. By extension, until all propositions in the target belief are in the last proposition layer in the planning graph model, the parallel relationship between the effect actions is converted into a hierarchical relationship to determine the hierarchical graph; wherein the initial belief is the belief state after the previous observation action node; the target state is the belief state before the next observation action node; and the first level of the planning graph model includes all propositions in the initial belief.

4. The method for emergency planning based on action parallelization and graph transformation according to claim 3, characterized in that: During the expansion process, if in the linear effect-action sequence, there is any effect action whose prerequisite is satisfied in the previous proposition layer, then the effect action is inserted into the next action layer, and the effect of the effect action is added to the next proposition layer.

5. The method for emergency planning based on action parallelization and graph transformation according to claim 3, characterized in that: During the expansion process, mutually exclusive relationships between nodes in the planning graph model are constructed; there are three types of mutually exclusive constraints between two actions at the same level; the mutually exclusive constraints include demand competition constraints, inconsistent effect constraints, and execution interference constraints; the demand competition constraint is that the two actions have mutually exclusive prerequisites in the previous proposition layer; the inconsistent effect constraint is that the effect of one action is the negation of the effect of another action; the execution interference constraint is that the effect of one action negates the prerequisite of another action; If the inconsistent support condition is met, the two propositions at the same level are mutually exclusive; the inconsistent support condition is that the two propositions negate each other, or all the action combinations that realize the proposition in the previous action layer are mutually exclusive in pairs.

6. The method for emergency planning based on action parallelization and graph transformation according to claim 3, characterized in that: All hierarchical graphs and the observation action branch structures are recursively merged to construct an optimized global emergency planning tree, and tasks corresponding to user needs are executed according to the global emergency planning tree, specifically including: Based on the task corresponding to the user demand, traverse from the root node of the emergency planning tree to the next node, and record the intermediate effect action set as a linear effect action sequence; the next node is an observation action node or a leaf node; Taking the initial belief, the target belief related to the next node traversed, the linear effect action sequence and the next node as input, calling the local hierarchical graph conversion algorithm, determining the initial hierarchical graph, and constructing an optimized global emergency planning tree; the initial hierarchical graph currently only contains effect actions; If the next node traversed is a leaf node, return to the previous level graph; If the next node traversed is an observation action node, the observation action is added to the original hierarchical graph as a new level in the hierarchical graph, and the two observation action branch structures corresponding to the observation action node are processed respectively; The hierarchical graph is traversed from the initial hierarchical layer to the last hierarchical layer in sequence, and actions in the nodes in the hierarchical graph are executed level by level.

7. An emergency planning device based on action parallelization and graph transformation, characterized in that: The emergency planning device based on action parallelization and graph conversion includes: The emergency planning tree construction module is used to select an emergency planner and construct an emergency planning tree according to the task corresponding to the user's needs; the emergency planning tree includes multiple nodes; the nodes include observation action nodes and effect action nodes, and the edge between every two nodes on the emergency planning tree has a belief state; there are multiple effect actions between the observation actions corresponding to the two observation action nodes; the observation action is used to obtain environmental state information; the effect action is used to change the environmental state; An observation action branch structure construction module, used for constructing an observation action branch structure by branching based on each observation result of the observation action; each of the observation action branch structures includes a linear effect action sequence, and the linear effect action sequence includes a plurality of effect actions; An extraction module, used for extracting effect actions and belief states between two observation action nodes in the emergency planning tree; A parallelizable effect-action pair determination module, used to determine parallelizable effect-action pairs in the linear effect-action sequence based on the belief state; A hierarchical graph construction module is used to represent the parallelizable effect-action pairs as a hierarchical graph based on a planning graph model; the same-level effect-actions in the hierarchical graph can be executed in parallel; The optimized global emergency planning tree construction module is used to recursively merge all hierarchical graphs and the observation action branch structure to construct an optimized global emergency planning tree, and execute tasks corresponding to user needs according to the global emergency planning tree.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the emergency planning method based on action parallelization and graph transformation as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the emergency planning method based on action parallelization and graph transformation described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the emergency planning method based on action parallelization and graph transformation described in any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • Extended POMDP planning method and system based on robot accompanying behavior model

    CN112131754A

  • Reliable behavior tree task planning method and system based on human-computer interaction

    CN116010410A

  • Parallelization of language-integrated collection operations

    US20070250470A1